Michael A. Province

This paper introduces GiG, a graph AI framework that integrates and interprets whole-person medical and omics data to prioritize biomarkers and improve disease diagnosis.

The paper examines the relationship between erythrocyte count and mortality in older adults, finding a critical threshold below which mortality risk sharply increases.

CellTosg2Sequence integrates biomedical text and signaling graphs into a language model for single-cell analysis, improving performance over existing models.

BioMedGraphica integrates biomedical knowledge into a unified graph and introduces a Textual-Numeric Graph structure for multi-omics analysis.

This paper introduces a framework combining large language models with omics data analysis to prioritize disease targets and drug strategies, validated in Alzheimer's and pancreatic cancer.

The paper identifies epistatic interactions between HK1 and GCK genes affecting HbA1c levels using Bayesian methods and confirms findings in independent studies.

OmniCellAgent autonomously retrieves and analyzes scRNA-seq datasets to generate structured reports and hypotheses across disease settings.

This study evaluates polygenic risk scores (PRS) for predicting Alzheimer's disease risk in a cohort of families with exceptional longevity and finds limited predictive power due to population-specific genetic differences.

This study identifies novel protective genetic variants associated with TMT-B performance using a family-based GWLS approach in the Long Life Family Study.

This study identifies 22 novel gene-sleep duration interaction loci for blood pressure traits across 811,405 individuals, highlighting distinct genetic influences of short and long sleep on cardiovascular health.

M3NetFlow is a multi-scale multi-hop graph model for multi-omic data analysis that ranks targets and infers signaling pathways, achieving high accuracy in drug response and Alzheimer's disease studies.

FISHNET identifies significant genes missed by standard methods by analyzing gene-level P-values with network and function-based approaches, showing improved replication rates in cardiovascular traits.

GEM-Net constructs multi-modal gene networks using harmonized omics data from the Long Life Family Study, revealing a microbiome-immune axis linked to metabolic health.

This study introduces mosGraphFlow, a graph AI model for analyzing multi-omic data to identify AD-associated biomarkers and signaling pathways, achieving high classification accuracy.

mosGraphGPT is a foundation model for multi-omic signaling graphs trained on cancer data and fine-tuned for Alzheimer's Disease, improving classification accuracy and interpretability.

The paper identifies pleiotropic genetic factors shared between kidney function and sRAGE using GWAS and TWAS in the LLFS cohort.

The paper describes a system for quality assurance of whole genome sequence data in family studies, focusing on identifying germline variants and improving call accuracy through family-based filters.

PathFinder infers multi-cell signaling pathways and communications using a graph transformer model, identifying novel interactions in AD mouse models.

The paper identifies ARHGAP44 as a novel gene associated with longitudinal changes in HbA1c in non-diabetic individuals using linkage and sequence analysis from two studies.

The paper integrates multi-omics data to identify genes influencing cardiovascular risk traits in the Long Life Family Study, finding 64 significant genes and replicating 29 in the Framingham Heart Study.

mosGraphGen generates multi-omics signaling graphs to enable integrative and interpretable graph AI model development by converting multi-omics data into biologically meaningful graphs.

This study analyzes clonal hematopoiesis in over a million diverse individuals, identifying 72 genome-wide significant loci and linking CHIP to various phenotypes.

This study identifies 100 loci associated with mitochondrial DNA copy number and finds causal links between mitochondrial function and mortality.

The paper analyzes gene-environment interaction effects across multiple ancestries and traits, identifying population-specific genetic mechanisms and methodological biases in GxE studies.

This study identifies over 50 new genetic loci associated with pulmonary function through a multiethnic meta-analysis of 90,715 individuals.

VarExp estimates phenotypic variance explained by genetic variants using GWAS summary statistics without individual-level data.

This paper introduces a variance-components linkage analysis method that incorporates between-pedigree coancestry to improve detection of rare variant effects.