Mark Gerstein

Determining cellular phylogeny and migration at high resolution in spatial genomics

StarTrak infers cellular migration and phylogeny by integrating somatic variants, spatial data, and transcriptomics at single-pixel resolution in spatial genomics.

The dark transcriptome mouse organogenesis cell atlas

The paper presents a single-cell atlas of noncoding RNAs during mouse organogenesis, revealing their cell-type-specific and lineage-regulated expression patterns.

Population-scale Y chromosome assemblies reveal recurrent remodeling within constrained architectures

The paper presents a population-scale Y chromosome reference panel with 142 assemblies, revealing structural and epigenetic variation across 180,000 years of evolution.

A global view of human centromere variation and evolution

The paper assembles and characterizes 2,110 human centromeres, revealing novel haplotypes, mobile element insertions, and mutation rate variation across chromosomes.

Spatial Glyco-Codes Define Human Liver Pathology and Progression

This study introduces spatial-GPT, a platform for spatial glycan, protein, and transcriptome profiling in human liver tissues, revealing glyco-codes that define disease states and progression.

Epigenetic characterization of pseudogenes across human tissues

The paper characterizes the epigenetic features of pseudogenes across human tissues and identifies differences compared to protein-coding transcripts and lncRNAs.

Predicting Disease-Specific Histone Modifications and Functional Effects of Non-coding Variants by Leveraging DNA Language Models

The paper develops a disease-specific histone modification prediction model using a large language model and MoE architecture, achieving high AUROC scores and identifying AD-associated variants.

Machine Learning Models Based on Histological Images from Healthy Donors Identify ImageQTLs and Predict Chronological Age

This paper develops models linking histological images to genotype, transcriptome, and age, identifying 906 imageQTLs and predicting gene expression and chronological age from images.

DNA shape and epigenomics distinguish the mechanistic origin of human genomic structural variations

The paper uses genomic and epigenomic data to identify mechanisms underlying the origin of structural variations in the human genome.

Comprehensive analysis of pseudogene expression in human and macaque brains compared with other tissues

The paper surveys pseudogene expression in human and macaque brains compared to 29 other tissues, finding elevated and consistent brain expression and associations with neuropsychiatric disorders.

chronODE: A framework to integrate time-series multi-omics data based on ordinary differential equations combined with machine learning

chronODE integrates time-series multi-omics data using ordinary differential equations and machine learning to model gene and chromatin dynamics during brain development.

Complex genetic variation in nearly complete human genomes

Hybrid HiFi/ultra-long ONT assemblies of 65 diverse humans yield 130 haplotypes, 1,246 complete centromeres, and a pangenome panel enabling short-read genome inference at median QV 45.

An expanded reference catalog of translated open reading frames for biomedical research

The paper expands and refines a reference catalog of human non-canonical open reading frames (ncORFs) by incorporating more datasets and introducing a translation signature score framework to prioritize high-quality ncORFs.

A Discard-and-Restart MD algorithm for the sampling of realistic protein transition states and enhance structure-based drug discovery

The paper introduces a Discard-and-Restart MD algorithm to efficiently sample protein transition states, enhancing structure-based drug discovery by reducing simulation times by up to 2000x.

Generative World Models to compute protein folding pathways

This paper develops a generative World Model to simulate protein folding pathways using dihedral rotations and validates it against MD data.

Characterization of gut microbiomes in rural Honduras reveals novel species and associations with human genetic variation

The paper characterizes gut microbiomes in rural Honduras, identifying novel species and host-microbiome associations through metagenomic sequencing and genomic data integration.

Multi-omic Characterization of HIV Effects at Single Cell Level across Human Brain Regions

This study uses single-nucleus multiome sequencing to identify HIV-associated transcriptional and epigenetic changes in brain regions of individuals with HIV, revealing altered glial cell states and pro-inflammatory signaling.

NoisyFlow: Differentially Private Optimal Transport Using Neural Networks for Secure Biomedical Data Sharing

NoisyFlow enables secure biomedical data sharing by aligning data distributions across institutions using differentially private optimal transport with neural networks.

ASTRO: Automated Spatial Whole-Transcriptome RNA-Expression Workflow

ASTRO is an automated pipeline for spatial transcriptomics analysis, optimized for FFPE samples and capable of detecting coding and non-coding RNAs.

An Expanded Registry of Candidate cis-Regulatory Elements for Studying Transcriptional Regulation

The paper expands the ENCODE Registry of candidate cis-regulatory elements (cCREs) to include 2.35 million human and 927 thousand mouse cCREs, revealing novel regulatory functions and identifying KLF1 as a causal gene for red blood cell traits.

Digital phenotyping from wearables using AI characterizes psychiatric disorders and identifies genetic associations

This paper uses wearable data and AI to identify genetic associations with psychiatric disorders by creating intermediate phenotypes from continuous physiological features.

A comprehensive catalog of 3D genome organization in diverse human genomes facilitates understanding of the impact of structural variation on chromatin structure

The paper develops a Hi-C analysis pipeline to catalog TADs and loops in human genomes and quantifies the impact of SVs on chromatin structure and gene expression.

The Cellular Underpinnings of the Human Cortical Connectome

The paper shows that cell type distributions in the cortex are spatially aligned with functional organization patterns from fMRI.

A Variational Graph Partitioning Approach to Modeling Protein Liquid-liquid Phase Separation

This paper introduces a Graph Partitioned GNN (GP-GNN) to predict protein liquid-liquid phase separation by focusing on subgraphs containing intrinsically disordered regions.

REPIC -- an ensemble learning methodology for cryo-EM particle picking

REPIC uses ensemble learning to identify high-quality cryo-EM particles by consensus, reducing manual effort and improving consistency across different pickers.

The GENCODE CLS project: massively expanding the lncRNA catalog through capture long-read RNA sequencing

The paper expands the lncRNA catalog using capture long-read RNA sequencing, significantly increasing the number of annotated transcripts in human and mouse genomes.

BC-Design: A Biochemistry-Aware Framework for Inverse Protein Design

BC-DO_SCPLOWESIGNC_SCPLOW improves inverse protein design by integrating continuous physicochemical properties with structural geometry, achieving high sequence recovery and functional design accuracy.

Epitope-anchored contrastive transfer learning for paired CD8+ T cell receptor-antigen recognition

This paper introduces EPACT, a deep-learning framework for predicting TCR-antigen binding pairs, showing high accuracy in epitope recognition and TCR repertoire analysis.

Spatially Exploring RNA Biology in Archival Formalin-Fixed Paraffin-Embedded Tissues

This paper introduces Patho-DBiT, a method for spatial transcriptomics in FFPE tissues, enabling RNA biology analysis including splicing, variants, and regulatory networks in clinical samples.

Impact and characterization of serial structural variations across humans and great apes

The paper introduces NAHRwhals, a method to detect serial structural variations in long-read genomes, identifies 37 sSV loci in humans, and shows their relevance to disease.