Ontology-based-PPI-explanation-using-LLMs

Ontology-based protein-protein interaction explanation using large language models

Models Fine-tuned

Llama2 13b: done -> llama2_finetuning_ppi.ipynb
Llama3.1 8b : done -> llama3.1_finetuning_ppi.ipynb
Llama4: script ready, not able to run due to insufficient disk space -> llama4_finetuning_ppi.ipynb
Mistral 7b: done -> Fine tuned model: "mistralai/Mistral-7B-Instruct-v0.2" -> mistral_finetuning_ppi.ipynb
Qwen 2.5: done -> Fine tuned model: "Qwen/Qwen2.5-7B-Instruct-1M" -> qwen_finetuning_ppi.ipynb

01.09.2025 Update: Scripts Updated with Better Evaluation. New Scripts:

Name		Name	Last commit message	Last commit date
Latest commit History 33 Commits
INO.txt		INO.txt
README.md		README.md
all-ppi.json		all-ppi.json
bioinfer_invest.ipynb		bioinfer_invest.ipynb
finetuned_13b_chat.xlsx		finetuned_13b_chat.xlsx
infer_llama_new_ino.py		infer_llama_new_ino.py
llama2_finetuning.py		llama2_finetuning.py
llama3.1_finetuning_ppi.ipynb		llama3.1_finetuning_ppi.ipynb
llm_finetuning.ipynb		llm_finetuning.ipynb
mistral_finetuning_ppi.ipynb		mistral_finetuning_ppi.ipynb
qwen2.5_finetuning_ppi.ipynb		qwen2.5_finetuning_ppi.ipynb
requirements-llama3.1.txt		requirements-llama3.1.txt
requirements-qwen2.5_instructv3.txt		requirements-qwen2.5_instructv3.txt
test.py		test.py
token_wise_metrics.py		token_wise_metrics.py
zero_one_few_shot.ipynb		zero_one_few_shot.ipynb