Biomedical Data Science Shared Resource

With the advent and improvement of next-generation sequencing (NGS) technologies, recent ubiquity of clinical data in the form of electronic health records (EHR), and generation and availability of voluminous biomedical data, there is an emerging need to analyze biomedical data with state-of-the-art bioinformatics, machine-learning and deep-learning methods. Biomedical data science focuses on storing, retrieving, analyzing and organizing biomedical data (genomic, sensor, electronic health records data) and knowledge. The Biomedical Data Science Shared Resource (BDSSR) provides bespoke solutions on large-scale data projects and strives to help cancer researchers traverse the landscape of omics technology, artificial intelligence and cancer biology to select the appropriate technology and approach, so that research insights can be mined from the massive amount of data available. In addition, the BDSSR maintains large-scale multimodal research data, like the Molecular Twin Data Commons, for the Cedars-Sinai community. The BDSSR is committed to data management and offers training and educational resources for various skill levels. This resource addresses the growing need for effective analysis of biomedical data available from electronic health records and generated by next-generation sequencing technologies, and offers a solution for developing innovative approaches to analyzing and interpreting biomedical data.