ResGene-T: A Tensor-Based Residual Network Approach for Genomic Prediction

TL;DR

This paper introduces ResGene-T, a tensor-based deep learning model for genomic prediction that outperforms existing methods by effectively capturing biological interactions through a novel 3D tensor representation.

Contribution

The paper proposes a novel 3D tensor representation for genotype data and integrates it with ResNet-18, significantly improving prediction accuracy in genomic prediction tasks.

Findings

ResGene-T outperforms seven popular models with 14.51% to 41.51% gains.

The 3D tensor representation enhances biological interaction modeling.

ResGene-T achieves near state-of-the-art performance with improved efficiency.

Abstract

In this work, we propose a new deep learning model for Genomic Prediction (GP), which involves correlating genotypic data with phenotypic. The genotypes are typically fed as a sequence of characters to the 1D-Convolution Neural Network layer of the underlying deep learning model. Inspired by earlier work that represented genotype as a 2D-image for genotype-phenotype classification, we extend this idea to GP, which is a regression task. We use a ResNet-18 as the underlying architecture, and term this model as ResGene-2D. Although the 2D-image representation captures biological interactions well, it requires all the layers of the model to do so. This limits training efficiency. Thus, as seen in the earlier work that proposed a 2D-image representation, our ResGene-2D performs almost the same as other models (3% improvement). To overcome this, we propose a novel idea of converting the 2D-image into a 3D/ tensor and feed this to the ResNet-18 architecture, and term this model as ResGene-T. We evaluate our proposed models on three crop species having ten phenotypic traits and compare it with seven most popular models (two statistical, two machine learning, and three deep learning). ResGene-T performs the best among all these seven methods (gains from 14.51% to 41.51%).