A Ranking Approach to Genomic Selection

Abstract

BackgroundGenomic selection (GS) is a recent selective breeding method which uses predictive models based on whole-genome molecular markers. Until now, existing studies formulated GS as the problem of modeling an individual’s breeding value for a particular trait of interest, i.e., as a regression problem. To assess predictive accuracy of the model, the Pearson correlation between observed and predicted trait values was used.ContributionsIn this paper, we propose to formulate GS as the problem of ranking individuals according to their breeding value. Our proposed framework allows us to employ machine learning methods for ranking which had previously not been considered in the GS literature. To assess ranking accuracy of a model, we introduce a new measure originating from the information retrieval literature called normalized discounted cumulative gain (NDCG). NDCG rewards more strongly models which assign a high rank to individuals with high breeding value. Therefore, NDCG reflects a prerequisite objective in selective breeding: accurate selection of individuals with high breeding value.ResultsWe conducted a comparison of 10 existing regression methods and 3 new ranking methods on 6 datasets, consisting of 4 plant species and 25 traits. Our experimental results suggest that tree-based ensemble methods including McRank, Random Forests and Gradient Boosting Regression Trees achieve excellent ranking accuracy. RKHS regression and RankSVM also achieve good accuracy when used with an RBF kernel. Traditional regression methods such as Bayesian lasso, wBSR and BayesC were found less suitable for ranking. Pearson correlation was found to correlate poorly with NDCG. Our study suggests two important messages. First, ranking methods are a promising research direction in GS. Second, NDCG can be a useful evaluation measure for GS.

Genomic Prediction of Pumpkin Hybrid Performance

“…There is still room for improvement to develop methods for evaluating genomic prediction for ordinal traits. The ranking method proposed by Blondel et al (2015) could be a promising one.…”

DeepGS: Predicting phenotypes from genotypes using Deep Learning

“…This process was repeated 10 times until each group was used once for testing; the predicted phenotypic trait values were finally combined for performance evaluation. The prediction performance of each GS model for selecting individuals with high phenotypic values is assessed by the measure: the mean normalized discounted cumulative gain value (MNV) (Blondel, et al, 2015). Given n individuals, the predicted and observed phenotypic values form an n × 2 matrix of score pairs (X, Y).…”

Sensitivity analysis based ranking reveals unknown biological hypotheses for down regulated genes in time buffer during administration of PORCN-WNT inhibitor ETC-1922159 in CRC†

“…Finally, the current work tests the effectiveness of the variance based (SOBOL) sensitivity indices apropos the density and kernel based (HSIC) sensitivity indices. Finally, [92] provides a range of comparison for 10 different regression methods and a score to measure the models. Compared to the frame provided in [92], the current pipeline takes into account biological information an converts into sensitivity scores and uses them as discriminative features to provide rankings.…”

“…Finally, [92] provides a range of comparison for 10 different regression methods and a score to measure the models. Compared to the frame provided in [92], the current pipeline takes into account biological information an converts into sensitivity scores and uses them as discriminative features to provide rankings. Thus the proposed method is algorithm independent.…”