Ontario Team Uses Genetics and AI to Fight Soybean White Mold
Researchers in Ontario are combining genetic analysis, machine learning, and computer modeling to find soybean genes that resist white mold. The disease, caused by Sclerotinia sclerotiorum, thrives in cool wet conditions and can cause major yield losses. The work aims to help breeders develop varieties with stronger resistance and reduce reliance on fungicides.
The Ontario project, led by Bahram Samanfar of Agriculture and Agri-Food Canada, pairs genomic analysis with machine learning and computer simulations. Its target is Sclerotinia sclerotiorum, the fungus behind white mold, which spreads in cool, damp weather and thick soybean stands, especially at flowering.
The team has pinpointed several candidate genes and at least ten genome areas not reported before that are tied to resistance. Because many genes and environmental conditions shape infection, researchers see genetic markers as a way to help breeders screen resistant lines faster. The work is partly funded through Canada's AgriScience Program under the Sustainable Canadian Agricultural Partnership.
Soybean growers could eventually see lower fungicide costs and steadier yields if resistant varieties reach farms, especially in cool, wet seasons. Breeders and seed companies may gain faster screening tools, while consumers and livestock producers could see modest supply or price effects. Reduced fungicide reliance may offer environmental benefits, though these depend on commercial development and farmer adoption. Because the research is still identifying genes, near-term impacts may be limited.