Systematic interrogation of diverse Omic data reveals interpretable, robust, and generalizable transcriptomic features of clinically successful therapeutic targets

PLoS Computational Biology
Andrew D RouillardPankaj Agarwal

Abstract

Target selection is the first and pivotal step in drug discovery. An incorrect choice may not manifest itself for many years after hundreds of millions of research dollars have been spent. We collected a set of 332 targets that succeeded or failed in phase III clinical trials, and explored whether Omic features describing the target genes could predict clinical success. We obtained features from the recently published comprehensive resource: Harmonizome. Nineteen features appeared to be significantly correlated with phase III clinical trial outcomes, but only 4 passed validation schemes that used bootstrapping or modified permutation tests to assess feature robustness and generalizability while accounting for target class selection bias. We also used classifiers to perform multivariate feature selection and found that classifiers with a single feature performed as well in cross-validation as classifiers with more features (AUROC = 0.57 and AUPR = 0.81). The two predominantly selected features were mean mRNA expression across tissues and standard deviation of expression across tissues, where successful targets tended to have lower mean expression and higher expression variance than failed targets. This finding supports the conve...Continue Reading

References

Jun 22, 2001·Journal of the American Medical Informatics Association : JAMIA·M H Coletti, H L Bleich
Jan 29, 2002·Lancet·David A Grimes, Kenneth F Schulz
Mar 21, 2002·Proceedings of the National Academy of Sciences of the United States of America·Andrew I SuJohn B Hogenesch
Apr 13, 2004·Proceedings of the National Academy of Sciences of the United States of America·Andrew I SuJohn B Hogenesch
Mar 1, 2006·BMC Bioinformatics·Sudhir Varma, Richard Simon
Jul 29, 2006·Science·G E Hinton, R R Salakhutdinov
Dec 8, 2006·Nature·Ed S LeinAllan R Jones
Sep 22, 2007·BMC Bioinformatics·Qingliang Li, Luhua Lai
Oct 30, 2007·Proteomics·Huan XuXin Chen
Dec 18, 2007·Genome Research·Lixia Yao, Andrey Rzhetsky
Dec 24, 2008·Proceedings of the National Academy of Sciences of the United States of America·Kasper LageSøren Brunak
Jan 24, 2009·Bioinformatics·Tala M Bakheet, Andrew J Doig
Dec 4, 2009·Methods in Molecular Biology·Itziar Frades, Rune Matthiesen
Apr 22, 2010·Nephron. Clinical Practice·Giovanni TripepiCarmine Zoccali
Nov 4, 2010·Statistical Applications in Genetics and Molecular Biology·Belinda Phipson, Gordon K Smyth
Jun 28, 2011·Current Opinion in Chemical Biology·Eric B FaumanEnoch S Huang
Sep 29, 2011·Drug Discovery Today·Isabella GashawKhusru Asadullah
Jan 10, 2012·The FEBS Journal·Rosario M Piro, Ferdinando Di Cunto
Jul 4, 2012·Methods : a Companion to Methods in Enzymology·Max KotlyarIgor Jurisica
Jul 4, 2012·Nature Reviews. Genetics·Yves Moreau, Léon-Charles Tranchevent
Jul 24, 2012·American Journal of Human Genetics·Michael P EpsteinGlen A Satten
Aug 3, 2012·The Journal of Physiology·Guillaume CalmettesSarah L Vowler
Sep 22, 2012·Nature·Michael J HawrylyczAllan R Jones
Oct 23, 2012·Methods in Molecular Biology·Detlef GrothJoachim Selbig
May 30, 2013·Nature Genetics·UNKNOWN GTEx Consortium
Jul 23, 2013·PLoS Computational Biology·Xiujuan WangHaiyuan Yu
Jul 23, 2013·PloS One·Raamesh DeshpandeChad L Myers
Aug 2, 2013·Nature Reviews. Drug Discovery·John Arrowsmith, Philip Miller
Dec 3, 2013·Advances in Experimental Medicine and Biology·Cheng ZhuAnil G Jegga
Jan 1, 2006·Metabolomics : Official Journal of the Metabolomic Society·Carina M RubinghAge K Smilde
Feb 26, 2014·BMC Systems Biology·Hiroaki IwataYoshihiro Yamanishi
May 17, 2014·Nature Reviews. Drug Discovery·David CookMenelas N Pangalos
Oct 31, 2014·Nucleic Acids Research·Garth R BrownTerence D Murphy
Nov 2, 2014·Nucleic Acids Research·Kristian A GrayElspeth A Bruford
Jan 24, 2015·Science·Mathias UhlénFredrik Pontén
Mar 31, 2015·PloS One·Simon C Bull, Andrew J Doig

❮ Previous
Next ❯

Citations

Jan 12, 2020·Scientific Reports·Yanrong JiRamana V Davuluri
Feb 10, 2019·BMC Bioinformatics·Jin YaoPankaj Agarwal
May 12, 2019·Scientific Reports·Maria Ryaboshapkina, Mårten Hammar
Apr 13, 2019·Nature Reviews. Drug Discovery·Jessica VamathevanShanrong Zhao
Jun 7, 2021·Journal of Translational Medicine·Dominik HartlAdrian Roth
Nov 4, 2020·Journal of Chemical Information and Modeling·Ke YuKayhan Batmanghelich
Aug 17, 2021·Artificial Intelligence Review·Suresh DaraMohamed Jawed Ahsan

❮ Previous
Next ❯

Software Mentioned

Scipy
Random
HPA
Harmonizome
Random Forest
learn
Omics
Numpy
GTEx
Fastcluster

Related Concepts

Related Feeds

Adhesion Molecules in Health and Disease

Cell adhesion molecules are a subset of cell adhesion proteins located on the cell surface involved in binding with other cells or with the extracellular matrix in the process called cell adhesion. In essence, cell adhesion molecules help cells stick to each other and to their surroundings. Cell adhesion is a crucial component in maintaining tissue structure and function. Discover the latest research on adhesion molecule and their role in health and disease here.