Dual-extraction modeling:A multi-modal deeplearning architecture for phenotypic prediction and functional gene mining of complex traits

作     者：Yanlin Ren Chenhua Wu He Zhou Xiaona Hu Zhenyan Miao 

作者机构：State Key Laboratory for Crop Stress Resistance and High-Efficiency ProductionCenter of BioinformaticsCollege of Life SciencesNorthwest A&F UniversityYanglingShaanxi 712100China College of Chemistry&PharmacyNorthwest A&F UniversityYanglingShaanxi 712100China Key Laboratory of Biology and Genetics Improvement of Maize in Arid Area of Northwest RegionMinistry of AgricultureNorthwest A&F UniversityYanglingShaanxi 712100China 

出 版 物：《Plant Communications》 (植物通讯（英文）)

年 卷 期：2024年第5卷第9期

页      面：54-71页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(32370723 32000410) 

主　　题：deep learning complex traits multi-omics phenotypic prediction gene mining 

摘      要：Despite considerable advances in extracting crucial insights from bio-omics data to unravel the intricate mechanisms underlying complex traits,the absence of a universal multi-modal computational tool with robust interpretability for accurate phenotype prediction and identification of trait-associated genes remains a *** study introduces the dual-extraction modeling(DEM)approach,a multi-modal deep-learning architecture designed to extract representative features from heterogeneous omics datasets,enabling the prediction of complex trait *** comprehensive benchmarking experiments,we demonstrate the efficacy of DEM in classification and regression prediction of complex *** consistently exhibits superior accuracy,robustness,generalizability,and ***,we establish its effectiveness in predicting pleiotropic genes that influence both flowering time and rosette leaf number,underscoring its commendable *** addition,we have developed user-friendly software to facilitate seamless utilization of DEM’s *** summary,this study presents a state-of-the-art approach with the ability to effectively predict qualitative and quantitative traits and identify functional genes,confirming its potential as a valuable tool for exploring the genetic basis of complex traits.