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

Cellworks Group, NCI-DREAM Community, Hao Tang

Research output: Contribution to journalArticle

104 Citations (Scopus)

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

Fingerprint

Computer Simulation
Drug Combinations
Transcriptome
Gene expression
Screening
B-Lymphocytes
Cells
Therapeutics

ASJC Scopus subject areas

  • Applied Microbiology and Biotechnology
  • Biotechnology
  • Molecular Medicine
  • Bioengineering
  • Biomedical Engineering

Cite this

A community computational challenge to predict the activity of pairs of compounds. / Cellworks Group; NCI-DREAM Community; Tang, Hao.

In: Nature Biotechnology, Vol. 32, No. 12, 01.12.2014, p. 1213-1222.

Research output: Contribution to journalArticle

Cellworks Group, NCI-DREAM Community & Tang, H 2014, 'A community computational challenge to predict the activity of pairs of compounds', Nature Biotechnology, vol. 32, no. 12, pp. 1213-1222. https://doi.org/10.1038/nbt.3052
Cellworks Group ; NCI-DREAM Community ; Tang, Hao. / A community computational challenge to predict the activity of pairs of compounds. In: Nature Biotechnology. 2014 ; Vol. 32, No. 12. pp. 1213-1222.
@article{7e8553be47b6481f853651146f9095bc,
title = "A community computational challenge to predict the activity of pairs of compounds",
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.",
author = "{Cellworks Group} and {NCI-DREAM Community} and Mukesh Bansal and Jichen Yang and Charles Karan and Hao Tang and Costello, {James C.} and Hao Tang and Guanghua Xiao and Yajuan Li and Jeffrey Allen and Rui Zhong and Beibei Chen and Minsoo Kim and Tao Wang and Heiser, {Laura M.} and Ronald Realubit and Michela Mattioli and Alvarez, {Mariano J.} and Yao Shen and Daniel Gallahan and Dinah Singer and Julio Saez-Rodriguez and Yang Xie and Gustavo Stolovitzky and Andrea Califano and Abbuehl, {Jean Paul} and Altman, {Russ B.} and Shawn Balcome and Ana Bell and Andreas Bender and Bonnie Berger and Jonathan Bernard and Bieberich, {Andrew A.} and Giorgos Borboudakis and Christina Chan and Chen, {Ting Huei} and Jaejoon Choi and Coelho, {Luis Pedro} and Creighton, {Chad J.} and Will Dampier and Davisson, {V. Jo} and Raamesh Deshpande and Lixia Diao and {Di Camillo}, Barbara and Murat Dundar and Adam Ertel and Goswami, {Chirayu P.} and Assaf Gottlieb and Gould, {Michael N.} and Jonathan Goya and Michael Grau",
year = "2014",
month = "12",
day = "1",
doi = "10.1038/nbt.3052",
language = "English (US)",
volume = "32",
pages = "1213--1222",
journal = "Biotechnology",
issn = "0733-222X",
publisher = "Nature Publishing Group",
number = "12",

}

TY - JOUR

T1 - A community computational challenge to predict the activity of pairs of compounds

AU - Cellworks Group

AU - NCI-DREAM Community

AU - Bansal, Mukesh

AU - Yang, Jichen

AU - Karan, Charles

AU - Tang, Hao

AU - Costello, James C.

AU - Tang, Hao

AU - Xiao, Guanghua

AU - Li, Yajuan

AU - Allen, Jeffrey

AU - Zhong, Rui

AU - Chen, Beibei

AU - Kim, Minsoo

AU - Wang, Tao

AU - Heiser, Laura M.

AU - Realubit, Ronald

AU - Mattioli, Michela

AU - Alvarez, Mariano J.

AU - Shen, Yao

AU - Gallahan, Daniel

AU - Singer, Dinah

AU - Saez-Rodriguez, Julio

AU - Xie, Yang

AU - Stolovitzky, Gustavo

AU - Califano, Andrea

AU - Abbuehl, Jean Paul

AU - Altman, Russ B.

AU - Balcome, Shawn

AU - Bell, Ana

AU - Bender, Andreas

AU - Berger, Bonnie

AU - Bernard, Jonathan

AU - Bieberich, Andrew A.

AU - Borboudakis, Giorgos

AU - Chan, Christina

AU - Chen, Ting Huei

AU - Choi, Jaejoon

AU - Coelho, Luis Pedro

AU - Creighton, Chad J.

AU - Dampier, Will

AU - Davisson, V. Jo

AU - Deshpande, Raamesh

AU - Diao, Lixia

AU - Di Camillo, Barbara

AU - Dundar, Murat

AU - Ertel, Adam

AU - Goswami, Chirayu P.

AU - Gottlieb, Assaf

AU - Gould, Michael N.

AU - Goya, Jonathan

AU - Grau, Michael

PY - 2014/12/1

Y1 - 2014/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84924338899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924338899&partnerID=8YFLogxK

U2 - 10.1038/nbt.3052

DO - 10.1038/nbt.3052

M3 - Article

VL - 32

SP - 1213

EP - 1222

JO - Biotechnology

JF - Biotechnology

SN - 0733-222X

IS - 12

ER -