Aligning sequence and structure representations leveraging protein domains for function prediction

Mingqing Wang

doi:10.1016/j.eswa.2025.127246

2025-06-01

PRE

Athanasios V. Vasilakos

Zhixiang Ren *

DOI：10.1016/j.eswa.2025.127246

原文链接

原文求助

摘要

En 中文

蛋白质功能预测传统上通过序列或结构建模进行，往往忽视了多种数据源的有效融合。蛋白质结构域作为功能独立的构建模块，决定了蛋白质的生物学功能，但其在功能预测任务中的潜力尚未得到充分挖掘。为解决这一问题，我们引入了一种多模态融合神经网络，利用功能感知的结构域嵌入作为桥梁。我们通过将结构域语义与基因本体论（GO）术语和文本描述对齐来预训练这些嵌入。此外，我们还基于连续结构域区域将蛋白质划分为子视图，以进行对比学习，并由一种新颖的三元组InfoNCE损失进行监督。我们的方法在各类基准测试中优于当前最优方法，并能比竞争对手更清晰地区分携带不同功能的蛋白质。

Keyword:

Protein function prediction

Protein domain

Deep learning

Functional priors

Contrastive learning

期刊

Expert Systems with Applications

IF:

7.5

论文数:

2.9W

被引数:

10.2W

机构

univ agder

学者数:

论文数: 77

被引数: 39

Pengcheng Lab

学者数:

论文数: 30

被引数: 7

引用论文

Domain-PFP allows protein function prediction using function-aware domain embedding representations

COMMUNICATIONS BIOLOGY

IF5.1

2023-10-31

OAAI

Ibtehaz, Nabil; Kagaya, Yuki; Kihara, Daisuke

I-TASSER-MTD: a deep-learning-based platform for multi-domain protein structure and function prediction I-tasser-mtd: 基于深度学习的多域蛋白质结构和功能预测平台

NATURE PROTOCOLS

IF16

2022-08-05

214

PREAI

Zhou, Xiaogen; Zheng, Wei; Li, Yang; Pearce, Robin; Zhang, Chengxin; Bell, Eric W.; Zhang, Guijun; Zhang, Yang

NetGO: improving large-scale protein function prediction with massive network information

NUCLEIC ACIDS RESEARCH

IF13.1

2019-05-20

OAAI

You, Ronghui; Yao, Shuwei; Xiong, Yi; Huang, Xiaodi; Sun, Fengzhu; Mamitsuka, Hiroshi; Zhu, Shanfeng

Assigning protein function from domain-function associations using DomFun

BMC Bioinformatics

IF0

2022-01-15

OAAI

Elena Rojano; Fernando M. Jabato; James R. Perkins; José Córdoba-Caballero; Federico García-Criado; Ian Sillitoe; Christine Orengo; Juan A. G. Ranea; Pedro Seoane-Zonjic

ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning ProtTrans: 通过自我监督学习来理解生活语言

IEEE Transactions on Pattern Analysis and Machine Intelligence

IF0

2022-10-01

OAAI

Ahmed Elnaggar; Michael Heinzinger; Christian Dallago; Ghalia Rehawi; Yu Wang; Llion Jones; Tom Gibbs; Tamas Feher; Christoph Angerer; Martin Steinegger; Debsindhu Bhowmik; Burkhard Rost

Protein function prediction for newly sequenced organisms

NATURE MACHINE INTELLIGENCE

IF23.9

2021-12-09

PREAI

Torres, Mateo; Yang, Haixuan; Romero, Alfonso E.; Paccanaro, Alberto

InterPro in 2022 InterPro 2022年

NUCLEIC ACIDS RESEARCH

IF13.1

2022-11-09

1.1K

OAAI

Paysan-Lafosse, Typhaine; Blum, Matthias; Chuguransky, Sara; Grego, Tiago; Pinto, Beatriz Lazaro; Salazar, Gustavo A.; Bileschi, Maxwell L.; Bork, Peer; Bridge, Alan; Colwell, Lucy; Gough, Julian; Haft, Daniel H.; Letunic, Ivica; Marchler-Bauer, Aron; Mi, Huaiyu; Natale, Darren A.; Orengo, Christine A.; Pandurangan, Arun P.; Rivoire, Catherine; Sigrist, Christian J. A.; Sillitoe, Ian; Thanki, Narmada; Thomas, Paul D.; Tosatto, Silvio C. E.; Wu, Cathy H.; Bateman, Alex

LM-GVP: an extensible sequence and structure informed deep learning framework for protein property prediction

SCIENTIFIC REPORTS

IF3.9

2022-04-27

OAAI

Wang, Zichen; Combs, Steven A.; Brand, Ryan; Calvo, Miguel Romero; Xu, Panpan; Price, George; Golovach, Nataliya; Salawu, Emmanuel O.; Wise, Colby J.; Ponnapalli, Sri Priya; Clark, Peter M.

Machine learning for functional protein design 功能蛋白质设计的机器学习

NATURE BIOTECHNOLOGY

IF41.7

2024-02-15

PREAI

Notin, Pascal; Rollins, Nathan; Gal, Yarin; Sander, Chris; Marks, Debora

Molecular dynamics and protein function

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA

IF9.1

2005-05-03

993

OAAI

Karplus, M; Kuriyan, J

查看更多内容