Prediction of Multiple-Trait and Multiple-Environment Genomic Data Using Recommender Systems

G3: Genes, Genomes, Genetics

article

Osval A. Montesinos-López¹  Abelardo Montesinos-López²  José Crossa³  José C. Montesinos-López⁴  David Mota-Sanchez⁵  Fermín Estrada-González¹  Jussi Gillberg⁶  Ravi Singh³  Suchismita Mondal³  Philomin Juliana³ 

[1] Facultad de Telemática, Universidad de Colima, 28040 Colima, México;Departamento de Matemáticas, Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, 44430 Jalisco, México;International Maize and Wheat Improvement Center (CIMMYT), Apdo. Postal 6-641, 06600 México City, México;Departamento de Estadística, Centro de Investigación en Matemáticas (CIMAT), 36240 Guanajuato, México;Department of Entomology,Michigan State University, East Lancing, Michigan 48824;Department of Computer Science, Aalto University, FI00076,Finland

关键词: genomic information;    item-based collaborative filtering;    matrix factorization;    multi-trait;    genotype;    environment interaction;    prediction accuracy;    collaborative filtering;    GenPred;    Shared Data Resources;    Genomic Selection;   

DOI  :  10.1534/g3.117.300309

学科分类：社会科学、人文和艺术（综合）

来源: Genetics Society of America

【 摘 要 】

In genomic-enabled prediction, the task of improving the accuracy of the prediction of lines in environments is difficult because the available information is generally sparse and usually has low correlations between traits. In current genomic selection, although researchers have a large amount of information and appropriate statistical models to process it, there is still limited computing efficiency to do so. Although some statistical models are usually mathematically elegant, many of them are also computationally inefficient, and they are impractical for many traits, lines, environments, and years because they need to sample from huge normal multivariate distributions. For these reasons, this study explores two recommender systems: item-based collaborative filtering (IBCF) and the matrix factorization algorithm (MF) in the context of multiple traits and multiple environments. The IBCF and MF methods were compared with two conventional methods on simulated and real data. Results of the simulated and real data sets show that the IBCF technique was slightly better in terms of prediction accuracy than the two conventional methods and the MF method when the correlation was moderately high. The IBCF technique is very attractive because it produces good predictions when there is high correlation between items (environment–trait combinations) and its implementation is computationally feasible, which can be useful for plant breeders who deal with very large data sets.

【 授权许可】

CC BY|CC BY-NC