Atul M. Deshpande

The paper introduces SPHERE-PCA, a method to interpret single-cell state transitions using spherical geometry, revealing structured patterns in developmental and disease datasets.

The paper identifies periductal fibroblast density as a key factor in immune exclusion in pancreatic cancer, showing that CD44-dependent stromal checkpoints restrict leukocyte access to tumor epithelium.

UQ-PhysiCell provides a Python framework for uncertainty quantification, calibration, and model analysis in PhysiCell simulations, enabling scalable and reproducible uncertainty-aware analysis of agent-based models.

The paper calibrates a spatial QSP model using CODEX data to predict TME states and identify biomarkers for HCC immunotherapy response.

TRACER improves cellular profile coherence in spatial transcriptomics by resolving mixed profiles and reconstructing undetected cells, enhancing downstream analyses.

STAPLE automates spatial transcriptomics analysis by integrating multiple tools into a modular framework and provides AI-driven interpretation of results.

The paper develops a 3D multi-omic pipeline using deep learning to analyze chemotherapy response in pancreatic cancer, identifying molecular signatures of resistance and fibroblast-cancer interactions.

The paper introduces a framework for mathematical modeling of multicellular systems using interpretable cell behavior rules derived from biological knowledge and multi-omics data.

The paper introduces FunCN, a method to analyze cellular neighborhoods in PDAC, revealing distinct immune interactions in primary and metastatic sites.

The paper uses virtual patient models to evaluate biomarkers for predicting response to PD-1 blockade in TNBC, finding that early on-treatment biomarkers and blood-based markers offer better performance.

This study uses spatial multi-omics to identify TLS-associated immune niches in PDAC that correlate with improved survival in immunotherapy responders.

The paper uses spatial analysis to show metastasis-initiating cancer cells in breast tumors are closely associated with specific macrophage subtypes, suggesting these interactions promote metastasis.

This paper introduces SpaceMarkers, a method to infer molecular changes from cell-cell interactions in spatial transcriptomics data, applied to tumor-immune interactions in metastasis and immunotherapy.

scatterHatch creates accessible scatter plots for single-cell data using color and patterns to improve readability for color-vision deficient readers.

This paper introduces SINGE, a method for gene regulatory network inference from ordered single-cell transcriptomic data, showing improved performance over existing methods in mouse stem cell differentiation studies.