Extracting functional insights from loss-of-function screens using deep link prediction.
CRISPR screening
PPI networks
bioinformatics
cancer cell lines
deep learning
drug targets
functional screening
link prediction
machine learning
systems biology
Journal
Cell reports methods
ISSN: 2667-2375
Titre abrégé: Cell Rep Methods
Pays: United States
ID NLM: 9918227360606676
Informations de publication
Date de publication:
28 02 2022
28 02 2022
Historique:
received:
21
07
2021
revised:
09
12
2021
accepted:
25
01
2022
entrez:
27
4
2022
pubmed:
28
4
2022
medline:
28
4
2022
Statut:
epublish
Résumé
We present deep link prediction (DLP), a method for the interpretation of loss-of-function screens. Our approach uses representation-based link prediction to reprioritize phenotypic readouts by integrating screening experiments with gene-gene interaction networks. We validate on 2 different loss-of-function technologies, RNAi and CRISPR, using datasets obtained from DepMap. Extensive benchmarking shows that DLP-DeepWalk outperforms other methods in recovering cell-specific dependencies, achieving an average precision well above 90% across 7 different cancer types and on both RNAi and CRISPR data. We show that the genes ranked highest by DLP-DeepWalk are appreciably more enriched in drug targets compared to the ranking based on original screening scores. Interestingly, this enrichment is more pronounced on RNAi data compared to CRISPR data, consistent with the greater inherent noise of RNAi screens. Finally, we demonstrate how DLP-DeepWalk can infer the molecular mechanism through which putative targets trigger cell line mortality.
Identifiants
pubmed: 35474966
doi: 10.1016/j.crmeth.2022.100171
pii: S2667-2375(22)00023-6
pmc: PMC9017186
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Pagination
100171Informations de copyright
© 2022 The Authors.
Déclaration de conflit d'intérêts
The authors declare no competing interests.
Références
Cancer Biother Radiopharm. 2013 Sep;28(7):516-22
pubmed: 23713868
Mol Oncol. 2017 May;11(5):534-551
pubmed: 28296343
Nat Cancer. 2020 Feb;1(2):235-248
pubmed: 32613204
Nucleic Acids Res. 2020 Jan 8;48(D1):D498-D503
pubmed: 31691815
Elife. 2020 May 28;9:
pubmed: 32463358
BMC Biol. 2014 Nov 11;12:94
pubmed: 25385277
Wiley Interdiscip Rev Syst Biol Med. 2017 Jan;9(1):
pubmed: 27863091
Genome Biol. 2010;11(5):R53
pubmed: 20482850
Oncotarget. 2016 Jun 7;7(23):34956-76
pubmed: 27144335
Cell Rep. 2016 Mar 15;14(10):2490-501
pubmed: 26947069
Bioinformatics. 2020 Feb 15;36(4):1241-1251
pubmed: 31584634
J Biomed Inform. 2019 May;93:103159
pubmed: 30926470
Science. 2014 Jan 3;343(6166):84-87
pubmed: 24336571
Nat Commun. 2016 Feb 01;7:10331
pubmed: 26831545
Sci Rep. 2017 Jan 09;7:40321
pubmed: 28067293
Nucleic Acids Res. 2019 Jan 8;47(D1):D786-D792
pubmed: 30304474
Nat Commun. 2018 Nov 2;9(1):4610
pubmed: 30389920
Sci Rep. 2019 Jul 29;9(1):11002
pubmed: 31358864
Bioinformatics. 2011 Jun 15;27(12):1739-40
pubmed: 21546393
Nat Biotechnol. 2016 Jun;34(6):631-3
pubmed: 27111720
Nat Med. 2017 Apr 7;23(4):405-408
pubmed: 28388612
Proc Natl Acad Sci U S A. 2005 Oct 25;102(43):15545-50
pubmed: 16199517
Nat Cell Biol. 2009 Nov;11(11):1275-6
pubmed: 19884882
Oncotarget. 2017 Jun 13;8(24):39460-39475
pubmed: 28467801
Cancer Cell. 2005 Jul;8(1):49-59
pubmed: 16023598
Nat Commun. 2020 Feb 5;11(1):729
pubmed: 32024854
KDD. 2016 Aug;2016:855-864
pubmed: 27853626
J Mol Biol. 2009 Dec 11;394(4):732-46
pubmed: 19782090
Nat Genet. 2017 Dec;49(12):1779-1784
pubmed: 29083409
Curr Opin Microbiol. 2011 Oct;14(5):599-607
pubmed: 21943683
Cell. 2017 Jul 27;170(3):577-592.e10
pubmed: 28753431
Cell. 2017 Jul 27;170(3):564-576.e16
pubmed: 28753430
PLoS One. 2015 Mar 04;10(3):e0118432
pubmed: 25738806
Drug Discov Today. 2005 Oct 15;10(20):1385-91
pubmed: 16253877
Mol Oncol. 2014 Dec;8(8):1404-18
pubmed: 24950801
BMC Syst Biol. 2017 Oct 3;11(Suppl 5):94
pubmed: 28984192