Development of a metabolomics and machine learning based high-throughput screening platform for data-driven drug discovery

Project Summary High throughput omics technologies allow for measuring various biomolecules comprehensively and over the past decade have become exponentially less expensiveCoupling these developing emerging technologies with automation approaches and the phenotypic based drug discovery paradigm allows fordata drivendrug discoveryDDfocuses on a complete cellular readoutquantitatively measurings tos of biomoleculesrather than focusing on a single proteinpathwayor physiological traitThe complexity of this data requires computational tools for proper analysis and interpretationA pioneering project and dataset for Dis the Broad Institute s Connectivity Mapwhich is a transcriptomics screening and query platform for drug characterizationdiscoveryand repositioningThough with many successesthe Connectivity Map is based on only a single biomolecule typeRNAand downstream effects caused by chemical perturbations to proteins and metabolites are ignoredIn this proposalwe combine the dual strengths of experts in LC MS MS based metabolomicsOmix Technologieswith leaders in metabolic network modeling and metabolomics data analysisSinopia Biosciencesto develop a metabolomics based high throughput compound screening platformOur preliminary data for two major drugsdoxorubicin and rapamycinshowcases that our approach has technical validityaccuracyand provides potential biological utility that complements transcriptomics based approachesThis Phase I proposal will assess the biological utility of a metabolomics based screening platformFirstwe will profileFDA approved small molecules from a broad range of drug classesSecondwe will develop the necessary bioinformatics pipelinesmechanistic metabolic modelsand machine learning algorithms to analyze and interpret these complex datasetsFinallywe will assess whether adding metabolomics data to the Connectivity Map boosts Dpredictions including assessing compound mechanisms of actionscompound similarityidentifying biomarkers for drug efficacy and safetyand identifying drug repurposing opportunitiesAfter the biological utility of this approach is demonstrated in Phase IPhase II will focus on profiling of novel chemical and genetic perturbations to further demonstrate the power of the platform and identify commercial opportunities for treating rare genetic diseases Project Narrative Data driven drug discovery provides the potential to accelerate drug development timelinesdecrease costsand ultimately provide better care to patientsCombining Sinopia Bioscience s and Omix Technologies strengths in high throughput data generation and analysiswe will build a unique platform focused on the impact of human metabolism in diseaseThis proposal will test the viability of this approach and focus on several rare genetic diseases with significant unmet needs