PatchProt: Hydrophobic patch prediction using protein foundation models

TL;DR

PatchProt leverages fine-tuned protein foundation models to accurately predict hydrophobic patches and related properties from sequences, outperforming existing methods and demonstrating the benefits of multi-task learning.

Contribution

This study introduces a novel fine-tuning approach for large language models to predict protein surface properties, integrating multi-task learning for enhanced accuracy.

Findings

Outperforms existing hydrophobic patch prediction methods.

Multi-task learning improves global property predictions.

Efficient fine-tuning avoids computationally expensive analyses.

Abstract

Hydrophobic patches on protein surfaces play important functional roles in protein-protein and protein-ligand interactions. Large hydrophobic surfaces are also involved in the progression of aggregation diseases. Predicting exposed hydrophobic patches from a protein sequence has been shown to be a difficult task. Fine-tuning foundation models allows for adapting a model to the specific nuances of a new task using a much smaller dataset. Additionally, multi-task deep learning offers a promising solution for addressing data gaps, simultaneously outperforming single-task methods. In this study, we harnessed a recently released leading large language model ESM-2. Efficient fine-tuning of ESM-2 was achieved by leveraging a recently developed parameter-efficient fine-tuning method. This approach enabled comprehensive training of model layers without excessive parameters and without the need to include a computationally expensive multiple sequence analysis. We explored several related tasks, at local (residue) and global (protein) levels, to improve the representation of the model. As a result, our fine-tuned ESM-2 model, PatchProt, cannot only predict hydrophobic patch areas but also outperforms existing methods at predicting primary tasks, including secondary structure and surface accessibility predictions. Importantly, our analysis shows that including related local tasks can improve predictions on more difficult global tasks. This research sets a new standard for sequence-based protein property prediction and highlights the remarkable potential of fine-tuning foundation models enriching the model representation by training over related tasks.