Volodymyr Kuleshov
Cornell University, NY·Computer Science·Early-career
Datasets now contain millions of genomes from people, plants and animals. Turning them into answers about how genes and environment shape traits and disease requires new computational tools.
- Fields
Computer Science
Genetics
Mathematics & Statistics
- Topics
statistical genetics
machine learning
deep learning
- Grants
- 2 known grants, through Jul 2028
What they work on
- Develop a deep generative neural network model of genetic sequences that replaces classical hidden Markov models and handles high dimensionality and long-range dependencies along the genome.
- Reduce the cost of genome assays by building algorithms and open-source software for genotype imputation and low-pass sequencing based on the new generative model.
- Create machine learning methods for modeling linkage disequilibrium, the co-inheritance of nearby variants, and for haplotyping across large human genome datasets.
- Develop algorithms to analyze genome-wide association study (GWAS) data, identify causal variants, and score disease risk from combined genetic and environmental factors.
More about the research
Older statistical methods struggle with data at this scale. These grants apply modern machine learning (ML) to statistical genetics, the study of how genetic variation links to traits. They also produce open-source software that scientists and clinicians can use. One grant develops the core models of genetic variation. The other extends them across many tasks in human genetics.
Why it matters
Cheaper, more accurate methods to read and interpret genomes could lower the cost of genetic testing. They could reveal new genetic factors in disease and sharpen risk prediction in preventive medicine and pharmacogenomics. The same tools could help large genetic studies, animal breeding and the breeding of more nourishing crops.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Andrew D Kern
University of Oregon, OR·Ecology & Evolution
Develop methods to infer dispersal, how far individuals move, directly from population genomic data, and assess how spatial structure affects GWAS, genome-wide studies linking variants to traits, with Anopheles gambiae data in mind.
Kaixiong Ye
University of Georgia, GA·Genetics
Develop and apply statistical tests to detect genetic and polygenic responses to the Agricultural Revolution using ancient DNA, identifying adaptive variants whose mismatch with modern lifestyles may underlie today's common diseases.
Penny Gordon-Larsen
University of North Carolina at Chapel Hill, NC·Public Health & Epidemiology
Identify gene-expression signals underlying severe obesity using whole-blood RNA sequencing from more than 15,000 people, and build ancestry-informed eQTL maps for underrepresented populations.
The school
Cornell University: 37 labs on PI Pages, $1.6B a year on research, 537 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.