A Software Platform for the Identification of Cell Surface Antigens Using RNA-seq Data

Human monoclonal antibodies are among the fastest growing therapeutic modalitieswith over sixty compounds approved by FDA to treat infectionsautoimmunitychronic inflammation and cancerIn combinationthese diseases are responsible for the deaths ofmillion people annuallyaccording to the World Health OrganizationHoweverthe advent of therapeutic immunologics is expected to significantly reduce the associated morbidity and mortalityparticularly for oncologic diseasesCurrentlyimmuno oncologicIOtreatments are commercially available and comprise a growing market that is expected to reach $B byIO therapeutics effectively attack cancer by selectively binding tumor specific protein domains on the cell surfacereferred to as tumor associated ectodomainsTAEsHowevermany cancers remain insensitive to available IO as effective and safe TAEs are difficult to identifyStandard methods to detect TAEs are costlytime consuming and limited in their ability to discover novel targetsnecessitating the development of innovative technologies to circumvent this burdenRNAseq is currently the most effective method to discover novel splicing isoformsis high throughputsensitive and inexpensiveEnvisagenics has been at the forefront of RNAseqbased splicing characterization since the release of its SpliceCoreplatformHerewe propose to develop SpliceIOa novel drug discovery platform that integrates the EnvisagenicsSpliceCore knowledge base with machine learning algorithms to enable rapid identification of aberrant splicing derived TAEs using RNAseq dataIn this Phase I SBIR proposalwe will develop and apply SpliceIO in the context of Acute Myeloid Leukemiaa cancer particularly resistant to IO but highly associated with splicing mis regulation and mutations within key spliceosome componentsWe will identify and validate TAEs in vitro using established leukemia cell lines and patient derived bone marrow aspirates in collaboration with DrOmar Abdel Wahab from Memorial Sloan Kettering Cancer CenterCollectivelythe aims outlined herein will allow us to both develop and validate a novel splicing dependent TAE identification platform to provide new sources of drug targets while dramatically reducing the time and cost associated with their developmentIn additionthis will allow Envisagenics to create new partnership opportunities for IO codevelopment with pharmaceutical companiesIf successfulthis pipeline can be used to identify drug targets and or biomarkers for patient stratification in cancer and inflammatory diseases in the context of an SBIR Phase II grant Despite the recent success of immune based treatments in melanomathe majority of cancers remain insensitive and resistant to therapynecessitating the development of approaches to rapidly identify novel drug targetsHerewe propose to build a target discovery platform that combines our proprietary database of RNA splicing mutations in cancers with machine learning to identify the most clinically relevant targets for subsequent drug development