Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge
A major goal of large-scale genomics projects is to enable the use of data from high-throughput experimental methods to predict complex phenotypes such as disease susceptibility. The DREAM5 Systems Genetics B Challenge solicited algorithms to predict soybean plant resistance to the pathogen Phytopht...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Public Library of Science
2012
|
| Online Access: | http://hdl.handle.net/1721.1/69039 https://orcid.org/0000-0002-2724-7228 |
| _version_ | 1811075352267587584 |
|---|---|
| author | Loh, Po-Ru Tucker, George Jay Berger, Bonnie |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Loh, Po-Ru Tucker, George Jay Berger, Bonnie |
| author_sort | Loh, Po-Ru |
| collection | MIT |
| description | A major goal of large-scale genomics projects is to enable the use of data from high-throughput experimental methods to predict complex phenotypes such as disease susceptibility. The DREAM5 Systems Genetics B Challenge solicited algorithms to predict soybean plant resistance to the pathogen Phytophthora sojae from training sets including phenotype, genotype, and gene expression data. The challenge test set was divided into three subcategories, one requiring prediction based on only genotype data, another on only gene expression data, and the third on both genotype and gene expression data. Here we present our approach, primarily using regularized regression, which received the best-performer award for subchallenge B2 (gene expression only). We found that despite the availability of 941 genotype markers and 28,395 gene expression features, optimal models determined by cross-validation experiments typically used fewer than ten predictors, underscoring the importance of strong regularization in noisy datasets with far more features than samples. We also present substantial analysis of the training and test setup of the challenge, identifying high variance in performance on the gold standard test sets. |
| first_indexed | 2024-09-23T10:04:22Z |
| format | Article |
| id | mit-1721.1/69039 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:04:22Z |
| publishDate | 2012 |
| publisher | Public Library of Science |
| record_format | dspace |
| spelling | mit-1721.1/690392022-09-26T15:32:25Z Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge Loh, Po-Ru Tucker, George Jay Berger, Bonnie Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Mathematics Berger Leighton, Bonnie Loh, Po-Ru Tucker, George Jay Berger, Bonnie A major goal of large-scale genomics projects is to enable the use of data from high-throughput experimental methods to predict complex phenotypes such as disease susceptibility. The DREAM5 Systems Genetics B Challenge solicited algorithms to predict soybean plant resistance to the pathogen Phytophthora sojae from training sets including phenotype, genotype, and gene expression data. The challenge test set was divided into three subcategories, one requiring prediction based on only genotype data, another on only gene expression data, and the third on both genotype and gene expression data. Here we present our approach, primarily using regularized regression, which received the best-performer award for subchallenge B2 (gene expression only). We found that despite the availability of 941 genotype markers and 28,395 gene expression features, optimal models determined by cross-validation experiments typically used fewer than ten predictors, underscoring the importance of strong regularization in noisy datasets with far more features than samples. We also present substantial analysis of the training and test setup of the challenge, identifying high variance in performance on the gold standard test sets. National Science Foundation (U.S.). Graduate Research Fellowship Program National Defense Science and Engineering Graduate Fellowship 2012-02-08T17:16:30Z 2012-02-08T17:16:30Z 2011-12 2011-04 Article http://purl.org/eprint/type/JournalArticle 1932-6203 http://hdl.handle.net/1721.1/69039 Loh, Po-Ru, George Tucker, and Bonnie Berger. “Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge.” Ed. Mark Isalan. PLoS ONE 6.12 (2011): e29095. Web. 8 Feb. 2012. https://orcid.org/0000-0002-2724-7228 en_US http://dx.doi.org/10.1371/journal.pone.0029095 PLoS ONE Creative Commons Attribution http://creativecommons.org/licenses/by/2.5/ application/pdf Public Library of Science PLoS |
| spellingShingle | Loh, Po-Ru Tucker, George Jay Berger, Bonnie Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge |
| title | Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge |
| title_full | Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge |
| title_fullStr | Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge |
| title_full_unstemmed | Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge |
| title_short | Phenotype Prediction Using Regularized Regression on Genetic Data in the DREAM5 Systems Genetics B Challenge |
| title_sort | phenotype prediction using regularized regression on genetic data in the dream5 systems genetics b challenge |
| url | http://hdl.handle.net/1721.1/69039 https://orcid.org/0000-0002-2724-7228 |
| work_keys_str_mv | AT lohporu phenotypepredictionusingregularizedregressionongeneticdatainthedream5systemsgeneticsbchallenge AT tuckergeorgejay phenotypepredictionusingregularizedregressionongeneticdatainthedream5systemsgeneticsbchallenge AT bergerbonnie phenotypepredictionusingregularizedregressionongeneticdatainthedream5systemsgeneticsbchallenge |