SimBoost: a read-across approach for predicting drug-target binding affinities using gradient boosting machines

被引:397
作者
He, Tong [1 ]
Heidemeyer, Marten [1 ]
Ban, Fuqiang [2 ]
Cherkasov, Artem [2 ]
Ester, Martin [1 ]
机构
[1] Simon Fraser Univ, Sch Comp Sci, 8888 Univ Dr, Burnaby, BC V5A 1S6, Canada
[2] Univ British Columbia, Fac Med, Vancouver Prostate Ctr, Vancouver, BC V6H 3Z6, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Read-across; Gradient boosting; Drug-target interaction; Prediction interval; Applicability Domain; QSAR; KINASE; QSAR;
D O I
10.1186/s13321-017-0209-z
中图分类号
O6 [化学];
学科分类号
070301 [无机化学];
摘要
Computational prediction of the interaction between drugs and targets is a standing challenge in the field of drug discovery. A number of rather accurate predictions were reported for various binary drug-target benchmark data-sets. However, a notable drawback of a binary representation of interaction data is that missing endpoints for non-interacting drug-target pairs are not differentiated from inactive cases, and that predicted levels of activity depend on pre-defined binarization thresholds. In this paper, we present a method called SimBoost that predicts continuous (non-binary) values of binding affinities of compounds and proteins and thus incorporates the whole interaction spectrum from true negative to true positive interactions. Additionally, we propose a version of the method called SimBoostQuant which computes a prediction interval in order to assess the confidence of the predicted affinity, thus defining the Applicability Domain metrics explicitly. We evaluate SimBoost and SimBoostQuant on two established drug-target interaction benchmark datasets and one new dataset that we propose to use as a benchmark for read-across cheminformatics applications. We demonstrate that our methods outperform the previously reported models across the studied datasets.
引用
收藏
页数:14
相关论文
共 45 条
[1]
[Anonymous], 2014, NIPS WORKSH HIGH EN
[2]
[Anonymous], 2010, Networks: An Introduction, DOI 10.1162/artl_r_00062
[3]
Ball N, 2015, ALTEX, V33, P149
[4]
Supervised reconstruction of biological networks with local models [J].
Bleakley, Kevin ;
Biau, Gerard ;
Vert, Jean-Philippe .
BIOINFORMATICS, 2007, 23 (13) :I57-I65
[5]
Supervised prediction of drug-target interactions using bipartite local models [J].
Bleakley, Kevin ;
Yamanishi, Yoshihiro .
BIOINFORMATICS, 2009, 25 (18) :2397-2403
[6]
Drug target identification using side-effect similarity [J].
Campillos, Monica ;
Kuhn, Michael ;
Gavin, Anne-Claude ;
Jensen, Lars Juhl ;
Bork, Peer .
SCIENCE, 2008, 321 (5886) :263-266
[7]
Chen T., 2016, KDD16 P 22 ACM, P785, DOI [DOI 10.1145/2939672.2939785, 10.1145/2939672.2939785]
[8]
Structure-based maximal affinity model predicts small-molecule druggability [J].
Cheng, Alan C. ;
Coleman, Ryan G. ;
Smyth, Kathleen T. ;
Cao, Qing ;
Soulard, Patricia ;
Caffrey, Daniel R. ;
Salzberg, Anna C. ;
Huang, Enoch S. .
NATURE BIOTECHNOLOGY, 2007, 25 (01) :71-75
[9]
Prediction of chemical-protein interactions: multitarget-QSAR versus computational chemogenomic methods [J].
Cheng, Feixiong ;
Zhou, Yadi ;
Li, Jie ;
Li, Weihua ;
Liu, Guixia ;
Tang, Yun .
MOLECULAR BIOSYSTEMS, 2012, 8 (09) :2373-2384
[10]
Chin WS, 2016, J MACH LEARN RES, V17