Update README.md

README.md

@@ -1,3 +1,217 @@
----
-license: llama3.1
----
+---
+license: llama3.1
+datasets:
+- BAAI/OPI
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- Life Science
+- AI4Science
+- Biology
+- Protein
+- LLM
+- Instruction
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+---
+![OPI_logo](./OPI_logo.png)
+
+# Model Card of OPI-Llama-3.1-8B-Instruct
+OPI-Llama-3.1-8B-Instruct was fine-tuned from the Meta-Llama-3.1-8B-Instruct model using the complete OPI dataset (i.e.,[OPI_full_1.61M.json](https://huggingface.co/datasets/BAAI/OPI/blob/main/OPI_DATA/OPI_full_1.61M_train.json)).
+For more details of training and testing, please visit [https://github.com/baaihealth/opi](https://github.com/baaihealth/opi).
+
+![Overview](./OPI_experiment_outline.png)
+
+# Evaluation of OPI-Llama-3.1-8B-Instruct on 9 tasks 
+Each testing result is derived from the Meta-Llama-3.1-8B-Instruct model that has been fine-tuned using [OPI_full_1.61M.json](https://huggingface.co/datasets/BAAI/OPI/blob/main/OPI_DATA/OPI_full_1.61M_train.json) and subsequently evaluated on the respective testing set for each specific task.
+
+<table border="1" style="text-align:center; border-collapse:collapse; width: 100%;">
+  <thead>
+    <tr>
+      <th style="text-align:center;">Task Type</th>
+      <th style="text-align:center;">Task Name</th>
+      <th style="text-align:center;">Testing file</th>
+      <th style="text-align:center;">Accuracy</th>
+      <th style="text-align:center;">Precision</th>
+      <th style="text-align:center;">Recall</th>
+      <th style="text-align:center;">F1</th>
+      <th style="text-align:center;">Rouge-L</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="6">Sequence Understanding</td>
+      <td rowspan="2">EC Number Prediction (split100)</td>
+      <td>CLEAN_EC_number_new_test</td>
+      <td>-</td>
+      <td>0.3724</td>
+      <td>0.3374</td>
+      <td>0.3468</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>CLEAN_EC_number_price_test</td>
+      <td>-</td>
+      <td>0.0738</td>
+      <td>0.0738</td>
+      <td>0.0738</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td rowspan="3">Fold Type Prediction</td>
+      <td>fold_type_test_Fold_Holdout</td>
+      <td>0.1045</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>fold_type_test_Superfamily_Holdout</td>
+      <td>0.1507</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>fold_type_test_Family_Holdout</td>
+      <td>0.6145</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Subcellular Localization Prediction</td>
+      <td>subcell_loc_test</td>
+      <td>0.4214</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td rowspan="9">Annotation Prediction</td>
+      <td rowspan="3">Function Keywords Prediction</td>
+      <td>CASPSimilarSeq_keywords_test</td>
+      <td>-</td>
+      <td>0.4202</td>
+      <td>0.5057</td>
+      <td>0.4385</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>IDFilterSeq_keywords_test</td>
+      <td>-</td>
+      <td>0.6762</td>
+      <td>0.6905</td>
+      <td>0.6650</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>UniProtSeq_keywords_test</td>
+      <td>-</td>
+      <td>0.7606</td>
+      <td>0.7489</td>
+      <td>0.7374</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td rowspan="3">Gene Ontology(GO) Terms Prediction</td>
+      <td>CASPSimilarSeq_go_terms_test</td>
+      <td>-</td>
+      <td>0.1113</td>
+      <td>0.0936</td>
+      <td>0.099</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>IDFilterSeq_go_terms_test</td>
+      <td>-</td>
+      <td>0.6686</td>
+      <td>0.6287</td>
+      <td>0.6304</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>UniProtSeq_go_terms_test</td>
+      <td>-</td>
+      <td>0.7150</td>
+      <td>0.6897</td>
+      <td>0.6849</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td rowspan="3">Function Description Prediction</td>
+      <td>CASPSimilarSeq_function_test</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0.7524</td>
+    </tr>
+    <tr>
+      <td>IDFilterSeq_function_test</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0.4786</td>
+    </tr>
+    <tr>
+      <td>UniProtSeq_function_test</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0.5144</td>
+    </tr>
+    <tr>
+      <td rowspan="3">Knowledge Mining</td>
+      <td>Tissue Location Prediction from Gene Symbol</td>
+      <td>gene_symbol_to_tissue_test</td>
+      <td>-</td>
+      <td>0.4002</td>
+      <td>0.9356</td>
+      <td>0.5466</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Cancer Prediction from Gene Symbol</td>
+      <td>gene_symbol_to_cancer_test</td>
+      <td>-</td>
+      <td>0.2890</td>
+      <td>0.2701</td>
+      <td>0.2664</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Cancer Prediction from Gene Name</td>
+      <td>gene_name_to_cancer_test</td>
+      <td>-</td>
+      <td>0.2786</td>
+      <td>0.2707</td>
+      <td>0.2659</td>
+      <td>-</td>
+    </tr>
+  </tbody>
+</table>
+
+# Prediction comparison with SOTA mdoels
+
+![model_compare](model_compare/task1_EC_number.png)
+![model_compare](model_compare/task2_fold_type.png)
+![model_compare](model_compare/task3_subcell_loc.png)
+![model_compare](model_compare/task4_keywords.png)
+![model_compare](model_compare/task5_GO.png)
+![model_compare](model_compare/task6_function.png)
+![model_compare](model_compare/task7_gsymbol2tissue.png)
+![model_compare](model_compare/task8_gsymbol2cancer.png)
+![model_compare](model_compare/task9_gname2cancer.png)
+
+
+# Demo
+We use the [FastChat](https://github.com/lm-sys/FastChat) platform to visually demonstrate the ability of OPI_full_Galactica-6.7B model on various evaluation tasks.
+
+![OPI Demo](./OPI_demo.gif)