A community computational challenge to predict the activity of pairs of compounds

Mukesh Bansal, Jichen Yang, Charles Karan, Michael P. Menden, James C. Costello, Hao Tang, Guanghua Xiao, Yajuan Li, Jeffrey Allen, Rui Zhong, Beibei Chen, Minsoo Kim, Tao Wang, Laura M. Heiser, Ronald Realubit, Michela Mattioli, Mariano J. Alvarez, Yao Shen, Daniel Gallahan, Dinah SingerJulio Saez-Rodriguez, Yang Xie, Gustavo Stolovitzky, Andrea Califano, Jean Paul Abbuehl, Russ B. Altman, Shawn Balcome, Ana Bell, Andreas Bender, Bonnie Berger, Jonathan Bernard, Andrew A. Bieberich, Giorgos Borboudakis, Christina Chan, Ting Huei Chen, Jaejoon Choi, Luis Pedro Coelho, Chad J. Creighton, Will Dampier, V. Jo Davisson, Raamesh Deshpande, Lixia Diao, Barbara Di Camillo, Murat Dundar, Adam Ertel, Chirayu P. Goswami, Assaf Gottlieb, Michael N. Gould, Jonathan Goya, Michael Grau, Joe W. Gray, Hussein A. Hejase, Michael F. Hoffmann, Krisztian Homicsko, Max Homilius, Woochang Hwang, Adriaan P. Ijzerman, Olli Kallioniemi, Bilge Karacali, Samuel Kaski, Junho Kim, Arjun Krishnan, Junehawk Lee, Young Suk Lee, Eelke B. Lenselink, Peter Lenz, Lang Li, Jun Li, Han Liang, John Patrick Mpindi, Chad L. Myers, Michael A. Newton, John P. Overington, Juuso Parkkinen, Robert J. Prill, Jian Peng, Richard Pestell, Peng Qiu, Bartek Rajwa, Anguraj Sadanandam, Francesco Sambo, Arvind Sridhar, Wei Sun, Gianna M. Toffolo, Aydin Tozeren, Olga G. Troyanskaya, Ioannis Tsamardinos, Herman W T Van Vlijmen, Wen Wang, Joerg K. Wegner, Krister Wennerberg, Gerard J P Van Westen, Tian Xia, Yang Yang, Victoria Yao, Yuan Yuan, Haoyang Zeng, Shihua Zhang, Junfei Zhao, Jian Zhou

Research output: Contribution to journalArticlepeer-review

130 Scopus citations

Abstract

Recent therapeutic successes have renewed interest in drug combinations, but experimental screening approaches are costly and often identify only small numbers of synergistic combinations. The DREAM consortium launched an open challenge to foster the development of in silico methods to computationally rank 91 compound pairs, from the most synergistic to the most antagonistic, based on gene-expression profiles of human B cells treated with individual compounds at multiple time points and concentrations. Using scoring metrics based on experimental dose-response curves, we assessed 32 methods (31 community-generated approaches and SynGen), four of which performed significantly better than random guessing. We highlight similarities between the methods. Although the accuracy of predictions was not optimal, we find that computational prediction of compound-pair activity is possible, and that community challenges can be useful to advance the field of in silico compound-synergy prediction.

Original languageEnglish (US)
Pages (from-to)1213-1222
Number of pages10
JournalNature biotechnology
Volume32
Issue number12
DOIs
StatePublished - Dec 1 2014

Bibliographical note

Publisher Copyright:
© 2014 Nature America, Inc. All rights reserved.

Fingerprint

Dive into the research topics of 'A community computational challenge to predict the activity of pairs of compounds'. Together they form a unique fingerprint.

Cite this