MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering
This work addresses the need for explainable and engineerable tools in protein mutation studies for life sciences researchers, representing a novel method for a known bottleneck.
The paper tackles the problem of protein language models lacking explicit and explainable mutation representations by introducing MutaPLM, a framework that captures explicit mutation features and uses text-based supervision, resulting in improved human-understandable explanations and prioritization of novel mutations with desirable properties.
Studying protein mutations within amino acid sequences holds tremendous significance in life sciences. Protein language models (PLMs) have demonstrated strong capabilities in broad biological applications. However, due to architectural design and lack of supervision, PLMs model mutations implicitly with evolutionary plausibility, which is not satisfactory to serve as explainable and engineerable tools in real-world studies. To address these issues, we present MutaPLM, a unified framework for interpreting and navigating protein mutations with protein language models. MutaPLM introduces a protein delta network that captures explicit protein mutation representations within a unified feature space, and a transfer learning pipeline with a chain-of-thought (CoT) strategy to harvest protein mutation knowledge from biomedical texts. We also construct MutaDescribe, the first large-scale protein mutation dataset with rich textual annotations, which provides cross-modal supervision signals. Through comprehensive experiments, we demonstrate that MutaPLM excels at providing human-understandable explanations for mutational effects and prioritizing novel mutations with desirable properties. Our code, model, and data are open-sourced at https://github.com/PharMolix/MutaPLM.