Drug target prediction through deep learning functional representation of gene signatures
Preprint
- 28 September 2023
- preprint
- Published by Springer Nature in Research Square
Abstract
Many machine learning applications in bioinformatics currently rely on gene identities extracted from input gene signatures, and fail to take advantage of preexisting knowledge about gene functions. We developed the Functional Representation of Gene Signatures (FRoGS) approach by training a deep learning model. FRoGS represents gene signatures projected onto their biological functions, instead of their identities, similar to how the word2vec technique works in natural language processing. We demonstrated that its application to L1000 datasets resulted in more effective compound-target predictions than models based on gene identities alone. Through further integration of additional pharmacological activity data sources, FRoGS significantly contributed to a large number of high-quality compound-target predictions, which were supported by in silico and/or experimental evidence. These results underscore the general utility of FRoGS in machine learning-based bioinformatics applications. Prediction networks pre-equipped with the knowledge of gene functions may help more readily uncover relationships among gene signatures acquired by large-scale OMICs studies on compounds, cell types, disease models, and patient cohorts.Keywords
All Related Versions
This publication has 75 references indexed in Scilit:
- The Cancer Genome Atlas Pan-Cancer analysis projectNature Genetics, 2013
- A selective aryl hydrocarbon receptor modulator 3,3'-Diindolylmethane inhibits gastric cancer cell growthJournal of Experimental & Clinical Cancer Research, 2012
- Identifying Compound-Target Associations by Combining Bioactivity Profile Similarity Search and Public Databases MiningJournal of Chemical Information and Modeling, 2011
- Aryl Hydrocarbon Receptor Antagonists Promote the Expansion of Human Hematopoietic Stem CellsScience, 2010
- Pathway Reporter Assays Reveal Small Molecule Mechanisms of ActionSLAS Technology, 2009
- Mephentermine2007
- The NCI60 human tumour cell line anticancer drug screenNature Reviews Cancer, 2006
- The Connectivity Map: Using Gene-Expression Signatures to Connect Small Molecules, Genes, and DiseaseScience, 2006
- Stochasticity in gene expression: from theories to phenotypesNature Reviews Genetics, 2005
- Resveratrol, a natural aryl hydrocarbon receptor antagonist, protects lung from DNA damage and apoptosis caused by benzo[a]pyreneJournal of Applied Toxicology, 2003