Key message: This review provides a comprehensive atlas of QTLs, genes, and alleles conferring resistance to 28 important diseases in all major soybean production regions in the world. Breeding disease-resistant soybean [Glycine max (L.) Merr.] varieties is a common goal for soybean breeding programs to ensure the sustainability and growth of soybean production worldwide. However, due to global climate change, soybean breeders are facing strong challenges to defeat diseases. Marker-assisted selection and genomic selection have been demonstrated to be successful methods in quickly integrating vertical resistance or horizontal resistance into improved soybean varieties, where vertical resistance refers to R genes and major effect QTLs, and horizontal resistance is a combination of major and minor effect genes or QTLs. This review summarized more than 800 resistant loci/alleles and their tightly linked markers for 28 soybean diseases worldwide, caused by nematodes, oomycetes, fungi, bacteria, and viruses. The major breakthroughs in the discovery of disease resistance gene atlas of soybean were also emphasized which include: (1) identification and characterization of vertical resistance genes reside rhg1 and Rhg4 for soybean cyst nematode, and exploration of the underlying regulation mechanisms through copy number variation and (2) map-based cloning and characterization of Rps11 conferring resistance to 80% isolates of Phytophthora sojae across the USA. In this review, we also highlight the validated QTLs in overlapping genomic regions from at least two studies and applied a consistent naming nomenclature for these QTLs. Our review provides a comprehensive summary of important resistant genes/QTLs and can be used as a toolbox for soybean improvement. Finally, the summarized genetic knowledge sheds light on future directions of accelerated soybean breeding and translational genomics studies.

Key message: Incorporating feature-engineered environmental data into machine learning-based genomic prediction models is an efficient approach to indirectly model genotype-by-environment interactions. Complementing phenotypic traits and molecular markers with high-dimensional data such as climate and soil information is becoming a common practice in breeding programs. This study explored new ways to combine non-genetic information in genomic prediction models using machine learning. Using the multi-environment trial data from the Genomes To Fields initiative, different models to predict maize grain yield were adjusted using various inputs: genetic, environmental, or a combination of both, either in an additive (genetic-and-environmental; G+E) or a multiplicative (genotype-by-environment interaction; GEI) manner. When including environmental data, the mean prediction accuracy of machine learning genomic prediction models increased up to 7% over the well-established Factor Analytic Multiplicative Mixed Model among the three cross-validation scenarios evaluated. Moreover, using the G+E model was more advantageous than the GEI model given the superior, or at least comparable, prediction accuracy, the lower usage of computational memory and time, and the flexibility of accounting for interactions by construction. Our results illustrate the flexibility provided by the ML framework, particularly with feature engineering. We show that the feature engineering stage offers a viable option for envirotyping and generates valuable information for machine learning-based genomic prediction models. Furthermore, we verified that the genotype-by-environment interactions may be considered using tree-based approaches without explicitly including interactions in the model. These findings support the growing interest in merging high-dimensional genotypic and environmental data into predictive modeling.

This review summarizes the history and current state of the known genetic basis for soybean resistance to Soybean mosaic virus (SMV), and examines how the integration of molecular markers has been utilized in breeding for crop improvement. SVM causes yield loss and seed quality reduction in soybean based on the SMV strain and the host genotype. Understanding the molecular underpinnings of SMV–soybean interactions and the genes conferring resistance to SMV has been a focus of intense research interest for decades. Soybean reactions are classified into three main responses: resistant, necrotic, or susceptible. Significant progress has been achieved that has greatly increased the understanding of soybean germplasm diversity, differential reactions to SMV strains, genotype–strain interactions, genes/alleles conferring specific reactions, and interactions among resistance genes and alleles. Many studies that aimed to uncover the physical position of resistance genes have been published in recent decades, collectively proposing different candidate genes. The studies on SMV resistance loci revealed that the resistance genes are mainly distributed on three chromosomes. Resistance has been pyramided in various combinations for durable resistance to SMV strains. The causative genes are still elusive despite early successes in identifying resistance alleles in soybean; however, a gene at the Rsv4 locus has been well validated.

The wide adoption of dicamba-tolerant (DT) soybean has led to numerous cases of off-target dicamba damage to non-DT soybean and dicot crops. This study aimed to develop a method to differentiate soybean response to dicamba using unmanned-aerial-vehicle-based imagery and machine learning models. Soybean lines were visually classified into three classes of injury, i.e., tolerant, moderate, and susceptible to off-target dicamba. A quadcopter with a built-in RGB camera was used to collect images of field plots at a height of 20 m above ground level. Seven image features were extracted for each plot, including canopy coverage, contrast, entropy, green leaf index, hue, saturation, and triangular greenness index. Classification models based on artificial neural network (ANN) and random forest (RF) algorithms were developed to differentiate the three classes of response to dicamba. Significant differences for each feature were observed among classes and no significant differences across fields were observed. The ANN and RF models were able to precisely distinguish tolerant and susceptible lines with an overall accuracy of 0.74 and 0.75, respectively. The imagery-based classification model can be implemented in a breeding program to effectively differentiate phenotypic dicamba response and identify soybean lines with tolerance to off-target dicamba damage.