Datasets:

PranavHarshan

/

sharegpt_formatted_cord19_fulltext_convo

like 0

[ { "from": "human", "value": "Full Text: Mycoplasma pneumoniae is a common cause of upper and lower respiratory tract infections. It remains one of the most frequent causes of atypical pneumonia particu-larly among young adults. [1, 2, 3, 4, 5] Although it is highly transmissible, most infections caused by this organism are relatively minor and include pharyngitis, tracheobronchitis, bronchiolitis, and croup with one fifth of in-fections being asymptomatic. [6, 7] Only 3 -10% of infected subjects develop symptoms consistent with bronchopneumonia and mortality from infection is rare. [6, 7] The organism is fastidious and difficult to grow on cultures. Therefore, diagnosis of infections caused by this organism is usually confirmed with serological tests or polymerase chain reaction-gene amplification techniques. At King Abdulaziz University Hospital (KAUH), Jeddah, Saudi Arabia, the facility to perform Mycoplasma culture has been available since January 1997. As published information concerning M. pneumoniae infections in Saudi Arabia is scarce, [8, 9, 10] we wished to study the epidemiology and clinical features of cultureproven infections caused by this organism at this hospital.\nKAUH is a tertiary care teaching hospital with a bed capacity of 265 beds and annual admissions of 18000 to 19000 patients. Patients with M. pneumoniae positive cultures from respiratory specimens were identified over a 24-months\" period from January, 1997 through December, 1998 for this review.\nDuring the study period, respiratory specimens (sputum, nasopharyngeal aspiration, endotracheal secretion, and bronchoalveolar lavage) for M. pneumoniae culture were obtained from patients with upper or lower respiratory tract infections seen as inpatients or in the outpatient or emergency departments. Respiratory specimens were aslo Gram-stained and cultured for bacteria and viruses. M. pneumoniae serological tests for IgG or IgM were not available at KAUH during the study period. All positive culture results were obtained from the Microbiology laboratory records. Charts of patients were reviewed with standardized data collection. Information collected included patients' demographics, comorbidities, clinical manifestations, complications, and outcome.\nM. pneumoniae was cultured using the classic M. pneumoniae agar medium (M.P. agar) and the Pneumofast tray (Pneumofast ® , International Microbio, Signes, France). Specimens were processed according to the instructions of the manufacturer. The M.P. agars and Pneumofast trays were incubated anaerobically at 37°C and inspected daily for 4 weeks. The organism was identified based on typical colonial morphology (granular colonies, rarely fried-egg-like, 10-150 ∝ in diameter) on the M.P. agar medium and the change in the Pneumofast broth color from red to orange then to yellow (glucose fermentation) in the absence of turbidity of the broth. Antibiotic sensitivity profile on the Pneumofast tray was also used for identification according to the instructions of the manufacturer. Bacterial and viral cultures were performed using standard methods.\nM. pneumoniae isolates were considered community-acquired if they were recovered from unhospitalized patients or within 72 hours of admission to the hospital, and nosocomial if they were recovered beyond that period.\nPneumonia was diagnosed based on clinical symptoms and signs, along with radiographic evidence of pneumonia when possible. Severe pneumonia was defined as pneumonia associated with tachycardia (>140 /minute), tachypnoea (>30/minute), hypotension (Systolic blood pressure <90 mmHg), hypoxemia (arterial oxygen partial pressure <8 kPa or oxygen saturation <90%), and/or more than 2 areas of consolidation.\nOutcome of patients with M. pneumoniae infection was classified into 4 categories; uneventful recovery, recovery following complications, death due to M. pneumoniae infection, or death unrelated to M. pneumoniae infection.\nThe Statistical Package for Social Sciences (SPSS) program was used for data analysis. Comparison of categorical data was by Chi-square statistic or Fisher's exact test for small expected values.\nA total of 40 respiratory specimens from 40 patients were positive for M. pneumoniae over the 24-months study period. The demographic and epidemiological characteristics of the patients are summarized in Table 1 . Of all isolates, 37 (92.5%) were community-acquired and 3 (7.5%) were nosocomial. Thirty-three (82.5%) patients required admission to the hospital and the remaining 7 (17.5%) were treated as outpatients. Twenty-four isolates (60%) were associated with pneumonia, 14 (35%) with upper respiratory tract infections, and 2 (5%) with bronchiolitis. Of the 24 cases of pneumonia, 21 were confirmed radiologically and the remaining 3 were diagnosed clinically. The two cases of bronchiolitis occurred in 2 children, one and three years old. Thirty-one patients (77.5%) had comorbidities. Eleven patients (27.5%) had cardiopulmonary comorbidities (asthma, 8, lung fibrosis, 1, congestive heart failure, 1, congenial heart disease, 1), 9 patients (22.5%) were immunocompromised (malignancy, 7, steroid therapy, 3, Human immunodeficiency virus infection, 1), and 11 patients (27.5%) had other comorbidities (premature newborns, 2, and one each of myelodysplastic syndrome, myelopro-liferative disorder, sickle cell anemia, Evan's syndrome, Down syndrome, sarcoidosis, demyelinating disease, cerebral palsy, and spinal muscle atrophy). Organisms concomitantly isolated with M. pneumoniae from the respiratory tract included herpes simplex virus type 1 (2 occasions), adenovirus (2 occasions), cytomegalo virus (1 occasion), respiratory syncytial virus (1 occasion), and bacterial isolates (2 occasions: Acinetobacter species, 1, and Enter obacter cloacae, 1).\nClinical manifestations associated with M. pneumoniae infections are summarized in Table 2 . Pneumonia was more common than upper respiratory tract infections (57.5 % versus 27.5%, respectively). Immunocompromised patients were more likely to present with pneumonia as opposed to upper respiratory tract infection or bronchiolitis than non-immunocompromised patients (8/9 versus 16/31, P = 0.05). Similarly, there was a tendency for patients 60 years of age or older to present with pneumonia more frequently than those below 60 (4/4 versus 20/36, P = 0.1). Of the 24 patients with clinically or radiologically confirmed pneumonia, 19 (79.2%) had crepitations and only 6 (25%) had bronchial breath sounds on physical examination. Of the 16 patients in whom wheezes were detected, 9 (56.3%) were not known to have asthma or other obstructive airway disease. Table 3 . Of the 24 patients with pneumonia, 21 (87.5%) were admitted to the hospital, and 20 (83.3%) had comorbidities. All patients with upper respiratory tract infections (11 patients) or bronchiolitis (2 patients) had uneventful recovery. Of the 24 patients with pneumonia, 14 (58.3%) had uneventful recovery, 4 (16.7%) recovered following some complications (acute respiratory distress syndrome, 2, respiratory failure, 1, septic shock, 1), 3 (12.5%) died because of M pneumoniae infection, and 3 (12.5%) died due to underlying comorbidities. The 3 patients who died of M pneumoniae pneumonia had other comorbidities; one had congestive heart failure, the second had congenital heart disease, and the third was a 3months old infant born prematurely at 32 weeks of gestation who previously had 3 episodes of pneumonia due to other pathogens.\nMycoplasma pneumoniae is one of the most common causes of atypical pneumonia accounting for 5-23% of community-acquired pneumonia, [1, 2, 3, 4, 5] In a study of 511 children with acute respiratory tract infection in Riyadh, Saudi Arabia, Mycoplasma pneumoniae was found to be the second most common causative agent after Respiratory syncytial virus (RSV) accounting for 9% of all cases, [8] In a study of 112 adult patients with community acquired pneumonia admitted to a military hospital in Riyadh, Saudi Arabia, this organism accounted for 6% of all cases, [9] In another retrospective study of 567 pneumonic episodes in adult patients from Al-Qassim area, the organism accounted for 23% of all episodes, [10] The organism also causes other relatively minor infections such as pharyngitis, tracheobronchitis, bronchiolitis, and croup. It is transmitted from person-to-person by infected respiratory droplets during close contact. It is most common in school-aged children, military recruits, and college students. [11] Most cases occur singly or as family outbreaks. Larger outbreaks can also occur in closed populations such as military recruit camps or boarding schools, [12] Infection occurs most frequently during the fall and winter in temperate climates but may develop year-round, [13] The average incubation period is 3 weeks following exposure, [6] Although rare, complications are protean and may involve virtually any organ system such as the respiratory system (e.g.: pleurisy, pneumothorax, acute respiratory distress syndrome, lung abscess), the hematologic system (e.g.: hemolytic anemia, intravascular coagulation, thrombocytopenia), the dermatologic system (e.g.: maculopapular or urticarial rashes, erythema multiforme, erythema nodosum), the musculoskeletal system (e.g.: myalgias, arthralgias, arthritis), the cardiovascular system (e.g.: pericarditis, myocarditis), the nervous system (e.g.: meningoencephalitis, Guillain-Barre syndrome, neuropathies, acute psychosis), or the eye (optic disc edema, optic nerve atrophy, retinal exudation and hemorrhages). [6, 7, 14, 15, 16, 17, 18] Immunity following infection is not long lasting. [11] In our study, the infection affected all age groups but was most common in infants (32.5%) and preschool children (22.5%), and least common in adults aged 15 to 30 years (2.5%) and elderly above 70 years of age (5%). This contrasts with data from temperate countries where the infection is most common in school-aged children, and young adults. [11] One possible explanation for this difference is that infants and preschool children perhaps had more severe infections than did school-aged children, and young adults which prompted presentation of the former group to the hospital. The infection occurred year-round but was most common in the fall (35%), and spring (30%), and least common in the summer (10%). Most infections were community-acquired (92.5%).\nMore than one half of patients (57.5%) presented with pneumonia, and about a third (27.5%) presented with upper respiratory tract infection, Immunocompromised patients and patients 60 years of age or older were more likely to present with pneumonia as opposed to upper respiratory tract infection than non-immunocompromised patients or those below 60 years of age. Cough (82.5%), fever (75%), and malaise (58.8%) were the most common presenting symptoms. Cough was usually dry or slightly productive of white sputum and mild to moderate in severity. Most febrile patients had mild to mod- erate fever of 39°C or less; high-grade fever of more than 39°C was rare. Crepitations (60%), and wheezes (40%) were the most common signs. Wheezes were as common in patients with no history of obstructive airway disease (9 patients) as it was in those with such a history (7 patients). Bronchial breathing as a sign of consolidation was detected in only one fourth of patients with pneumonia, which is consistent with the known disparity between clinical and radiological signs of M pneumoniae pneumonia. Crepitations, however, were detected in the majority (79.2%) of patients. Pleuritic chest pain and pleural effusion were rare.\nMore than half (56.5%) of the patients with pneumonia had uneventful recovery. Mortality from M. pneumoniae pneumonia was high (12.5%) and occurred only in patients with underlying comorbidities. None of the 9 patients with no underlying comorbidities died of M pneumoniae pneumonia. The relatively high complications rate (16.7%) and mortality (12.5%) related to M. pneumoniae pneumonia are likely due to selection bias as most patients with pneumonia were sick enough to require admission to the hospital (21/24 or 87.5%) and most of them had comorbidities (20/24 or 83.3%).\nIn conclusion, our data shed some light on the epidemiology and clinical features of M pneumoniae infections in one of the Saudi tertiary care centers. The data are comparable to those of other countries except for the finding that infections were more common in infants and preschool children than in school children and young adults. Additionally, mortality attributable to M. pneumoniae pneumonia was relatively high in patients with comorbidities. It is hoped this information will assist clinicians in their approach and management of respiratory tract infections." }, { "from": "gpt", "value": "Summary: [Summary placeholder]" } ]

[ { "from": "human", "value": "Full Text: Since its discovery as a biological messenger molecule more than 10 years ago, the gaseous molecule nitric oxide (NO • ) is now well recognized for its involvement in diverse biological processes, including vasodilation, bronchodilation, neurotransmission, tumor surveillance, antimicrobial defense and regulation of inflammatory-immune processes [1] [2] [3] . In the respiratory tract, NO • is generated enzymically by three distinct isoforms of NO • synthase (NOS-1, NOS-2 and NOS-3) that are present to different extents in numerous cell types, including airway and alveolar epithelial cells, neuronal cells, macrophages, neutrophils, mast cells, and endothelial and smoothmuscle cells. In contrast with the other two NOS isoforms (NOS-1 and NOS-3), which are expressed constitutively and activated by mediator-induced or stress-induced cell activation, NOS-2 activity is primarily regulated transcriptionally and is commonly induced by bacterial products and pro-inflammatory cytokines. As such, inflammatory diseases of the respiratory tract, such as asthma, acute respiratory distress syndrome (ARDS) and bronchiectasis, are commonly characterized by an increased expression of NOS-2 within respiratory epithelial and inflammatory-immune cells, and a markedly elevated local production of NO • , presumably as an additional host defense mechanism against bacterial or viral infections. The drawback of such excessive NO • production is its accelerated metabolism to a family of potentially harmful reactive nitrogen species (RNS), including peroxynitrite (ONOO -) and nitrogen dioxide (NO 2 • ), especially in the presence of phagocyte-generated oxidants. The formation of such RNS is thought to be the prime reason why NO • can in many cases contribute to the etiology of inflammatory lung disease [4] [5] [6] . Despite extensive research into both pro-inflammatory and anti-inflammatory actions of NO • , the overall contribution of NO • to inflammatory conditions of the lung is not easily predicted and seems to depend on many factors, such as the site, time and degree of NO • production in relation to the local redox status, and the acute or chronic nature of the immune response. In addition, our current understanding of the pro-inflammatory or pro-injurious mechanisms of NO • or related RNS is incomplete; this commentary will focus primarily on these latter aspects.\nTo explore a role for NO • (or NOS) in infectious or inflammatory diseases, two general research approaches have been taken: the use of pharmacological inhibitors of NOS isoenzymes, and the targeted deletion of individual NOS enzymes in mice. Both approaches suffer from the shortcoming that animal models of respiratory tract diseases generally do not faithfully reflect human disease. The use of NOS inhibitors to determine the contribution of individual NOS isoenzymes is also hindered by problems related to specificity and pharmacokinetic concerns. However, the unconditional gene disruption of one or more NOS isoforms, leading to lifelong deficiency, can have a markedly different outcome from pharmacological inhibition at a certain stage of disease, as the involvement of individual NOS isoenzymes can be different depending on disease stage and severity. Despite these inherent limitations, studies with the targeted deletion of NOS isoforms have led to some insights, indicating a role for NO • and NOS-2 in the etiology of some inflammatory lung diseases. For instance, mice deficient in NOS-2 are less susceptible to lethality after intranasal inoculation with influenza A virus, suffer less lung injury after administration of endotoxin, and display reduced allergic eosinophilia in airways and lung injury in a model of asthma, than their wild-type counterparts [7] [8] [9] . However, although the contribution of NOS-2 is expected in inflammatory conditions, recent studies have determined that NOS-1, rather than NOS-2, seems to be primarily involved in the development of airway hyper-reactivity in a similar asthma model [10] . The linkage of NOS-1 to the etiology of asthma was more recently supported in asthmatic humans by an association of a NOS-1 gene polymorphism with this disease, although the physiological basis for this association remains unclear [11] .\nDespite the potential contribution of NOS-2-derived NO • to lung injury after endotoxemia, the sequestration of neutrophils in the lung and their adhesion to postcapillary and postsinusoidal venules after administration of endotoxin were found to be markedly increased in NOS-2-deficient mice, and NOS-2 deficiency did not alleviate endotoxininduced mortality. It therefore seems that the 'harmful' and 'protective' effects of NOS-2 might contend with each other within the same model, which makes the assessment of the potential role of NOS in human disease even more difficult. In this context, it is interesting to note that humans or animals with cystic fibrosis have subnormal levels of NOS-2 in their respiratory epithelium, related to a gene mutation in the cystic fibrosis transmembrane conductance regulator [12] . This relative absence of epithelial NOS-2 might be one of the contributing factors behind the excessively exuberant respiratory tract inflammatory response in patients with cystic fibrosis, even in the absence of detectable respiratory infections. Overall, the apparently contrasting findings associated with NOS deficiency, together with concerns about animal disease models used, make interpretations and conclusions with regard to human lung disease all the more difficult.\nPharmacological inhibitors of NOS have also been found to reduce oxidative injury in several animal models of lung injury, such as ischemia/reperfusion, radiation, paraquat toxicity, and endotoxemia (see, for example, [13] [14] [15] ). However, results are again not always consistent, and in some cases NOS inhibition has been found to worsen lung injury, indicating anti-inflammatory or protective roles for NO • . All in all, despite these inconsistencies, there is ample evidence from such studies to suggest a contributing role of NO • in various respiratory disease conditions, which continues to stimulate research into mechanistic aspects underlying such pro-inflammatory roles and modulation of NO • generation as a potential therapeutic target.\nAlthough the pro-inflammatory and injurious effects of NO • might be mediated by a number of diverse mechanisms, it is commonly assumed that such actions are largely due to the generation of reactive by-products generated during the oxidative metabolism of NO • ; these are collectively termed RNS. One of the prime suspects commonly implicated in the adverse or injurious properties of NO • is ONOO -, a potent oxidative species formed by its almost diffusion-limited reaction with superoxide (O 2\n•-), which is a product of activated phagocytes and of endothelial or epithelial cells [4, 5, 13] . The formation of ONOOseems highly feasible under conditions of elevated production of both NO • and O 2\n•in vivo, and its oxidative and cytotoxic potential is well documented [5, 6] . However, because the direct detection of ONOOunder inflammatory conditions is virtually impossible because of its instability and high reactivity, the formation of ONOOin vivo can be demonstrated only by indirect methods. Thus, many investigators have relied on the analysis of characteristic oxidation products in biological molecules, such as proteins and DNA, most notably free or protein-associated 3-nitrotyrosine, a product of tyrosine oxidation that can be formed by ONOO -(and several other RNS) but not by NO • itself (see, for commentary review reports primary research http://respiratory-research.com/content/1/2/067 example, [5] ). Indeed, elevated levels of 3-nitrotyrosine have been observed in many different inflammatory conditions of the respiratory tract [16] , which illustrates the endogenous formation of ONOOor related RNS in these cases. However, without known evidence for functional consequences of (protein) tyrosine nitration, the detection of 3-nitrotyrosine should not be regarded as direct proof of a pro-inflammatory role of NO • . Moreover, although the detection of 3-nitrotyrosine has in most cases been interpreted as conclusive evidence for the formation of ONOOin vivo (see, for example, [17] ), it should be realized that other RNS formed by alternative mechanisms might also contribute to endogenous tyrosine nitration. Indeed, it has recently become clear that the presence of inflammatory-immune cells, and specifically their heme peroxidases myeloperoxidase (MPO) and eosinophil peroxidase (EPO), can catalyze the oxidization of NO • and/or its metabolite NO 2 to more reactive RNS and thereby contribute to protein nitration [16, 18, 19] . This notion is further supported by the fact that 3-nitrotyrosine is commonly detected in tissues affected by active inflammation, mostly in and around these phagocytic cells and macrophages, which can also contain active peroxidases originating from apoptotic neutrophils or eosinophils. Hence, the detection of 3-nitrotyrosine in vivo cannot be used as direct proof of the formation of ONOO -, but merely indicates the formation of RNS by multiple oxidative pathways, possibly including ONOObut more probably involving the activity of phagocyte peroxidases [16, 20] . In this regard, a preliminary study with EPO-deficient mice has recently demonstrated the critical importance of EPO in the formation of 3-nitrotyrosine in a mouse model of asthma [21] . Future studies with animals deficient in MPO and/or EPO will undoubtedly help to clarify this issue.\nGiven the considerable interest in 3-nitrotyrosine as a collective marker of the endogenous formation of NO •derived RNS, the crucial question remains of whether the detection of 3-nitrotyrosine adequately reflects the toxic or injurious properties of NO • . The formation of ONOO -(or of other RNS that can induce tyrosine nitration) might in fact represent a mechanism of decreasing excessive levels of NO • that might exert pro-inflammatory actions by other mechanisms. For instance, NO • can promote the expression of pro-inflammatory cytokines or cyclo-oxygenase (responsible for the formation of inflammatory prostanoids) by mechanisms independent of ONOO - [22, 23] , and the removal of NO • would minimize these responses. Furthermore, although ONOOor related NO •derived oxidants can be cytotoxic or induce apoptosis, these effects might not necessarily relate to their ability to cause protein nitration (see, for example, [16]). For instance, the bactericidal and cytotoxic properties of ONOOare minimized by the presence of CO 2 , even though aromatic nitration and other radical-induced modifications are enhanced [5] . Similarly, the presence of NO 2 in the incubation medium decreases the cytotoxicity of MPO-derived hypochlorous acid (HOCl) toward epithelial cells or bacteria, despite increased tyrosine nitration of cellular proteins (A van der Vliet and M Syvanen, unpublished data). Thus, it would seem that the cytotoxic properties of NO • and/or its metabolites might instead be mediated through preferred reactions with other biological targets, and these might not necessarily be correlated with the degree of tyrosine nitration. The extent of nitrotyrosine immunoreactivity in bronchial biopsies of asthmatic patients was correlated directly with measured levels of exhaled NO • and inversely with the provocation concentration for methacholine (PC 20 ) and forced expiratory volume in 1 s [24] . However, an immunohistochemical analysis of nitrotyrosine and apoptosis in pulmonary tissue samples from lung transplant recipients did not identify patients with an imminent risk of developing obliterative bronchiolitis [25] . It is therefore still unclear to what degree tyrosine nitration relates to disease progression.\nSeveral studies with purified enzymes have suggested that nitration of critical tyrosine residues adversely affects enzyme activity, but there is as yet no conclusive evidence in vivo for biological or cellular changes as a direct result of tyrosine nitration [16, 20] . For instance, tyrosine nitration was suggested to have an effect on cellular pathways by affecting cytoskeletal proteins or tyrosine phosphorylation, thereby affecting processes involved in, for example, cell proliferation or differentiation [16, 26] . Recent studies have provided support for selective tyrosine nitration within certain proteins [27, 28] and of selective cellular targets for nitration by RNS (see, for example, [29, 30] ), and such specificity might indicate a potential physiological role for this protein modification. However, in none of these cases could tyrosine nitration be linked directly to changes in enzyme function. Chemical studies have indicated that tyrosine nitration by RNS accounts for only a minor fraction of oxidant involved, and reactions with other biological targets (thiols, selenoproteins, or transition metal ions) are much more prominent [5, 6] . Indeed, the extent of tyrosine nitration in vivo is very low (1-1000 per 10 6 tyrosine residues according to best estimates [16]), although different analytical methods used to detect 3-nitrotyrosine in biological systems have often given inconsistent results. It is important to note that recent rigorous studies have unveiled substantial sources of artifact during sample preparation, which might frequently have led to an overestimation of tyrosine nitration in vivo in previous studies [31] .\nOn the basis of current knowledge, the formation of 3-nitrotyrosine seems to be merely a marker of NO •derived oxidants, with as yet questionable pathophysiological significance. In view of the low efficiency of tyrosine nitration by biological RNS, and the endogenous presence of variable factors that influence protein nitration (antioxidants or other RNS scavengers), it seems unlikely that tyrosine nitration is a reliable mechanism of, for example, enzyme regulation. Nevertheless, the recent discovery of enzymic 'denitration' mechanisms that can reverse tyrosine nitration [32] merits further investigation of the possibility that tyrosine nitration might reflect a signaling pathway, for example analogous to tyrosine phosphorylation or sulfation.\nThe biological effects of NO • are mediated by various actions, either by NO • itself or by secondary RNS, and the overall biochemistry of NO • is deceptively complex. Moreover, the metabolism and chemistry of NO • depend importantly on local concentrations and pH; the recently described acidification of the airway surface in asthmatics [33] might significantly affect NO • metabolism in these patients. It is well known that interactions with the ion centers of iron or other transition metals are responsible for many of the signaling properties of NO • ; the activation of the heme enzyme guanylyl cyclase and the consequent formation of cGMP is involved not only in smooth-muscle relaxation but also in the activation of certain transcription factors, the expression of several pro-inflammatory and anti-inflammatory genes (including cytokines and cyclo-oxygenase), and the production of respiratory mucus [22] [23] [24] [25] [26] [27] [28] [29] [30] [31] [32] [33] [34] . In addition to such direct signaling properties, many actions of NO • might be due largely to secondary RNS that can react with multiple additional targets, in some cases forming nitroso or nitro adducts as potentially unique NO • -mediated signaling mechanisms. As discussed, the formation of protein nitrotyrosine has been postulated as a potential RNSspecific signaling pathway. Even more interest has been given to the reversible S-nitros(yl)ation of protein cysteine residues, which has been proposed to affect a number of redox-sensitive signaling pathways, for example by the activation of p21 ras or the inhibition of protein tyrosine phosphatases [35, 36] . Similar modifications of reactive cysteine residues in transcription factors such as nuclear factor-κB or of caspases contribute to the regulation of gene expression and apoptosis [37] [38] [39] . The precise mechanisms leading to protein S-nitrosylation in vivo are still not clarified, but might involve dinitrogen trioxide (formed during the autoxidation of NO • ), iron-nitrosyl complexes, and perhaps ONOO - [16] ; changes in NO • metabolism during inflammatory lung diseases undoubtedly affect such NO • -dependent signaling pathways. In addition, S-nitrosylation can be reversed by either enzymic (thioredoxin or glutaredoxin) or chemical (metals or oxidants) mechanisms, and evidence is increasing that this reversible modification is complementary to more widely accepted oxidant-dependent redox signaling pathways [40] . The reported alterations in S-nitrosothiol levels in tracheal secretions of patients with asthma or cystic fibrosis further point to altered NO • metabolism in these cases, and might provide new clues to the role of S-nitrosylation in controlling such disease processes [41, 42] . Unfortunately, technical limitations to detect S-nitrosylation in specific protein targets in vivo have limited a full understanding of this potential signaling pathway; further research in these areas can be expected to establish more clearly its significance in the pathophysiological properties of NO • .\nDespite the by now overwhelming evidence for the increased formation of NO • and NO • -derived oxidants in many different lung diseases, the exact contribution of NO • or its metabolites to inflammatory lung disease is still unclear. Indeed, NO • might have distinctly different roles in different stages of respiratory tract inflammatory diseases, being pro-inflammatory or pro-injurious in acute and severe stages but perhaps being protective and antiinflammatory in more stable conditions; it is uncertain whether NOS is a suitable therapeutic target in the management of inflammatory lung disease. Caution is clearly needed when interpreting observations of tyrosine nitration in animal models of disease or in human tissues, which does not automatically implicate ONOO -(as often thought), but rather indicates the formation of RNS by various mechanisms. Furthermore, animal models of chronic lung disease that usually reflect short-term or acute inflammation might not always be applicable to chronic airway diseases in humans. For instance, phagocyte degranulation, a common feature observed in association with human airway inflammatory diseases such as asthma, does not seem to occur in mouse models of asthma [43] . Therefore the importance of granule proteins, such as heme peroxidases, in the pathology of human airway diseases might not be adequately reflected in such animal models. More work with animal models more characteristic of human diseases or with biopsy materials from human subjects will be required to unravel the precise role of NO • in inflammatory lung disease, and might establish more clearly whether the pharmacological inhibition of NOS isoenzymes can be beneficial. This brings up the interesting paradox that, despite presumed adverse roles of NO • in such inflammatory lung diseases as septic shock and ARDS, NO • inhalation has been suggested as a potential therapeutic strategy to improve overall gas exchange [44] . Intriguingly, in a rat model of endotoxemia, inhalation of NO • was found to reduce neutrophilic inflammation and protein nitration [45] , again supporting the crucial involvement of inflammatory-immune cells in this protein modification.\nFor a better assessment of the role of NO • in respiratory tract diseases in humans, the production of RNS and/or characteristic markers would need to be more carefully monitored during various disease stages. Care should be given to analytical techniques, their quantitative capacity and the possibility of artifacts. The monitoring of exhaled NO • , although convenient and non-invasive, does not reflect the actual production or fate of NO • in the respiratory tract and is not well correlated with NOS activity in the lung [46] . We therefore need to continue research into the local biochemistry of NO • in the lung, taking into account the presence of secreted or phagocyte peroxidases and possible changes in local pH, as in asthmatic airways [33] , that might modulate NO • activity and metabolism. This might result in a better understanding of relationships between the various metabolic endproducts of NO • (NO 2 -, NO 3 -, or nitroso and nitro adducts) and its pro-inflammatory or injurious properties." }, { "from": "gpt", "value": "Summary: [Summary placeholder]" } ]

[ { "from": "human", "value": "Full Text: Surfactant protein-D (SP-D) is a member of the collagenous subfamily of calcium-dependent lectins (collectins) that includes pulmonary surfactant protein A (SP-A) and the serum mannose-binding lectin [1] [2] [3] . Collectins inter-act with a wide variety of microorganisms, lipids, and organic particulate antigens, and can modulate the function of immune effector cells and their responses to these ligands. This article reviews what is currently known about the sites of production, structure, function, and regulated expression of SP-D. Emphasis will be placed on functional attributes, known ligand interactions, and structure-function relationships believed to be important for host defense. For additional information on SP-A and other members of the collectin family, the reader is referred to other recent reviews [4] [5] [6] .\nSP-D is synthesized and secreted into the airspaces of the lung by the respiratory epithelium [1] . At the alveolar level, SP-D is constitutively synthesized and secreted by alveolar type II cells. More proximally in the lung, SP-D is secreted by a subset of bronchiolar epithelial cells, the non-ciliated Clara cells. Because SP-D is stored within the secretory granules of Clara cells [7, 8] , it seems likely that SP-D is subject to regulated secretion via granule exocy-tosis at this level of the respiratory tract. In some species, SP-D is also synthesized by epithelial cells and/or submucosal glands associated with the bronchi and trachea [9] . Although many alveolar macrophages show strong cytoplasmic and/or membrane labeling with antibody against SP-D, they do not contain detectable SP-D message.\nThe lung seems to be the major site of SP-D production. However, there is increasing evidence for extrapulmonary sites of expression as assessed with monoclonal or affinity-purified antibodies, reverse-transcriptase-mediated PCR (RT-PCR), and/or hybridization assays of tissues from humans and other large mammals [10 • ,11-14] (summarized in Table 1 ). It is difficult to entirely exclude crossreactions or amplification of related sequences; however, localization to many of these sites in human tissues was confirmed by using monoclonal antibodies in combination with RT-PCR with sequencing of the amplified products [10 • ]. Non-pulmonary expression seems to be largely restricted to cells lining epithelial surfaces or ducts and certain glandular epithelial cells that are in direct or indirect continuity with the environment. Notable exceptions to this generalization might include heart, brain, pancreatic islets, and testicular Leydig cells. SP-D has also been identified in amnionic epithelial cells by immunohistochemistry [15] ; however, it is unclear whether this is synthesized locally or derived from the lung by way of the amniotic fluid. Interestingly, in many of these sites SP-D microscopically co-localizes with gp-340, an SP-D binding protein and putative SP-D receptor [10 • ].\nSites of extrapulmonary expression have also been described in small mammals. In the rat, SP-D message was identified in RNA extracted from skin and blood vessel [16] , and both protein and message were identified in gastric mucosa [17] and mesentery [13] . Using RT-PCR, SP-D message has also been identified in mouse stomach, heart, and kidney [14] .\nSP-D (43 kDa, reduced) consists of at least four discrete structural domains: a short, N-terminal domain; a relatively long collagenous domain, a short amphipathic connecting peptide or coiled-coil neck domain, and a C-terminal, Ctype lectin carbohydrate recognition domain (CRD). Each molecule consists of trimeric subunits (3 × 43 kDa), which associate at their N-termini (Fig. 1) . Although most preparations of SP-D contain a predominance of dodecamers (that is, four trimeric subunits), the proportions of various oligomers vary between species. For example, rat lavage and recombinant rat SP-D are almost exclusively assembled as dodecamers (four trimers), whereas recombinant human SP-D is secreted as trimers, dodecamers and higher-order multimers [18] . SP-D isolated from the lavage of some patients with alveolar proteinosis consists predominantly of higher-order multimers, which can contain up to 32 (or more) trimeric subunits (Fig. 1 ).\nRecent crystallographic and mutagenesis studies suggest that the structural determinants of saccharide binding are similar to those originally described for mannose-binding lectin [19,20,21 • ,22 • ]. At least two bound calcium ions and two intrachain disulfide crosslinks stabilize the required tertiary structure, and Glu321 and Asn323 within the CRD participate in glucose/mannose type recognition. Interactions with at least one glycolipid ligand, phosphatidylinositol (PI), require the participation of the C-terminal end of the protein [23, 24] .\nA trimeric cluster of CRDs is necessary for high-affinity binding to carbohydrate ligands [21 • ,25]. The crystal structure of human SP-D suggests that the spatial distribution of CRDs within a trimeric subunit permits simultaneous and cooperative interactions with two or three glycoconjugates displayed on the surface of a particulate ligand [21 • ]. Furthermore, solid-phase binding studies have shown that monomeric CRDs have an approximately 10-fold lower binding affinity for multivalent ligands than trimeric CRDs.\nCrystallographic studies of human SP-D further suggest that the spatial organization of CRDs within a trimer is stabilized by interactions of the C-terminal sequence with the trimeric neck domain [21 • ,26]. Interestingly, the three CRDs show a deviation from threefold asymmetry, suggesting some flexibility of the CRDs in relation to the neck. Thus, the dependence of the binding of PI on the C-terminal sequence could reflect conformational effects, rather than the direct participation of this sequence in ligand interactions.\nThe collagen domain length of SP-D is highly conserved and lacks interruptions in the repeating Gly-X-Y sequence (in which X and Y are different amino acids). As for other collagenous proteins, this domain is enriched in imino acids and contains hydroxyproline. Unlike SP-A, SP-D also contains hydroxylysine. Although the collagen domain of rat, human, bovine, and mouse SP-D lacks cysteine residues, cDNA sequencing has identified a codon for cysteine within the collagen domain of pig SP-D [27 • ]; this suggests the possibility of alternative patterns of chain association and oligomeric assembly for pig SP-D.\nThe first translated exon of SP-D contains a highly conserved and unusually hydrophilic Gly-X-Y sequence that shows little homology with the remainder of the collagen sequence. The functional significance of this region is unknown. However, it has been suggested that this region contributes to oligomer assembly or mediates interactions with cellular receptors.\nThe collagen domain determines the maximal spatial separation of trimeric, C-terminal lectin domains within SP-D molecules, but might also contribute to normal oligomeric assembly and secretion. For example, deletion of the entire collagen domain of rat SP-D results in the secretion of trimers rather than dodecamers [28] . In addition, 2,2-dipyridyl, an inhibitor of prolyl hydroxylation that interferes with the formation of a stable collagen helix, causes the intracellular accumulation of 43 kDa monomers and dimers [29] . In any case, the complete conservation of the number of Gly-X-Y triplets suggests that the spatial separation of trimeric CRDs is critical for normal SP-D function.\nThe N-terminal peptide of the mature protein contains two conserved cysteine residues at positions 15 and 20. These residues participate in interchain disulfide crosslinks that stabilize the trimer, as well as the N-terminal association of four or more trimeric subunits. Stable oligomerization of trimeric subunits permits cooperative or bridging interactions between spatially separated binding sites on the same surface or on different particles.\nThe process of forming interchain disulfide bonds is complex, and appropriate crosslinking of the N-terminal domains might be rate limiting for secretion [30] . Subcellular fractionation studies suggest that interchain bonds form initially between the three chains of a trimeric subunit. Subsequent rearrangements within the rough endoplasmic reticulum might allow the covalent crosslinking of a single chain from one subunit and two crosslinked chains of another, with the associated elimination of free thiol groups. Mutant proteins that contain unpaired N-terminal cysteine residues are not secreted. However, it is unclear whether this results from abnormalities in disulfide bonding itself, or the failure to stabilize the required N-terminal conformation.\nThe collagen domain contains hydroxylysyl-derived glycosides and a single N-linked oligosaccharide. In most species (human, rat, mouse, and cow) the site of N-linked glycosylation is located near the N-terminal end of the collagenous domain. Recently, it was shown that pig SP-D has an additional potential site of N-linked glycosylation within the CRD [27 • ]. Although rat and human lung lavage SP-D seem to be sialylated, as suggested by charge heterogeneity and cleavage with highly purified neuraminidase, preparations of human amniotic fluid and bovine lavage SP-D recovered from amniotic fluid showed predominantly complex type biantennary structures and no sialic acid [31] .\nA variant form of SP-D (50 kDa) has been identified in lavage from a subset of human lavage samples; this protein shows O-linked glycosylation of threonyl residues within the N-terminal peptide domain [32 • ]. At present, the functional significance of these sugars is not known. The presence of O-linked glycosylation within the N-terminal domain might be predicted to interfere with normal dodecamer assembly. In this regard, the O-glycosylated 50 kDa form of human SP-D is recovered as trimeric subunits or smaller species.\nAs for many glycoproteins, the functional role of the attached carbohydrate is unknown. Mutational analysis has shown that the N-linked sugar on rat SP-D is not required for secretion, for dodecamer formation, or for interactions with a variety of microorganisms [29,33].\nConsistent with its designation as a 'mannose-type' C-type lectin, SP-D preferentially binds to simple and complex saccharides containing mannose, glucose, or inositol [34, 35] . SP-D also interacts with specific constituents of pulmonary surfactant including PI [36-38] and glucosylceramide [39] . Binding to glucosylceramide involves interactions of the carbohydrate-binding sequences of the CRD with the glucosyl moiety. However, the interaction of SP-D with PI involves interactions with the lipid, as well as CRD-dependent interactions with the inositol moiety [24, 40] .\nMicroorganisms are surfaced with a diverse and complex array of polysaccharides and glycoconjugates, and most classes of microorganism contain one or more sugars recognized by SP-D. However, the outcome of this interaction depends on the specific organism and can be modified by the conditions of microbial growth. The potential consequences of this interaction include the following: varying degrees of lectin-dependent aggregation (namely, microbial agglutination), enhanced binding of microorganisms or microbial aggregates to their 'receptors' on host cells, phagocyte activation, and opsonic enhancement of phagocytosis and killing, potentially involving one or more cellular receptors for SP-D. Binding to organisms in suspension is often -but not always -accompanied by some degree of aggregation.\nSP-D binds to purified lipopolysaccharide (LPS) isolated from a variety of Gram-negative organisms [35, 41] . In addition, LPS is the major cell wall component that is labeled on lectin blotting of outer membranes isolated from Escherichia coli [41] . The latter interactions involve the recognition of the core oligosaccharide domain, which contains glucose and heptose [41] . SP-D interacts preferentially with purified LPS molecules characterized by short or absent O-antigens and preferentially agglutinates bacterial strains expressing a predominance of rough (O-antigen-deficient) LPS [41, 44] .\nAlthough the core oligosaccharide domain of LPS constitutes the major ligand for SP-D on at least some Gram-negative bacteria, the mechanism of interaction with this group of microorganisms is probably heterogeneous. SP-D binds to some smooth, unencapsulated strains of Gram-negative bacteria by immunofluorescence. The mechanism is uncertain; the quantity or quality of binding differs from that observed for rough strains and does not necessarily result in agglutination. LPS molecules on the surfaces of bacteria show heterogeneity in the extent of maturation, so it is possible that this interaction is mediated by a subpopulation of LPS with deficient O-antigens and that the density of binding sites is too low for high-affinity binding.\nThe recognition of the surface glycoconjugates on Gramnegative bacteria by SP-D depends not only on the expression of lectin-specific residues by a given strain or species, but also on the accessibility of these residues [1, 45] . For example, SP-D binds inefficiently to the core region of LPS of encapsulated Klebsiella, but efficiently agglutinates the corresponding unencapsulated phase variants. Interactions of SP-D with the core oligosaccharides of Gram-negative organisms are also influenced by the number of repeating saccharide units associated with the terminal O-antigen of the LPS [41,44].\nOther potential ligands include the O-antigen domain of LPS, certain capsular polysaccharides, and membraneassociated glycoproteins. In this regard, SP-D can bind to di-mannose containing O-antigens expressed by a subset of Klebsiella serotypes (I Ofek, H Sahly and EC Crouch, unpublished data). Although other C-type lectins, specifically SP-A and the mannose receptor, can interact with specific capsular polysaccharides [46], a specific interaction of SP-D with capsular glycoconjugates or exopolysaccharides has not been described.\nThe mechanism of interaction with Gram-positive organisms has not been elucidated. Lipoteichoic acids, which are the major glycolipids associated with the Gram-positive cell wall, do not detectably compete with LPS for binding to SP-D (I Ofek, A Mesika, M Kalina, Y Keisari, D Chang, D McGregor and EC Crouch, manuscript submitted). In preliminary studies we observed that binding was competed only partly with maltose and/or EDTA, raising the possibility that binding might be more complex than for some Gram-negative organisms. . However, similar effects were observed when the neutrophils were preincubated with SP-D, and there was only a slight enhancement of uptake when bacteria were incubated with human SP-D and washed before their addition to neutrophils. Notably, the extent of binding and internalization was dependent on the extent of multimerization, with human SP-D multimers demonstrating the highest potency. Differences in cell type, the extent of SP-D multimerization, or differences in size or organization of bacterial aggregates could account for some of the apparent inconsistencies.\nAlthough LPS mediates the binding of SP-D to at least some Gram-negative bacteria, SP-D can also bind to spe- In the latter study the authors suggested that fungal aggregation inhibits phagocytosis. Interestingly, SP-D binding directly inhibited fungal growth and decreased the outgrowth of pseudohyphae, the invasive form of the fungus, in the absence of phagocytic cells [57] . It is possible that these effects are also secondary to agglutination, possibly as result of nutrient deprivation.\nPurified rat and human SP-D inhibit the infectivity and hemagglutination activity of influenza \nSP-D can interact with host cells, both directly and indirectly. As indicated above, SP-D can enhance the phagocytosis and killing of certain microorganisms and enhance the oxidant response to microbial binding. However, at present there is only one study that suggests that the enhancement of phagocytosis by SP-D might involve the participation of an opsonic receptor. Furthermore, the enhanced uptake of IAV seems to be mediated by viral aggregation, with enhanced interactions of the virus with its natural receptors on the host cell.\nIn any case, SP-D can interact directly with host cells, and in some cases can influence their behavior. SP-D is chemotactic and haptotactic for neutrophils and certain mononuclear phagocytes [59 • ,67-69] and can elicit directional actin polymerization in alveolar macrophages [69] . In this regard, SP-D is considerably more potent than SP-A. Early studies with natural proteins isolated from silicotic animals reported directed effects on the oxidant metabolism of isolated alveolar macrophages [70] . However, such effects can probably be attributed to endotoxin contamination and/or aggregation. Purified dodecamers do not significantly increase the production of nitric oxide [71] or of proinflammatory cytokines such as tumor necrosis factor-α (Y Kesari, H Wang, A Mesika, E Crouch and I Ofek, unpublished data). Interestingly, purified SP-D has been reported to increase the production of several metalloproteinases in the absence of a significant effect on proinflammatory cytokine production [72] .\nDespite the ability of SP-D to modulate a variety of cellular functions, little is currently known about potential cellular receptors for this protein. compartments [73] , but it is unclear whether the uptake is receptor dependent and whether SP-D is being internalized in association with specific ligands.\nThere are at least two classes of binding to host cells: CRD-dependent and CRD-independent. Some studies have demonstrated CRD-dependent binding to phagocytes that can be inhibited with EDTA or competing saccharides, both in vitro and in vivo.\nAs indicated above, the ability of SP-D to elicit the chemotaxis of neutrophilic and monocytic cells depends on the lectin activity of SP-D [68] . In addition, Kuan and coworkers reported that extracting formaldehyde-fixed alveolar macrophages with detergents largely eliminates the binding of purified SP-D, suggesting a membrane-associated ligand or glycolipid receptor [73] . Dong and Wright have extended these findings and suggest that PI can contribute to SP-D binding by alveolar macrophages [74] .\nIt is of interest that SP-D can bind to recombinant sCD14 through interactions with N-linked oligosaccharides [51 • ].\nGiven that the membrane-associated form of CD14 is widely expressed on host cells, it is possible that CD14 can serve as a binding site on macrophages and other cell types.\nThe phagocytic uptake of certain bacteria by neutrophils is also inhibited by calcium chelation or competing sugars [42]; however, this could result from the inhibition of microbial agglutination rather than lectin-dependent interactions with the phagocyte. Wang et al suggested that SP-D can bind to lymphocytic cells by a lectin-dependent mechanism [75 •• ] . In this regard, it is interesting to note that glucosylceramide, a ligand for SP-D in vitro, is one of the most abundant neutral glycolipids expressed by lymphoid cells.\nReid and co-workers were the first to present evidence for lectin-independent binding [76] . These and other studies suggested that binding does not involve known C1q or collectin receptors. The only putative receptor protein, gp-340, is a widely expressed member of the scavenger receptor superfamily [77,78 • ]. It binds to the CRD of SP-D in a calcium-dependent manner that does not require the lectin activity of SP-D. Although the protein has been immunolocalized to alveolar macrophage membranes and distributes together with SP-D in many different human tissues [10 • ,77], it has not yet been shown to mediate the binding of SP-D to these cells or to participate in signal transduction events. The cDNAs isolated from lung have not shown a membrane-spanning region [77] , and the protein is abundant as a soluble component in BAL. Given that gp-340 is a highly multimerized protein that contains numerous potential ligand binding domains (Fig. 1b) , it is possible that the protein cooperates with SP-D in the neu-tralization or clearance of certain ligands rather than specifically mediating the interactions of SP-D with host cells.\nWright and co-workers have demonstrated the binding of SP-D to isolated type II pneumocytes. The mechanism seems distinct from the binding to macrophages [79 • ]. The binding was dependent on concentration, time, and temperature and required calcium; it was not sensitive to protease treatment or to PI-phospholipase C. Although the internalized SP-D was degraded or recycled to lamellar bodies, SP-D binding did not alter the uptake of surfactant lipids.\nSP-D has demonstrated comparatively few direct effects on the metabolism of host cells, at least in situations where self-aggregation and endotoxin contamination have been excluded. One possible explanation is that modulation of cellular function requires the prior interaction of SP-D with a ligand. This would have numerous potential physiological advantages, because the presence of 'active' protein might be restricted to sites of microbial or antigenic deposition. The binding of complex, multivalent, particulate antigens to two or more CRDs could markedly alter the conformation of SP-D molecules, with respect to the spatial orientation of the arms in relation to the N-terminal crosslinking domain and/or with respect to the spatial orientation of the CRDs within a given trimeric subunit. Thus, the 'charging' of SP-D with a particulate ligand could lead to local or distant conformational changes that expose 'cryptic' binding sites for cellular receptors.\nThere is some preliminary evidence consistent with the notion that the interaction of SP-D with a ligand alters its capacity to activate host cells. Table 3 and discussed below.\nSP-D can be isolated in different multimeric forms from proteinosis lavage [32 • ] and are produced by Chinese hamster ovary K1 cells transfected with human SP-D cDNA [18] . As described previously, the effects of SP-D on the neutrophil response to influenza virus are highly dependent on the ability of SP-D to agglutinate the viral particles, and the agglutination activity is directly correlated with the extent of multimerization. Trimers can bind to the virus but have little capacity to modulate neutrophil interactions. By contrast, highly multimerized proteins show greater activity than dodecamers [81] .\nGiven these observations, factors that favor enhanced oligomerization or lead to the accumulation of trimeric subunits promote might influence SP-D function. For example, the liberation of active trimers by a hypothetical microbial protease could lead to the accumulation of molecules that might inhibit the aggregation-dependent activities of SP-D.\nIn contrast, recombinant trimeric CRDs can stimulate chemotaxis [67] and decrease viral infectivity [65 • ]. Although higher-order oligomers of SP-D can self-aggregate and precipitate in the presence of calcium in vitro, the functional consequences are not known.\nThe lectin activity of SP-A is decreased after the nitric oxide-dependent nitration of tyrosine residues [82] , and nitration decreases the ability of SP-A to enhance the adherence of Pneumocystis to alveolar macrophages [83] . However, similar findings have not yet been reported for SP-D. Conditions of mildly acidic pH, as might be found in endocytic compartments, are predicted to disrupt the lectin-dependent activities of SP-D [34]. Proteolytic degradation remains an important possibility. However, SP-D is highly resistant to degradation by a wide variety of neutral proteases in vitro, and degradation products have not yet been shown to accumulate under pathological conditions in vivo.\nGlucose concentrations at levels encountered in diabetes can interfere with SP-D's ability to interact with specific strains of IAV or other microorganisms in vitro [84 • ]. Many microorganisms release cell wall polysaccharides or glycoconjugates, which might interfere with the binding of collectins to the same or other organisms. In this regard, SP-D recovered from rats after the instillation of LPS into the airway shows decreased lectin activity, which is attributed to occupancy of the CRD with LPS [49 • ]. It seems reasonable to speculate that some organisms might compete with other organisms for binding to SP-D. Such a situation could conceivably predispose to secondary infections. Lastly, the potential inhibitory effects of competing saccharide ligands presents important methodological considerations for experiments using carbohydrate-containing cell culture medium or buffers. Non C-type lectins (such as ficolins)\nIt is difficult to predict the functions of SP-D within the airspace. Other lectins with overlapping specificity are also present. Although the levels of mannose-binding lectin are probably low in the absence of increased vascular permeability, SP-A and the macrophage mannose receptor could conceivably interact with the same ligands in the distal airways and alveoli. Such interactions could lead to antagonistic or cooperative effects. Furthermore, we have little knowledge regarding the microanatomic distribution of these molecules in specific circumstances in vivo.\nAlthough most SP-A is probably associated with the insoluble phase of the alveolar lining material, and the macrophage mannose receptor is membrane-associated, the distribution might be altered in the setting of lung injury.\nModels of SP-D deficiency show no detectable anatomical or physiological abnormalities at birth. However, the animals gradually develop a patchy, subpleural alveolar lipidosis with associated type II cell hypertrophy, the accumulation of enlarged and foamy macrophages, and an apparent expansion of peribronchial lymphoid tissue [85 • ,86 • ]. Interestingly, the mice eventually develop distal-acinar emphysema and areas of subpleural fibrosis, which could reflect a continuing inflammatory reaction associated with abnormal oxidant metabolism and metalloproteinase activity [87 • ]. By contrast, SP-A-deficient mice (-/-) show essentially normal respiratory function and surfactant lipid metabolism [88, 89] but numerous apparent host defense abnormalities [90] .\nThe capacity of SP-D to bind to specific strains of influenza A in vitro is highly correlated with the capacity of the virus to proliferate in mice in vivo [62] . Specifically, strains with more oligosaccharide attachments on the HA are preferentially neutralized by SP-D in vitro and show decreased proliferation in mice. Because the administration of mannan together with the virus increased the replication of IAV in the lung, the involvement of a mannose-type, C-type lectin was implicated.\nSP-D-sensitive IAV strains also replicate to higher titers in the lungs of diabetic mice than in nondiabetic controls [84 • ]. Replication of the virus is positively correlated with blood glucose level, and decreases in response to insulin treatment. Significantly, blood glucose levels comparable to those measured in the diabetic mice were sufficient to inhibit the interaction of SP-D with these viral strains in vitro. PR-8, a strain that does not interact with SP-D but does interact with SP-A, replicated to the same extent in diabetic and control mice.\nSP-D levels increase in association with certain infections. For example, SP-D levels, but not the levels of serum mannose-binding lectin, increase markedly after IAV infection [62] . Impressive increases in SP-D have also been observed in murine models of Pneumocystis carinii [91] and P. aeruginosa infection [92] .\nSP-D-deficient mice have not yet been extensively characterized with respect to host defense function. However, they show decreased viral clearance and enhanced inflammation after challenge with respiratory syncytial virus [93] and IAV (AM Levine, personal communication). In addition, they show increased inflammation, increased oxidant production, and decreased macrophage phagocytosis in response to intratracheally instilled group B streptococcus and Haemophilus influenzae (AM Levine, personal communication). Although the overexpression of wild-type SP-D in type II pneumocytes with the SP-D-deficient mice can prevent the lipidosis and inflammatory changes [94] , the ability of overexpressed wild-type SP-D or exogenous SP-D to ameliorate these abnormalities has not yet been described. The coexisting pulmonary abnormalities also complicate the interpretation of challenge models. For example, macrophage activation might enhance killing and offset any decrease that results more directly from SP-D deficiency. SP-D deficiency modifies the host response to instilled LPS with decreased lung injury and inflammatory cell recruitment [50].\nMolecules that can bind to potential antigens and deliver them to macrophages and other antigen-presenting cells might contribute to the development of acquired immunity. In this regard, a few published observations suggest possible roles in the development of humoral and/or cellular immunity in response to microorganisms or complex organic antigens. For example, SP-D can decrease interleukin-2dependent T-lymphocyte proliferation [95 • ]. Interestingly, single-arm mutants were at least as potent as intact dodecamers in mediating this effect. SP-D also binds to oligosaccharides associated with dust mite allergen [96 • ], and can inhibit the binding of specific IgE to these allergens, possibly through direct, CRD-dependent binding to lymphocytes [96 • ]. Thus, alterations in the level of SP-D (or the state of oligomerization) might influence the development of immunological responses and contribute to the pathogenesis of asthma and other hypersensitivity disorders.\nThere are other potential interplays between humoral immunity and collectins with regard to antimicrobial host defense. For example, increased glycosylation of IAV coat proteins, an adaptation that is believed to help the virus to evade antibody-mediated neutralization, is associated with increased reactivity with SP-D and other collectins [62]. Thus, the relative potential importance of antibody and collectin-mediated host defenses might be influenced by subtle variations in the structure of the microbial surface.\nThere is little recent information on the developmental regulation of SP-D expression. In general, SP-D increases rapidly late in gestation [97] [98] [99] [100] . The production of SP-D increases during the culture of fetal lung explants, and expression can be increased with glucocorticoids [98, 100, 101] . The exposure of fetal rats to glucocorticoids in vivo leads to precocious expression with increased numbers of SP-D-expressing cells and increased cellular levels of SP-D message [98, 101, 102] .\nAlthough SP-D is produced constitutively within the lung, protein accumulation and gene expression are inducible and increases in SP-D expression have been observed in a number of disease states or models (Tables 4 and 5 ). In general, the synthesis and secretion of SP-D increase in association with lung injury and activation of the respiratory epithelium [1] . For example, levels of SP-D mRNA and SP-D accumulation are increased within 24-72 h after intratracheal instillation of LPS [103 • ], and SP-D expression by alveolar and bronchiolar epithelial cells increases after exposure of rats to 95% O 2 for 12 h [104] . Keratinocyte growth factor (KGF) increases SP-D expression and protein production in association with pneumocyte hyperplasia and after injury caused by bleomycin [105] . In addition, the levels of SP-D can increase markedly in response to the overexpression of certain cytokines, such as interleukin-4, or in response to microbial challenge [91, 92] .\nStudies of the upstream regulatory region of the SP-D gene have demonstrated increased promoter activity in the presence of glucocorticoids, which is consistent with the findings in vivo and in lung organ culture [106] . However, no functional glucocorticoid response elements have been identified, and the effects of dexamethasone seem to be secondary and involve the effects of other transregulatory molecules.\nThe activity of the human SP-D promoter is dependent on a conserved activator protein-1 (AP-1) element (-109) that binds to members of the fos and jun families of transcriptional factors [107] . In addition, the promoter contains multiple functional binding sites for CCAAT-enhancer-binding protein (C/EBP) transcription factors. Mutagenesis experiments suggest that these are required for basal and stimulated promoter activity, and promoter activity is markedly increased in H441 cells after co-transfection with C/EBPβ cDNA (YC He and E crouch, unpublished data). The importance of the conserved AP-1 element and the presence of multiple binding sites for C/EBP transcription factors is consistent with the observed modulation of SP-D expression in the setting of tissue injury.\nSP-D promoter activity is not dependent on the binding of thyroid transcription factor 1 (TTF-1) [107] . However, promoter activity is dependent on two interacting forkhead binding sites, upstream and downstream of the AP-1 element; these sites bind to hepatic nuclear factor-3α and apparently other forkhead box proteins in H441 lung adenocarcinoma nuclear extracts [107] .\nInitial comparison of genomic and cDNA sequence suggested the existence of genetic polymorphisms in the SP-D coding sequence, including one in the N-terminal propeptide domain (Thr11 compared with Met11 in the mature protein) and three additional differences within the collagen domain at positions 102, 160, and 186 [108] . The latter substitutions are conservative to the extent that they are not expected to disrupt the collagen helix. Floros Table 5 Increased SP-D accumulation or expression in animal models\nSilicosis Rat [118] Hyperoxia Rat [104] Endotoxin (LPS) Rat [103] Challenge with P. aeruginosa Mouse [92] Challenge with IAV Mouse\n[62]\nChallenge with Pneumocystis carinii SCID mouse [91] Rat [119] Overexpression of interleukin-4 Mouse [120] SCID, severe combined immunodeficiency. and co-workers have recently confirmed the existence of polymorphisms at positions 11 and 160 of the mature protein [109] . The potential biological significance, if any, is not known. Interestingly, the 50 kDa variant of SP-D showed O-linked glycosylation of Thr11 [32 • ], suggesting that this polymorphism might be associated with altered glycosylation. Interestingly, the 50 kDa variant was recovered as trimeric subunits, raising the possibility that differences in the glycosylation of residue 11, which is immediately N-terminal to Cys15, could influence multimerization and the capacity of SP-D to participate in bridging interactions.\nThere is increasing evidence that SP-D interacts specifically with a wide variety of respiratory pathogens, modulates the leukocyte response to these organisms, and participates in aspects of pulmonary immune and inflammatory regulation (Table 6) . SP-D can influence the activity of phagocytes through CRD-dependent and CRD-independent interactions. At least some of the effects of SP-D result from aggregation with enhanced binding of the agglutinated ligand to their natural 'receptors'. Although the lung is the major site of SP-D expression, it is likely that the protein has more generalized roles in host defense and the acute response to infection and tissue injury. 16 " }, { "from": "gpt", "value": "Summary: [Summary placeholder]" } ]

[ { "from": "human", "value": "Full Text: from Xenopus laevis [16] . ETA receptors in normal lung are found in greatest abundance on vascular and airway smooth muscle, whereas ETB receptors are most often found on the endothelium. Clearance of ET-1 from the circulation is mediated by the ETB receptor primarily in the lung, but also in the kidney and liver [17] .\nActivation of both ETA and ETB receptors on smooth muscle cells leads to vasoconstriction whereas ETB receptor activation leads to bronchoconstriction. Activation of ETB receptors located on endothelial cells leads to vasodilation by increasing nitric oxide (NO) production. The mitogenic and inflammatory modulator functions of ET-1 are primarily mediated by ETA receptor activity. Binding of the ligand to its receptor results in coupling of cell-specific G proteins that activate or inhibit adenylate cyclase, stimulate phosphatidyl-inositol-specific phosholipase, open voltage gated calcium and potassium channels, and so on. The varied effects of ET-1 receptor activation thus depend on the G protein and signal transduction pathways active in the cell of interest [18] . A growing number of receptor antagonists exist with variable selectivity for one or both receptor subtypes.\nRegulation of ET-1 is at the level of transcription, with stimuli including shear stress, hypoxia, cytokines (IL-2, IL-1β, tumor necrosis factor α, IFN-β, etc), lipopolysaccharides, and many growth factors (transforming growth factor-β, platelet-derived growth factor, epidermal growth factor, etc) inducing transcription of ET-1 mRNA and secretion of protein [18] . ET-1 acting in an autocrine fashion may also increase ET-1 expression [19] . ET-1 expression is decreased by NO [20] . Some stimuli may additionally enhance preproET-1 mRNA stability, leading to increased and sustained ET-1 expression. The number of ETA and ETB receptors is also cell specific and regulated by a variety of growth factors [18] . Because ET-1 and receptor expression is influenced by many diverse physical and biochemical mechanisms, the role of ET-1 in pathologic states has been difficult to define, and these are addressed in subsequent parts of this article.\nIn the airway, ET-1 is localized primarily to the bronchial smooth muscle with low expression in the epithelium. Cellular subsets of the epithelium that secrete ET-1 include mucous cells, serous cells, and Clara cells [21] . ET binding sites are found on bronchial smooth muscle, alveolar septae, endothelial cells, and parasympathetic ganglia [22, 23] . ET-1 expression in the airways, as previously noted, is regulated by inflammatory mediators. Eosinophilic airway inflammation, as may be seen in severe asthma, is associated with increased ET-1 levels in the lung [24] . ET-1 secretion may also act in an autocrine or paracrine fashion, via the ETA receptor, leading to increased transepithelial potential difference and ciliary beat frequency, and to exerting mitogenic effects on airway epithelium and smooth muscle cells [25] [26] [27] [28] .\nAll three endothelins cause bronchoconstriction in intact airways, with ET-1 being the most potent. Denuded bronchi constrict equally to all three endothelins, suggesting considerable modulation of ET-1 effects by the epithelium [29] . The vast majority of ET-1 binding sites on bronchial smooth muscle are ETB receptors, and bronchoconstriction in human bronchi is not inhibited by ETA antagonists but augmented by ETB receptor agonists [30] [31] [32] . Since cultured airway epithelium secretes equal amounts of ET-1 and ET-3, which have equivalent affinity for the ETB receptor, bronchoconstriction could be mediated by both endothelins [33] .\nWhile ET-1 stimulates release of multiple cytokines important in airway inflammation, it does not enhance secretion of histamine or leukotrienes. ET-1 does increase prostaglandin release [32] . Inhibition of cyclo-oxygenase, however, has no effect on bronchoconstriction suggesting that, despite the release of multiple mediators, ET-1 mediated bronchoconstriction is a direct effect of activation of the ETB receptor [32] . ETA mediated bronchoconstriction may also be important following ETB receptor desensitization or denudation of the airway epithelium, as may occur during airway inflammation and during the late, sustained airway response to inhaled antigens [31, 34, 35] . Interestingly, heterozygous ET-1 knockout mice, with a 50% reduction in ET-1 peptide, have airway hyperresponsiveness but not remodeling, suggesting the decrease in ET-1 modulates bronchoconstriction activity by a functional mechanism, possibly by decreasing basal NO production [36, 37] .\nAsthma is also an inflammatory airway disease characterized by bronchoconstriction and hyperreactivity with influx of inflammatory cells, mucus production, edema, and airway thickening. ET-1 may have important roles in each of these processes. While ET-1 causes immediate bronchoconstriction [38] , it also increases bronchial reactivity to inhaled antigens [35] as well as influx of inflammatory cells [39, 40] , increased cytokine production [40] , airway edema [41] , and airway remodeling [28, 42, 43] . Airway inflammation also leads to increased ET-1 synthesis, possibly perpetuating the inflammation and bronchoconstriction [44] . ET-1 release from cultured peripheral mononuclear and bronchial epithelial cells from asthmatics is also increased [45, 46] . Inhibition of ETA or combined ETA and ETB receptors additionally leads to decreased airway inflammation in antigen-challenged animals, suggesting that the proinflammatory effects of ET-1 in the airway are mediated by ETA receptors [39, 47] .\nChildren with asthma have increased circulating levels of ET-1 [48] . Adult asthmatics have normal levels between attacks but, during acute attacks, have elevated serum ET-1 levels that correlate inversely with airflow measurements and decrease with treatment [49] . Bronchoalveolar lavage (BAL) ET-1 in asthmatics is similarly increased to concentrations that cause bronchoconstriction and inversely correlates with forced expiratory volume in 1 s (FEV 1 ) [29, 50, 51] . As in cultured epithelial cells, ET-1 and ET-3 are found in equal amounts in BAL fluid from asthmatics [33, 52] . There is also a relative increase in ETB versus ETA receptor expression in asthmatic patients, which may contribute to increased bronchoconstriction [53] . Not all asthmatics, however, have increased ET-1 as patients with nocturnal asthma have decreased BAL ET-1 levels [54] . Treatment of acute asthma exacerbations with steroids, beta-adrenergic agonists or phosphodiesterase inhibitors resulted in decreased BAL ET-1 [52, 55] . Immunostaining and in situ hybridization for ET-1 in biopsy specimens from asthmatics have shown an increase in ET-1 in the bronchial epithelium that correlates with asthma symptoms [46, 56] .\nCigarette smoking leads to increased circulating ET-1 [57] but patients with chronic obstructive pulmonary disease, in the absence of pulmonary hypertension and hypoxemia, do not have increased plasma ET-1 [58] [59] [60] . Increases in urinary ET-1 instead correlate with decreases in oxygenation, possibly through hypoxic release of ET-1 from the kidney [61, 62] . Smokers also have impaired ET-1 mediated vasodilation that correlates with bronchial hyperresponsiveness and may contribute to pulmonary hypertension [63, 64] .\nET-1 has been implicated in the pathogenesis of bronchiectasis by its ability to promote neutrophil chemotaxis, adherence, and activation [65] [66] [67] [68] [69] . Sputum ET-1 levels are increased in patients with cystic fibrosis [59] , and sputum ET-1 correlated with Pseduomonas infection in noncystic fibrosis related bronchiectasis [70] .\nET-1 has also been implicated in the pathogenesis of bronchiolitis obliterans (BO), which is characterized by injury to small conducting airways resulting in formation of proliferative, collagen rich tissue obliterating airway architecture. BO is the leading cause of late mortality from lung transplantation, and ET-1 is increased in lung allografts [71] . The pro-inflammatory and mitogenic properties of ET-1 in the airways has led to speculation that ET-1 may be involved in formation of the lesion [28] . This is further supported by the increase in BAL ET-1 in lung allografts [72, 73] . The in vivo gene transfer of ET-1 to the airway epithelium using the hemagglutinating virus of Japan in rats recently resulted in pathologic changes in the distal airways identical to those seen in human BO specimens [74] . These changes were not due to nonspecific effects of the hemagglutinating virus of Japan itself, but could be attributed to the presence of the ET-1 gene, which was localized to the airway epithelium, hyperplastic lesions, and alveolar cells.\nPulmonary hypertension is a rare and progressive disease characterized by increases in normally low pulmonary vascular tone, pulmonary vascular remodeling, and progressive right heart failure. ET-1 has been implicated as a mediator in the changes seen in pulmonary hypertension. In the pulmonary vasculature, ET-1 is found primarily in endothelial cells and to a lesser extent in the vascular smooth muscle cells. The endothelium secretes ET-1 primarily to the basolateral surface of the cell. ET-1 secretion may be increased by a variety of stimuli including cytokines, catecholamines, and physical forces such as shear stress, and decreased by NO, prostaglandins, and oxidant stress [20, [75] [76] [77] [78] . Hypoxia has been reported to increase, have no effect, or decrease ET-1 release from endothelial cells [79] [80] [81] [82] [83] .\nActivation of the receptors for ET-1 in the pulmonary vasculature leads to both vasodilation and vasoconstriction, and depends on both cell type and receptor. In the whole lung, ETA receptors are the most abundant and are localized to the medial layer of the arteries, decreasing in intensity in the peripheral circulation [84, 85] . ETB receptors are also found in the media of the pulmonary vessels, increasing in intensity in the distal circulation, while intimal ETB receptors are localized in the larger elastic arteries [85] . This distribution of receptors has important implications in understanding ET-1 regulation of vascular tone. Vascular ET-1 receptors may be increased by several factors including angiotensin and hypoxia [80, [85] [86] [87] .\nET-1 can act as both a vasodilator and vasoconstrictor in the pulmonary circulation. Generation of NO or opening of ATP-sensitive potassium channels leading to hyperpolarization results in vasodilation mediated by ETB receptors on pulmonary endothelium [88, 89] . In hypertensive, chronically hypoxic lungs with increased ETB receptor expression, augmented vasodilation is due to increased ETB mediated NO release that is inhibited by hypoxic ventilation, while inhibition of NO synthesis leads to increased ET-1 mediated vasoconstriction [85, [90] [91] [92] . Both ETA and ETB receptors, conversely, acting on vascular smooth muscle, mediate ET-1 induced vasoconstriction. In the normal lung, ET-1 causes vasoconstriction primarily by activation of the ETA receptors in the large, conducting vessels of the lung [93, 94] . In the smaller, resistance vessels of the lung, ETB receptors in the media predominate and are responsible for the ET-1 induced vasoconstriction [93] . Interestingly, preconstriction of the pulmonary circulation resulted in a shift from primarily ETA mediated to ETB mediated vasoconstriction [94] .\nThe overall effect of ET-1 on vascular tone depends on both the dose and on the pre-existing tone in the lung. ET-1 administration during acute hypoxic vasoconstriction will result in transient pulmonary vasodilation [89] . This effect is dose dependent, with lower doses leading to vasodilation while higher or repetitive doses cause vasoconstriction following an initial, brief vasodilation [89] . The role of ET-1 in the acute hypoxic vasoconstriction in the lung is not certain. ETA receptor antagonism attenuates hypoxic pulmonary vasoconstriction in several species [95] , and ET-1 may be implicated in the mechanism of acute hypoxic response by inhibition of K-ATP channels [96] .\nSeveral lines of evidence have suggested the importance of ET-1 in chronic hypoxic pulmonary hypertension. ET-1 is increased in plasma and lungs of rats following exposure to hypoxia [80, 97] . Treatment with either ETA or combined ETA and ETB receptor antagonists additionally attenuates the development of hypoxic pulmonary hypertension [98, 99] . ET-1 has also been implicated in the vascular remodeling associated with chronic hypoxia through its mitogenic effects on vascular smooth muscle cells [98, 100] .\nET-1 has also been implicated in other animal models of pulmonary hypertension. ET-1 is increased in fawn hooded rats that develop severe pulmonary hypertension when raised under conditions of mild hypoxia and in monocrotaline treated rats [101, 102] . The increase in ET-1 in both of these forms of pulmonary hypertension may be contributing to increases in vascular tone as well as in vascular remodeling [103] [104] [105] [106] 114] . Interestingly, transgenic mice overexpressing the human preproET-1 gene, with modestly increased lung ET-1 levels (35-50%), do not develop pulmonary hypertension under normoxic conditions or an exaggerated response to chronic hypoxia [107] .\nHuman pulmonary hypertension is classified as primary, or unexplained, or secondary to other cardiopulmonary diseases or connective tissue diseases (ie scleroderma). Hallmarks of the disease include progressive increases in pulmonary vascular resistance and pulmonary vascular remodeling, with thickening of the medial layer small pulmonary arterioles and formation of the complex plexiform lesion [108] . Circulating ET-1 is increased in humans with pulmonary hypertension, either primary or due to other cardiopulmonary disease [109] . Levels are highest in patients with primary pulmonary hypertension. Since the lung is the major source for clearance of ET-1 from the circulation, increased arterio-venous ratios as seen in primary pulmonary hypertension suggest either decreased clearance or increased production in the lung [17, 109] . ET-1 is also increased in lungs of patients with pulmonary hypertension, with the greatest increase seen in the small resistance arteries and the plexiform lesions [110] , and may correlate with pulmonary vascular resistance [111] . Interestingly, treatment with continuous infusion of prostacyclin resulted in clinical improvement and a decrease in the arterio-venous ratio of ET-1 [112] , possibly by decreasing ET-1 synthesis from endothelial cells [76] . Studies using ET-1 receptor antagonists in the treatment of primary pulmonary hypertension are underway and may offer hope to patients with this disease by inhibiting this pluripotent peptide's effects on vascular tone and remodeling.\nSeveral lines of evidence suggest the importance of ET-1 in lung allograft survival and rejection. The peptide has been implicated as an important factor in ischemia-reperfusion injury at the time of transplant as well as in acute and chronic rejection of the allograft.\nCirculating ET-1 is increased in humans undergoing lung transplant immediately following perfusion of the allograft. Plasma ET-1 increased threefold within minutes, remained high for 12 hours following transplantation, and declined to near normal levels within 24 hours [113] . This increase in ET-1 correlated with the increase in pulmonary vascular resistance occurring about 6 hours post-transplantation, suggesting that the release of ET-1 in the circulation may have mediated this event. ET-1 in BAL fluid from recipients of lung allografts is similarly increased several fold and remains elevated up to 2 years post-transplant [72, 73] . In recipients of single lung transplants, ET-1 was increased 10-fold in BAL fluid from the transplanted lung compared with the native lung, suggesting that the increase in ET-1 was due to the graft and not the underlying disease requiring transplant [72] . ET-1 in BAL fluid did not, however, correlate with episodes of infection or rejection.\nThe cellular source of ET-1 in lung allografts is unknown. The expression of ET-1 in nontransplanted human lungs is low and found primarily in the vascular endothelium [114] . Transbronchial biopsy specimens obtained either for surveillance or for clinical suspicion of infection or rejection following transplantation revealed the presence of ET-1 in the airway epithelium and in alveolar macrophages [115] . ET-1 was occasionally seen in lymphocytes but not in the endothelium or pneumocytes. ET-1 localization was no different in surveillance specimens compared with infected or rejecting lungs, or changed over time from transplantation. This study suggests that the source of the increased BAL ET-1 in transplanted lungs is due to the increased number of alveolar inflammatory cells and de novo expression in the airway epithelium. The biologic importance of the ET-1 from inflammatory cells is supported by the observation that peripheral mononuclear cells from dogs with mild to moderate lung allograft rejection cause vasoconstriction in pulmonary arterial rings, which is attenuated by the ETA blocker BQ123 [116] .\nAnalysis of ET-1 binding activity in failed transplanted human lungs suggested that ET-1 binding activity was not different compared with normal lung in the lung parenchyma, bronchial smooth muscle, or perivascular infiltrates. ET-1 binding was, however, decreased in small muscular arteries (pulmonary arteries and bronchial arteries) in the failed transplants, suggesting a role for ET-1 in impaired vasoregulation of transplanted lungs [117] .\nIschemia-reperfusion injury is the leading cause of early post-operative graft failure and death. In its severest manifestation, increased pulmonary vascular resistance, hypoxia, and pulmonary edema lead to cor pulmonale and death [118] . ET-1 has been implicated as a mediator of these events. The increase in pulmonary vascular resistance observed in human recipients of lung allografts follows an increase in circulating ET-1 and falls with decreases in circulating ET-1 [113] . A similar pattern is seen in dogs subjected to allotransplantation [119] . Conscious dogs with left pulmonary allografts demonstrate an increase in both resting pulmonary perfusion pressure and acute pulmonary vasoconstrictor response to hypoxia [120] . Administration of ETA selective or combined ETA and ETB receptor blockers did not change the resting tone. ETB receptor mediated hypoxic pulmonary vasoconstriction appeared, however, to be increased in allograft recipients. In another study, administration of a mixed ETA and ETB receptor antagonist (SB209670) to dogs before reperfusion of the allograft resulted in a marked increase in oxygenation, decreases in pulmonary arterial pressures and improved survival compared with control animals [121] . In a model of ischemia reperfusion, inhibitors of ECE additionally attenuated the increase in circulating ET-1 and the severity of lung injury [122] . ET-1 receptor antagonists did not, however, completely eliminate the ischemia-reperfusion injury, suggesting that changes in other vasoactive mediators, such as an increase in thromboxane, a decrease in prostaglandins, or a decrease in NO, may also contribute to the increased pulmonary vascular resistance. Administration of NO donor (FK409) to both donor and recipient dogs before lung transplantation reduced pulmonary arterial pressure, lung edema, and inflammation, and improved survival. This suggests that reductions in NO following transplantation may be partly responsible for early graft failure [123] . Treatment with NO donor was also associated with a decrease in plasma ET-1 levels.\nAcute rejection is manifested by diffuse infiltrates, hypoxia, and airflow limitation, and may lead to respiratory insufficiency and death. BAL ET-1 was increased in dogs during episodes of acute rejection that decreased with immunosuppressive treatment [124] . Acute episodes of rejection in humans, however, are not associated with further increases in BAL ET-1 [72] . Chronic rejection of allografts, manifested as BO, is the major cause of morbidity and mortality in long-term lung transplant survivors [71] . The etiology of BO following transplant is unclear but may be related to repeated episodes of acute rejection, chronic low-grade rejection, or organizing pneumonia [125] . As discussed earlier, a chronic increase in ET-1, as seen in lung allografts, may contribute to bronchospasm and proliferative bronchiolitis obliterans due to the bronchoconstrictor and smooth muscle mitogenic effects of ET-1 [28, 126] . This is further supported by the increase of BAL ET-1 in the transplanted lung, which is susceptible to BO, but not the native lung in recipients of single lung transplants [72] .\nThe mitogenic effects of ET-1 may play a role in the development of pulmonary malignancy as well as metastasis to the lung. Many human tumor cell lines, including prostate, breast, gastric, ovary, colon, etc, produce ET-1. The importance of the ET-1 may lie in its mitogenic effects on tumor growth and survival. This has been suggested by blockade of ETA receptors resulting in a decrease in mitogenic effects of ET-1 in a prostate cancer and colorectal cell lines [127, 128] . ET-1 receptors in tumor cells may also be altered with increases in the ETA receptor and downregulation of ETB receptors [129] . Other tumors may have an increase in ETB receptors, however, and blockade of ETB results in a decrease in tumor growth [130, 131] . Tumor cells may, as a result of this altered balance, lose the ability to respond to regulatory signals from their environment. ET-1 may additionally protect against Fas-ligand mediated apoptosis [132] .\nET-1 has been detected using immunohistochemistry and in situ hybridization in pulmonary adenocarcinomas and squamous cell tumors and, to a lesser extent, small cell and carcinoid tumors [133] . In situ hybridization also demonstrated a similar pattern of ET-1 mRNA expression in non-neuroendocrine tumors. ET-1 receptors have also been found in a variety of pulmonary tumor cell lines. ETA receptors were found in small cell tumors, adenocarcinomas and large cell tumors, while ETB receptors were expressed primarily in adenocarcinomas and small cell tumors [134] . ECE, which converts big ET-1 to ET-1, the committed step in ET-1 biosynthesis, was also found in human lung tumors but not in adjacent normal lung [135] . These findings, combined with the presence of ET-1 in lung tumors, suggest a possible autocrine loop that sustains and supports the growth of lung tumors. A recent study, however, suggested that, while ETA and ECE-1 were detectable in lung tumors, these genes were downregulated compared with normal bronchial epithelial cell lines [136] . It was proposed that the role of ET-1 in lung tumors is not that of an autocrine factor, but that of a paracrine growth factor to the stroma and vasculature surrounding the tumor allowing angiogenesis.\nTumor angiogenesis is necessary for continued growth of the tumor beyond the limits of oxygen diffusion. The growth of vessels into the tumor is also important to metastatic potential of the tumor. ET-1 may play an important role in angiogenesis and tumor growth and survival Available online http://respiratory-research.com/content/2/2/090 commentary review reports primary research through induction of vascular endothelial growth factor expression and sprouting of new vessels into the tumor and surrounding tissue [137, 138] . ET-1 binding activity was found in blood vessels and vascular stroma surrounding lung tumors at the time of resection, most markedly surrounding squamous cell tumors [139] . ET-1 production may be further augmented by the hypoxic environment found within large solid tumors [140] . Since metastasis is dependent on neo-vascularization, ET-1 may also be an important mediator of this phenomenon. ET-1 receptor antagonists may have a useful role in the treatment of neoplastic disease by inhibiting growth as well as metastatic potential of human tumors.\nExperimental lung injury of many different types results in increased circulating ET-1, BAL ET-1, and lung tissue ET-1 [18] . ET-1 levels in humans are also increased in sepsis, burns, disseminated intravascular coagulation, acute lung injury, and acute respiratory distress syndrome (ARDS) [141] [142] [143] [144] [145] [146] [147] . ET-1 increases also correlate with a poorer outcome with multiple organ failure, increased pulmonary arterial pressure, increased airway pressure and decreased PiO 2 /FiO 2 , while clinical improvement correlates with decreased ET-1 levels [144, 145, 147] . The arterio-venous ratio for ET-1 is increased in patients with ARDS but it is not clear whether this is due to increased secretion of ET-1 in the lungs or decreased clearance [142, 144] . In patients who succumbed to ARDS, there was also a marked increase in tissue ET-1 immunostaining in vascular endothelium, alveolar macrophages, smooth muscle, and airway epithelium compared with lungs of patients who died without ARDS. Interestingly, these same patients also had a decrease in immunostaining for both endothelial nitric oxide synthase and inducible nitric oxide synthase in the lung [148] . ARDS is also characterized by the presence of inflammatory cells in the lung. Since ET-1 may act as an immune modulator, an increase in ET-1 may contribute to lung injury by inducing expression of cytokines including tumor necrosis factor and IL-6 and IL-8 [149] . These cytokines may in turn stimulate the production of many inflammatory mediators, leading to lung injury. ET-1 additionally activated neutrophils, and increased neutrophil migration and trapping in the lung [65] [66] [67] [68] [69] .\nAnother hallmark of ARDS is disruption and dysfunction of the pulmonary vascular endothelium leading to accumulation of lung water. The role of endothelin in formation of pulmonary edema is uncertain. Infusion of ET-1 raises pulmonary vascular pressure, but it is uncertain whether ET-1 by itself increased pulmonary protein or fluid transport in the lung [150] [151] [152] . ET-1 may rather be acting synergistically with other mediators to lead to pulmonary edema [153, 154] .\nPulmonary fibrosis is the final outcome for a variety of injurious processes involving the lung parenchyma. The final common pathway in response to injury to the alveolar wall involves recruitment of inflammatory cells, release of inflammatory mediators, and resolution. The reparative phase occasionally becomes disordered, resulting in progressive fibrosis.\nET-1 in the lung may be important in the initial events in lung injury by activating neutrophils to aggregate and release elastase and oxygen radicals, increasing neutrophil adherence, activating mast cells, and inducing cytokine production from monocytes [65] [66] [67] [68] [69] 149, 155] . Among the many cytokines induced by ET-1 that are important in mediating pulmonary fibrosis are transforming growth factor-β and tumor necrosis factor α [156, 157] . ET-1 is also profibrotic by stimulating fibroblast replication, migration, contraction, and collagen synthesis and secretion while decreasing collagen degradation [158] [159] [160] [161] [162] . ET-1 additionally enhances the conversion of fibroblasts into contractile myelofibroblasts [43, 163] . ET-1 also increases fibronectin production by bronchial epithelial cells [164] . Finally, ET-1 has mitogenic effects on vascular and airway smooth muscle [126, 28] . ET-1 may thus play an important role in the initial injury and eventual fibrotic reparative process of many inflammatory events in the lung.\nSeveral lines of evidence regarding the importance of ET-1 in pulmonary fibrosis are available. Plasma and BAL ET-1 levels are increased in idiopathic pulmonary fibrosis [50, 165] . Lung biopsies from patients with idiopathic pulmonary fibrosis have additionally increased ET-1 immunostaining in airway epithelial cells and type II pneumocytes, which correlates with disease activity [166] . Scleroderma is commonly associated with pulmonary hypertension and pulmonary fibrosis. Plasma and BAL ET-1 is increased in these patients [160, 167, 168] , but it is unclear whether the presence of either pulmonary hypertension or pulmonary fibrosis increases these levels further [167] . BAL fluid from patients with scleroderma increased proliferation of cultured lung fibroblasts, which was inhibited by ETA receptor antagonist. This suggests that the ET-1 in the airspace may be contributing significantly to the fibrotic response [160] . An increase in ET-1 binding has also been reported in lung tissue from patients with scleroderma associated pulmonary fibrosis [169] . Pulmonary inflammatory cells also appear to be primed for ET-1 production because cultured alveolar macrophages from patients with scleroderma and lung involvement secrete increased amounts of ET-1 in response to stimulation with lipopolysaccharide [170] . These observations collectively suggest that augmented ET-1 release may contribute to and perpetuate the inflammatory process. Bleomycin-induced pulmonary fibrosis in animals is associated with increased ET-1 expression in alveolar macrophages and epithelium [171] . The increase in ET-1 proceeds the development of pulmonary fibrosis. The use of ET-1 receptor antagonists has produced mixed results in limiting the development of bleomycin-induced fibrosis. A decrease in fibroblast replication and secretion of extracellular matrix proteins in vitro but not a decrease in lung collagen content in vivo has been shown using ETA or combined ETA and ETB receptor antagonists after bleomycin [172] . Another group did, however, observe a decrease in fibrotic area in lungs of rats following bleomycin that were treated with a mixed ETA and ETB receptor antagonist [173] .\nWhile ET-1 seems to correlate with pulmonary fibrosis, it remains uncertain whether the increase in ET-1 is a cause or consequence of the lung disease. Pulmonary fibrosis was recently reported in mice that constitutively overexpress human ET-1 [107] . These mice were known to develop progressive nephrosclerosis in the absence of systemic hypertension [174] . The transgene was localized throughout the lung, with the strongest expression in the bronchial wall. In the lung, the mice developed age-dependent accumulation of collagen and accumulation of CD4+ lymphocytes in the perivascular space. This observation suggests that an increase in lung ET-1 alone may play a causative role in the development of pulmonary fibrosis [107, 175] .\nSince its discovery 12 years ago, much evidence has accumulated regarding the biologic activity and potential role of ET-1 in a variety of diseases of the respiratory track. As compelling as much of this evidence is, the causal relationship between ET-1 activity and disease is not complete. The increasing use of ECE and endothelin receptor antagonists in experimental and human respiratory disorders will help to clarify the role of this pluripotent peptide in health and disease." }, { "from": "gpt", "value": "Summary: [Summary placeholder]" } ]

[ { "from": "human", "value": "Full Text: RSV and PVM are viruses of the family Paramyxoviridae, subfamily pneumovirus; they are enveloped, singlestranded, nonsegmented RNA viruses that can cause intense viral bronchiolitis in humans and mice, respectively. In its most severe form, the lower respiratory tract infection caused by pneumoviruses is associated with the development of peribronchiolar infiltrates that are accompanied by submucosal edema and bronchorrhea, and ultimately leads to bronchiolar obstruction and compromised oxygen transfer. As the infection is confined to the respiratory epithelium, the responses of these cells are clearly of primary importance in determining the nature and extent of the resulting inflammatory process.\nMost of our understanding of responses to pneumovirus infection has emerged from studies of RSV infection of human epithelial target cells in vitro; a list of genes and/or gene products produced by epithelial cells in response to RSV infection in vitro is provided in Table 1 . At the cellular level, epithelial cells initially respond to RSV infection by reducing their ciliary beat frequency. Production and release of chemoattractant cytokines (chemokines) can be observed as early as 12 h after infection, leading to the recruitment of specific leukocyte subsets to the lung tissue. RSV-infected epithelial cells become resistant to tumor necrosis factor (TNF)-α-induced apoptosis, but later fuse to form giant-cell syncytia and die by cellular necrosis. We review the molecular bases (to the extent that they\nare understood) of these specific responses, and discuss several novel strategies that may permit us to study the responses to RSV and PVM infection in a more coherent and systematic manner.\nTristram et al [1] observed that explanted respiratory epithelial cells slow their ciliary beat frequency almost immediately after exposure to RSV, with complete ciliostasis seen as early as 6 h after the initial infection. The molecular basis of ciliostasis remains completely unknown.\nThe chemokines and cytokines with production and release that has been associated with RSV infection of human epithelial cells are listed in Table 1 . Much of this work was also recently reviewed elsewhere [2, 3] . We focus here on the three chemokines whose molecular mechanisms and physiologic implications are best understood.\nThe earliest reports on this subject described production of the neutrophil chemoattractant IL-8 from tissue culture supernatants from RSV-infected cells [4] [5] [6] and in nasal secretions from patients with viral rhinitis [7] . IL-8 has since been detected in lower airway secretions from patients with severe RSV bronchiolitis [8] , and the neutrophil influx observed in response to this infection is probably due, at least in part, to the activity of this chemokine.\nAt the cellular level IL-8 production can be observed in response to inactivated RSV virions, whereas IL-8 production in response to active infection was inhibited by ribavarin, amiloride, and antioxidants [9, 10] . Several groups have demonstrated activation of the transcription factor nuclear factor-κB (NF-κB) in response to RSV infection, and NF-κB is recognized for its central role in eliciting the production of IL-8 [9, 11, 12] . The transcription factor NF-IL-6 is also produced in response to RSV infection [13] , and participates in a co-operative manner with NF-κB in the regulation of IL-8 gene expression [11] , although later studies suggest that activator protein-1 may function preferentially in this role [14] . Interestingly, the NF-κB regulator IκBα, which functions by inhibiting NF-κB activation in response to TNF-α, was produced with different kinetics and does not promote a reversal of NF-κB activation in response to RSV infection as it does in response to TNF-α [15] . Most recently, Casola et al [16] demonstrated that the IL-8 promoter contains independent response elements, with nucleotides -162 to -132 representing a unique RSV response element that is distinct from elements necessary for IL-8 production in response to TNF-α. This concept of a stimulus-specific response will probably make an important contribution toward our understanding of how pneumoviruses promote transcription of unique and specific sets of independent gene products.\nThe pleiotropic chemokine regulated upon activation, normal T-cell expressed and secreted (RANTES) has also been detected in supernatants from RSV-infected epithelial cells in culture [17, 18] , as well as in upper and lower airway secretions from patients infected with this virus [7, 8] . RANTES acts as a chemoattractant for eosinophils and monocytes in vitro, although its role in vivo is somewhat less clear. Similar to IL-8, RANTES can be produced in vitro in response to inactivated virions [8] , and involves NF-κB activation, binding, and nuclear translocation [19] . However, Koga et al [20] demonstrated that stabilization of RANTES mRNA, a response to RSV infection mediated in part by nucleotides 11-389 of the RANTES gene, is probably the primary mechanism underlying increased production and secretion of RANTES protein. Further studies will determine whether a similar mechanism is also in place for IL-8 and other RSV-mediated responses. \nSeveral groups have recently shown that macrophage inflammatory protein (MIP)-1α is released from RSVinfected cells in culture [7, 21] ; MIP-1α was also detected in upper and lower airway secretions from RSV-infected patients [7, 8] . Interestingly, of the three aforementioned chemokines, MIP-1α is the one that is most closely correlated with the presence of eosinophil degranulation products; this, together with data from our PVM model of pneumovirus infection [22] , has suggested to us that MIP-1α plays a pivotal role in eosinophil recruitment in response to primary pneumovirus infection. Interestingly, production of MIP-1α in cell culture requires active viral replication [8] , which suggests that this response may proceed by a mechanism that is completely distinct from that which elicits production of RANTES and IL-8. However, no reports to date have addressed the molecular mechanism that underlies the RSV-mediated MIP-1α response.\nA list of cell-surface molecules that have been reported as expressed in response to RSV infection is shown in Table 1 . We focus here on the expression of intercellular adhesion molecule (ICAM)-1 (CD54) and the leukocyte integrin CD18.\nIncreased expression of this cell-surface adhesion protein was observed in both respiratory epithelial cell lines [23, 24] and in human nasal epithelial cells [25] in response to infection with RSV in vitro. Chini et al [26] demonstrated that the expression of ICAM-1 mRNA, similar to IL-8 and RANTES, was dependent on an intact NF-κB site in the gene promoter, and demonstrated a role for the consensus binding site for the factor CCAAT/ enhancer-binding protein. Stark et al [27] demonstrated that ICAM-1 and CD18 expressed in response to RSV serve to enhance neutrophil and eosinophil binding to epithelial cells.\nCD18 is a polypeptide of the integrin family that functions in mediating cell-cell interactions. Several groups have observed expression of CD18 on epithelial cells in response to RSV infection [27, 28] , with CD18 shown to enhance the degranulation of eosinophils in this specific setting [28] . Of particular interest are the recent findings relating expression of CD18 (along with CD14) to earlier literature on bacterial superinfections in the setting of viral infections. Earlier studies [29, 30] reported enhanced binding of bacteria to respiratory epithelial cells that were infected with RSV, findings that had clinical implications relating to acute bacterial otitis media in infants.\nTwo more recent studies addressed the question of binding sites. Saadi et al [31] determined that two strains of the pathogen Bordetella pertussis bound more efficiently to RSV-infected cells, and that the binding was reduced upon pretreatment of the cells with anti-CD14 or anti-CD18 antibodies. Similarly, Raza et al [32] reported that both CD14 and CD18 on RSV-infected epithelial cells contributed to the binding of nonpilate Neisseria meningitidis. In vivo testing is required before the clinical significance of these intriguing findings can be appreciated.\nRSV-infected epithelial cells in culture do not show features that are suggestive of apoptosis (ie no evidence of membrane blebbing, fragmentation of chromosomal DNA, or characteristic changes in nuclear morphology). Takeuchi et al [33] showed that, although RSV-infected epithelial cells express a number of apoptosis-associated genes, including interferon regulatory factor-1, IL-1β-converting enzyme and caspase 3, they do not undergo formal apoptosis.\nAs part of our attempts to understand mucosal responses in a more systematic manner (see below), we discovered that RSV-infected epithelial cells express the recently described antiapoptosis gene IEX-1L [34] . In our studies, we found that expression of IEX-1L is a response to active virus; no gene expression was observed in response to irradiated, replication-incompetent virus. Moreover, expression of IEX-1L is not observed in response to adenoviral infection, suggesting that expression of this gene is not a universal response to cellular perturbation, or indeed to all viral infections. Functionally, we also demonstrated that RSV infection protects epithelial cells from TNF-α-induced apoptosis, an effect that is temporally associated with the expression of IEX-1L.\nApoptosis is generally considered to be a highly efficient self-defense mechanism employed by host target cells, because it permits the infected host to dispose of viral proteins and nucleic acids on a single-cell basis without inducing an inflammatory response. It is thus not surprising that many viruses have evolved strategies to circumvent this response. Of interest, Krilov et al [35] demonstrated that monocytes and cord blood mononuclear cells are similarly protected from apoptosis when infected with RSV.\nAlthough virus-induced protection from apoptosis appears advantageous to the virus alone, another interpretation may be considered. Because respiratory epithelial cells are now recognized as a major source of leukocyte chemoattractants, and because leukocyte recruitment to the lung has been associated with enhanced viral clearance and prolonged survival in pneumovirus infection [22] , the ability to maintain chemoattractant production from viable cells may ultimately benefit the host organism as well.\nAvailable online http://respiratory-research.com/content/2/4/225\nIn tissue culture, RSV-infection is characterized by the formation of giant-cell syncytia. The mechanisms for the formation of these fused masses of cells depend in part on the expression of the RSV-specific fusion (F) protein on the surface of infected host cells, and in part on virusmediated changes in cytoskeletal architecture. It is important to note that RSV-induced changes in cytoskeletal architecture are not restricted to cell lines grown in vitro, as giant-cell syncytia have also been found in pathologic lung specimens obtained from both humans and animals that were infected with RSV.\nAgain, as part of our systematic study of gene expression in response to pneumovirus infection, we found that human respiratory epithelial cells respond to RSV infection with increased expression of the cytoskeletal protein cytokeratin-17 [36] . Cytokeratin-17 is a 46-kDa cytoskeletal protein that belongs to the class I acidic cytokeratin family. In the lung, expression of cytokeratin-17 is normally restricted to basal epithelial cells of the larynx, trachea, and bronchi. In RSV-infected cells, we found expression of Ck-17 predominantly at sites of syncytia formation, and thus provided the first description of a unique component of these pathognomonic structures at the molecular level. Similar to what has been reported for the production of IL-8, expression of Ck-17 is dependent on the activity of the transcription factor NF-κB, and future studies will determine the role of the NF-κB consensus site (-200 to -208 of the cytokeratin-17 promoter) in mediating this response.\nTo date, efforts to study pneumovirus-induced alterations in gene expression have relied heavily on in vitro models of virus-infected cells and cell lines. The intrinsic value of characterizing the genes identified in this artificial system is by definition limited, and the clinical and physiologic sig-nificance of any findings must ultimately be tested in vivo.\nTo some extent, the study of gene products in clinical specimens is possible, but this approach is limited, cumbersome, and dictated by sample availability. It is clear that an appropriate animal model of inflammatory bronchiolitis is required to characterize the alterations in gene expression discovered using the available in vitro models. Although RSV has been used for the study of specific allergic reactions to viral antigens, it is not a natural pathogen of mice, and intranasal inoculation of virus at high titer results in, at best, a minimal primary infection with a correspondingly minimal inflammatory response. In order to study gene expression in response to primary pneumovirus infection in vivo, we developed a novel mouse model of inflammatory bronchiolitis using the natural rodent pneumovirus pathogen and closest phylogenetic relative of RSV [37] -PVM. We presented our initial findings on PVM infection in mice in three recent publications [22, 38, 39] . A summary of these findings is presented in Table 2 and Fig. 1 .\nTo begin, we described the cellular and biochemical pathology observed in response to PVM infection in mice [38] . We found that infection could be established with as few as 30 plaque-forming units (pfu) of PVM in the inoculum, with infection resulting in significant morbidity and mortality, and viral recoveries in the order of 10 8 pfu/g lung tissue. We also noted inflammatory bronchiolitis as among the immediate responses to this infection, with bronchoalveolar lavage fluid containing virtually 100% neutrophils and eosinophils obtained as early as 3 days after inoculation. Furthermore, we found that infection was accompanied by the production of the proinflammatory chemokine MIP-1α, which was previously shown by Cook et al [40] to be an important component of the inflammatory response to the orthomyxovirus influenza virus.\nWe also described the role played by MIP-1α in the pathogenesis of PVM-induced bronchiolitis [22] . Specifi- cally, we explored the responses of gene-deleted mice to infection with PVM, and found no inflammatory response in mice deficient in MIP-1α expression (MIP-1α -/-) and only minimal virus-induced inflammation in mice that lacked the major MIP-1α receptor on granulocytes chemokine receptor (CCR)1 (CCR1 -/-). Although the inflammatory response is often considered to be unnecessary and indeed detrimental, we demonstrated that the absence of granulocytic inflammation was associated with enhanced recovery of infectious virions, as well as with accelerated mortality. These results suggest that the MIP-1α/CCR1-mediated acute inflammatory response protects mice by delaying the lethal sequelae of viral infection.\nOur most recent report on this subject [39] presents a direct comparison between the responses of mice to challenge with PVM and RSV. Although RSV is not a natural pathogen of mice, it has been used extensively in mouse models of human infection because a limited, or 'semipermissive' infection can be established via intranasal inocula-tion of virus at very high titers. In this regard, we found (as have others) that RSV infection did not result in any measurable degree of morbidity, and that viral recovery was significantly lower than that found in the inoculum; these results suggested that there was no significant viral replication in mouse lung tissue. We further demonstrated that the inflammatory response to RSV challenge was minimal, as few leukocytes were recruited to the lungs (Fig. 1) .\nTaken together, our results suggest that infection of mice with PVM provides a superior model for the study of acute inflammatory bronchiolitis in response to pneumovirus infection in vivo. The advantages of this model include the following: clinical parameters -morbidity and mortalitythat can be measured clearly and specifically; clear evidence of viral replication in lung tissue, with incremental recoveries that, at peak, are in excess of 10 8 pfu/g in response to as few as 30 pfu in the inoculum; and a dramatic granulocytic response that is modulated at least in part by the proinflammatory chemokine MIP-1α and its receptor CCR1. \nTraditionally, analysis of gene expression through measurement of steady-state levels of individual mRNAs could be conducted only one gene at a time using northern blotting, dot blots, or quantitative reverse transcription-PCR. Differential display, serial analysis of gene expression, and total gene analysis offer great promise, because they are multiplex technologies that provide simultaneous analysis of multiple mRNAs isolated under conditions of interest via PCR amplification techniques. DNA hybridization arrays are theoretically the most efficient of the gene expression analysis techniques. Although many skeptics have described these genome-based approaches as expensive, nonhypothesis-driven 'fishing expeditions', we view them as broad-based screening techniques that will enable us to identify patterns of gene expression that can then be subjected to careful characterization and analysis.\nDifferential display is a semiquantitative, reverse transcription-PCR-based technique that is used to compare mRNAs from two or more conditions of interest. Both increased and decreased expression of specific amplicons will be evident -an obvious advantage to this approach. Total RNA can be isolated from virus infected versus uninfected cells or mouse lungs both before and during infection, and differential display is performed using degenerate T11(XY) anchoring primers and random upstream oligomers, as described elsewhere [34, 36] . The resulting PCR products are separated by electrophoresis, and the gel is dried and exposed to film. An example of our results comparing cDNA amplicons from RNA extracted from RSV-infected epithelial cells daily for 4 days is shown in Fig. 2 . Differentially expressed bands are cut from the gel, eluted and reamplified using the same primers that generated the original signal, and northern blots generated from RNA extracted from pneumovirus-infected cells or tissue over time and probed with the differentially expressed amplicons serve to confirm differential expression of the identified sequence.\nThe DNA sequences of the newly identified differentially expressed amplicons are compared with sequences present in the GenBank database. Viral sequences are expected to be upregulated over time and can be identified immediately, because the entire genomes of both PVM and RSV are present in GenBank. In cases in which the amplicon represents a newly discovered gene, potential openreading frames are compared with sequences that are present in the Swiss protein database; motifs that share homologies with known proteins represent important clues to the identity of the differentially expressed gene.\nWith the help of differential display, we have identified and characterized several genes that are upregulated in RSV-infected respiratory epithelial cells. Two specific examples of genes that were found to be induced during RSV infection, and later characterized as playing independent roles in the pathophysiology of RSV infection, are the antiapoptosis gene IEX-1L [34] and the gene that encodes the cytoskeletal protein cytokeratin-17 [36] .\nUnlike DNA viruses, which are known to encode virus-specific antiapoptosis genes, RSV -an RNA virus with a small (approximately 15.2 kb) viral genome -was shown to alter host cell expression of the apoptosis inhibitor IEX-1L. After demonstrating that IEX-1L mRNA was present at sevenfold higher concentrations in RSV-infected respiratory epithelial cells when compared with uninfected cells, we concluded that this cellular response protected against TNF-α-induced programmed cell death during viral infection. Further efforts to determine which of the 11 RSV proteins participate in the trans-activation of the IEX-1L gene (either directly or indirectly) are ongoing.\nA second example of a gene that is specifically upregulated in RSV-infected respiratory epithelium, as identified by differential display, is that which encodes cytokeratin-17 [36] . Upon characterizing the molecular events that are important for cytokeratin-17 induction, we demonstrated a link to an NF-κB signaling pathway. Above, we discussed the importance of this transcription factor in the regulation of proinflammatory cytokine gene expression, and because of this involvement we were not surprised to discover its role in virus-induced cytokeratin-17 gene regulation. Perhaps the most interesting observation made during these experiments was the in situ localization of cytokeratin-17 protein to areas of cytopathic syncytia formation, suggesting a role for this cytoskeletal protein in their formation. Of note, we observed a dramatic decrease in RSV replication and in syncytia formation when we blocked cytokeratin-17 expression, suggesting that blocking syncytia formation, at least in part, impairs the direct cell-cell spread and productive replication of virus.\nAlthough there are several companies that market these systems and components, the cytokine gene macroarray systems recently developed by R&D Systems (Sigma Genosys ® ; Minneapolis, MN, USA) and Clontech (Atlas ® ; Palo Alto, CA, USA) represent some of the newer opportunities available that have a focus on gene products that are known to be involved in inflammation. These arrays consist of different cDNAs printed as PCR products onto charged nylon membranes. An example of our experience with the Sigma Genosys array is shown in Fig. 3 . For this example, total RNA was extracted from RSV-infected HEp-2 cells and uninfected controls at day 3 after infection. Three micrograms of total RNA was used in a cDNA synthesis reaction, using a proprietary mixture of 378 primer pairs and trace amounts of 32 P-radiolabeled dCTP.\nThe resulting radiolabeled products were hybridized to the macroarrays overnight at 65°C, and then washed and exposed to film. The arrow highlights one of the most obviously upregulated sequences from this experiment, which was identified as the gene encoding human MIP-1α. The physiologic importance of MIP-1α upregulation during human RSV infection and during rodent PVM bronchiolitis has already been described.\nMicroarrays can be differentiated from macroarrays in several ways. Among these differences, the microarray matrix is a glass or plastic slide, probes are labeled with fluorescent dye rather than via radioisotopes, and, most significantly, microarrays generally include a larger number and a higher density of imbedded sequences than do macroarrays. Although this may seem to be highly appealing at first, the massive amounts of data generated by microarray technology poses new challenges with respect to data normalization, management, and development of mathematical models to assist in data interpretation.\nThe pneumoviruses RSV and PVM enter respiratory epithelial cells via a receptor-mediated event. During hostcell attachment and internalization, the target cell begins to alter its gene expression, which, among other events, involves the transcriptional upregulation of cytokine and chemokine genes. As RSV replication progresses, additional changes in cellular gene expression can be observed, including induction of the potent antiapoptosis gene IEX-1L and increased expression of the otherwise quiescent gene that encodes cytokeratin-17. What we know regarding the physiologic importance of these genes and their gene products has been described, but there is more to be learned. As the available technologies evolve, we can continue to capitalize on the use of Display of amplicons generated from RNA extracted from RSV-infected cells at daily intervals following infection (days 0-4) using a single anchoring primer, T11GC (downstream primer 8) and (A-H) eight random 10mers. Two differentially expressed sequences are highlighted by arrows (the black arrow shows an upregulated amplicon, and the white arrow highlights a downregulated amplicon). Several other differentially expressed signals are also seen.\ngenomic approaches as large-scale screening tools to identify genes that play important roles in the pathophysiology of pneumovirus infection. These elegant and simple tools will provide us with the means for thorough and systematic exploration of gene expression, both in the estab- Cytokine macroarray probed with radiolabelled cDNA generated from total RNA extracted from epithelial cells 48 h after RSV infection (upper panel) or 48 h after exposure to conditioned medium (lower panel). Signal intensity of each gene under each condition is compared. The arrow highlights the signal for human MIP-1α present at 12-fold higher concentration in infected epithelial cells compared with the uninfected controls." }, { "from": "gpt", "value": "Summary: [Summary placeholder]" } ]

[ { "from": "human", "value": "Full Text: The genetic information of RNA viruses is organized very ef®ciently. Practically every nucleotide of their genome is utilized, either as protein-coding sequence or as cis-acting signals for translation, RNA synthesis or RNA encapsidation. As part of their genome expression strategy, several groups of positive-strand RNA (+RNA) viruses produce subgenomic (sg) mRNAs (reviewed by Miller and Koev, 2000) . The replication of their genomic RNA, which is also the mRNA for the viral replicase, is supplemented with the generation of sg transcripts to express structural and auxiliary proteins, which are encoded downstream of the replicase gene in the genome. Sg mRNAs of +RNA viruses are always 3¢-co-terminal with the genomic RNA, but different mechanisms are used for their synthesis.\nSome viruses, such as brome mosaic virus, initiate sg mRNA synthesis internally on the full-length minus strand RNA template (Miller et al., 1985) . Others, exempli®ed by red clover necrotic mosaic virus (RCNMV), may rely on premature termination of minus strand synthesis from the genomic RNA template, followed by the synthesis of sg plus strands from the truncated minus strand template (Sit et al., 1998) . Members of the order Nidovirales, which includes coronaviruses and arteriviruses, have evolved a third and unique mechanism, which employs discontinuous RNA synthesis for the generation of an extensive set of sg RNAs (reviewed by Brian and Spaan, 1997; Lai and Cavanagh, 1997; Snijder and Meulenberg, 1998) . Nidovirus sg mRNAs differ fundamentally from other viral sg RNAs in that they are not only 3¢-coterminal, but also 5¢-co-terminal with the genome ( Figure 1A) . A 5¢ common leader sequence of 65±221 nucleotides, derived from the 5¢ end of the genomic RNA, is attached to the 3¢ part of each sg RNA (thè mRNA body').\nVarious models have been put forward to explain the cotranscriptional fusion of non-contiguous parts of the nidovirus genome during sg RNA synthesis ( Figure 1B and C). Central to each of these models are short transcription-regulating sequences (TRSs), which are present both at the 3¢ end of the leader and at the 5¢ end of the sg RNA body regions in the genomic RNA. The TRS is copied into the mRNA and connects its leader and body part (Spaan et al., 1983; Lai et al., 1984) . Synthesis of sg mRNAs initially was proposed to be primed by free leader transcripts, which would base-pair to the complementary TRS regions in the full-length minus strand, and would be extended subsequently to make sg plus strands ( Figure 1B ; Baric et al., 1983 Baric et al., , 1985 . This model, however, was based on the report that sg minus strands were not present in coronavirus-infected cells (Lai et al., 1982) . The subsequent discovery of such molecules (Sethna et al., 1989) resulted in reconsideration of the initial`leader-primed transcription' model. Sawicki and Sawicki (1995) have proposed an alternative model ( Figure 1C ), in which the discontinuous step occurs during minus instead of plus strand RNA synthesis. In this model, minus strand synthesis would be attenuated after copying a body TRS from the plus strand template. Next, the nascent minus strand, with the TRS complement at its 3¢ end, would be transferred to the leader TRS and attach by means of TRS±TRS base pairing. RNA synthesis would be reinitiated to complete the sg minus strand by adding the complement of the genomic leader sequence. Subsequently, the sg minus strand would be used as template for sg mRNA synthesis, and the presence of the leader complement at its 3¢ end might allow the use of the same RNA signals that direct genome synthesis from the fulllength minus strand.\nSequence requirements for RNA strand transfer during nidovirus discontinuous subgenomic RNA synthesis The EMBO Journal Vol. 20 No. 24 pp. 7220±7228, 2001 Using site-directed mutagenesis of TRSs of the arterivirus equine arteritis virus (EAV), we have shown previously that base pairing between the sense leader TRS and antisense body TRSs is crucial for sg mRNA synthesis (van Marle et al., 1999a) . However, base pairing is only one step of the nascent strand transfer process and is essential in both models outlined in Figure 1 . The EAV genomic RNA contains several sequences that match the leader TRS precisely, but nevertheless are not used for sg RNA synthesis (den Boon et al., 1996; Pasternak et al., 2000) . This suggests that leader±body TRS similarity alone is, though necessary, not suf®cient for the strand transfer to occur.\nTo gain further insight into the cis-acting signals regulating sg RNA synthesis, we performed a comprehensive site-directed mutagenesis study of the EAV leader and body TRSs. Every nucleotide of the TRS (5¢-UCAACU-3¢) was substituted with each of the three alternative nucleotides. Our analysis revealed a number of striking similarities with the process of copy-choice RNA recombination, as it occurs in RNA viruses. Whereas the leader TRS plays only a targeting role in translocation of the nascent strand, body TRS nucleotides appear to ful®l diverse position-speci®c and base-speci®c functions. In addition, the sequence of the leader±body junctions of the sg mRNAs produced by these mutants provided strong evidence for the discontinuous minus strand extension model.\nEAV genome replication is not signi®cantly affected by leader TRS and body TRS mutations To dissect EAV RNA synthesis, we routinely use a fulllength cDNA clone (van Dinten et al., 1997) , from which infectious EAV RNA is in vitro transcribed. Following transfection of the RNA into baby hamster kidney (BHK-21) cells, intracellular RNA is isolated and analysed by northern blot hybridization and RT±PCR (van Marle et al., 1999a) . Due to differences in transfection ef®ciency, the total amount of virus-speci®c RNA (genomic RNA and sg mRNA) isolated from transfected cell cultures is somewhat variable. Thus, the accurate quantitation of sg mRNA synthesis by TRS mutants requires an internal standard for transfection ef®ciency. The amount of viral genomic RNA can be this standard, but only if its ampli®cation is not dramatically affected by the TRS mutations. To prove that this is the case, we used the previously described mutants L4, B4 and LB4 (van Marle et al., 1999a) , in which ®ve nucleotides of the TRS (5¢-UCAAC-3¢) were replaced by the sequence 5¢-AGUUG-3¢, either in the leader TRS (L4), RNA7 body TRS (B4) or both TRSs (LB4).\nThe three mutants were tested in three independent experiments. Intracellular RNA was isolated at 14 h posttransfection, early enough to prevent spread of the wildtype control virus to non-transfected cells (®rst cycle analysis). Transfection ef®ciencies were determined by immuno¯uorescence assays (see Materials and methods) and varied between 10 and 23% (data not shown). Prior to RNA analysis, the amount of isolated intracellular RNA was corrected for the transfection ef®ciency of the sample, so that each lane in Figure 2 represents EAV-speci®c RNA from an approximately equal number of EAV-positive cells. Phosphoimager quantitation revealed that genomic RNA replication of mutants L4, B4 and LB4 varied by not more than 30% (Table I) . These differences could re¯ect, for example, a slight in¯uence of RNA secondary structure changes in the TRS regions on genomic RNA synthesis. Remarkably, however, the genomic RNA level of the leader±body TRS double mutant LB4 was not affected by more than 10%. In view of the results obtained with these pentanucleotide TRS mutants, we assumed that the amount of genomic RNA could indeed be used as an internal standard during the analysis of mutants containing only single nucleotide replacements in leader TRS and/or RNA7 body TRS. The regions of the genome specifying the leader (L) sequence, the replicase gene (ORFs 1a and 1b) and the structural genes are indicated. The nested set of EAV mRNAs (genome and sg mRNAs 2±7) is depicted below. The black boxes in the genomic RNA indicate the position of leader and major body TRSs. (B and C) Alternative models for nidovirus discontinuous sg RNA synthesis. The discontinuous step may occur during either plus strand (B) or minus strand (C) RNA synthesis. In the latter case, sg mRNAs would be synthesized from an sg minus strand template. For details see text. Northern analysis of EAV-speci®c RNA isolated from cells transfected with RNA transcribed either from the wild-type EAV infectious cDNA clone or from TRS pentanucleotide mutants (UCAAC to AGUUG). The results of two independent experiments are shown.\nThe RNA±RNA interaction between the leader and body TRSs is not the only factor that regulates EAV sg RNA synthesis There are numerous examples of regulatory RNA±RNA interactions in both eukaryotic and prokaryotic cells, as well as in RNA viruses. Essential processes such as translation, replication and encapsidation of RNA virus genomes frequently depend on RNA±RNA interactions and higher order RNA structures. Regulation of sg RNA synthesis of +RNA viruses by RNA±RNA interactions is also not without precedent. In tomato bushy stunt virus, an RNA element located 1000 nucleotide upstream of the sg RNA2 promoter base-pairs with the promoter and is necessary for sg RNA production (Zhang et al., 1999) . Similarly, base pairing interactions between complementary sequences in the 5¢ end of the potato virus X genomic RNA and sequences upstream of two major sg RNA promoters are required for ef®cient sg RNA synthesis (Kim and Hemenway, 1999) . In RCNMV, an intermolecular RNA±RNA interaction is required for sg RNA synthesis (Sit et al., 1998) .\nRecently, we have established the pivotal role of an interaction between sense and antisense RNA sequences in the life cycle of EAV (van Marle et al., 1999a) . In that study, the role of TRS nucleotides C 2 and C 5 was tested by substituting them with G. It was concluded that base pairing between the sense leader TRS and the antisense body TRS plays a crucial role in nidovirus sg RNA synthesis. We now took a more systematic approach and performed an extensive site-directed co-variation mutagenesis study of the entire leader TRS and RNA7 body TRS, which directs the synthesis of the most abundant EAV sg RNA. Every nucleotide of the TRS (5¢-UCA-ACU-3¢) was replaced with each of the other possible nucleotides. As in the study of van Marle et al. (1999a) , every mutation was introduced into leader TRS, RNA7 body TRS and both TRSs, resulting in 54 mutant constructs. Each mutant was given a unique name: e.g. BU 1 A refers to a mutant in which a U has been changed to A at position 1 of the body TRS; LU 1 A refers to the same substitution in the leader TRS; and DU 1 A means that these two substitutions were combined in one double mutant construct. The amount of sg RNA7 was quantitated by phosphoimager scanning of hybridized gels and was corrected for the amount of genomic RNA in the same lane (as outlined above). Figure 3 shows the relative sg RNA7 level of the 54 mutants, compared with the RNA7 level of the wild-type control. For a selection of 11 interesting mutants (see below), the analysis was repeated three times (Figure 4 ), without observing signi®cant variations in sg RNA synthesis.\nThe comprehensive analysis of the effects of TRS mutations considerably expanded our understanding of van Dinten et al., 1997) was taken along as a positive control. For every mutant, the level of sg RNA7 synthesis was calculated as [(sg/g)/(sg/g) wt ] 3 100%: it was corrected for the level of genomic RNA (used as an internal standard; see text) and subsequently was related to the level of sg RNA7 produced by the wild-type control in the same experiment, which was also corrected for the corresponding genomic RNA level. The relative sg RNA7 level of the wild-type control was set at 100%.\nA.O. Pasternak et al. discontinuous sg RNA synthesis. Remarkably, the effects of single (leader or body) TRS mutations were mostly base speci®c, i.e. different nucleotide substitutions at the same position affected sg RNA7 synthesis to different extents. For example, at position 1, the BU 1 A mutant retained 44% of the wild-type RNA7 synthesis level, whereas both the BU 1 C and BU 1 G mutants lost RNA7 synthesis almost completely. Conversely, when U 1 of the leader TRS was changed to A or G, RNA7 synthesis was completely abolished, whereas 13% of the wild-type level was still maintained by LU 1 C. For position 2, only the BC 2 U mutant retained 30% of the wild-type RNA7 synthesis level, while all the other position 2 single mutants have lost 90% or more of wild-type RNA7 synthesis. Another example is position 6: BU 6 C left only 5% of wild-type RNA7 synthesis, whereas BU 6 A produced much higher RNA7 levels. This implied that for some positions (1, 2 and 6), certain mismatches in the duplex between plus leader TRS and minus body TRS, such as U±U (BU 1 A and BU 6 A) or C±A (LU 1 C and BC 2 U), are allowed to a limited extent. In contrast, no mismatches were allowed for position 5, where all single nucleotide substitutions abolished RNA7 synthesis almost completely. Surprisingly, both body TRS U to C substitutions at positions 1 and 6 (BU 1 C and BU 6 C) resulted in low levels of RNA7, despite the fact that these mutations allow the formation of a G±U base pair between the plus leader TRS, providing the U nucleotide, and the minus body TRS, providing the G. On the other hand, for positions 3 and 4, G±U base pairing was shown to be functional, because mutants LA 3 G and LA 4 G, which can form G±U base pairs between the G in the plus leader TRS and U in the minus body TRS, were the only position 3 and 4 single mutants that produced reasonable levels of RNA7. Taken together, these ®ndings suggest that other factors, besides leader± body base pairing, also play a role in sg RNA synthesis and that the primary sequence (or secondary structure) of TRSs may dictate strong base preferences at certain positions. Our analysis of the degree of complementation by the double mutants provided strong support for this assumption.\nDifferentiating between effects at the level of primary TRS sequence and the level of leader±body duplex formation For some TRS nucleotides (2, 5 and 6, except in the case of DU 6 C), the RNA7 level of double mutants was clearly higher than that of the corresponding single mutants. This means that base pairing between these leader and body TRS nucleotides is involved in sg RNA synthesis. However, none of these double mutants reached the wild-type sg RNA7 level. In the other double mutants (all position 1, 3 and 4 mutants, and DU 6 C), in clear contradiction to the predictions of the`base pairing model', RNA7 synthesis was not signi®cantly restored. Moreover, a comparison of the values for the B and D mutants in Figure 3 showed that, for almost all of these mutants (e.g. the position 1 mutants), the amount of sg RNA7 produced by the double mutant appeared to be limited by the level allowed by the body TRS mutation. Sometimes the RNA7 level of the double mutant was even less than that of the leader mutant (DU 1 C, DA 3 G, DA 4 G or DU 6 C). Clearly, for these substitutions, restoration of the possibilities for leader±body duplex formation did not restore sg RNA synthesis. Apparently this is because the effect of body TRS mutations at the level of primary sequence or secondary structure can be`dominant' over the duplex-restoring effects of the double mutations.\nBody TRS mutants thus fell into two distinct types, determined by the position and chemistry of the substitution. In mutants of the ®rst type, sg RNA synthesis was impaired mainly because of the disruption of the leader± body TRS duplex. This effect could be compensated for by introduction of the corresponding mutation in the leader TRS and, in the double mutant, sg RNA synthesis was restored compared with the corresponding single mutants. In mutants of the second type, sg RNA synthesis was down-regulated as a consequence of both TRS duplex disruption and disruption of the primary sequence (or secondary structure) of the body TRS. Obviously, the latter effect could not be compensated for by mutating the leader TRS, and the corresponding double mutants did not show restoration of sg RNA synthesis.\nIn contrast to our ®ndings with the body TRS mutants, we did not obtain leader TRS mutations that appeared to determine the level of sg RNA7 synthesis of the corresponding double mutant (Figure 3) . Thus, effects of mutations in the leader TRS were not`dominant' over the duplex-restoring effects of the double mutations, suggesting that they only affected duplex formation. This indicated that the leader TRS probably does not have an additional, sequence-speci®c function in sg RNA synthesis in addition to its participation in TRS±TRS base pairing. The fact that single leader TRS mutations at all six Nidovirus discontinuous subgenomic RNA synthesis positions severely repressed RNA7 synthesis indicated that base pairing of every TRS nucleotide contributes to sg RNA production. In this respect, it was signi®cant that the two leader TRS mutants with the highest RNA7 levels, LA 3 G and LA 4 G, can form G±U base pairs to maintain the duplex.\nThe observation that leader TRS mutations could bè rescued' by introducing complementary mutations in the body TRS, but that many body TRS mutations could not bè rescued' by corresponding changes in the leader TRS, is clearly illustrated by the U 1 A mutants. Due to the restoration of TRS base pairing possibilities, the RNA7 synthesis of double mutant DU 1 A was signi®cantly increased compared with that of LU 1 A, but not above the level of BU 1 A. Thus, restoration of the leader±body duplex in DU 1 A exerted a clear effect on sg RNA7 production compared with LU 1 A, but had no effect on sg RNA synthesis compared with BU 1 A. This exempli®ed the dominant nature of a mutation in the primary sequence of a body TRS. In contrast, for instance, the BC 2 U mutation probably affected duplex formation only, because RNA7 synthesis was restored almost to wildtype levels in the DC 2 U double mutant.\nThese results indicate that there are strong base preference constraints for some body TRS positions. To interpret these base preferences accurately, it is necessary to limit the analysis to the double mutants only, because in these mutants the down-regulation of sg RNA synthesis was only due to the sequence changes in the body TRS, and not to the disruption of the leader±body TRS duplex. There were strict preferences for positions 1, 3 and 4 of the body TRS: at position 1, only the U to A substitution allowed for a signi®cant RNA7 level (~40% of wild-type); and at positions 3 and 4, only the A to U mutants retained 15±20% of the wild-type level. For positions 2 and 5, the sequence constraints were less stringent (all substitutions allowed for >20% of wild-type level), but still only DC 2 A and DC 2 U reached >50%. At position 6 of the body TRS, only U to C was not allowed, whereas the other two double mutants still produced 50% or more of RNA7. In other words, the functional EAV RNA7 body TRS (based on the analysis of our single nucleotide substitutions) can be described as U 1 (C/u/a) 2 A 3 A 4 C 5 (U/a/g) 6 , with wild-type nucleotides shown in upper case and nucleotides that allowed for at least 50% of the wild-type RNA7 level shown in lower case. Remarkably, TRS nucleotides A 3 , A 4 and C 5 are conserved in the TRSs of all other arteriviruses (Snijder and Meulenberg, 1998) . Also the fact that DC 2 U retained 80% of RNA7 synthesis corresponded nicely to the presence of a U at this position in other arteriviruses.\nUntil recently (Almazan et al., 2000; Thiel et al., 2001) , infectious cDNA clones were lacking for coronaviruses. Consequently, most studies on coronavirus sg RNA synthesis were carried out using defective interfering (DI) RNAs. These replicons carried body TRSs from which moderate levels of sg mRNAs could be produced in the presence of helper virus. Using this system, Joo and Makino (1992) and van der Most et al. (1994) performed body TRS mutagenesis studies for the murine coronavirus (MHV). Joo and Makino systematically mutagenized the core of the MHV body TRS. In contrast to our results, they found that in only two of 21 body TRS mutants was sg RNA synthesis from the DI RNA genome abolished, whereas all others supported normal levels of sg RNA production. Thus, it is possible that the MHV TRS which was used in that study is more tolerant to single-nucleotide mismatches than the EAV sg RNA7 TRS.\nIn a similar study, van der Most et al. (1994) observed that U to C substitutions at positions 1 and 3 of the MHV body TRS, which maintained the duplex by changing a U±A base pair into a U±G base pair, reduced sg RNA levels more strongly than substitutions that disrupted the duplex (van der Most et al., 1994) . This implies that, as in the case of EAV, leader±body TRS duplex formation is not the only factor that determines coronavirus sg RNA synthesis. However, because of the limitations of the DI RNA system, the leader TRS could not be mutagenized in these studies, and body TRS-speci®c effects could not be distinguished from effects at the level of leader±body duplex formation.\nThe discontinuous step in nidovirus sg RNA synthesis occurs during minus strand RNA synthesis Due to recent studies of arterivirus and coronavirus sg RNA synthesis (van Marle et al., 1999a; Baric and Yount, 2000; Sawicki et al., 2001) , the discontinuous minus strand extension model ( Figure 1C ) has been gaining more and more ground. This model predicts that the TRSderived sequence that forms the leader±body junction in the sg mRNA is a copy of the body TRS, and not of the leader TRS. The leader-primed transcription model predicts the opposite ( Figure 1B) . Therefore, determining the origin of the leader±body junction of sg mRNAs would help to distinguish between the two models. However, in the wild-type situation, EAV leader and body TRSs are identical and consequently one cannot determine the origin of the sg mRNA leader±body junction. This problem could be overcome by tracing the mutations introduced in leader or RNA7 body TRS mutants, most of which retained part of their ability to produce mRNA7. In a previous study (van Marle et al., 1999a) , we found that nucleotides 2 and 5 of the mRNA7 leader±body junction sequence were derived exclusively from the body TRS, and not from the leader TRS. This was shown by direct sequencing of RT±PCR products obtained from the residual mRNA7 produced by mutants BC 2 G, LC 2 G, BC 5 G and LC 5 G ( van Marle et al., 1999a) .\nUsing the same approach, we analysed mRNA7 from mutants BC 2 A and BC 2 U, and these transcripts also contained the mutated nucleotide derived from the body TRS (data not shown). Assuming that only one crossover event occurs during leader±body joining, we could thus map this crossover between positions ±1 and +2 of the sg RNA junction sequence. This left the intriguing question of whether the crossover site could be mapped even more precisely. In other words, was nucleotide +1 of the junction sequence derived from the body TRS or the leader TRS?\nUsing the position 1 mutants described above, we could answer this question ( Figure 5) . The most striking result was that mRNA7 of mutants BU 1 A, BU 1 G and LU 1 C contained exclusively the body TRS-derived nucleotide at position +1. Thus, for these mutants, the crossover site could be mapped precisely between TRS nucleotide positions ±1 and +1, meaning that the complete leader± body junction sequence in an EAV sg mRNA can be body TRS derived. On the other hand, sg RNAs from mutants LU 1 A, BU 1 C and LU 1 G contained mixed populations of leader TRS-and body TRS-derived nucleotides at position +1 ( Figure 5 ): A and U for LU 1 A, C and U for BU 1 C, and G and U for LU 1 G. Remarkably, this pattern correlated with the relative amounts of sg mRNA7 produced by these mutants (Figure 3 ). Mutants that produced populations of sg RNAs that were mixed with respect to the origin of the nucleotide at position +1 of the leader±body junction had lost RNA7 synthesis almost completely. On the other hand, mutants that contained exclusively the body nucleotide at position +1 retained higher levels of RNA7 synthesis. This observation may be explained as follows: in the wild-type situation, the large majority of the crossovers probably occur between positions ±1 and +1, leading to a body TRS-derived nucleotide at position +1 in the sg RNA; however, a low number of crossovers take place between nucleotides +1 and +2, resulting in a leader TRS-derived nucleotide at position +1. Mutants in which almost all sg RNA synthesis is blocked by a substitution at position +1 may somehow be de®cient in the crossover between ±1 and +1, but may have retained the ability for crossovers between +1 and +2, which were detected by sequence analysis. Conversely, in position +1 mutants that retain reasonable sg RNA synthesis, most crossovers occur between positions ±1 and +1, and they obscure the minority of crossovers between +1 and +2 in the sequencing electropherogram. Alternatively, position +1 TRS mutations that strongly interfere with sg RNA synthesis may force a shift of the crossover site in the remaining molecules.\nWe believe that our present ®ndings strongly support the discontinuous minus strand extension model. Indeed, the fact that a complete body TRS can be copied into the sg RNA is very dif®cult to reconcile with the alternative model, in which sg RNA synthesis from the genomic minus strand template is primed by free plus strand leader transcripts that contain the leader TRS at their 3¢ end ( Figure 1B) . To explain the presence of a complete copy of the body TRS in the sg mRNA in this model, one would have to assume that a 3¢±5¢ exonuclease activity trims back the free leader transcript prior to its extension into an sg mRNA (Baker and Lai, 1990) . Note that there would not be a single base pair left to hold these`trimmed' leader molecules on the template. Such an enzymatic activity, which is unprecedented in +RNA viruses, exists in yeast retrotransposon Ty5 (Ke et al., 1999) , in which reverse transcription is primed by an internal region in a tRNA. However, in this system, it is not a part of the duplex that is removed, but the single-stranded 3¢ tail of the tRNA, which cannot base-pair with the Ty5 RNA.\nRemoval of the TRS at the 3¢ end of the nidovirus leader, which has already base paired with the template, would be very energetically unfavourable for the RdRp. Instead of starting elongation using the intact and properly positioned leader as a primer, it would have to disrupt the newly formed duplex, degrade part of the leader RNA and then reinitiate polymerization, without any base pairing between primer and template. It has been shown that in¯uenza virus transcription does not require a sequence match between the (cellular) RNA primer and the (viral) template (Plotch et al., 1981) . However, if in the nidovirus system the`trimmed' leader RNA could also be ®xed on the template solely by RNA±protein interactions, the targeting of the nascent strand by TRS base pairing would be extremely puzzling.\nSequence data of sg RNA leader±body junctions from other arteriviruses are also dif®cult to reconcile with the leader-primed transcription model. For the porcine and simian arteriviruses (Meulenberg et al., 1993; Godeny et al., 1998) , the leader±body junctions of some sg RNAs mapped two nucleotides upstream of the body TRS, which again would not leave a single nucleotide to hold the putative free leader on the template after the hypothetical back trimming'. On the other hand, these ®ndings and our data can be explained readily by the discontinuous minus strand extension model ( Figure 1C ). The six-nucleotide Fig. 5 . Sequence analysis of mRNA7 leader±body junctions from position 1 TRS mutants. Sequences were determined directly from sg mRNA7-speci®c RT±PCR products. For the U 1 A and U 1 C mutants, the sequence shown corresponds to the plus strand of sg RNA7. For sequencing-related technical reasons, the minus strand sequence was determined for the U 1 G mutants; a mirror image of the electropherogram is shown with the corresponding plus strand sequence listed at the top of the panel. For every mutant, a sequence alignment of the leader (red) and body (blue) TRSs and surrounding sequences is shown (TRSs are boxed). The mRNA7 leader±body junctions detected by our sequence analysis are shown in yellow. duplex formed between the body TRS complement at the 3¢ end of the leaderless sg minus strand and the leader TRS in the genomic RNA template should suf®ce to position the nascent minus strand properly for subsequent elongation to add the complement of the leader sequence. In most cases, the nascent minus strand contains the entire body TRS complement at its 3¢ end at the moment of strand transfer, leading to a body TRS-derived leader±body junction sequence in the sg mRNA molecule. In a small number of transcripts, however, minus strand synthesis appears to be interrupted before nucleotide +1 of the body TRS is copied and, after strand transfer, resumes by incorporating the complement of the +1 nucleotide of the leader TRS. As stated above, we postulate that the detection of this phenomenon is determined by the level of crossovers between the ±1 and +1 position that is allowed by the mutations introduced at the +1 position of body TRS or leader TRS. We cannot, however, formally exclude that a`back trimming' activity degrades the 3¢-terminal nucleotide of the minus strand before or after strand transfer. However, note that in the discontinuous minus strand extension model ( Figure 1C ), such an activity would not disturb the proper positioning of the nascent minus strand on the leader template, because the TRS± TRS duplex would be shortened by one nucleotide only.\nNidovirus discontinuous minus strand extension resembles similarity-assisted, copy-choice RNA recombination Due to their discontinuous sg RNA synthesis, nidoviruses occupy a special`niche' in the +RNA virus world. Their mode of sg RNA production is clearly different from that of other +RNA viruses and resembles another welldocumented +RNA virus feature: RNA recombination (for recent reviews see Nagy and Simon, 1997; Aaziz and Tepfer, 1999; Worobey and Holmes, 1999) . Most of the experimental evidence supports an RdRp template switch (Kirkegaard and Baltimore, 1986) as the main mechanism of RNA recombination. Mechanistically, such a template switch involves the transfer of a nascent strand from one RNA template (donor) to the other (acceptor). Also, nidovirus discontinuous sg RNA synthesis involves transfer of a nascent RNA strand, the sg RNA, but now from one site to another in the same template.\nBased on the data currently available, we refer to the discontinuous minus strand extension model as our working model for nidovirus sg RNA synthesis. If one applies the`recombination terms' to this model (Chang et al., 1996; Brian and Spaan, 1997; van Marle et al., 1999a) , the donor strand would be the body part of the genomic RNA template, the acceptor strand would be the leader part of the genomic RNA template and the nascent strand would be the discontinuously synthesized minus strand. Nagy and Simon (1997) have de®ned three main classes of RNA recombination: similarity-essential, similarity-non-essential and similarity-assisted recombination. The latter is de®ned as a mechanism in which strand transfer is determined by both sequence similarity between the parental RNAs and additional RNA determinants, present in only one of the parental RNAs.\nThe results of our present study strongly suggest that nidovirus discontinuous sg RNA synthesis can be considered a special case of high-frequency similarity-assisted RNA recombination. While the only obvious function of the leader TRS is to ensure the ®delity of the strand transfer by base pairing with the 3¢ end of the nascent strand, the body TRS in the donor template indeed has additional, sequence-speci®c functions. One of these functions apparently is to pause (or terminate) nascent strand synthesis and thereby provide the opportunity for strand transfer. In addition, body TRS-derived nucleotides may play a role in the reinitiation of nascent strand synthesis on the acceptor template. Given the compact nature of the EAV TRS, it is quite possible that some nucleotides ful®l multiple tasks.\nRNA secondary structure of the body TRS may regulate sg RNA synthesis The sequence-speci®c function of the body TRS, revealed in this study, may be exerted at the level of either primary sequence or secondary structure. For a number of +RNA viruses, RNA secondary structure motifs located in the (proximity of) sg RNA promoters are vital for sg RNA synthesis. In alfalfa mosaic virus (Haasnoot et al., 2000) , turnip crinkle virus (TCV) (Wang et al., 1999) and barley yellow dwarf virus (Koev et al., 1999) , stem±loop structures in sg RNA promoter regions of the template strand are required for sg RNA synthesis. The sg RNA1 promoter of the latter virus is especially interesting, since it contains two stem±loop domains. For one of them, secondary structure, but not the primary sequence, is important for sg RNA synthesis, whereas the other domain acts through primary sequence, and not secondary structure (Koev et al., 1999) . Similarly, RNA secondary structure may play only a minor role in the sequence-speci®c recognition of the BMV sg RNA promoter by the RdRp Siegel et al., 1997) .\nWe have suggested previously that RNA secondary structure of body TRS regions contributes to their attenuating potential and thereby determines the relative portion of the nascent minus strands that is transferred to the leader TRS in the template (Pasternak et al., 2000) . At present, it is unknown whether EAV body TRSs are part of an RNA structural motif that is essential for body TRS function, or whether they are recognized by a protein factor in a sequence-speci®c manner. However, the latter seems less likely than the former, since even LB4 (Figure 2 ), in which ®ve TRS nucleotides were substituted, still produced some sg RNA7, although~30-fold less than the wild-type control. The fact that some sequences in the EAV genome match the leader TRS perfectly, but are not used for sg mRNA synthesis, also argues against the recognition of a speci®c sequence (Pasternak et al., 2000) . More probably, mutagenesis of the RNA7 body TRS disturbed an RNA structure that is necessary for its function. This could, for example, explain the fact that the BU 6 C substitution reduced the amount of RNA7 by 20-fold (and could not be rescued by the same mutation in the leader TRS), whereas the wild-type RNA6 body TRS contains a C at the same position. If a protein factor were involved in sequence-speci®c TRS recognition, then one would expect it to recognize all TRSs similarly. If RNA structure is important for recognition by such a protein, then the BU 6 C substitution probably disturbs a structural motif of the RNA7 TRS, which is not present in the RNA6 TRS. On the other hand, conservation of part of the TRS in other arteriviruses suggests a sequence-speci®c recognition. Further studies are required to distinguish between these possibilities.\nIn the TCV satellite RNA recombination system, the hairpin structure in the acceptor strand, as well as the donor±acceptor homology region, are necessary for the template switch . The hairpin has been postulated to bind the RdRp, whereas the homology region targets the nascent strand to the crossover site. The TCV RdRp probably recognizes the secondary and/or tertiary structure of the hairpin, while individual nucleotides play a less important role . In EAV, the leader TRS in the acceptor template is predicted to reside in the loop of an extensive hairpin, and its base pairing interaction with the body TRS complement at the 3¢ end of the nascent minus strand would resemble certain antisense RNA-regulated control mechanisms that are based on interactions between single-stranded tails and hairpin loops (van Marle et al., 1999a, and references therein) . It is possible that the EAV RdRp, or its accessory proteins, also binds to the stem of the long hairpin that presents the leader TRS. In any case, the leader TRS itself does not seem to be recognized by a protein in a sequence-speci®c manner.\nThe body TRS is a better candidate to serve as a protein recognition site. This protein would then mediate the pausing of the nascent strand synthesis and/or nascent strand transfer. This would resemble the DNA-dependent RNA polymerase I termination system, in which speci®c DNA-binding terminator proteins bind to termination sequences (Reeder and Lang, 1997) , or a function of the HIV nucleocapsid protein, which promotes the minus strand strong-stop DNA transfer (Guo et al., 1997) . The EAV replicase component nsp1, which recently was shown to possess an sg RNA synthesis-speci®c activity (Tijms et al., 2001) , may be a good candidate for such a regulatory role. Residues predicted to form a zinc ®nger structure in nsp1 were shown to be necessary for sg RNA synthesis. Interestingly, zinc ®nger structures in the HIV nucleocapsid protein facilitate strand transfer (Guo et al., 2000) . Finally, it should be noted that the RNA structure of the nascent strand may also in¯uence pausing, strand transfer or reinitiation, as illustrated by the fact that stable hairpin structures in the nascent strand promote termination of transcription by Escherichia coli RNA polymerase (Wilson and von Hippel, 1995) .\nSite-directed mutagenesis, RNA transfections and immuno¯uorescence analysis Site-directed mutagenesis of EAV leader and body TRSs was carried out as described by van Marle et al. (1999a) , and all mutant constructs were sequenced. Following in vitro transcription from infectious cDNA clones, full-length EAV RNA was introduced into BHK-21 cells by electroporation, as described by van Dinten et al. (1997) . Immuno¯uorescence assays with EAV-speci®c antisera were performed at 14 h posttransfection as described by van der Meer et al. (1998) . To visualize the nuclei for cell counting, nuclear DNA was stained with 5 mg/ml Hoechst B2883 (Sigma). Cells were counted using the Scion Image software (Scion Corporation) and the percentage of transfected cells was calculated on the basis of the number of cells positive for the EAV replicase component nsp3 (Pedersen et al., 1999) .\nFor RNA analyses, cells were lysed at 14 h post-transfection. Intracellular RNA isolation was performed using the acidic phenol method as described by Pasternak et al. (2000) . Total intracellular RNA was resolved in denaturing agarose±formaldehyde gels. Hybridization of dried gels with the radioactively labelled oligonucleotide probe E154, which is complementary to the 3¢ end of the EAV genome and recognizes all viral mRNA molecules (genomic and subgenomic), and phosphoimager quantitation of individual bands were performed as described by Pasternak et al. (2000) . To determine the leader±body junction sequence of sg mRNA7, mRNA7-speci®c RT±PCRs were carried out as described by van Marle et al. (1999b) using an antisense (RT and PCR) primer from the RNA7 body region and a sense PCR primer matching a part of the leader sequence. RT±PCR products were sequenced directly as described by Pasternak et al. (2000) using the leader-derived primer, an ABI PRISMÔ sequencing kit (Perkin Elmer) and an ABI PRISMÔ 310 Genetic Analyser (Perkin Elmer)." }, { "from": "gpt", "value": "Summary: [Summary placeholder]" } ]

[ { "from": "human", "value": "Full Text: Anaemia is a common condition in critically ill patients, and RBC transfusions are often used in the treatment and management of this patient population. In fact, one study [1] reported that 25% of all critically ill patients received RBC transfusions. Many laboratory studies [2] [3] [4] [5] [6] [7] [8] have examined the physiological responses (ie compensatory mechanisms) of the body to anaemia, which include the following [9] : increased cardiac output, decreased blood viscosity, capillary changes, increased oxygen extraction, and other tissue adaptations to meet oxygen requirements. Although critically ill patients are affected by a number of factors that predispose them to the adverse consequences of anaemia, persistence of this condition is of particular concern because it may cause the compensatory mechanisms in these patients to become impaired, risking oxygen deprivation in vital organs [9] . However, critically ill patients may also be at increased risk from the adverse effects of RBC transfusions, such as pulmonary oedema from volume overload, immune suppression resulting in increased risk of infection, and microcirculatory injury from poorly deformable RBCs.\nIt is the aim of the present commentary to justify the statement 'Transfusing to normal haemoglobin concentration will not improve outcome.' If we define normal haemoglobin as being greater than 115 g/l for women and greater than 125 g/l for men, then there is no evidence in the literature to justify maintaining such high concentrations by the use of RBC transfusions in any anaemic patient. There may, however, be some debate about adopting a transfusion threshold of 100 g/l, which is well below 'normal'. transfusion threshold would, obviously, reduce the number of allogeneic RBCs transfused. It is our goal to impress upon the reader that transfusing to a level equal to or greater than 100 g/l does not improve mortality and other clinically important outcomes in a critical care setting. We first explore the reasons why a reduction in the total number of allogeneic blood transfusions would be beneficial. Second, we examine the current evidence for using a lower transfusion strategy, specifically that employed in the Transfusion Requirements In Critical Care (TRICC) trial.\nRBC transfusions have inherent risks that may be categorized as follows [11] [12] [13] [14] [15] : transfusion-transmitted infections; immune-related reactions (acute or delayed haemolytic reactions, febrile, allergic, anaphylactic reactions and graft-versus-host disease); and nonimmunerelated reactions (fluid overload, hypothermia, electrolyte toxicity and iron overload).\nMajor improvements in donor screening procedures and laboratory testing have dramatically improved the safety of the blood supply [16] . Currently, the risk of transmitting an infectious agent through blood transfusion ranges from 1:100,000 for hepatitis B virus to 1:1,000,000 for HIV (Canadian Blood Services, personal communication, 2000). The most important threats to the blood supply remain new and unknown pathogens. More recently, concern has focused on the potential transmission of prions through RBCs. Also, infectious agents with long latency periods pose particular risks to young individuals who require RBCs, such as multiple trauma victims. The risk : benefit ratio for a 24-year-old trauma victim with a 50-year life expectancy differs markedly from that for a person aged 80 years who is undergoing coronary artery bypass surgery. In summary, because there is a risk of transmitting diseases through the blood supply, we should always strive to use RBCs according to the best available evidence in order to ensure that we do more good than harm to our patients.\nIt is a long-standing observation [17] [18] [19] [20] [21] that blood transfusions are associated with immune suppression. This clinical phenomenon was first observed in renal transplant patients who had received blood transfusions while on dialysis before the transplant [22] , and has been observed repeatedly in transplant centres around the world [23, 24] . Recently, Opelz et al [25] reported a multicentre clinical trial in which all renal allograft recipients received modern immunosuppressive regimens. Those patients who were allocated to receive three allogeneic RBC units before renal transplant had a 1-year graft survival rate of 90%, as compared with 82% for patients who were not transfused (P = 0.02). These data suggest that there are long-term immunosuppressive effects following transfusion of nonleukocyte-reduced allogeneic RBCs.\nA large number of studies [26] [27] [28] [29] [30] [31] [32] [33] [34] have also suggested that allogeneic transfusions accelerate cancer growth, perhaps due to altered immune surveillance. These altered immune responses after allogeneic RBC transfusions may also predispose critically ill transfusion recipients to nosocomial infections [35] [36] [37] [38] [39] [40] and increased rates of multiplesystem organ failure [41] , which may ultimately result in higher mortality rates. However, most studies that examined the association between cancer recurrence and postoperative infection after transfusion [42, 43] only provided weak causal inferences because of poor study design and the lack of independence between allogeneic RBC transfusions and the potential complication.\nA recent meta-analysis [44] combined the results from seven RCTs, and was unable to detect clinically important decreases in mortality and postoperative infections. We added the results of a new RCT by van de Watering et al [45] to the above meta-analysis. The relative risk for allcause mortality was 1.05 (95% confidence interval 0.88-1.25), and was 1.10 (95% confidence interval 0.85-1.43) for postoperative infections. However, this meta-analysis excluded two positive RCTs [40, 46] because of the significant statistical heterogeneity introduced by these two studies. If all available RCTs are combined, ignoring heterogeneity, then the relative risk difference for postoperative infections across all studies is 1.60 (95% confidence interval 1.00-2.56; P = 0.05). Thus, the available evidence suggests that universal prestorage leukoreduction could have clinical effects that range from none to decreasing rates of infection by as much as 50% in high-risk patients. In summary, despite convincing laboratory evidence and some supportive clinical studies, the clinical significance of the immunosuppressive effects of allogeneic RBC transfusions have not been clearly established [47] . More importantly, the impact of a leukoreduction programme has not been studied in a large population of patients who are expected to have significant exposure to allogeneic RBCs.\nThe majority of complications from allogeneic RBC transfusion, however, are no more frequent in the intensive care setting than in other patient populations, with the possible exception of pulmonary oedema, hypothermia and electrolyte disturbance. Hypothermia and electrolyte disturbances occur most frequently with massive transfusions. In critically ill patients, the optimal effective circulatory volume may be difficult to determine, and as a consequence pulmonary oedema may be a much more frequent complication of RBC transfusion than in other patient populations. This may explain the significantly higher rate of pulmonary oedema in patients transfused using a threshold of 100 g/l (5.3% in the restrictive transfusion group versus 10.7% in the liberal transfusion group; P < 0.01), as reported in the TRICC trial [10] . As an alternative explanation, the more frequent use of RBCs might have resulted in more frequent episodes of transfusion-related acute lung injury in the liberal strategy group (7.7% in the restrictive strategy versus 11.4% in the liberal strategy; P = 0.06), as reported in the TRICC trial.\nClinical evidence is also insufficient to definitively establish a correlation between the age of RBCs being transfused and patient mortality; however, laboratory evidence has shown many storage-related changes that may result in impairment of blood flow and oxygen delivery at the microcirculatory level. Marik et al [48] demonstrated an association between a fall in gastric intramucosal pH and transfusion of RBCs stored for longer than 15 days. In addition, there is ample laboratory evidence that prolonged RBC storage adversely affects RBCs, potentially results in the generation of cytokines, and alters host immune function. In another study, Fitzgerald et al [49] , using an animal model of transfusion, consistently observed a lack of efficacy of transfused, stored rat blood to improve tissue oxygen consumption as compared with fresh cells or other blood substitutes.\nThree retrospective clinical studies tested the association between the age of transfused blood and duration of stay in the intensive care unit (ICU) [50] and mortality [51, 52] . Martin et al [50] observed a statistically significant association between the transfusion of aged blood (>14 days old) and increased duration of ICU stay (P = 0.003) in 698 critically ill patients. In patients who received a transfusion, aged RBCs was the only predictor of duration of stay (P < 0.0001). In survivors, only median age of blood was predictive of duration of stay (P < 0.0001). Purdy et al [51] demonstrated a negative correlation (r = -0.73) between the proportion of RBC units of a given age transfused to survivors and increasing age of RBCs in patients admitted to the ICU with a diagnosis of severe sepsis (n = 31). Those investigators also noted that these latter units were more likely to be older. A recently reported study by Vamvakas and Carven [52] evaluated the effect of duration of RBC storage on postoperative pneumonia in 416 consecutive patients undergoing coronary artery bypass grafting. Those investigators noted an adjusted increase of 1% in the risk of postoperative pneumonia per day of average increase in the duration of RBC storage (P < 0.005) in transfused patients. Each of these three studies also noted that patients who received a large number of RBC units had a higher mortality. Although these risks are relatively small when viewed collectively, they become significant when one considers that 25% of all critically ill patients in Canada are transfused during their ICU stay [1] .\nUntil recently, physicians have depended on clinical judgement when deciding at what haemoglobin level to transfuse a critically ill patient. As a result, significant variation has been shown to exist in transfusion practice among Canadian critical care physicians [53] , which is due largely to a lack of published data on the subject. An arbitrary haemoglobin level of 100 g/l has historically been used as a threshold to transfuse critically ill patients.\nSix observational studies investigated the importance of anaemia on transfusion practices in various settings. Of these, three large cohort studies, which were performed in different patient populations (intensive care [1] , coronary artery bypass surgery [54] and hip fractures [55]), reached different conclusions. RBC transfusions in particular improved outcome in critically ill patients with cardiovascular disease, but increased the risk of myocardial infarction in coronary artery bypass surgery patients. Transfusion had no impact on short-term or long-term mortality in hip-fracture patients. Three smaller studies [56] [57] [58] evaluated the relationship between anaemia and adverse outcomes in vascular disease patients. Although increased numbers of ischaemic events were observed in anaemic patients, the validity of these studies is uncertain, given that the decision to transfuse a patient was often correlated with illness burden of the patient. It is also possible that comorbidity was not adequately adjusted for in those studies.\nTransfusion thresholds were compared in 10 randomized clinical trials [10, [59] [60] [61] [62] [63] [64] [65] [66] [67] . Although the clinical settings varied, each trial randomized patients to be transfused on the basis of a 'conservative' or a 'liberal' strategy. The definitions of conservative and liberal strategies varied, and actually overlapped between studies. Of these 10 trials, only three included more than 100 patients and only one trial evaluated the impact of transfusion on symptoms. In the first trial of patients undergoing elective coronary artery bypass surgery [65] , the differences between perioperative haemoglobin levels were small, event rates were very low, and there were no differences in any outcome. In the second trial [67] , patients undergoing knee arthroplasty were randomly assigned to receive autologous blood transfusion immediately after surgery or to receive autologous blood if haemoglobin level fell below 9 g/dl [67] . Again, no differences in outcome were observed. The third trial of hip fracture patients undergoing surgical repair [64] found no differences in outcomes; however, five deaths were recorded at 60 days after surgery in the symptomatic group, and two deaths occurred in the 10 g/dl group. The numbers of patients in these trials were too small to evaluate the effect of lower transfusion triggers on clinically important outcomes such as mortality, morbidity and functional status.\nIn 1999, Hebert et al [10] reported the results of the TRICC trial. Patients (n = 838) were randomized either to a restrictive strategy (haemoglobin concentration maintained between 70 and 90 g/l, with a trigger set at 70 g/l) or to a liberal strategy (haemoglobin concentration maintained between 100 and 120 g/l, with a trigger at 100 g/l). To date, the TRICC trial is the only large study that has investigated these parameters. The groups were comparable at baseline. The average daily haemoglobin concentration ranged from 85 ± 7.2 g/l in the restrictive group to 107 ± 7.3 g/l in the liberal group (P < 0.01). The average number of transfusions was reduced by 52% in the restrictive group (2.6 ± 4.1 versus 5.6 ± 5.3 RBCs/patient; P < 0.01). Cardiac events, primarily pulmonary oedema and myocardial infarction, were more frequent in the liberal strategy (P < 0.01; Table 1 ). On examination of composite outcomes, the number of patients with multiorgan failure was found to be substantially increased in both groups, with the results being marginally better in the restrictive strategy group (20.6% versus 26.0%; P = 0.07; Table 2 ). Overall, the restrictive transfusion group showed a lower 30-day mortality (18.7% versus 23.3%; P = 0.11; Fig. 1 ). Kaplan-Meier survival curves, however, were significantly different in the subgroup of patients with an Acute Physiology and Chronic Health Evaluation II score of 20 or less (P = 0.02; Fig. 2 ). In addition, although 60-day mortality (22.8% versus 26.5%; P = 0.23) and ICU mortality (13.9% versus 16.2%; P = 0.29) were not statistically significant, they did show a consistent trend in terms of absolute values that favoured the restrictive strategy. The key observation from the TRICC trial is not that the restrictive strategy is better, but rather that it is at worst equivalent to the liberal strategy and at best superior to the liberal strategy.\nAt this juncture, preclinical and clinical evidence support the adoption of a more restrictive transfusion strategy in most critically ill patients. However, there remain divergent views regarding the risks and benefits of treating anaemia in patients with cardiovascular disease. Laboratory-based studies [68, 69] suggest that patients with cardiovascular disease may require higher haemoglobin concentrations to maintain oxygen delivery in partially occluded or diseased coronary arteries. Studies to demonstrate how anaemia affects contractile function of the left ventricle have rarely shown important effects above haemoglobin concentrations of 70 g/l. Indeed, it is more important to address the underlying pathophysiological causes of the acute coronary syndrome with proven therapy such as aspirin and β-blockers, rather than treating mild-to-moderate anaemia as an initial step. If the effects of RBC transfusion were either limited or increased then there would be no debate; however, the use of allogeneic RBCs has been shown to be associated with immunomodulation [12, 47] and/or alteration in the delivery of oxygen in the microcirculation [70, 71] , resulting in increased rates of infections and organ failure.\nFew clinical studies have attempted to elucidate the risk : benefit ratio of anaemia and transfusion in cardiac patients. Two small RCTs [62, 72] examined transfusion practice in patients undergoing coronary artery bypass grafting, and concluded that a conservative approach to the administration of RBCs may be safe. However, two recent cohort studies suggested that anaemia may increase the risk of mortality in critical illness [73] and following surgery in patients with cardiovascular disease [74] . There were 418 and 420 patients in the restrictive and liberal transfusion groups, respectively. *Difference calculated by subtracting mean values of restrictive group from those of liberal group. † Three patients were lost to 60-day mortality rate; therefore n = 835. ‡ Nonsurvivors are considered to have all organs failing on date of death. § Changes in MOD score from baseline, while also incorporating adjustment for death. Data from Hébert et al [10] .\nIn a study of Jehovah's Witnesses (a group that refuses RBC transfusion on religious grounds) undergoing surgical procedures [74] , it was noted that mortality was significantly increased in patients with cardiac disease after a decrease in haemoglobin levels from 100-110 g/l to 60-69 g/l. In that study, patients with no cardiac disease and similar changes in haemoglobin levels showed no increase in mortality, which is in accordance with the results of the TRICC trial [10] . In the study by Hébert et al. [73] of 4470 critically ill patients, a correlation between Critical Care Vol 5 No 2 Alvarez et al [10] .\nKaplan-Meier estimates of survival in the 30 days after admission to the ICU in the restrictive and liberal transfusion strategy groups (all patients). Data from Hébert et al [10] .\nKaplan-Meier estimates of survival in the 30 days after admission to the ICU in the restrictive and liberal transfusion strategy groups (patients with APACHE II score ≤20). Data from Hébert et al [10] .\nanaemia and mortality rates was observed. Those investigators also found that the risk of anaemia appeared to decrease with RBC transfusion in patients with cardiac disease. In patients with cardiac disease, mortality increased when haemoglobin concentrations were below 95 g/l, as compared with anaemic patients with other diagnoses (55% versus 42%; P = 0.09). In the subgroup of patients with cardiac disease, increasing haemoglobin values in anaemic patients was associated with improved survival (odds ratio 0.80 for each 10 g/l increase; P = 0.012). One possible explanation for the discrepancy between the TRICC trial and this observational study may be that the attending physicians who recruited patients into the study did not enter those patients who were considered to have severe cardiac disease.\nHébert et al. [73] sought to examine further whether a restrictive transfusion strategy was at least as effective as a liberal strategy in critically ill patients with cardiac disease. In the subgroup of patients with cardiovascular disease from the TRICC trial, those investigators suggested that most haemodynamically stable critically ill patients with cardiovascular disease may be transfused when haemoglobin concentrations fall below 70 g/l, and that the hemoglobin concentration should be maintained between 70 and 90 g/l. Average daily haemoglobin concentrations were 85 ± 6.2 g/l in the restrictive transfusion group and 103 ± 6.7 g/l in the liberal transfusion group (P < 0.01). In the 357 patients with cardiovascular disease, the 30-day mortality rate was 23% in the restrictive transfusion group versus 23% in the liberal group (95% confidence interval of the difference -8.4% to 9.1%; P = 1.00). Other mortality rates, including 60-day (26% versus 27%; P = 0.90), ICU (19% versus 16%; P = 0.49) and hospital mortality (27% versus 28%; P = 0.81), were not significantly different between groups. Kaplan-Meier survival curves comparing time to death demonstrated similar trends in the two groups ( Fig. 3 ; P = 0.98). The multiple organ dysfunction (MOD) scores, during the entire study period, were also not significantly different between groups (8.6 ± 4.9 versus 9.0 ± 4.4; P = 0.40), but the change in MOD score from baseline values was significantly lower in the restrictive group than in the liberal group (0.2 ± 4.2 versus 1.3 ± 4.4; P = 0.02).\nCombined measures of morbidity and mortality, or composite outcomes, were also examined. When all patients who died were given a score of 24, the total MOD score between groups was not different (P = 0.39), or were the changes in MOD scores significantly different from baseline (2.7 ± 6.9 versus 4.0 ± 7.3; P = 0.08). Among the specific subset of cardiac patients with ischaemic heart disease (n = 257), there were no discernible differences in 30-day and 60-day as well as ICU mortality rates. However, a nonsignificant (P = 0.3) decrease in overall survival rate in the restrictive group was noted in those patients with confirmed ischaemic heart disease, severe peripheral vascular disease or severe comorbid cardiac disease (Fig. 4) .\nIn conclusion, a restrictive RBC transfusion strategy generally appears to be safe in most critically ill patients with cardiovascular disease, with the possible exception of patients experiencing acute myocardial infarction or unstable angina. \nSurvival over 30 days in patients with ischemic heart disease in the restrictive and liberal allogeneic RBC transfusion strategy groups. This graph illustrates Kaplan-Meier survival curves for all patients with ischemic heart disease in both study groups. There is no difference in mortality in patients in the restrictive group (dashed line) as compared to the liberal group (solid line) (P = 0.30).\nThe need to reduce the amount of allogeneic blood transfusions in order to reduce the associated risks has been firmly established. RBCs are associated with clinically important immune suppression, and stored RBCs have been shown to cause adverse microcirculatory effects that result in increased organ failure.\nThe question for some time has been whether critically ill patients are able to tolerate lower levels of haemoglobin without deleterious effects, thus reducing the amount of exposure to allogeneic transfusions. In the only large RCT, Hébert et al [10] established that there was no difference in mortality rates between restrictive and liberal transfusion strategies in noncardiac, critically ill patients. Although those investigators were able to show convincing trends that the liberal strategy may in fact be deleterious in terms of absolute values, statistical significance was not achieved. However, the fact that no difference between the two strategies was achieved is of great importance, because this means that the total number of transfusions can be reduced by approximately half without any impact on mortality. In addition, these findings are easily put into clinical practice. Although many questions remain, the TRICC trial and many laboratory and clinical studies have established that transfusing to normal haemoglobin concentrations does not improve organ failure and mortality in the critically ill patient. As such, a restrictive transfusion strategy will reduce exposure to allogeneic transfusions, result in more efficient use of RBCs, save blood overall, and decrease health care costs." }, { "from": "gpt", "value": "Summary: [Summary placeholder]" } ]

[{"from":"human","value":"Full Text: This year's symposium was dominated by the results of recent cl(...TRUNCATED)

[{"from":"human","value":"Full Text: The heme oxygenase-1/carbon monoxide (HO-1/CO) system has recen(...TRUNCATED)

[{"from":"human","value":"Full Text: Unfortunately, conventional public health disease surveillance-(...TRUNCATED)