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

2026-02-28

AI Summary

This study addresses the limitations in accuracy and efficiency of current methods for modeling genotype–phenotype associations in genomic prediction. The authors propose a novel approach that, for the first time, encodes genotype data as three-dimensional tensors and leverages a ResNet-18 residual network for regression-based trait prediction, effectively capturing high-order epistatic interactions among genes. By integrating deep residual learning with convolutional architecture, the method achieves substantial improvements in predictive performance. Systematic evaluation across ten traits in three crop species demonstrates that the proposed framework outperforms seven state-of-the-art methods, yielding accuracy gains ranging from 14.51% to 41.51%. These results highlight its superior predictive power and computational efficiency, offering a promising advancement for genomic selection applications.

Technology Category

• Machine Learning: Matrix & Tensor Methods
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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%).

Problem

• Genomic Prediction
• Genotype-Phenotype Correlation
• Deep Learning
• Tensor Representation
• Crop Traits

Innovation

• Tensor-based representation
• Residual Network
• Genomic Prediction
• 3D genotype encoding
• Deep learning