Linker-Tuning: Optimizing Continuous Prompts for Heterodimeric Protein Prediction

TL;DR

This paper introduces Linker-tuning, a lightweight method that optimizes continuous prompts to adapt ESMFold for heterodimer protein structure prediction, achieving significant accuracy improvements and faster inference.

Contribution

The paper presents Linker-tuning, a novel prompt-learning approach that enables ESMFold to accurately predict heterodimer structures with improved efficiency and generalization.

Findings

Predicts 56.98% of interfaces on heterodimer test set

Achieves +12.79% improvement over baseline

Runs 9 times faster than AF-Multimer

Abstract

Predicting the structure of interacting chains is crucial for understanding biological systems and developing new drugs. Large-scale pre-trained Protein Language Models (PLMs), such as ESM2, have shown impressive abilities in extracting biologically meaningful representations for protein structure prediction. In this paper, we show that ESMFold, which has been successful in computing accurate atomic structures for single-chain proteins, can be adapted to predict the heterodimer structures in a lightweight manner. We propose Linker-tuning, which learns a continuous prompt to connect the two chains in a dimer before running it as a single sequence in ESMFold. Experiment results show that our method successfully predicts 56.98% of interfaces on the i.i.d. heterodimer test set, with an absolute improvement of +12.79% over the ESMFold-Linker baseline. Furthermore, our model can generalize well to the out-of-distribution (OOD) test set HeteroTest2 and two antibody test sets Fab and Fv while being $9\times$ faster than AF-Multimer.