Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kuldeep Pathak, Kapil Ahuja, Eric de Sturler

TL;DR

This work proposes a new deep learning model for Genomic Prediction (GP), which involves correlating genotypic data with phenotypic traits and proposes 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.

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%).

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

TL;DR

This work proposes a new deep learning model for Genomic Prediction (GP), which involves correlating genotypic data with phenotypic traits and proposes 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.

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%).
Paper Structure (16 sections, 3 equations, 6 figures, 8 tables)

This paper contains 16 sections, 3 equations, 6 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Statistical Methods
  4. Machine Learning Methods
  5. Deep Learning Methods
  6. Our proposed ResGene model
  7. Structure of the Data
  8. ResGene-2D
  9. ResGene-T
  10. Result
  11. Datasets
  12. Baseline Models
  13. Tuning and Setup
  14. Evaluation Metric
  15. Performance
  16. ...and 1 more sections

Figures (6)

  • Figure 1: Pipeline for genotype to tensor image transformation. (a) Original genotype represented as a sequence of characters. (b) Conversion of the genotype sequence into a 2D-image. (c) Transformation of the 2D-image into a tensor representation.
  • Figure 2: Biological interaction among different SNPs.
  • Figure 3: ResNet-18 architecture.
  • Figure 4: Model Performance on Soybean Dataset.
  • Figure 5: Model Performance on Rice Dataset.
  • ...and 1 more figures