ASURAGEN, INC. — Department of Health and Human Services SBIR Phase I: 400

Description

Project SummaryAn extensible analysis platform will be developed to accurately perform the automated genotyping of PCR capillary electrophoresisCEtraces for multiple disease associated short tandem repeaterSTRassaysThis study will evaluate the feasibility of developing generalizable and adaptive molecular analysis modelsand will ultimately establish a new paradigm for deep learning analytical tools in the molecular diagnostic spaceAdvanced machine learning strategies will be applied to interpret genotypes of inherited disorders caused by genetically unstable STR DNA sequencesSTRs have traditionally been difficult to investigate due to their lengthon the order of kilobasesand low sequence complexitywhich elude detection by traditional and nextgeneration sequencing technologiesHoweveradvances in PCR CE technology have enabled the amplification and fragment sizing of STR DNA fragmentsadvancing clinical research and diagnostic test development for several neurodegenerative disorderssuch as fragile X syndrome and amyotrophic lateral sclerosisDespite these advancesthe analysis of PCR CE data from assays targeting STRs remains a manualburdensomeand subjective processThere is a clear need to create a system that can scale with the development of new assaysand the proposed approach utilizes modern breakthroughs in artificial intelligence to fulfill that needThis method will leverage recent advances in representation learning to establish a generalized and adaptive framework for automated PCR CE annotation that can scale to new assays and improve automatically with the inclusion of new dataThe project will benefit from Asuragen s experience in optimizing repeat primed chemistries to develop and commercialize multiple high performance assays including the AmplideX PCR CE FMRkitImportantlythe proposed modeling strategy will borrow strength across multiple established PCR CE assays and generalize to future PCR CE assays for novel STR disease associated biomarkersThis system will be paramount to enabling a continuous learning platform wherein computationally assisted annotation of PCR CE assays can be continuously improved and integrated in to clinical research tools and diagnostics Project NarrativeWe are developing AmplideX DeepNetan artificial intelligence based analysis system that can accurately perform computationally assisted analysis of molecular diagnostic assaysThe proposed system will build upon recent breakthroughs in artificial intelligence to allow it to easily adapt to new assays and to continue to improveThe system will be applied to assays for several disordersincluding fragile X syndromeamyotrophic lateral sclerosisALSmyotonic dystrophyand Huntington s diseaseand will provide a number of benefits over current analysis methods by reducing turn around time for assay results and assuring reproducible reporting between operators and labs