Large-scale crop dataset and deep learning-based multi-modal fusion framework for more accurate G×E genomic prediction

Qixiang Zou, Shuaishuai Tai, Qianguang Yuan, Yating Nie, Heping Gou, Longfei Wang, Chuanxiu Li, Yi Jing, Fangchun Dong, Zhen Yue, Yi Rong, Xiaodong Fang, Shengwu Xiong

Abstract: Highlights•Large-scale genotype-environment-phenotype data are organized for genomic prediction.•We design a deep learning-based multi-modal fusion framework for genomic prediction.•Bi-LSTM and Transformer are used to process time-series environmental variables.•Extensive experiments indicate the effectiveness and superiority of our framework.•The prediction mechanism of our method is explored in the interpretability analysis.

External IDs:dblp:journals/cea/ZouTYNGWLJDYRFX25