ProtFAD: Introducing function-aware domains as implicit modality towards protein function prediction

TL;DR

ProtFAD introduces a novel function-aware domain representation and contrastive learning strategy that significantly improves protein function prediction by leveraging domain semantics and multi-view contrastive training.

Contribution

It proposes a new integration approach for domain-aware protein representation and a contrastive learning method that aligns domain semantics with functional annotations.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively differentiates proteins with distinct functions.

Enhances protein function prediction accuracy.

Abstract

Protein function prediction is currently achieved by encoding its sequence or structure, where the sequence-to-function transcendence and high-quality structural data scarcity lead to obvious performance bottlenecks. Protein domains are "building blocks" of proteins that are functionally independent, and their combinations determine the diverse biological functions. However, most existing studies have yet to thoroughly explore the intricate functional information contained in the protein domains. To fill this gap, we propose a synergistic integration approach for a function-aware domain representation, and a domain-joint contrastive learning strategy to distinguish different protein functions while aligning the modalities. Specifically, we align the domain semantics with GO terms and text description to pre-train domain embeddings. Furthermore, we partition proteins into multiple sub-views based on continuous joint domains for contrastive training under the supervision of a novel triplet InfoNCE loss. Our approach significantly and comprehensively outperforms the state-of-the-art methods on various benchmarks, and clearly differentiates proteins carrying distinct functions compared to the competitor. Our implementation is available at https://github.com/AI-HPC-Research-Team/ProtFAD.