Saved in:
Bibliographic Details
Main Authors: Pathak, Kuldeep, Ahuja, Kapil, de Sturler, Eric
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.00744
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910036652982272
author Pathak, Kuldeep
Ahuja, Kapil
de Sturler, Eric
author_facet Pathak, Kuldeep
Ahuja, Kapil
de Sturler, Eric
contents 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%).
format Preprint
id arxiv_https___arxiv_org_abs_2603_00744
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ResGene-T: A Tensor-Based Residual Network Approach for Genomic Prediction
Pathak, Kuldeep
Ahuja, Kapil
de Sturler, Eric
Machine Learning
92B05, 68T09
I.2.1; J.3
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%).
title ResGene-T: A Tensor-Based Residual Network Approach for Genomic Prediction
topic Machine Learning
92B05, 68T09
I.2.1; J.3
url https://arxiv.org/abs/2603.00744