Literature DB >> 32428219

TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments.

Lifan Chen1,2, Xiaoqin Tan1,2, Dingyan Wang1,2, Feisheng Zhong1,2, Xiaohong Liu1,3, Tianbiao Yang1,2, Xiaomin Luo1, Kaixian Chen1,3, Hualiang Jiang1,3, Mingyue Zheng1.   

Abstract

MOTIVATION: Identifying compound-protein interaction (CPI) is a crucial task in drug discovery and chemogenomics studies, and proteins without three-dimensional structure account for a large part of potential biological targets, which requires developing methods using only protein sequence information to predict CPI. However, sequence-based CPI models may face some specific pitfalls, including using inappropriate datasets, hidden ligand bias and splitting datasets inappropriately, resulting in overestimation of their prediction performance.
RESULTS: To address these issues, we here constructed new datasets specific for CPI prediction, proposed a novel transformer neural network named TransformerCPI, and introduced a more rigorous label reversal experiment to test whether a model learns true interaction features. TransformerCPI achieved much improved performance on the new experiments, and it can be deconvolved to highlight important interacting regions of protein sequences and compound atoms, which may contribute chemical biology studies with useful guidance for further ligand structural optimization.
AVAILABILITY AND IMPLEMENTATION: https://github.com/lifanchen-simm/transformerCPI.
© The Author(s) 2020. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Mesh:

Substances:

Year:  2020        PMID: 32428219     DOI: 10.1093/bioinformatics/btaa524

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.937


  20 in total

1.  DeepTFactor: A deep learning-based tool for the prediction of transcription factors.

Authors:  Gi Bae Kim; Ye Gao; Bernhard O Palsson; Sang Yup Lee
Journal:  Proc Natl Acad Sci U S A       Date:  2021-01-12       Impact factor: 11.205

2.  AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification.

Authors:  Mehdi Yazdani-Jahromi; Niloofar Yousefi; Aida Tayebi; Elayaraja Kolanthai; Craig J Neal; Sudipta Seal; Ozlem Ozmen Garibay
Journal:  Brief Bioinform       Date:  2022-07-18       Impact factor: 13.994

3.  DTI-BERT: Identifying Drug-Target Interactions in Cellular Networking Based on BERT and Deep Learning Method.

Authors:  Jie Zheng; Xuan Xiao; Wang-Ren Qiu
Journal:  Front Genet       Date:  2022-06-08       Impact factor: 4.772

4.  nhKcr: a new bioinformatics tool for predicting crotonylation sites on human nonhistone proteins based on deep learning.

Authors:  Yong-Zi Chen; Zhuo-Zhi Wang; Yanan Wang; Guoguang Ying; Zhen Chen; Jiangning Song
Journal:  Brief Bioinform       Date:  2021-11-05       Impact factor: 11.622

Review 5.  An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph.

Authors:  Xiaozhe Wan; Xiaolong Wu; Dingyan Wang; Xiaoqin Tan; Xiaohong Liu; Zunyun Fu; Hualiang Jiang; Mingyue Zheng; Xutong Li
Journal:  Brief Bioinform       Date:  2022-05-13       Impact factor: 13.994

6.  TransDTI: Transformer-Based Language Models for Estimating DTIs and Building a Drug Recommendation Workflow.

Authors:  Yogesh Kalakoti; Shashank Yadav; Durai Sundar
Journal:  ACS Omega       Date:  2022-01-12

7.  MGraphDTA: deep multiscale graph neural network for explainable drug-target binding affinity prediction.

Authors:  Ziduo Yang; Weihe Zhong; Lu Zhao; Calvin Yu-Chian Chen
Journal:  Chem Sci       Date:  2022-01-05       Impact factor: 9.825

8.  Sequence-based prediction of protein binding regions and drug-target interactions.

Authors:  Ingoo Lee; Hojung Nam
Journal:  J Cheminform       Date:  2022-02-08       Impact factor: 5.514

9.  Nucleosome positioning based on DNA sequence embedding and deep learning.

Authors:  Guo-Sheng Han; Qi Li; Ying Li
Journal:  BMC Genomics       Date:  2022-04-13       Impact factor: 3.969

10.  ScaffComb: A Phenotype-Based Framework for Drug Combination Virtual Screening in Large-Scale Chemical Datasets.

Authors:  Zhaofeng Ye; Fengling Chen; Jiangyang Zeng; Juntao Gao; Michael Q Zhang
Journal:  Adv Sci (Weinh)       Date:  2021-11-01       Impact factor: 16.806

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.