Strengthening the Biomedical Data Science Training Program at Jackson State University

点击翻译按钮获取中文摘要

PROJECT SUMMARY Jackson State University (JSU) proposes to develop a Biomedical Data Science Training Program (BDS-TP) to train the next generation of scientists to address the monumental challenge associated with the curation, integration, analysis, and interpretation of biomedical big data. This training program will strengthen the biomedical research infrastructure of the newly established RCMI Center for Health Disparities Research at JSU. With a special emphasis on the use and management of health disparities datasets representing multiple levels and domains of influence articulated in the National Institute of Minority Health and Health Disparities (NIMHD) Research Framework, the above-stated goal of the BDS-TP will be accomplished through two specific aims that include: 1) Forster Collaborations between biomedical data scientists and BDS-TP participants and RCHDR investigators. Approach: Identify and invite renowned scientists with expertise in specific areas of BDS to serve as leaders/instructors of specific BSD-TP training modules, and facilitate multidisciplinary collaborations; and 2) Build the capacity of JSU and other Mississippi’s HBCU- Historically Black Colleges and Universities (Alcorn State University, Mississippi Valley State University, and Tugaloo College) in biomedical data science. Approach: Organize Train-the-Trainer bootcamps to train the STEM (science, technology, engineering and technology) faculty and post-doctoral research fellows on how to apply cutting-edge data science techniques to different biomedical data types, how to use Galaxy and computational resources like Jupyter Hub, and coding with R, Python, and other data science tools such R-Studio, Galaxy, or Carpentries; and organize Codeathons focused on specific biomedical topics using various types of datasets. The achievement of these specific aims will significantly enhance the data science skills of program participants, ranging from basic best practices in data collection, curation and analysis to complex computational techniques like machine learning and artificial intelligence that are critical for advancing the science of minority health and health disparities.