FP-GNN: a versatile deep learning architecture for enhanced molecular property prediction

被引:110
作者
Cai, Hanxuan [1 ]
Zhang, Huimin [1 ]
Zhao, Duancheng [1 ]
Wu, Jingxing [1 ]
Wang, Ling [1 ]
机构
[1] South China Univ Technol, Guangzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
artificial intelligence; drug design and discovery; machine learning; molecular representation; graph attention networks; DRUG; DATABASE; QSAR;
D O I
10.1093/bib/bbac408
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Accurate prediction of molecular properties, such as physicochemical and bioactive properties, as well as ADME/T (absorption, distribution, metabolism, excretion and toxicity) properties, remains a fundamental challenge for molecular design, especially for drug design and discovery. In this study, we advanced a novel deep learning architecture, termed FP-GNN (fingerprints and graph neural networks), which combined and simultaneously learned information from molecular graphs and fingerprints for molecular property prediction. To evaluate the FP-GNN model, we conducted experiments on 13 public datasets, an unbiased LIT-PCBA dataset and 14 phenotypic screening datasets for breast cell lines. Extensive evaluation results showed that compared to advanced deep learning and conventional machine learning algorithms, the FP-GNN algorithm achieved state-of-the-art performance on these datasets. In addition, we analyzed the influence of different molecular fingerprints, and the effects of molecular graphs and molecular fingerprints on the performance of the FP-GNN model. Analysis of the anti-noise ability and interpretation ability also indicated that FP-GNN was competitive in real-world situations. Collectively, FP-GNN algorithm can assist chemists, biologists and pharmacists in predicting and discovering better molecules with desired functions or properties.
引用
收藏
页数:12
相关论文
共 68 条
[1]  
[Anonymous], 2017, TOX21 DAT CHALL
[2]  
[Anonymous], 2019, HYPEROPT DISTRIBUTED
[3]  
Artemov G N, 2016, Tsitologiia, V58, P315
[4]   The future of phenotypic drug discovery [J].
Berg, Ellen L. .
CELL CHEMICAL BIOLOGY, 2021, 28 (03) :424-430
[5]  
Bolton EE, 2010, ANN REP COMP CHEM, V4, P217, DOI 10.1016/S1574-1400(08)00012-1
[6]  
Breiman RF, 2001, CLIN INFECT DIS, V32, P283, DOI 10.1086/318461
[7]   Rcpi: R/Bioconductor package to generate various descriptors of proteins, compounds and their interactions [J].
Cao, Dong-Sheng ;
Xiao, Nan ;
Xu, Qing-Song ;
Chen, Alex F. .
BIOINFORMATICS, 2015, 31 (02) :279-281
[8]   Molecular fingerprint similarity search in virtual screening [J].
Cereto-Massague, Adria ;
Jose Ojeda, Maria ;
Valls, Cristina ;
Mulero, Miguel ;
Garcia-Vallve, Santiago ;
Pujadas, Gerard .
METHODS, 2015, 71 :58-63
[9]  
Chen T., 2015, R PACKAGE VERSION 04, V1, P1
[10]   QSAR Modeling: Where Have You Been? Where Are You Going To? [J].
Cherkasov, Artem ;
Muratov, Eugene N. ;
Fourches, Denis ;
Varnek, Alexandre ;
Baskin, Igor I. ;
Cronin, Mark ;
Dearden, John ;
Gramatica, Paola ;
Martin, Yvonne C. ;
Todeschini, Roberto ;
Consonni, Viviana ;
Kuz'min, Victor E. ;
Cramer, Richard ;
Benigni, Romualdo ;
Yang, Chihae ;
Rathman, James ;
Terfloth, Lothar ;
Gasteiger, Johann ;
Richard, Ann ;
Tropsha, Alexander .
JOURNAL OF MEDICINAL CHEMISTRY, 2014, 57 (12) :4977-5010