Saumyadipta Pyne

This paper develops a multimodal fusion method for high-resolution neuroretinal rim phenotypes, identifying structural heterogeneity and clinically relevant degeneration regions.

The paper introduces SFinx, a framework for spatial functional analysis of transcriptomic data, revealing spatially varying pathway interactions in lupus nephritis.

The paper develops DyViA-GAN to predict personalized aging phenotype trajectories using longitudinal data, showing its potential in healthspan research.

DyViA uses generative AI to create personalized aging trajectory models for femoral neck BMD, showing dynamic progression from 66 to 89 years.

The paper uses growth curve modeling to identify differentially expressed gene profiles in pediatric lupus and links them to clinical phenotypes across racial groups.

This paper evaluates the performance of linear combination tests for gene set enrichment using different covariance estimators in unbalanced studies, finding ridge estimation more reliable for unbalanced designs.

GRAIL reconstructs intermediate cellular states between two developmental stages using a combination of LSH-based cell selection, latent space interpolation, and GAN-based gene expression generation.

The paper develops a mathematical model of human neutrophil maturation using single-cell RNA-seq data, identifying key transition states and rates.

The paper introduces GWLCT, a geographically weighted linear combination test for gene set analysis of continuous spatial phenotypes, showing improved performance in detecting spatially varying gene-set associations in tumor samples.

FLARE is a framework for fast and automatic detection of rare cell populations in flow cytometry data using hierarchical Bayesian models and parallel computation.