CSGDN: Contrastive Signed Graph Diffusion Network for Predicting Crop Gene-phenotype Associations

TL;DR

This paper introduces CSGDN, a contrastive signed graph diffusion network that improves prediction of gene-phenotype associations in crops by reducing noise and requiring fewer samples.

Contribution

The paper proposes a novel contrastive learning approach with signed graph diffusion to enhance robustness and accuracy in gene-phenotype link prediction.

Findings

Outperforms state-of-the-art methods by up to 9.28% AUC in crop datasets.

Effectively reduces noise and interference in gene-phenotype association prediction.

Demonstrates robustness with fewer training samples.

Abstract

Positive and negative association prediction between gene and phenotype helps to illustrate the underlying mechanism of complex traits in organisms. The transcription and regulation activity of specific genes will be adjusted accordingly in different cell types, developmental stages, and physiological states. There are the following two problems in obtaining the positive/negative associations between gene and trait: 1) High-throughput DNA/RNA sequencing and phenotyping are expensive and time-consuming due to the need to process large sample sizes; 2) experiments introduce both random and systematic errors, and, meanwhile, calculations or predictions using software or models may produce noise. To address these two issues, we propose a Contrastive Signed Graph Diffusion Network, CSGDN, to learn robust node representations with fewer training samples to achieve higher link prediction accuracy. CSGDN employs a signed graph diffusion method to uncover the underlying regulatory associations between genes and phenotypes. Then, stochastic perturbation strategies are used to create two views for both original and diffusive graphs. Lastly, a multi-view contrastive learning paradigm loss is designed to unify the node presentations learned from the two views to resist interference and reduce noise. We conduct experiments to validate the performance of CSGDN on three crop datasets: Gossypium hirsutum, Brassica napus, and Triticum turgidum. The results demonstrate that the proposed model outperforms state-of-the-art methods by up to 9.28% AUC for link sign prediction in G. hirsutum dataset.