Jagan Mohan Reddy Dwarampudi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jagan Mohan Reddy Dwarampudi has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Kunal Rai
University of Texas MD Anderson Cancer Center
5 shared publications - Ishtyaq Mahmud
University of Houston
4 shared publications - Suresh Satpati
The University of Texas MD Anderson Cancer Center 3 Department of Genomic Medicine, MDACC Epigenomics Therapy Initiative Houston, Texas
4 shared publications - Tania Banerjee
University of Houston
4 shared publications - Veena Kochat
MD Anderson Cancer Center, Houston
4 shared publications - Humaira Anzum
University of Houston
2 shared publications
Latest Publications
- Open Access
NanoCellAnnotator: Formalizing Expert Cell Type Annotation with Large Language Models
Motivation: Cell-type annotation in spatial transcriptomics is challenging due to sparse gene panels, spatial heterogeneity, and limited availability of tissue-matched reference atlases. Recent approaches have explored large language models (LLMs) for integrating biological knowledge during annotation, but unconstrained inference can produce biologically unsupported predictions and hallucinated cell types. In addition, many LLM-based pipelines rely on large cloud-hosted models that limit reproducibility and deployment in privacy-sensitive environments. Results: We introduce NanoCellAnnotator, a biologically constrained and confidence-aware framework for automated cell-type annotation in spatial transcriptomics. The framework de-couples spatial structure discovery, deterministic biological evidence construction, and language model-based semantic inference. Spatial clusters are identified using hybrid spatially regularized non-negative matrix factorization (hSNMF), after which cluster-level marker genes are abstracted into ontology-derived functional programs using Gene Ontology enrichment and GO-slim projection. A lightweight locally executable language model performs constrained label selection within a curated admissible label space derived from PanglaoDB and CellMarker. Annotation confidence is estimated independently using marker support strength and lineage separation, enabling ambiguous or heterogeneous clusters to be explicitly flagged. We evaluate NanoCellAnnotator on Xenium spatial transcriptomics data from intrahepatic cholangiocarci-noma and an independent breast cancer spatial transcriptomics dataset. The framework recovers canonical cell populations with high confidence while identifying heterogeneous or transitional spatial domains as ambiguous. Agreement with manual annotations was evaluated using accuracy and adjusted Rand index. Availability: Code available at https://github.com/ishtyaqmahmud/NanoCellAnnotator.
Open AccessNanoCellAnnotator: Formalizing Expert Cell Type Annotation with Large Language Models
Motivation: Cell-type annotation in spatial transcriptomics is challenging due to sparse gene panels, spatial heterogeneity, and limited availability of tissue-matched reference atlases. Recent approaches have explored large language models (LLMs) for integrating biological knowledge during annotation, but unconstrained inference can produce biologically unsupported predictions and hallucinated cell types. In addition, many LLM-based pipelines rely on large cloud-hosted models that limit reproducibility and deployment in privacy-sensitive environments. Results: We introduce NanoCellAnnotator, a biologically constrained and confidence-aware framework for automated cell-type annotation in spatial transcriptomics. The framework de-couples spatial structure discovery, deterministic biological evidence construction, and language model-based semantic inference. Spatial clusters are identified using hybrid spatially regularized non-negative matrix factorization (hSNMF), after which cluster-level marker genes are abstracted into ontology-derived functional programs using Gene Ontology enrichment and GO-slim projection. A lightweight locally executable language model performs constrained label selection within a curated admissible label space derived from PanglaoDB and CellMarker. Annotation confidence is estimated independently using marker support strength and lineage separation, enabling ambiguous or heterogeneous clusters to be explicitly flagged. We evaluate NanoCellAnnotator on Xenium spatial transcriptomics data from intrahepatic cholangiocarci-noma and an independent breast cancer spatial transcriptomics dataset. The framework recovers canonical cell populations with high confidence while identifying heterogeneous or transitional spatial domains as ambiguous. Agreement with manual annotations was evaluated using accuracy and adjusted Rand index. Availability: Code available at https://github.com/ishtyaqmahmud/NanoCellAnnotator.
- Open Access
Ambiguity-Aware Multi-Stage Cell-Type Annotation for Spatial Transcriptomics
Spatial transcriptomics enables characterization of cellular organization in intact tissue, but robust cell-type annotation remains challenging due to heterogeneous expression profiles, mixed populations, and transitional states. Existing methods often enforce a single label per cluster, obscuring biologically meaningful ambiguity and producing overconfident assignments. We propose an ambiguity-aware, multi-stage framework for spatial cell-type annotation. The method combines hybrid spatial–feature clustering with constrained language-model inference over curated label sets, and assigns confidence scores based on marker coverage, candidate separation, and entropy. Low-confidence clusters are selectively refined via local reclustering of ambiguous regions, while unresolved clusters are preserved as mixed rather than forcibly labeled. Applied to 10x Genomics Xenium spatial transcriptomics data from cholangiocarcinoma, the proposed refinement reduces cluster-level ambiguity from 16.1% to 2.27% and cell-level ambiguity from 18.4% to 0.86%, while improving confidence calibration. Spatial ablation confirms that topological integration resolves structural ambiguity over feature-only baselines, while constrained inference via a lightweight language model ensures scalable and biologically coherent annotations. These results highlight the importance of explicit ambiguity handling for reliable spatial annotation in heterogeneous tumors.
Open AccessAmbiguity-Aware Multi-Stage Cell-Type Annotation for Spatial Transcriptomics
Spatial transcriptomics enables characterization of cellular organization in intact tissue, but robust cell-type annotation remains challenging due to heterogeneous expression profiles, mixed populations, and transitional states. Existing methods often enforce a single label per cluster, obscuring biologically meaningful ambiguity and producing overconfident assignments. We propose an ambiguity-aware, multi-stage framework for spatial cell-type annotation. The method combines hybrid spatial–feature clustering with constrained language-model inference over curated label sets, and assigns confidence scores based on marker coverage, candidate separation, and entropy. Low-confidence clusters are selectively refined via local reclustering of ambiguous regions, while unresolved clusters are preserved as mixed rather than forcibly labeled. Applied to 10x Genomics Xenium spatial transcriptomics data from cholangiocarcinoma, the proposed refinement reduces cluster-level ambiguity from 16.1% to 2.27% and cell-level ambiguity from 18.4% to 0.86%, while improving confidence calibration. Spatial ablation confirms that topological integration resolves structural ambiguity over feature-only baselines, while constrained inference via a lightweight language model ensures scalable and biologically coherent annotations. These results highlight the importance of explicit ambiguity handling for reliable spatial annotation in heterogeneous tumors.
- Open Access
A Counterfactual Framework for Directional Cell–Cell Interaction Analysis in Spatial Transcriptomics
Understanding how neighboring cells influence cellular states is central to spatial transcriptomics, yet most existing methods rely on correlation or predefined ligand–receptor (LR) pairs and do not explicitly test directionality. We introduce a counterfactual, intervention-based framework for inferring directional cell–cell influence that is LR-agnostic and tests sender specificity. A neighborhood-conditioned graph model predicts receiver cell state from local spatial context. Directional influence is quantified by counterfactually replacing neighbors of a candidate sender type and measuring the resulting displacement in predicted receiver state. We define a Counterfactual Directionality Score (CDS) that quantifies directional influence, and compute pair-level CDS by aggregating across receiver cells and test cores for each ordered sender–receiver pair. Applied to Xenium cholangiocarcinoma tissue microarrays (38 cores), the framework identified reproducible, asymmetric interactions between tumor, immune, and stromal compartments, most prominently Tumor-EMT → Macrophage (CDS = 0.0828) and Fibroblast → Macrophage (CDS = 0.0582). Effects exceeded label-permutation and spatial-shuffle null models ( p < 0.001, FDR-controlled) and remained stable under core-level bootstrap resampling. Inferred directional strengths correlated strongly with matched LR scores ( r = 0.758, p = 0.0027), supporting biological concordance. These results demonstrate counterfactual testing as a statistically rigorous and scalable approach for directional cell–cell communication analysis in spatial transcriptomics.
Open AccessA Counterfactual Framework for Directional Cell–Cell Interaction Analysis in Spatial Transcriptomics
Understanding how neighboring cells influence cellular states is central to spatial transcriptomics, yet most existing methods rely on correlation or predefined ligand–receptor (LR) pairs and do not explicitly test directionality. We introduce a counterfactual, intervention-based framework for inferring directional cell–cell influence that is LR-agnostic and tests sender specificity. A neighborhood-conditioned graph model predicts receiver cell state from local spatial context. Directional influence is quantified by counterfactually replacing neighbors of a candidate sender type and measuring the resulting displacement in predicted receiver state. We define a Counterfactual Directionality Score (CDS) that quantifies directional influence, and compute pair-level CDS by aggregating across receiver cells and test cores for each ordered sender–receiver pair. Applied to Xenium cholangiocarcinoma tissue microarrays (38 cores), the framework identified reproducible, asymmetric interactions between tumor, immune, and stromal compartments, most prominently Tumor-EMT → Macrophage (CDS = 0.0828) and Fibroblast → Macrophage (CDS = 0.0582). Effects exceeded label-permutation and spatial-shuffle null models ( p < 0.001, FDR-controlled) and remained stable under core-level bootstrap resampling. Inferred directional strengths correlated strongly with matched LR scores ( r = 0.758, p = 0.0027), supporting biological concordance. These results demonstrate counterfactual testing as a statistically rigorous and scalable approach for directional cell–cell communication analysis in spatial transcriptomics.
- Open Access
Spatially Anchored Regulatory State Inference in Melanoma
Spatial transcriptomics (ST) captures gene expression within tissue architecture but lacks direct regulatory information, while single-cell multiome assays profile transcriptional and chromatin states without spatial context. We present a framework for spatially anchored regulatory inference that integrates Visium ST with single-cell multiome data to infer spatially resolved regulatory programs. Building upon GraphST, we introduce spatially regularized cell-to-spot mapping and propagate chromatin accessibility and transcription factor motif activity into tissue space. Regulatory analysis is performed at the spatial domain level via joint differential expression and accessibility testing, along with quantitative concordance assessment. Applied to melanoma tissue sections, the framework reveals spatially localized regulatory programs and shows that assignment strategy substantially affects downstream regulatory stability. This modular approach enables interpretable gene-, peak-, and transcription factor–level outputs for multimodal spatial analysis.
Open AccessSpatially Anchored Regulatory State Inference in Melanoma
Spatial transcriptomics (ST) captures gene expression within tissue architecture but lacks direct regulatory information, while single-cell multiome assays profile transcriptional and chromatin states without spatial context. We present a framework for spatially anchored regulatory inference that integrates Visium ST with single-cell multiome data to infer spatially resolved regulatory programs. Building upon GraphST, we introduce spatially regularized cell-to-spot mapping and propagate chromatin accessibility and transcription factor motif activity into tissue space. Regulatory analysis is performed at the spatial domain level via joint differential expression and accessibility testing, along with quantitative concordance assessment. Applied to melanoma tissue sections, the framework reveals spatially localized regulatory programs and shows that assignment strategy substantially affects downstream regulatory stability. This modular approach enables interpretable gene-, peak-, and transcription factor–level outputs for multimodal spatial analysis.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Benchmarking Dimensionality Reduction Techniques for Spatial Transcriptomics
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessBenchmarking Dimensionality Reduction Techniques for Spatial Transcriptomics