Greg is a PhD student in the biomedical engineering department. He is developing methods for predicting interactions between microbes within communities such as the gut microbiome, as well as systems biology methods for studying the metabolism of gut microbes.
Basel is currently exploring the systems genetics of complex skeletal phenotypes related to bone strength, in Diversity Outbred mice. His research incorporates systems genetics, genomics, and network modeling approaches to elucidate the genetic determinants (genes and variants) of bone strength.
Jeffrey is studying the pathogenesis of large granular lymphocytic leukemia, a disorder characterized by abnormally sustained activation and malignant proliferation of reactive cytotoxic lymphocytes. He is interested in applying computational and experimental approaches to characterizing this disease. These include profiling somatic mutations in a cohort of patient leukemic genomes/epigenomes, building an integrated network model of aberrant signaling pathways, designing machine learning algorithms for phenotypic/prognostic prediction from experimental measurements, and testing candidate rational drug therapies. He has found the skills and techniques cultivated through the biomedical data science training program to be particularly applicable to working with large and complex datasets such as human the genome and its gene interaction networks.
Jack is a 3rd year PhD candidate in the computer science department. His research focuses on applying deep learning methods to solve problems in healthcare. In particular, he is interested in using deep learning for applications in DNA sequence prediction/understanding and healthcare question answering systems.
Alicia is a third year PhD student in Systems & Information Engineering and interested in using data-driven techniques to influence the delivery of population health policy and interventions, especially for social determinants of health, mental health, and accessibility to medical care. Her dissertation research is collaborative with the Department of Psychology and focuses on building predictive models for heightened suicide risk based on a multimodal dataset, including a clinical interview of mental health history, text messages, call history, emails, social media, and web browsing activity, collected from people with past non-fatal suicide attempts. In addition, she is the PI on a collaborative study, between faculty in the School of Medicine and an undergraduate student in the Curry School of Education, to develop a health insurance literacy assessment (i.e., how much do people understand about their health insurance plan and how does this impact their treatment-seeking behavior?)
Evan is applying data science principles to study the complex relationships between skeletal muscle structure, function, and injury susceptibility. To do this, large amounts of data are being collected from healthy subjects, including ultrasound and magnetic resonance images, images of muscle molecular structure, measures of muscle strength, and gait motion data. This large pool of data can then by analyzed using machine learning techniques to uncover unique patterns and develop data-driven models describing the effects of structural properties on muscle functional capacity. This work will lead to improved mechanical and kinematic simulation tools and may provide important clinical insight regarding the causes and effects of musculoskeletal pathologies.