#!/usr/bin/env python
# coding: utf-8

# # Different Expression Analysis with DEseq2
# 
# An important task of bulk rna-seq analysis is the different expression , which we can perform with omicverse. For different expression analysis, ov change the `gene_id` to `gene_name` of matrix first. 
# 
# Now we can use `PyDEseq2` to perform DESeq2 analysis like R
# 
# Paper: [PyDESeq2: a python package for bulk RNA-seq differential expression analysis](https://www.biorxiv.org/content/10.1101/2022.12.14.520412v1)
# 
# Code: https://github.com/owkin/PyDESeq2
# 
# Colab_Reproducibility：https://colab.research.google.com/drive/1fZS-v0zdIYkXrEoIAM1X5kPoZVfVvY5h?usp=sharing

# In[1]:


import omicverse as ov
ov.utils.ov_plot_set()


# Note that this dataset has not been processed in any way and is only exported by `featureCounts`, and Sequence alignment was performed from the genome file of CRCm39

# In[2]:


data=ov.utils.read('https://raw.githubusercontent.com/Starlitnightly/Pyomic/master/sample/counts.txt',index_col=0,header=1)
#replace the columns `.bam` to `` 
data.columns=[i.split('/')[-1].replace('.bam','') for i in data.columns]
data.head()


# ## ID mapping
# 
# We performed the gene_id mapping by the mapping pair file `GRCm39` downloaded before.

# In[ ]:


ov.utils.download_geneid_annotation_pair()


# In[3]:


data=ov.bulk.Matrix_ID_mapping(data,'genesets/pair_GRCm39.tsv')
data.head()


# ## Different expression analysis with ov
# 
# We can do differential expression analysis very simply by ov, simply by providing an expression matrix. To run DEG, we simply need to:
# 
# - Read the raw count by featureCount or any other qualify methods.
# - Create an ov DEseq object.

# In[4]:


dds=ov.bulk.pyDEG(data)


# We notes that the gene_name mapping before exist some duplicates, we will process the duplicate indexes to retain only the highest expressed genes

# In[5]:


dds.drop_duplicates_index()
print('... drop_duplicates_index success')


# Now we can calculate the different expression gene from matrix, we need to input the treatment and control groups

# In[6]:


treatment_groups=['4-3','4-4']
control_groups=['1--1','1--2']
result=dds.deg_analysis(treatment_groups,control_groups,method='DEseq2')


# One important thing is that we do not filter out low expression genes when processing DEGs, and in future versions I will consider building in the corresponding processing.

# In[7]:


print(result.shape)
result=result.loc[result['log2(BaseMean)']>1]
print(result.shape)


# We also need to set the threshold of Foldchange, we prepare a method named `foldchange_set` to finish. This function automatically calculates the appropriate threshold based on the log2FC distribution, but you can also enter it manually.

# In[8]:


# -1 means automatically calculates
dds.foldchange_set(fc_threshold=-1,
                   pval_threshold=0.05,
                   logp_max=10)


# ## Visualize the DEG result and specific genes
# 
# To visualize the DEG result, we use `plot_volcano` to do it. This fuction can visualize the gene interested or high different expression genes. There are some parameters you need to input:
# 
# - title: The title of volcano
# - figsize: The size of figure
# - plot_genes: The genes you interested
# - plot_genes_num: If you don't have interested genes, you can auto plot it.

# In[9]:


dds.plot_volcano(title='DEG Analysis',figsize=(4,4),
                 plot_genes_num=8,plot_genes_fontsize=12,)


# To visualize the specific genes, we only need to use the `dds.plot_boxplot` function to finish it.

# In[10]:


dds.plot_boxplot(genes=['Ckap2','Lef1'],treatment_groups=treatment_groups,
                control_groups=control_groups,figsize=(2,3),fontsize=12,
                 legend_bbox=(2,0.55))


# In[11]:


dds.plot_boxplot(genes=['Ckap2'],treatment_groups=treatment_groups,
                control_groups=control_groups,figsize=(2,3),fontsize=12,
                 legend_bbox=(2,0.55))


# ## Pathway enrichment analysis by Pyomic
# 
# Here we use the `gseapy` package, which included the GSEA analysis and Enrichment. We have optimised the output of the package and given some better looking graph drawing functions
# 
# Similarly, we need to download the pathway/genesets first. Five genesets we prepare previously, you can use `Pyomic.utils.download_pathway_database()` to download automatically. Besides, you can download the pathway you interested from enrichr: https://maayanlab.cloud/Enrichr/#libraries

# In[13]:


ov.utils.download_pathway_database()


# In[14]:


pathway_dict=ov.utils.geneset_prepare('genesets/WikiPathways_2019_Mouse.txt',organism='Mouse')


# To perform the GSEA analysis, we need to ranking the genes at first. Using `dds.ranking2gsea` can obtain a ranking gene's matrix sorted by -log10(padj).
# 
# $Metric=\frac{-log_{10}(padj)}{sign(log2FC)}$

# In[15]:


rnk=dds.ranking2gsea()


# We used `ov.bulk.pyGSEA` to construst a GSEA object to perform enrichment.

# In[16]:


gsea_obj=ov.bulk.pyGSEA(rnk,pathway_dict)


# In[17]:


enrich_res=gsea_obj.enrichment()


# The results are stored in the `enrich_res` attribute.

# In[18]:


gsea_obj.enrich_res.head()


# To visualize the enrichment, we use `plot_enrichment` to do.
# - num: The number of enriched terms to plot. Default is 10.
# - node_size: A list of integers defining the size of nodes in the plot. Default is [5,10,15].
# - cax_loc: The location of the colorbar on the plot. Default is 2.
# - cax_fontsize: The fontsize of the colorbar label. Default is 12.
# - fig_title: The title of the plot. Default is an empty string.
# - fig_xlabel: The label of the x-axis. Default is 'Fractions of genes'.
# - figsize: The size of the plot. Default is (2,4).
# - cmap: The colormap to use for the plot. Default is 'YlGnBu'.

# In[19]:


gsea_obj.plot_enrichment(num=10,node_size=[10,20,30],
                        cax_fontsize=12,
                        fig_title='Wiki Pathway Enrichment',fig_xlabel='Fractions of genes',
                        figsize=(2,4),cmap='YlGnBu',
                        text_knock=2,text_maxsize=30,
                        cax_loc=[2.5, 0.45, 0.5, 0.02],
                          bbox_to_anchor_used=(-0.25, -13),node_diameter=10,)


# Not only the basic analysis, pyGSEA also help us to visualize the term with Ranked and Enrichment Score. 
# 
# We can select the number of term to plot, which stored in `gsea_obj.enrich_res.index`, the `0` is `Complement and Coagulation Cascades WP449` and the `1` is `Matrix Metalloproteinases WP441`

# In[20]:


gsea_obj.enrich_res.index[:5]


# We can set the `gene_set_title` to change the title of GSEA plot

# In[22]:


fig=gsea_obj.plot_gsea(term_num=1,
                  gene_set_title='Matrix Metalloproteinases',
                  figsize=(3,4),
                  cmap='RdBu_r',
                  title_fontsize=14,
                  title_y=0.95)


# In[ ]: