Abstract: This IPERT R25 application will formalize and expand upon a series of unique Biomedical Data Science Innovation Lab online and in-person workshops whose immersive and hands-on approach will accelerate the ability of early-career biomedical and quantitative investigators to form new collaborations around biomedical science projects. Each year a distinct biomedical topic will be specifically identified which would benefit from a fresh or divergent data science perspective. During the Biomedical Data Science Innovation Lab events, professional facilitators and senior scientist mentors (with relevant expertise and exposure to the topic area) assist the participants - guiding the development of innovative research project proposals. The primary purpose of the facilitators is to build the community, strengthen the bonds between the participants, and help the teams to form. Program directorship will provide leadership, continuity, and logistical support, while other stakeholders provide vision, expertise, and ongoing program feedback. Senior faculty mentors will contribute topic background and data science applications while also providing oversight and feedback on the development of new projects. Early-career investigators (at the post-doc, assistant to newly associate professor level, research and tenure track) from quantitative (including but not limited to applied and/or theoretical mathematics, statistics, computer science, physics, and engineering) and biomedical fields (including but not limited to biological, biophysical, epidemiological, and clinical disciplines) will be welcomed to submit applications. A broad diversity of backgrounds is desired with women and members of underrepresented communities encouraged to apply. Throughout the year-long program, participants will benefit directly from explicit skills training in data science methods, reproducibility, Team Science, responsible conduct in research, and will learn about research funding mechanisms directly through interaction with NIH and NSF program officers. Participants will form multidisciplinary teams during the in-person workshop to develop biomedical topic domain projects involving mathematical modeling, statistical analytics, and other quantitative methods. Upon completion of the workshops, follow-up virtual activities will solidify teams and their research proposals as grant applications suitable for submission to federal and private funding agencies. Rigorous assessment and characterization of skills training activities as well as team effectiveness using emerging Science of Team Science-based approaches will strictly pursued. A rich program for dissemination of workshop activities includes broad-based outreach, a detailed website, and the development of professional-grade visual media and materials. With a well-suited team and a track record of prior success, this is a novel program for research community building, fully aligned with the goals of the IPERT R25 program. 1

Project Narrative - Public Health Relevance Statement: To encourage the creation of new research partnerships and to promote career path development, we will host a unique Biomedical Data Science Innovation Lab program focused on large-scale biomedical data to address salient challenges in health and disease. This event will follow a rigorous, interactive, mentored, and facilitated online and in-person program for data science skills training where novel team projects will be developed for NIH/NSF grant submissions. 1