Joseph Daniel Romano, PhD, MPhil, MA
Assistant Professor of Biostatistics and Epidemiology
CEET Investigator, Center of Excellence in Environmental Toxicology
Faculty member, Institute for Translational Medicine and Therapeutics
IBI Senior Fellow, Institute for Biomedical Informatics, University of Pennsylvania
Department: Biostatistics and Epidemiology
Graduate Group Affiliations
Contact information
403 Blockley Hall
423 Guardian Drive
Philadelphia, PA 19104
423 Guardian Drive
Philadelphia, PA 19104
Office: 215-573-5571
Publications
Links
Search PubMed for articles
The Romano Lab at the University of Pennsylvania
Joseph D. Romano - Google Scholar profile
Joseph D. Romano - Personal Website
Search PubMed for articles
The Romano Lab at the University of Pennsylvania
Joseph D. Romano - Google Scholar profile
Joseph D. Romano - Personal Website
Education:
B.S. (Molecular Genetics)
University of Vermont, 2014.
M.A. (Biomedical Informatics)
Columbia University, 2016.
MPhil (Biomedical Informatics)
Columbia University, 2018.
PhD (Biomedical Informatics)
Columbia University, 2019.
Permanent linkB.S. (Molecular Genetics)
University of Vermont, 2014.
M.A. (Biomedical Informatics)
Columbia University, 2016.
MPhil (Biomedical Informatics)
Columbia University, 2018.
PhD (Biomedical Informatics)
Columbia University, 2019.
Description of Research Expertise
My research uses translational bioinformatics and artificial intelligence to predict and explain associations between chemical exposures and human diseases, with a particular focus on environmental exposures.There are well over 1 million known environmental chemicals of toxicological concern, but traditional approaches can only be used to study a small handful of them. In the Romano Lab, we design data resources, tools, and algorithms to discover how they interact with the human body via strictly computational approaches. Some of our favorite techniques include graph machine learning, knowledge representation, ontology inference, and integrative data analysis.
Other areas of interest include automated machine learning, toxinology (the study of venoms and other naturally occurring toxins), drug discovery/repurposing, phylogenomics, and visualizing complex and high-dimensional data.
Selected Publications
Romano JD, Mei L, Senn J, Moore JH, & Mortensen HM: Exploring genetic influences on adverse outcome pathways using heuristic simulation and graph data science. Computational Toxicology. Elsevier, 25: 100261, February 2023.Romano JD, Truong V, Kumar R, Venkatesan M, Graham BE, Hao Y, Matsumoto N, Li X, Wang Z, Ritchie M, Shen L, & Moore JH: The Alzheimer's Knowledge Base - A knowledge graph for therapeutic discovery in Alzheimer's Disease research. JMIR Preprints February 2023 Notes: (Preprint - currently in review for full publication).
Hao Y, Romano JD, & Moore JH: Knowledge Graph Aids Comprehensive Explanation of Drug and Chemical Toxicity. CPT: Pharmacometrics & Systems Pharmacology 2023 Notes: (In press).
Romano JD: Omics Methods in Toxins Research—A Toolkit to Drive the Future of Scientific Inquiry. Toxins 14(11): 761, November 2022.
Manduchi E, Romano JD, & Moore JH: The promise of automated machine learning for the genetic analysis of complex traits. Human Genetics 141(9): 1529–1544, September 2022.
Hao Y, Romano JD, & Moore JH: Knowledge-guided deep learning models of drug toxicity improve interpretation. Patterns 3(9), August 2022.
Romano JD, Hao YH, Moore JH, & Penning T: Automating toxicological knowledge discovery using ComptoxAI. Chemical Research in Toxicology 35(8): 1370-1382, July 2022.
Romano JD: ComptoxAI - Tutorial - Neo4j Graph Database Browser. YouTube June 2022 Notes: Instructional video/tutorial available online at: https://youtu.be/WIzEGjfzGQQ. Online publication only.
Hao Y, Romano JD, & Moore JH: Knowledge-Guided Deep Learning Models of Drug Toxicity Improve Interpretation. Society of Toxicology Annual Meeting & ToxExpo March 2022 Notes: Peer-reviewed abstract and poster presented at conference; First Place, "Top 10 Best SOT-CTSS Abstract Award Competition"
Kumar R, Romano JD, & Moore JH: Extending Tree-Based Automated Machine Learning to Biomedical Image and Text Data Using Custom Feature Extractors. AMIA 2022 Informatics Summit March 2022 Notes: Peer-reviewed abstract presented at AMIA 2022 Informatics Summit.