Ananth Y. Grama

Solving High-Dimensional Population Balance Equations via Dynamics-Preserving Autoencoders

The paper introduces a hybrid framework combining mechanistic models and machine learning to solve high-dimensional population balance equations for cell-state dynamics.

Joint Modeling of Transcriptomic and Morphological Phenotypes for Generative Molecular Design

Pert2Mol generates molecular structures from paired transcriptomic and morphological data using a multi-modal framework, achieving better performance than single-modality or diffusion-based methods.

Generating Joint Transcriptomic and Morphological Responses to Drug Perturbations via Rectified Flow

PertFlow jointly predicts gene expression and cellular morphology from drug perturbations, achieving high correlation and expert-rated image similarity.

AnnotateAnyCell: Open-Source AI Framework for Efficient Annotation in Digital Pathology

AnnotateAnyCell reduces annotation time for histopathological images by 25% using a semi-supervised framework with active contrastive learning and human-in-the-loop feedback.

Take ACTION to characterize the functional identity of single cells

The paper introduces ACTION, a method to infer cell functional identity from transcriptomic data, identifies novel melanoma subtypes with distinct survival and therapeutic responses, and provides biomarkers and regulatory networks.

DECODE-ing sparsity patterns in single-cell RNA-seq

The paper introduces DECODE, an algorithm that identifies gene presence/absence patterns in single-cell RNA-seq data and distinguishes biological from technical zeros, improving functional inference and imputation.