Martin Prete

The paper builds a spatiotemporal map of human pilosebaceous unit development using single-cell multiomics and machine learning, showing how epithelial-mesenchymal interactions drive organogenesis and how sebaceous gland programs are disrupted in tumors.

TERRA is a foundation model for spatial transcriptomics that predicts tissue behavior under perturbation and identifies multi-scale biological insights across tissues.

The paper provides a high-resolution molecular and cellular analysis of Broca's area and motor cortex across developmental stages, identifying distinct cellular signatures and vulnerabilities to neurodevelopmental disorders.

This study uses spatial transcriptomics to map gene expression gradients in the human endometrium, revealing coordinated regeneration and niche architecture during menstrual breakdown.

This study creates a comprehensive spatial atlas of the human ovarian cortex, revealing molecular mechanisms of primordial follicle activation and follicle niche organization.

Tripso, a self-supervised transformer model, identifies gene program-specific embeddings and discovers novel gene programs, revealing biological insights in hematopoietic development and disease.

This study creates a spatially-resolved molecular atlas of human skin and uses deep learning to identify 26 niches, revealing novel immune memory structures in inflammatory skin diseases.

PerturbGen predicts how genetic perturbations affect cellular trajectories across time in human datasets, showing effects on immune responses, hematopoiesis, and skin development.

The paper presents a spatial transcriptomic atlas of autism-associated genes in the developing human brain, identifying convergence in the thalamus and germinal zones.

This study creates a spatial genomics atlas of human skin fibroblasts in health and disease, identifying six major populations and three disease-specific subtypes.

This study creates a single-cell multiomics atlas of B cell development in prenatal and adult bone marrow and in vitro models, identifying novel cell subsets and molecular signatures.

MintFlow is a generative AI algorithm that predicts how tissue perturbations reprogram cell states in disease, revealing novel cell populations and therapeutic targets in three human conditions.

The paper creates a regulon atlas mapping TF activity across human cell types and uses it to link disease signatures to cell types and TFs, improving disease risk locus analysis.

The paper introduces scCellFie, a framework to infer metabolic activities from single-cell and spatial transcriptomics data, revealing organ-specific metabolic programs and disease-associated alterations.

The paper maps the spatial organization of the human thymus across developmental stages using a multimodal atlas and identifies key cellular and molecular features of T cell development.

This study creates a single-cell spatial atlas of the developing human reproductive tract, identifying genes and mechanisms involved in sexual dimorphism and organ development.

The paper integrates single-cell RNA-seq datasets across the GI tract to identify epithelial metaplasia in inflammatory diseases, showing its role in inflammation through immune cell interactions.

WebAtlas integrates single cell and spatial transcriptomic data into a cloud-optimised format for interactive exploration.

This study constructs a multiomic atlas of human early skeletal development using single-nuclei transcriptomics, epigenomics, and spatial transcriptomics to uncover regulatory mechanisms and cell states involved in bone and joint formation.

This paper creates a human embryonic limb cell atlas using single-cell and spatial transcriptomics, identifying novel cell populations and developmental patterns.

CellHint harmonizes cell types across Human Cell Atlas datasets, revealing new cell states and providing a cross-tissue database with 3.7 million cells.

This paper uses spatial transcriptomics and single-cell data to identify cellular niches in the human heart, revealing new insights into cardiac function and potential drug targets.

This paper describes OME-Zarr, a cloud-optimized bioimaging file format developed through community collaboration to improve scalability and data access.

The paper introduces a method to determine X-inactivation states in single-cell transcriptomes and uses it to infer cellular phylogenies in human females.

This study maps the temporal and spatial dynamics of the human endometrium using single-cell and spatial reference maps, identifying key signaling pathways regulating cell fate in vivo and in vitro.

This study compares web-based visualization tools for scRNA-seq data and introduces an R package to standardize data formats for sharing.