Biomedical Data Science for Precision Medicine Vanathi Gopalakrishnan

Biomedical Data Science for Precision Medicine Vanathi Gopalakrishnan, Ph. D vanathi@pitt. edu Room 530, BAUM Personal Mobile: 412 -500 -1416 Associate Professor of Biomedical Informatics Associate Professor of Intelligent Systems Associate Professor of Computational & Systems Biology Associate Professor of Bioengineering Associate Professor of Clinical and Translational Science Director, PRo. BE Laboratory for Pattern Recognition from Biomedical Evidence Co-director, Bioengineering, Biotechnology and Innovation Area of Concentration School of Medicine Director, Intelligent Systems Program, School of Computing and Information University of Pittsburgh

PRo. BE Lab: Research Interests To accelerate Biomedical Knowledge Discovery to reduce disease burden by developing and applying novel hybrid Artificial Intelligence methods Obtained for example from: Literature, Ontologies, Past analyses PRIOR KNOWLEDGE DATA Integrative Modeling RULE LEARNING METHODOLOGIES Focus Areas: Disease prevention, Early detection, Monitoring PREDICTIVE MODELS FOR BIOMEDICINE Enable predictions about for example: mechanism of action, target selection, useful biomarkers for early detection or monitoring of disease, toxicity risk, and clinical trial outcomes. Obtained for example from: Biomedical Assays, Clinical Assessments, Imaging tests

SOME DATA TYPES WE HAVE WORKED WITH • Proteomic – Mass Spectral (large/wide/deep) – Immunoassay • Genomic – – GWAS/SNPs(very large) DNA Methylation Gene Expression micro. RNA • Images – Cardiac MRI – Brain f. MRI *The • From biomarker* discovery studies for early detection of: Amyotrophic Lateral Sclerosis Alzheimer’s Lung Cancer Breast Cancer Esophageal Cancer Inflammatory Bowel Diseases Ulcerative Colitis, Crohn’s – Coronary Artery Disease – Pediatric Cardiomyopathy – – – term “biomarker” or “biological marker”, refers to “a broad subcategory of medical signs – that is, objective indications of medical state observed from outside the patient – which can be measured accurately and reproducibly. Medical signs stand in contrast to medical symptoms, which are limited to those indications of health or illness perceived by patients themselves. ” Kyle Strimbu, Jorge A. Tavel. What are Biomarkers? Curr Opin HIV AIDS. 2010 Nov 5(6): 463– 466.

Example: Lung Cancer Early Detection Clinical History CT screen Results Blood Test RISK PREDICTION MODEL ? Accuracy of early detection # Unnecessary biopsies Multiplexed serologic Quantitative immunoassays Luminex x. MAP® technology Bigbee, W. L*. , Gopalakrishnan, V. *, Weissfeld J, L. , Wilson, D. O. , Dacic, S. Lokshin, A. E. , Siegfried, J. M. A Multiplexed Serum Biomarker Immunoassay Panel Discriminates Clinical Lung Cancer Patients from High-Risk Individuals Found to be Cancer-Free by CT Screening. J Thorac Oncol. 2012 Apr; 7(4): 698708. (*These authors contributed equally to the study).

Intelligent Systems Program (ISP) Director: Vanathi Gopalakrishnan (vanathi@pitt. edu) Administrator: Michele Thomas (paum 4 b@pitt. edu)

ISP Highlights • Age: approximately 33 years old • Focus: Graduate (doctoral mainly) training in multidisciplinary AI - Two tracks: – General and Biomedical Informatics – Around 30 current doctoral trainees Postgraduate training program proposals between ISP and BMI are in process • Faculty: Secondary appointments – Around 35 current faculty with primary appointments across University (11 departments): Computer Science, Information Science, Biomedical Informatics, Law, Education, Engineering, Psychology, Political Science, GSPIA (Economics), Computational and Systems Biology, Radiology

Current Projects/Publications (1) Ensemble Bayesian Rule Learning (EBRL) Classifiers for Precision Health Care – Goal: To fundamentally study and develop more precise EBRL classifiers. Application to: Hemorrhagic stroke and COVID-19 EHR data. Collaborators: Shyam Visweswaram and Sherry Chou (critical care medicine, UPMC) – R 01 Submitted to the NLM – October review (2) Dyspnea 2 Dx – Goal: how to shorten time taken for accurate diagnosis of cause of dyspnea, using EHR data. Collaborators: Yalini Senathirajah (DBMI), Negin Hajizadeh (Northwell Health) R 01 resubmission planned for Nov 2020 Key Publications: • Proteomic profiling of cerebrospinal fluid identifies biomarkers for amyotrophic lateral sclerosis. S Ranganathan, E Williams, P Ganchev, V Gopalakrishnan, D Lacomis, . . . Journal of neurochemistry 95 (5), 1461 -1471 • Discovery and verification of amyotrophic lateral sclerosis biomarkers by proteomics. H Ryberg, J An, S Darko, JL Lustgarten, M Jaffa, V Gopalakrishnan, . . Muscle & nerve 42 (1), 104 -111 A multiplexed serum biomarker immunoassay panel discriminates clinical lung cancer patients from high-risk individuals found to be cancer-free by CT screening. WL Bigbee, V Gopalakrishnan, JL Weissfeld, DO Wilson, S Dacic, . . . Journal of thoracic oncology 7 (4), 698708 •