We seamlessly integrate image-based phenotyping and ML-based features extraction of important traits. We conduct genome wide association (GWA) studies and genomic prediction analyses in soybean using a large diverse germplasm panel and leverage ML-based image-phenotyping pipelines that are developed in-house (due to a lack of community resource). The workflow for phenotyping (image capture → data storage and curation → trait extraction → ML-enabled rating is designed and efficiently to set up the software/hardware solutions, which are then applied for genome wide studies. This approach has more reliability and advantage of ML-enabled image-phenotyping pipeline by identifying previously reported locus and novel locus. We have also reported a significant improvement of the genomic prediction accuracy by integrating phenomics and genomics, which was one of the first such attempts in soybean.

We also conduct genome wide studies on traits of importance using traditional phenotyping. We have published GWAS related papers on charcoal rot, white mold, sudden death syndrome, iron deficiency chlorosis, soybean aphid, and other traits. We also combine GWAS with genome wide epistatic studies for enhanced genetic understanding. Where available, we leverage RNA-seq data for validation purposes. We also perform genomic prediction on germplasm collection to identify useful and resistant sources of disease resistance in the USDA soybean germplasm collection. We work on important yield limiting stresses, so that results are application in the breeding program. Additionally, we work on domestication related traits.

Outcomes: Seamlessly integrated image-based phenotyping and ML-based features extraction of important traits, which allows improved accuracy and precision (reduces rater variability) for data collection as well as in crop production. We identified new sources of resistance (accessions) from the soybean germplasm collection, reported trait associated molecular markers, and we reported putative candidate genes associated with functions controlling plant defense response to elucidate the mode of resistance. Using multiple genetic analyses, we disentangled complex information on mechanisms that will allow breeding strategies for important stress traits. 

Primary collaborators: Dr. Arti Singh, Dr. D. Mueller.
Funding: Iowa Soybean Association, R F Baker Center for Plant Breeding, Monsanto Chair in Soybean Breeding, Iowa Soybean Research Center.

Related Publications:

• Zhang J, AK Singh. 2020. Genetic control and geo-climate adaptation of pod dehiscence provide novel insights into the soybean domestication. G3. V 10: 545-554.
• Assefa T, J Zhang, RV Chowda-Reddy, AN Moran Lauter, A Singh, JA O’Rourke, MA Graham, AK Singh. 2020. Deconstructing the genetic architecture of iron deficiency chlorosis in soybean using genome-wide approaches. BMC Plant Biology. v20, Article number: 42.
• Natukunda MI, KA Parmley, JD Hohenstein, T Assefa, J Zhang, GC MacIntosh, AK Singh. 2019. Identification and Genetic Characterization of Soybean Accessions Exhibiting Antibiosis and Antixenosis Resistance to Aphis glycines (Hemiptera: Aphididae). Journal of Economic Entomology. 112(3): 1428-1438.
• Zhang J, HS Naik, T Assefa, S Sarkar, RV Chowda-Reddy, A Singh, B Ganapathysubramanian, AK Singh. 2017 Computer vision and machine learning for robust phenotyping in genome-wide studies. Scientific Reports, 7, Article number 44048.
• Peixoto LA, TC Moellers, J Zhang, AJ Lorenz, LL Bhering, WD Beavis, AK Singh. 2017. Leveraging Genomic Prediction to Scan Germplasm Collection for Crop Improvement. PLOS One 12 (6): e0179191.
• Moellers TC, A Singh, J Zhang, J Brungardt, M Kabbage, DS Mueller, CR Grau, A Ranjan, DL Smith, RV Chowda-Reddy, AK Singh. 2017. Main and epistatic loci studies in soybean for Sclerotinia sclerotiorum resistance reveal multiple modes of resistance in multi-environments. Scientific Reports 7, Article number: 3554.
• Coser SM, RV Chowdareddy, J Zhang, DS Mueller, A Mengistu, K Wise, TW Allen, A Singh, AK Singh. 2017. Genetic architecture of Charcoal Rot (Macrophomina phaseolina) Resistance in Soybean revealed using a diverse panel. Frontiers in Plant Science. 8:1626.
• Zhang J, A Singh, D Mueller, AK Singh. 2015. Genome-wide association and epistasis studies unravel the genetic architecture of sudden death syndrome resistance in soybean. The Plant Journal. 84(6):1124-36.