People

Atul Deshpande, PhD, is an Assistant Professor in the Department of Oncology (with a secondary appointment in Electrical & Computer Engineering) at the Johns Hopkins University School of Medicine. His research program bridges high-dimensional biological measurements and mechanistic understanding by developing bioinformatics methods and computational frameworks that calibrate models to multi-scale tissue data with quantified uncertainty. The lab builds bioinformatics tools for spatial biology and applies them to spatial and single-cell data from clinical and simulated biological data. The lab develops open source software for spatial biology which quantify tissue architecture and identify molecular interactions in the cellular microenvironment.

Dr. Deshpande applies these tools directly to clinical cancer specimens. His work includes the spatial characterization of metastatic PDAC by imaging mass cytometry, and, with the Popel laboratory, proof-of-concept for calibrating spatial agent-based (quantitative systems pharmacology) models to clinical specimens — showing that calibrated models reproduce observed tissue architectures and that the derived spatial metrics predict patient survival. He collaborates closely with investigators across Johns Hopkins, including the Popel (BME), Phillip (BME), Stein-O'Brien (Neuroscience), and Ho (Oncology) groups, and serves as the Johns Hopkins representative to the Break Through Cancer consortium, coordinating multi-institutional spatial-analysis efforts in PDAC. Dr. Deshpande is also a member of the Department of Biomedical Engineering and the Data Science and AI Institute.

He earned his PhD in Electrical Engineering at the University of Wisconsin–Madison, with prior degrees from IIT Madras and Visvesvaraya Technological University, and completed a postdoctoral fellowship in Oncology at Johns Hopkins with Elana J. Fertig.

Research interests: Computational biology; machine learning and statistical inference for biomedical data; data assimilation, model calibration, and uncertainty quantification; multi-scale modeling of biological systems.

Orian develops SpaceMarkers 2.0, extending the lab's spatial interaction discovery framework to additional platforms and analysis settings, and contributes to STAPLE, our automated spatial transcriptomics analysis pipeline.

Long leads TRACER, a method for reconstructing biologically coherent cellular profiles from imaging-based spatial transcriptomics, and SPHERE-PCA, a spatial/single-cell analysis project developed in collaboration with the Szalay group.

Chase works on organoid modeling and spatial quantitative systems pharmacology (spQSP / PhysiCell) approaches for pancreatic cancer, contributing to the lab's Lustgarten-funded spatial modeling of PDAC.

Sharanya is an undergraduate research assistant contributing to the lab's spatial biology projects.

Yeonju worked on imaging mass cytometry (IMC) analysis of the tumor microenvironment and led the FunCN study modeling functionally relevant cellular neighborhoods in primary and metastatic pancreatic cancer, published in Cancer Immunology Research.

Emily was an undergraduate research assistant in the lab.