Review

Deep Learning Algorithms for Complex Traits Genomic Prediction

Volume: 4 Number: 2 December 27, 2021
EN TR

Deep Learning Algorithms for Complex Traits Genomic Prediction

Abstract

The underlying perception of genomic selection (GS) is to use genome-wide from DNA sequence (“SNP markers”) along with phenotypes from an observed population to make prediction for the phenotypic outcomes of untested individuals in crop and livestock breeding programs. GS was firstly described by Meuwissen et al.(2001) in dairy cattle to identify genetically superior animals at an early age. The aim was to capture specific genes across the whole genome that are associated with desired traits. The major challenge in using GS programs is to predict the effect of many SNP markers using phenotypic information from a few individuals (aka small n big p problem, or p >> n). Many approaches including naïve and scaled elastic net, ridge regression BLUP Bayesian approaches (BayesA, BayesB, BayesCπ, BayesDπ) LASSO, Support Vector Regression have been conducted to address the small n big p (aka, p >> n) problem. These methods all perform well for (p>>n) by using linear approximation to set a functional relationship between genotypes and phenotypes. However, these methods may not fully capture non-linear effects which are possible to be crucial for complex traits. To deal with this limitation, many methods including neural networks (NN) were recommended to cover non-linearity for GS. Artificial NNs (ANNs) for GS was first presented by Okut et al. (2011) who establish a fully connected regularized multi-layer ANN (MLANN) comprising one hidden layer to predict the body mass index (BMI) in mice using dense molecular markers. Since then, rather complex ANNs approaches have been applied including deep learning (DL) networks. The different DL algorithms have their own advantages to deal with specific problems in complex trait GS. Four different major classes of DL approaches such as fully connected deep learning artificial neural networks (DL-MLANN), recurrent neural networks (RNN), convolutional neural networks (CNN) and long-short term memory (LSTM) and some variation of these network architectures will be summarized here.

Keywords

References

  1. Alkhudaydi, T., Reynolds, D., Zhou, J., Iglesia, B., and Griffiths, S., 2019. An exploration of deep-learning based phenotypic analysis to detect spike regions in field conditions for UK bread wheat. Plant Phenom.7368761. doi: 10.34133/2019/7368761.
  2. Azodi, BC., McCarren, A., Roantree, M., de los Campos, G. and Shiu, SH., 2019. Benchmarking Parametric and Machine Learning Models for Genomic Prediction of Complex Traits. G3-Genes, PMID: 31533955, PMCID: PMC6829122, DOI: 10.1534/g3.119.400498.
  3. Colah, C. Understating LSTM Network 2021. https://colah.github.io/posts/2015-08-Understanding-LSTMs/
  4. De los Campos G, Gianola D, Rosa GJM, Weigel KA, Crossa J., 2010 Semi-parametri genomic-enabled Prediction of genetic values using reproducing kernel Hilbert spaces methods. Genet Res. 92(4):295–308. Available from: http://dx.doi.org/10.1017/S0016672310000285.
  5. Koumakis, L., 2020. Deep learning models in genomics; are we there yet? Computational and Structural Biotechnology Journal 18, 1466–1473. https://doi.org/10.1016/j.csbj.2020.06.017.
  6. Liu, J., Li, J., Wang, H., and Yan, J. 2020. Application of deep learning in genomics. Sci China Life Sci 63, 1860–1878. https://doi.org/10.1007/s11427-020-1804-5.
  7. Lipton, C. Z., Berkowitz, J. and Elkan, C. A Critical 2021. Review of Recurrent Neural Networks for Sequence Learning. arXiv:1506.00019v4.
  8. Maldonado C, Mora-Poblete F, Contreras-Soto RI, Ahmar S, Chen J-T, do Amaral Júnior AT and Scapim CA., 2020. Genome-Wide Prediction of Complex Traits in Two Outcrossing Plant Species Through Deep Learning and Bayesian Regularized Neural Network. Front. Plant Sci. 11:593897. doi: 10.3389/fpls.2020.593897.

Details

Primary Language

English

Subjects

Agricultural Engineering

Journal Section

Review

Publication Date

December 27, 2021

Submission Date

December 22, 2021

Acceptance Date

December 29, 2021

Published in Issue

Year 2021 Volume: 4 Number: 2

APA
Okut, H. (2021). Deep Learning Algorithms for Complex Traits Genomic Prediction. Hayvan Bilimi Ve Ürünleri Dergisi, 4(2), 225-239. https://doi.org/10.51970/jasp.1039713
AMA
1.Okut H. Deep Learning Algorithms for Complex Traits Genomic Prediction. JASP. 2021;4(2):225-239. doi:10.51970/jasp.1039713
Chicago
Okut, Hayrettin. 2021. “Deep Learning Algorithms for Complex Traits Genomic Prediction”. Hayvan Bilimi Ve Ürünleri Dergisi 4 (2): 225-39. https://doi.org/10.51970/jasp.1039713.
EndNote
Okut H (December 1, 2021) Deep Learning Algorithms for Complex Traits Genomic Prediction. Hayvan Bilimi ve Ürünleri Dergisi 4 2 225–239.
IEEE
[1]H. Okut, “Deep Learning Algorithms for Complex Traits Genomic Prediction”, JASP, vol. 4, no. 2, pp. 225–239, Dec. 2021, doi: 10.51970/jasp.1039713.
ISNAD
Okut, Hayrettin. “Deep Learning Algorithms for Complex Traits Genomic Prediction”. Hayvan Bilimi ve Ürünleri Dergisi 4/2 (December 1, 2021): 225-239. https://doi.org/10.51970/jasp.1039713.
JAMA
1.Okut H. Deep Learning Algorithms for Complex Traits Genomic Prediction. JASP. 2021;4:225–239.
MLA
Okut, Hayrettin. “Deep Learning Algorithms for Complex Traits Genomic Prediction”. Hayvan Bilimi Ve Ürünleri Dergisi, vol. 4, no. 2, Dec. 2021, pp. 225-39, doi:10.51970/jasp.1039713.
Vancouver
1.Hayrettin Okut. Deep Learning Algorithms for Complex Traits Genomic Prediction. JASP. 2021 Dec. 1;4(2):225-39. doi:10.51970/jasp.1039713

Cited By


Indexed by:

Google Scholar        Directory of Research Journals Indexing       idealonline        19413        BASE (Bielefeld Academic Search Engine)        

Index Copernicus        Cite Factor        JournalTOCs

InfoBase Index        SIS Scientific Group        Food and Agriculture Organization of the United Nations

International Peer Reviewed Journal)
The journal doesn’t have APC or any submission charges.

Creative Commons License