Rxivist logo

A multiple-trait Bayesian Lasso for genome-enabled analysis and prediction of complex traits

By DANIEL GIANOLA, Rohan L. Fernando

Posted 22 Nov 2019
bioRxiv DOI: 10.1101/852749 (published DOI: 10.1534/genetics.119.302934)

A multiple-trait Bayesian LASSO (MBL) for genome-based analysis and prediction of quantitative traits is presented and applied to two real data sets. The data-generating model is a multivariate linear Bayesian regression on possibly a huge number of molecular markers, and with a Gaussian residual distribution posed. Each (one per marker) of the T x 1 vectors of regression coefficients (T: number of traits) is assigned the same T-variate Laplace prior distribution, with a null mean vector and unknown scale matrix SIGMA. The multivariate prior reduces to that of the standard univariate Bayesian LASSO when T=1. The covariance matrix of the residual distribution is assigned a multivariate Jeffreys prior and SIGMA is given an inverse-Wishart prior. The unknown quantities in the model are learned using a Markov chain Monte Carlo sampling scheme constructed using a scale-mixture of normal distributions representation. MBL is demonstrated in a bivariate context employing two publicly available data sets using a bivariate genomic best linear unbiased prediction model (GBLUP) for benchmarking results. The first data set is one where wheat grain yields in two different environments are treated as distinct traits. The second data set comes from genotyped Pinus trees with each individual was measured for two traits, rust bin and gall volume. In MBL, the bivariate marker effects are shrunk differentially, i.e., "short" vectors are more strongly shrunk towards the origin than in GBLUP; conversely, "long" vectors are shrunk less. A predictive comparison was carried out as well where, in wheat, the comparators of MBL where bivariate GBLUP and bivariate Bayes Cπ, a variable selection procedure. A training-testing layout was used, with 100 random reconstructions of training and testing sets. For the wheat data, all methods produced similar predictions. In Pinus, MBL gave better predictions than either a Bayesian bivariate GBLUP or the single trait Bayesian LASSO. MBL has been implemented in the Julia language package JWAS and is now available for the scientific community to explore with different traits, species, and environments. It is well known that there is no universally best prediction machine and MBL represents a new piece in the armamentarium for genome-enabled analysis and prediction of complex traits.

Download data

  • Downloaded 370 times
  • Download rankings, all-time:
    • Site-wide: 80,715
    • In genetics: 3,564
  • Year to date:
    • Site-wide: 121,969
  • Since beginning of last month:
    • Site-wide: 142,431

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide