arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.06275q-bio.QMcs.LG
收藏

蛋白质序列与结构联合表示学习的系统研究

A Systematic Study of Joint Representation Learning on Protein Sequences and Structures

IBM Research(IBM研究院);CIFAR AI Chair(加拿大高级研究所人工智能席位)

Zuobai Zhang, Chuanrui Wang, Minghao Xu, Vijil Chenthamarakshan, Aurélie Lozano, Payel Das, Jian Tang

AI总结:

本研究通过整合ESM-2与多种结构编码器探索蛋白质序列与结构的联合表示学习,引入三种融合策略及预训练技术,在功能注释任务上取得显著提升并树立新SOTA。

摘要:

学习有效的蛋白质表示在预测蛋白质功能等众多生物学任务中至关重要。近期基于蛋白质语言模型(PLMs)的序列表示学习方法在基于序列的任务中表现出色,但将其直接适配到涉及蛋白质结构的任务仍具挑战。相比之下,基于结构的方法利用3D结构信息并结合图神经网络,几何预训练方法在功能预测任务中展现出潜力,但受限于可用结构数量有限。为弥合此差距,本研究通过将最先进的PLM(ESM-2)与不同的结构编码器(GVP、GearNet、CDConv)相结合,对联合蛋白质表示学习进行了全面探索。我们引入了三种表示融合策略,并探究了不同的预训练技术。我们的方法相比现有的基于序列和结构的方法取得了显著提升,为功能注释树立了新的最先进水平。本研究强调了融合蛋白质序列与结构信息的若干重要设计选择。实现代码可在https://github.com/DeepGraphLearning/ESM-GearNet获取。

英文摘要:

Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein functions. Recent sequence representation learning methods based on Protein Language Models (PLMs) excel in sequence-based tasks, but their direct adaptation to tasks involving protein structures remains a challenge. In contrast, structure-based methods leverage 3D structural information with graph neural networks and geometric pre-training methods show potential in function prediction tasks, but still suffers from the limited number of available structures. To bridge this gap, our study undertakes a comprehensive exploration of joint protein representation learning by integrating a state-of-the-art PLM (ESM-2) with distinct structure encoders (GVP, GearNet, CDConv). We introduce three representation fusion strategies and explore different pre-training techniques. Our method achieves significant improvements over existing sequence- and structure-based methods, setting new state-of-the-art for function annotation. This study underscores several important design choices for fusing protein sequence and structure information. Our implementation is available at https://github.com/DeepGraphLearning/ESM-GearNet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑