Modeling drug mechanism of action with large scale gene-expression profiles using GPAR, an artificial intelligence platform

Background Querying drug-induced gene expression profiles with machine learning method is an effective way for revealing drug mechanism of actions (MOAs), which is strongly supported by the growth of large scale and high-throughput gene expression databases. However, due to the lack of code-free and user friendly applications, it is not easy for biologists and pharmacologists to model MOAs with state-of-art deep learning approach. Results In this work, a newly developed online collaborative tool, Genetic profile-activity relationship (GPAR) was built to help modeling and predicting MOAs easily via deep learning. The users can use GPAR to customize their training sets to train self-defined MOA prediction models, to evaluate the model performances and to make further predictions automatically. Cross-validation tests show GPAR outperforms Gene set enrichment analysis in predicting MOAs. Conclusion GPAR can serve as a better approach in MOAs prediction, which may facilitate researchers to generate more reliable MOA hypothesis.

[1]  Geoffrey I. Webb,et al.  Encyclopedia of Machine Learning and Data Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[2]  Kristen Fortney,et al.  Drug Repurposing Using Deep Embeddings of Gene Expression Profiles. , 2018, Molecular pharmaceutics.

[3]  Jing Li,et al.  Representing high throughput expression profiles via perturbation barcodes reveals compound targets , 2016, PLoS Comput. Biol..

[4]  Jing Zhao,et al.  The gene expression profiles in response to 102 traditional Chinese medicine (TCM) components: a general template for research on TCMs , 2017, Scientific Reports.

[5]  Laleh Soltan Ghoraie,et al.  Integrative Cancer Pharmacogenomics to Infer Large-Scale Drug Taxonomy. , 2017, Cancer research.

[6]  Eamonn J. Keogh,et al.  Curse of Dimensionality , 2017, Encyclopedia of Machine Learning and Data Mining.

[7]  R. Tagliaferri,et al.  Discovery of drug mode of action and drug repositioning from transcriptional responses , 2010, Proceedings of the National Academy of Sciences.

[8]  Emanuel J. V. Gonçalves,et al.  Drug mechanism‐of‐action discovery through the integration of pharmacological and CRISPR screens , 2020, Molecular systems biology.

[9]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[10]  Yi Li,et al.  Gene expression inference with deep learning , 2015, bioRxiv.

[11]  Emily G McDonald,et al.  A Randomized Trial of Hydroxychloroquine as Postexposure Prophylaxis for Covid-19 , 2020, The New England journal of medicine.

[12]  Andrew R. Leach,et al.  Drug mechanism‐of‐action discovery through the integration of pharmacological and CRISPR screens , 2020, bioRxiv.

[13]  Wu Zhong,et al.  Remdesivir and chloroquine effectively inhibit the recently emerged novel coronavirus (2019-nCoV) in vitro , 2020, Cell Research.

[14]  Paul A Clemons,et al.  The Connectivity Map: Using Gene-Expression Signatures to Connect Small Molecules, Genes, and Disease , 2006, Science.

[15]  P. Sanseau,et al.  Drug repurposing: progress, challenges and recommendations , 2018, Nature Reviews Drug Discovery.

[16]  Marc Hafner,et al.  L1000CDS2: LINCS L1000 characteristic direction signatures search engine , 2016, npj Systems Biology and Applications.

[17]  Avi Ma'ayan,et al.  Drug-induced adverse events prediction with the LINCS L1000 data , 2016, Bioinform..

[18]  Alexander Kutikov,et al.  Piperlongumine inhibits NF‐κB activity and attenuates aggressive growth characteristics of prostate cancer cells , 2014, The Prostate.

[19]  Diego di Bernardo,et al.  Mantra 2.0: an online collaborative resource for drug mode of action and repurposing by network analysis , 2014, Bioinform..

[21]  B H Mulsant,et al.  Pharmacologic profile of perphenazine's metabolites. , 2000, Journal of clinical psychopharmacology.

[22]  Julio Saez-Rodriguez,et al.  DvD: An R/Cytoscape pipeline for drug repurposing using public repositories of gene expression data , 2012, Bioinform..

[23]  Ying Chen,et al.  ExpTreeDB: Web-based query and visualization of manually annotated gene expression profiling experiments of human and mouse from GEO , 2014, Bioinform..

[24]  Song He,et al.  Deep learning-based transcriptome data classification for drug-target interaction prediction , 2018, BMC Genomics.

[25]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[26]  Julio Saez-Rodriguez,et al.  Signatures of cell death and proliferation in perturbation transcriptomics data—from confounding factor to effective prediction , 2018, bioRxiv.

[27]  Song He,et al.  Discovery of novel therapeutic properties of drugs from transcriptional responses based on multi-label classification , 2017, Scientific Reports.

[28]  Jacob K. Asiedu,et al.  The Drug Repurposing Hub: a next-generation drug library and information resource , 2017, Nature Medicine.

[29]  Sergey Plis,et al.  Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data. , 2016, Molecular pharmaceutics.

[30]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[31]  M. Köppen,et al.  The Curse of Dimensionality , 2010 .

[32]  M. Millan,et al.  Competitive antagonism of serotonin (5-HT)2C and 5-HT2A receptormediated phosphoinositide (PI) turnover by clozapine in the rat: A comparison to other antipsychotics , 1994, Neuroscience Letters.

[33]  Avi Ma'ayan,et al.  Connectivity Mapping: Methods and Applications , 2019, Annual Review of Biomedical Data Science.

[34]  Pablo Tamayo,et al.  Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[35]  Avi Ma'ayan,et al.  L1000FWD: fireworks visualization of drug‐induced transcriptomic signatures , 2018, Bioinform..

[36]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[37]  Peer Bork,et al.  Drug-Induced Regulation of Target Expression , 2010, PLoS Comput. Biol..

[38]  Angela N. Brooks,et al.  A Next Generation Connectivity Map: L1000 Platform and the First 1,000,000 Profiles , 2017, Cell.

[39]  Christian H. Holland,et al.  Signatures of cell death and proliferation in perturbation transcriptomics data—from confounding factor to effective prediction , 2019, Nucleic acids research.

[40]  D. di Bernardo,et al.  Identification of small molecules enhancing autophagic function from drug network analysis. , 2010, Autophagy.

[41]  Diego di Bernardo,et al.  gene2drug: a Computational Tool for Pathway-based Rational Drug Repositioning , 2017, bioRxiv.

[42]  Fei Li,et al.  GeneExpressionSignature: an R package for discovering functional connections using gene expression signatures. , 2013, Omics : a journal of integrative biology.

[43]  R. Taulli,et al.  NF‐kB inhibition as a strategy to enhance etoposide‐induced apoptosis in K562 cell line , 2006, American journal of hematology.

[44]  Andrew E. Jaffe,et al.  Bioinformatics Applications Note Gene Expression the Sva Package for Removing Batch Effects and Other Unwanted Variation in High-throughput Experiments , 2022 .

[45]  Y. Jeon,et al.  Suppression of IL-8 gene expression by radicicol is mediated through the inhibition of ERK1/2 and p38 signaling and negative regulation of NF-kappaB and AP-1. , 2001, International immunopharmacology.

[46]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.