Data Scientist | Computational Biologist | Public Health Enthusiast
Welcome to My Personal Website!

I am a research scientist with experience in computational modeling and knowledge inference from large and complex biomedical data-sets using modern machine learning and data mining techniques. My primary research spans on the opportunities at the intersection of health data science, computation, and biology. Throughout my career, I have tried to define my research interests by the demands of health care and how they could be satisfied by the modern computing approaches.
I primarily do research in data-intensive biology by building innovative tools and approaches for addressing a wide variety of real-world problems. My interest lies in understanding the rich contextual information associated with most data sets in a variety of real-world domains and using it to infer novel hidden patterns.
To this end, I have worked on designing efficient inference and learning pipelines for the models capable of handling uncertainties and interdependencies, a characteristic that is predominantly associated with large-scale data sets. I have computational modeling experience in diverse domains ranging from real-world engineering problems to medical diagnostics, immunology, epidemiology, bioinformatics, regulatory genomics, and clinical and health informatics.
Staff Scientist
Department of Medicine
Section of Computational Biomedicine and Biomedical Data Science
University of Chicago
Master in Public Health (Epidemiology)
Harvard T.H. Chan School of Public Health
Peri- & Post-natal Risk Factors Associated with Health of Newborns
Pre-print available at
medRxiv
January 2023
Recreational Cannabis Legalization and the US Opioid Epidemic
Working Manuscript
Coming Soon!
2023
Highlights of Recently Published and Ongoing Work
Risk of Preventable Injuries During Halloween Festivities
Published in
Public Health
October 2020
A Novel Quantitative Approach for Lumbar Spine
MRI Reporting
Published in
Spine
July 2021
Air Pollution and Risk of Psychiatric Disorders in the US and Denmark
Published in
PLOS Biology
August 2019
Machine Learning Approach for Predicting Past Occupational
Exposures
Published in Journal of Occupational and Environmental Medicine
July 2018
FIGS Package for Meta-Analysis of Cell-Specific Transcriptomic Data
Published in BMC Bioinformatics Download package from GitHub
June 2017
Quantification of Age-Related Degenerative Changes Seen in Lumbar Spine
Published in IEEE Journal of Biomedical and Health Informatics
June 2014
Recent Collaborative Efforts (Team Science)
Gene-Environment Interactions and Neuropsychiatric Disorders
Published in
Cell Reports Medicine
September 2022
Genetic and Environmental Contributions to Schizophrenia Risk
Published in
npj Schizophrenia
May 2022
Repurposed Drug for the Treatment of Glioblastoma Multiforme
Published in
Cell Reports
November 2021
Probing Seasonality of Psychiatric Disorders in US and Sweden
Published in
PLOS Biology
July 2021
Effects of Daylight Saving Time (DST) Shifts on Human Health
Published in
PLOS Computational Biology
June 2020
Department of Defense Study on Occupational Exposure Biomarkers and Health Effects
Publsihed in Journal of Occupational and Environmental Medicine
December 2019
Cell-Type Specific Pathogen
Response Network Explorer Tool
Link to PathCellNet Package
Journal of Immunological Methods
September 2016
Automatied Analysis of Flow Cytometry Datasets with Mixture Models
Published in
Cytometry Part A
October 2015
Featured Study: Environmental Pollution and Risk of Psychiatric Disorders
Thanks to my colleagues and collaborators (much obliged to my mentor Professor Andrey Rzhetsky, Edna K. Papazian Professor of Medicine at the University of Chicago), we recently published a trailblazing study on the association between environmental pollution and psychiatric disorders in the United States and Denmark. We did a computational investigation to study the complex interactions of environmental risk factors that are predictive of neuropsychiatric conditions.
This study is notable for its breadth, we analyzed over 150 million patients in the US and applied our model to Denmark to study the entire population of the country born between 1979 and 2002. The analyses showed that air and land pollution were significant predictors for the clinical frequency of several psychiatric disorders. An in-depth understanding of the environmental influence on mental health is needed to better characterize the health effects of exposure to pollutants. Evidence from most recent animal studies shows that air pollution causes neuroinflammation, which specifically supports our findings from massive clinical data mining.
The study was published in PLOS Biology on August 20, 2019.
