Machine learning and access to ever-expanding databases improves genomic prediction of human traits.
In theory, a scientist could predict your height using just your genome sequence. In practice, though, this is still the stuff of science fiction. It’s not only your genes that affect height—environment also plays a role—but the larger problem is that height is affected by tens of thousands of individual genetic variations. This is also true of other complex traits, such as susceptibility to particular diseases. To get closer to accurate genomic prediction of human traits, geneticists are using new approaches to harness the vast amounts of sequence data becoming available. In GENETICS, Lello et al. describe a machine learning approach to the problem that allowed them to make predictions within a few centimeters of reality.
“To me, genomic prediction is the actual decoding of the genome,” says senior author Stephen Hsu from Michigan State University. A theoretical physicist by training, Hsu explains that his lab became interested in the problem of genomic prediction several years ago as the cost of genotyping continued to drop and more datasets became available. They had previously argued that they could predict complex traits, like height, if they only had enough data.The release of nearly 500,000 UK Biobank genotypes allowed them an opportunity to test this hypothesis.
A genomic prediction approach is quite different from the more familiar genome-wide association study (GWAS). GWAS methods test each SNP one at a time, looking for statistically significant contributions to the phenotype. In contrast, genomic prediction makes use of all SNPs at once in trying to build the best possible predictors.
The authors took the Biobank genotype and phenotype data and used a type of regression to identify the combination of SNPs that, taken together, best correlate with the trait of interest. Since only a subset of SNPs influence each trait—even the thousands of loci that control height are only a tiny fraction of the total number of SNPs identified —they also introduced a penalization factor that prevents the model from including unneeded SNPs. They were essentially trying to solve an optimization problem: identify the fewest number of variables (i.e. SNPs) that will allow for the best prediction about the outcome (i.e. trait).
Having generated their algorithm, the authors then put it to the test. They constructed models for height, heel bone density, and educational attainment, and they found that their algorithm worked well, particularly for height. For example, it produced a nearly 0.65 correlation with actual height, and predicted heights were usually within a few centimeters of actual heights. “Our predictor actually captures almost all the heritability that we could expect to find,” says Hsu.
With enough data, Hsu believes, accurate genomic prediction for complex traits will no longer be sci-fi. As more and more genotypes are obtained, Hsu predicts that this kind of prediction could be applied for most traits in as little as five years.
CITATION:
Accurate Genomic Prediction of Human Height
Louis Lello, Steven G. Avery, Laurent Tellier, Ana I. Vazquez, Gustavo de los Campos, Stephen D. H. Hsu
Genetics October 2018 210: 477-497; https://doi.org/10.1534/genetics.118.301267
Science Writing and Communications Intern, Genetics Society of America.
View all posts by Marisa Wexler »Read more in
-
Early Career Leadership Spotlight: Julio Molina Pineda
We’re taking time to get to know the members of the GSA’s Early Career Scientist Committees. Join us to learn more about our early career scientist advocates. Julio Molina Pineda Policy and Advocacy University of Arkansas Research Interest My research interests focus on using model organisms to genetically dissect complex traits related to human disease. My…
-
Early Career Leadership Spotlight: Peiwei Chen
We’re taking time to get to know the members of the GSA’s Early Career Scientist Committees. Join us to learn more about our early career scientist advocates. Peiwei Chen Accessibility Subcommittee California Institute of Technology Research Interest Far from a harmonious place, the genome is a battleground, where every bit of DNA fights for inheritance and…
-
#Dros23 GSA Poster Award winners
We are pleased to announce the GSA Poster Award winners from the 64th Annual Drosophila Research Conference! Undergraduate and graduate student members of the GSA were eligible for the awards, and a hard-working team of postdocs volunteered their time as judges. Congratulations to all! Undergraduate Students 1st Place: Sofia Karter Lopez, University of Toronto “Rab11 mediates E-cadherin recycling during…
-
Congratulations to the Fall 2022 DeLill Nasser Awardees!
GSA is pleased to announce the recipients of the DeLill Nasser Award for Professional Development in Genetics for Fall 2022! Given twice a year to graduate students and postdoctoral researchers, DeLill Nasser Awards support attendance at meetings and laboratory courses. The award is named in honor of DeLill Nasser, a long-time GSA supporter and National Science Foundation…
-
New editors join GENETICS, G3 editorial boards
Several new editors are joining the GSA Journals. We’re excited to welcome Ricardo Zayas to the GENETICS editorial board under the Molecular Genetics of Development section, and on the G3: Genes|Genomes|Genetics board, we welcome Polly Campbell, Kevin Vogel, Joe Parker, and Ricardo Mallarino. Ricardo Zayas Associate Editor Ricardo Zayas is a Professor of Biology at…
-
Worms and Flies Provide Key Clues to Medical Mystery
This article is part of a series of posts outlining the history and impact of research in experimental organisms. The series is developed in collaboration with the GSA Public Communications and Engagement Committee. By the time Bertrand Might was six months old, it was clear something was amiss. His muscles weren’t developing normally; he was…
-
Congratulations to the 2023 Early Career Leadership Program Cohort!
The Genetics Society of America (GSA) is excited to announce the latest cohort of student, postdoc, and early-career research leaders joining the Early Career Leadership Program. Participants receive training and mentoring while serving on committees charged with understanding the needs, interests, concerns, and challenges of early career scientist members of the GSA. As part of…
-
GSA LOCI: Local Outreach Community Initiatives @ GSA Conferences
Highlights: Local Outreach Community Initiatives (LOCI): The Genetics Society of America is committed to supporting the communities of the host cities of our conferences. This new year, we are excited to reconnect with our GSA community in meaningful ways within and beyond our existing programming. The GSA membership has created a caring and supportive environment…
-
New members of the GSA Board of Directors: 2023–2025
We are pleased to announce the election of five new leaders to the GSA Board of Directors: 2023 Vice President/2024 President Mariana Wolfner Distinguished Professor of Molecular Biology and Genetics and Stephen H. Weiss Presidential Fellow My research has focused on the genes and pathways that mediate sexual development and reproduction, primarily in Drosophila. From…
-
Lance David Miller: Lighting Your Own Fire by Finding the Right Resources
By Daniel J. Gironda In the Paths to Science Policy series, we talk to individuals who have a passion for science policy and are active in advocacy through their various roles and careers. The series aims to inform and guide early career scientists interested in science policy. This series is brought to you by the…
-
Graça Almeida-Porada: The Importance of Communication in a Technologically Advancing World
By Daniel J. Gironda In the Paths to Science Policy series, we talk to individuals who have a passion for science policy and are active in advocacy through their various roles and careers. The series aims to inform and guide early career scientists interested in science policy. This series is brought to you by the…