Towards the explainability of protein language models | Nature Machine Intelligence

Hunklinger and Ferruz provide an overview of explainable artificial intelligence methods for protein language models.

References Casheekar, A., Lahiri, A., Rath, K., Prabhakar, K. S. & Srinivasan, K. A contemporary review on chatbots, AI-powered virtual conversational agents, ChatGPT: applications, open challenges and future research directions. Comput. Sci. Rev. 52, 100632 (2024). Article Google Scholar Huang, K., Xiao, C., Glass, L. M. & Sun, J. MolTrans: molecular interaction transformer for drug–target interaction prediction. Bioinformatics 37, 830–836 (2021). Article Google Scholar Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630,…

saved by

• Sarah

related reading

• Highly accurate protein structure prediction with AlphaFoldnature.com
• Language models of protein sequences at the scale of evolution enable accurate structure predictionbiorxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
• Large Language Models Reading List | Sebastian Raschka, PhDsebastianraschka.com
• Training Language Models to Explain Their Own Computationsarxiv.org
• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelsarxiv.org
• Transformer-based deep learning for predicting protein properties in the life sciences - PMCpmc.ncbi.nlm.nih.gov
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• Prediction, Explanation, or Over-interpretation?elena-baixy.github.io
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• Training Language Models to Explain Their Own Computationsarxiv.org