Jingyun Luo, Ph.D.

My research focuses on the intersection of multi‑omics data analytics and intelligent design breeding in Brassica napus (rapeseed). I aim to bridge the gap between high‑dimensional omics data and precision variety design through the following integrated approaches:

Multi‑omics integration and regulatory network dissection – I integrate genomic, transcriptomic, metabolomic, proteomic, epigenomic, and phenomic data, and develop efficient fusion algorithms and feature extraction models to systematically unravel the genetic regulatory networks underlying complex traits such as disease resistance, seed quality, and yield. This enables the precise identification of core regulatory genes and molecular markers.

Intelligent breeding models and predictive algorithm development – By combining classical statistical methods with advanced machine learning techniques (including deep learning and ensemble learning), I develop genomic design models tailored for rapeseed complex traits. These models optimise genomic prediction accuracy and provide robust computational tools for early‑generation selection of breeding materials.

Design breeding platform construction and deployment – I lead the development of an integrated analytical platform that covers the entire technical chain from gene discovery, through model prediction, to variety design. A major goal is to scale up and standardise the application of intelligent design breeding, particularly for disease resistance breeding in rapeseed, thereby accelerating the release of elite varieties.