SBIR-STTR Award

A strong consensus has emerged over the past 10 years in the pharmaceutical industry that the drug-target- focused drug discovery approach, to which the industry has subscribed almost entirely since the 1980s, has been a failure. Accordingly, over the past few years, the majority of R&D in the drug discovery and development space has been re-allocated to support alternative approaches, notably phenotypic screening to discover new drugs. This shift represents a new and growing business opportunity for new, big data science and technology products, such as those developed by the applicant organization, GeneCentrix. In common phenotypic screens, a chemical library is first screened against cells (e.g. HeLa cells), and a search is then undertaken for the primary molecular target of the most active compound. This search, known as target deconvolution, is challenging and is a rate-limiting step in the success of the screen. Accordingly, new technologies have been developed for target deconvolution. Specifically, target-specific arrays of drug-like chemical probes are increasingly being used in phenotypic screens (e.g. Novartis’ “MOA box”, the NIH’s MIPE platform, etc.). GeneCentrix is pioneering the development of an information product that can enhance phenotypic screens that use these target-specific arrays. Specifically, the off-targets of the target-specific compounds (polypharmacology) in the array are currently not taken into account in analyzing the results of the phenotypic screen. In addition, the expression level of drug targets in the cell line used in the phenotype screen is very likely a predictive variable in target deconvolution but is also not taken into account. Therefore, we propose two aims to adapt our technology for the purpose of re- ranking phenotype screen results: 1) generation of off-target annotation (polypharmacologic profiles) for all compounds in a standard target-specific array; 2) integration of the polypharmacologic profile with expression data of the targets, and re-ranking of targets by this combined score. We will then validate the performance of our technology versus standard analysis of screening results; for a test set of phenotypic screens, an improvement of 20% in sensitivity associated with an equal or greater accuracy, as measured by area under the receiver operating curve (AUC), will be considered sufficient validation to pursue technical and commercial feasibility of the product in a Phase II application.

Public Health Relevance Statement:
Project Narrative Big pharma early drug discovery is moving towards use of phenotypic discovery methods (as opposed to target- specific methods), and towards use of target-specific compounds in phenotypic screening. Integration of polypharmacologic target affinity data and gene expression data for those targets into the output of phenotypic screens that use target-specific compound libraries for target deconvolution will enhance the value of these screens, allowing for more accurate deconvolution of the mechanism of action of chemical probes emerging from phenotypic screens. This project thus harnesses extensive and diverse big biomedical data and translates it into knowledge of sufficient integrity to be packaged as a viable commercial product.

Project Terms:
Affinity; Algorithms; Analytical Chemistry; Area; arm; base; big biomedical data; Big Data; Big Data to Knowledge; Biological Markers; Businesses; CDK2 gene; Cell Line; Cells; Chemical Actions; Chemicals; Collection; Consensus; Custom; Data; Data Science; Databases; Development; Docking; drug development; drug discovery; Drug Industry; Drug Targeting; drug testing; Ecology; Economics; Engineering; Exhibits; Failure; Gene Expression; Generations; Gold; Hela Cells; Image; improved; Industry; Informatics; inhibitor/antagonist; Investments; Knowledge; Libraries; Ligands; Literature; Measures; Methods; Modeling; Molecular Computations; Molecular Mechanisms of Action; Molecular Target; Nature; new technology; novel therapeutics; Output; Participant; Pathway interactions; Performance; Pharmaceutical Preparations; Pharmacologic Substance; Phase; Phenotype; Probability; Race; Research; research and development; ROC Curve; Scanning; screening; Screening Result; small molecule; small molecule libraries; success; Technology; Testing; Tissues; Translating; United States National Institutes of Health; Validation

The public health problem addressed by the proposed project is the critical, long-term absence of progress in anti-addiction medication discovery and development. GeneCentrix’ “historeceptomics” technology has the potential to alter this trend by providing advanced insights during the process of anti-addiction medication discovery and development. Digital/computational advanced insights are recognized as the critical value- added emerging piece of technology in pharmaceutical R&D. The unique concept underlying our technology is specificity of anti-addiction drug action in different brain tissues. No software product currently provides this capability. The overall goal of this program is to commercialize a product that enhances anti-addiction medication discovery by providing previously unavailable advanced structure-activity insights specifically targeted to phenotypic screening assays. A Phase I award successfully established the technical merit, feasibility and commercial potential of the envisioned product, as well as identifying the key remaining concerns of customers who expressed intent to purchase the product capabilities. The overall objective of this Phase II renewal is to produce a commercialization ready software product that eliminates the remaining concerns of the customers for commercialization. Based on the prototype built in Phase I and the insights gained from market analysis, the remaining obstacles to commercialization and sustainability of the product have been identified. In this Phase II project, we will establish a partnership with a sister company in the space, Molsoft LLC, whose products already addresses a key customer concern. The GeneCentrix technology to enhance the translatability of phenotypic screens will be integrated as feature into Molsoft’s ICM product line (Aim 1). In addition, customer requested and sponsor (NIDA/NCATS)-desired R&D will update the product core to optimize it for anti-addiction drug discovery by incorporation of new and growing brain atlas, proteomic and pharmacokinetic big data (Aim 2). For this FOA, this application falls within Area 4: Tools and Model Systems for OUD Research and proposes a project including the development of drug discovery and development- enabling technologies. Funding is sought for activities and steps in the product development process encompassing the development and demonstration of the capability of bioinformatic methods or algorithms for research data integration and data harmonization. Accordingly, as required by the FOA, a broad validation study (Aim 3) will be performed of the technology that that will demonstrate and validate the commercial utility and value proposition of the proposed technology. The commercial plan establishes a clear and feasible approach to take advantage of a growing business opportunity that should lead to a sustainable product cycle with minimal further Phase III investment. Overall, a needed commercial software product could emerge from NIH product development support that could contribute to anti-addiction drug discovery. !

Public Health Relevance Statement:
Project Narrative ! Successful completion of a Phase I award justifies this renewal to commercialize a needed drug discovery software product that generates advanced insights based on specificity of drug action in different brain tissues. Critical new software features, designs and validation studies will complete the pre-commercialization phase of the development of this product. The envisioned product is expected to enhance anti-addiction drug candidate discovery and contribute to renewed confidence in small molecule drug development for opioid use disorders.

Project Terms:
addiction; Address; Adverse event; Agonist; Algorithms; Antipsychotic Agents; Area; Atlases; Award; base; Big Data; Big Data to Knowledge; Bioinformatics; Biological Assay; Biological Models; Brain; brain tissue; Buprenorphine; Bupropion; Businesses; Cell Nucleus; Cells; Clinic; Clinical; cloud based; Clozapine; Clozaril; commercialization; Computational Biology; computational chemistry; Computer software; craving; Data; data integration; Data Set; design; Development; digital; Disease; Drug Addiction; Drug Antagonism; drug candidate; drug development; drug discovery; Drug effect disorder; Drug Industry; Drug Kinetics; drug of abuse; Drug Screening; Epidemic; falls; Funding; Gene Expression; Goals; human tissue; Informatics; insight; interest; Investments; Lead; Licensing; Market Research; Mental Health; Methadone; Methods; Modeling; Molecular; Molecular Computations; molecular modeling; Molecular Target; mu opioid receptors; Naltrexone; National Institute of Drug Abuse; Neurosciences; novel; novel drug class; novel therapeutics; Nucleus Accumbens; opioid use disorder; Pattern; Performance; Pharmaceutical Preparations; Pharmacologic Substance; Pharmacology; Phase; Phenotype; prescription opioid; prevent; Probability; Process; product development; programs; protein expression; Proteomics; prototype; Psychiatry; Public Health; Publications; receptor; Reporting; Research; research and development; screening; screening program; Side; Sister; small molecule; Specificity; Spinal Ganglia; Statistical Models; Structure; Substance abuse problem; Technology; Testing; Time; Tissues; tool; Translating; Translations; trend; United States National Institutes of Health; Update; user-friendly; validation studies