TY - JOUR

T1 - A Community Challenge for Inferring Genetic Predictors of Gene Essentialities through Analysis of a Functional Screen of Cancer Cell Lines

AU - Gönen, Mehmet

AU - Weir, Barbara A

AU - Cowley, Glenn S

AU - Vazquez, Francisca

AU - Guan, Yuanfang

AU - Jaiswal, Alok

AU - Karasuyama, Masayuki

AU - Uzunangelov, Vladislav

AU - Wang, Tao

AU - Tsherniak, Aviad

AU - Howell, Sara

AU - Marbach, Daniel

AU - Hoff, Bruce

AU - Norman, Thea C

AU - Airola, Antti

AU - Bivol, Adrian

AU - Bunte, Kerstin

AU - Carlin, Daniel

AU - Chopra, Sahil

AU - Deran, Alden

AU - Ellrott, Kyle

AU - Gopalacharyulu, Peddinti

AU - Graim, Kiley

AU - Kaski, Samuel

AU - Khan, Suleiman A

AU - Newton, Yulia

AU - Ng, Sam

AU - Pahikkala, Tapio

AU - Paull, Evan

AU - Sokolov, Artem

AU - Tang, Hao

AU - Tang, Jing

AU - Wennerberg, Krister

AU - Xie, Yang

AU - Zhan, Xiaowei

AU - Zhu, Fan

AU - Aittokallio, Tero

AU - Mamitsuka, Hiroshi

AU - Stuart, Joshua M

AU - Boehm, Jesse S

AU - Root, David E

AU - Xiao, Guanghua

AU - Stolovitzky, Gustavo

AU - Hahn, William C

AU - Margolin, Adam A

AU - Broad-DREAM Community

N1 - Copyright © 2017. Published by Elsevier Inc.

PY - 2017/11/22

Y1 - 2017/11/22

N2 - We report the results of a DREAM challenge designed to predict relative genetic essentialities based on a novel dataset testing 98,000 shRNAs against 149 molecularly characterized cancer cell lines. We analyzed the results of over 3,000 submissions over a period of 4 months. We found that algorithms combining essentiality data across multiple genes demonstrated increased accuracy; gene expression was the most informative molecular data type; the identity of the gene being predicted was far more important than the modeling strategy; well-predicted genes and selected molecular features showed enrichment in functional categories; and frequently selected expression features correlated with survival in primary tumors. This study establishes benchmarks for gene essentiality prediction, presents a community resource for future comparison with this benchmark, and provides insights into factors influencing the ability to predict gene essentiality from functional genetic screens. This study also demonstrates the value of releasing pre-publication data publicly to engage the community in an open research collaboration.

AB - We report the results of a DREAM challenge designed to predict relative genetic essentialities based on a novel dataset testing 98,000 shRNAs against 149 molecularly characterized cancer cell lines. We analyzed the results of over 3,000 submissions over a period of 4 months. We found that algorithms combining essentiality data across multiple genes demonstrated increased accuracy; gene expression was the most informative molecular data type; the identity of the gene being predicted was far more important than the modeling strategy; well-predicted genes and selected molecular features showed enrichment in functional categories; and frequently selected expression features correlated with survival in primary tumors. This study establishes benchmarks for gene essentiality prediction, presents a community resource for future comparison with this benchmark, and provides insights into factors influencing the ability to predict gene essentiality from functional genetic screens. This study also demonstrates the value of releasing pre-publication data publicly to engage the community in an open research collaboration.

U2 - 10.1016/j.cels.2017.09.004

DO - 10.1016/j.cels.2017.09.004

M3 - Journal article

C2 - 28988802

VL - 5

SP - 485-497.e3

JO - Cell Systems

JF - Cell Systems

SN - 2405-4712

IS - 5

ER -