Taihei Murakami

Mechanistic Interpretability of Fine-Tuned Protein Language Models for Nanobody Thermostability Prediction

This paper fine-tunes a protein language model on nanobody thermostability data and uses sparse autoencoders to uncover biophysical rules governing stability, identifying both known and novel stabilizing features.

Transfer learning from computed stability data for nanobody melting-temperature prediction

The paper predicts nanobody melting temperatures using transfer learning with computed stability data, finding that free-energy perturbation labels and sequence diversity improve predictions.