@article{MbebiTongNikoloski2021,
  author    = {Mbebi, Alain J. and Tong, Hao and Nikoloski, Zoran},
  title     = {L-2,L-1-norm regularized multivariate regression model with applications to genomic prediction},
  series = {Bioinformatics},
  volume    = {37},
  journal   = {Bioinformatics},
  number    = {18},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1367-4803},
  doi       = {10.1093/bioinformatics/btab212},
  pages     = {2896 -- 2904},
  year      = {2021},
  abstract  = {Motivation: Genomic selection (GS) is currently deemed the most effective approach to speed up breeding of agricultural varieties. It has been recognized that consideration of multiple traits in GS can improve accuracy of prediction for traits of low heritability. However, since GS forgoes statistical testing with the idea of improving predictions, it does not facilitate mechanistic understanding of the contribution of particular single nucleotide polymorphisms (SNP). Results: Here, we propose a L-2,L-1-norm regularized multivariate regression model and devise a fast and efficient iterative optimization algorithm, called L-2,L-1-joint, applicable in multi-trait GS. The usage of the L-2,L-1-norm facilitates variable selection in a penalized multivariate regression that considers the relation between individuals, when the number of SNPs is much larger than the number of individuals. The capacity for variable selection allows us to define master regulators that can be used in a multi-trait GS setting to dissect the genetic architecture of the analyzed traits. Our comparative analyses demonstrate that the proposed model is a favorable candidate compared to existing state-of-the-art approaches. Prediction and variable selection with datasets from Brassica napus, wheat and Arabidopsis thaliana diversity panels are conducted to further showcase the performance of the proposed model.},
  language  = {en}
}
@article{MbebiBreitlerBordeauxetal.2022,
  author    = {Mbebi, Alain J. and Breitler, Jean-Christophe and Bordeaux, M'elanie and Sulpice, Ronan and McHale, Marcus and Tong, Hao and Toniutti, Lucile and Castillo, Jonny Alonso and Bertrand, Benoit and Nikoloski, Zoran},
  title     = {A comparative analysis of genomic and phenomic predictions of growth-related traits in 3-way coffee hybrids},
  series = {G3: Genes, genomes, genetics},
  volume    = {12},
  journal   = {G3: Genes, genomes, genetics},
  number    = {9},
  publisher = {Genetics Soc. of America},
  address   = {Pittsburgh, PA},
  issn      = {2160-1836},
  doi       = {10.1093/g3journal/jkac170},
  pages     = {11},
  year      = {2022},
  abstract  = {Genomic prediction has revolutionized crop breeding despite remaining issues of transferability of models to unseen environmental conditions and environments. Usage of endophenotypes rather than genomic markers leads to the possibility of building phenomic prediction models that can account, in part, for this challenge. Here, we compare and contrast genomic prediction and phenomic prediction models for 3 growth-related traits, namely, leaf count, tree height, and trunk diameter, from 2 coffee 3-way hybrid populations exposed to a series of treatment-inducing environmental conditions. The models are based on 7 different statistical methods built with genomic markers and ChlF data used as predictors. This comparative analysis demonstrates that the best-performing phenomic prediction models show higher predictability than the best genomic prediction models for the considered traits and environments in the vast majority of comparisons within 3-way hybrid populations. In addition, we show that phenomic prediction models are transferrable between conditions but to a lower extent between populations and we conclude that chlorophyll a fluorescence data can serve as alternative predictors in statistical models of coffee hybrid performance. Future directions will explore their combination with other endophenotypes to further improve the prediction of growth-related traits for crops.},
  language  = {en}
}