Publications – Learning from data

Below is a list of selected publications and topics they cover.

Human Genetics

My lab works on a variety of problems related to human genetics and how we can better understand and treat diseases. We bring information from multiple locations of the genome to better understand the genetic architecture, to aggregate data from multiple populations to identify mutations that protect humans from diseases, and train disease risk prediction models using genetic data. Below are some publications:

Broad genetic architecture

A unified genome constraint, pathogenicity, and pLoF model identifies new genes associated with epilepsy

Large-scale sequencing identifies multiple genes and rare variants associated with Crohn’s disease susceptibility

Protective genetic mutations

Inframe insertion and splice site variants in MFGE8 associate with protection against coronary atherosclerosis

Genetics of 35 blood and urine biomarkers in the UK Biobank

Rare protein-altering variants in ANGPTL7 lower intraocular pressure and protect against glaucoma

Deep resequencing of GWAS loci identifies independent rare variants associated with inflammatory bowel disease

Disease risk prediction

Large-scale multivariate sparse regression with applications to UK Biobank

Fast Lasso method for large-scale and ultrahigh-dimensional Cox model with applications to UK Biobank

Significant sparse polygenic risk scores across 813 traits in UK Biobank

A fast and scalable framework for large-scale and ultrahigh-dimensional sparse regression with application to the UK Biobank

Numerical Optimization Algorithms

My lab develops statistical methods that may be computationally efficient.

Efficient storage and regression computation for population-scale genome sequencing studies

Fast numerical optimization for genome sequencing data in population biobanks

Artificial Intelligence

My lab is working on computational methods in AI. Spring 2024 I taught a Generative AI in Healthcare course that I will be posting more information on.

Computational Chemistry

My lab is working on bridging lessons from computational genetics, statistical methods, and AI to try to see if we can scale some of the problems in computational chemistry. Below, are some papers that describe some of the recent work that I’ve led.

Smiles2Dock: an open large-scale multi-task dataset for ML-based molecular docking

Population biobanks

My lab is working on learning from population biobanks what type of environmental, genetic, and socioeconomic factors play a role in disease risk and other health traits. We use data from population biobanks.

Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank

Integrative machine learning approaches for predicting disease risk using multi-omics data from the UK Biobank

COVID-19

During COVID-19 my lab worked on better understanding the genetic risk factors for COVID severity and hospitalization.

Deconvoluting complex correlates of COVID-19 severity with a multi-omic pandemic tracking strategy

Mapping the human genetic architecture of COVID-19