Genotype-to-Phenotype Prediction in Rice with High-Dimensional Nonlinear Features

TL;DR

This paper introduces MLFformer, a Transformer-based model with Fast Attention and MLP modules, to improve genotype-to-phenotype prediction accuracy in rice by effectively handling high-dimensional nonlinear features.

Contribution

The paper presents MLFformer, a novel Transformer architecture that enhances prediction accuracy for high-dimensional nonlinear features in genomic data.

Findings

MLFformer reduces average MAPE by 7.73% compared to vanilla Transformer.

Achieves best predictive performance in univariate and multivariate scenarios.

Effectively handles high-dimensional nonlinear features with improved efficiency.

Abstract

Genotype-to-Phenotype prediction can promote advances in modern genomic research and crop improvement, guiding precision breeding and genomic selection. However, high-dimensional nonlinear features often hinder the accuracy of genotype-to-phenotype prediction by increasing computational complexity. The challenge also limits the predictive accuracy of traditional approaches. Therefore, effective solutions are needed to improve the accuracy of genotype-to-phenotype prediction. In our paper, we propose MLFformer. MLFformer is a Transformer-based architecture that incorporates the Fast Attention mechanism and a multilayer perceptron module to handle high-dimensional nonlinear features. In MLFformer, the Fast Attention mechanism is utilized to handle computational complexity and enhance processing efficiency. In addition, the MLP structure further captures high-dimensional nonlinear features. Through experiments, the results show that MLFformer reduces the average MAPE by 7.73% compared to the vanilla Transformer. In univariate and multivariate prediction scenarios, MLFformer achieves the best predictive performance among all compared models.