Genetic diversity and interaction between the maintainers of commercial soybean cultivars using self‐organizing maps

Abstract

Information on the genetic diversity of commercial cultivars is of fundamental importance for crop improvement. In addition, information about possible interactions between the maintainers developing these cultivars can help design a breeding program. The objective of this work was to study the genetic diversity of soybean [Glycine max (L.) Merr.] cultivars released in Brazil from 1998 to 2017 and compare the similarity between maintainers of these cultivars based on the phenotypic information disclosed. Data was collected on 1,587 soybean cultivars registered in the National Register of Cultivars of the Ministry of Agriculture, Livestock, and Supply belonging to 59 different maintainers. Among these cultivars, 12 agromorphological traits were evaluated. To perform the grouping and select the main discriminating traits of the cultivars, the Random Forest method was used. Multiple correspondence analysis was performed to obtain the variance explanation percentage of the traits evaluated in each dimension and coordinates among the maintainers. The maintainers were organized through Kohonen self‐organizing map (SOM) through the respective coordinates. There is a wide variety of maintainers of soybean cultivars in Brazil with different objectives for launching new cultivars. Among the maintainers, Soymax presented the most restricted genetic base. The other private companies showed more remarkable similarities and a broader genetic base. The public institution EMBRAPA presented the greatest genetic diversity in its population base. Federal University of Uberlândia and Federal University of Viçosa can be partners to launch soybean cultivars given the proximity between neurons in Kohonen analysis. The high diversity of traits shows that the genetic base of soybean in Brazil is large.

Change Is Upon Us, and We Need to Adapt

“…It is exciting to see the first uses of deep learning tools for stress analysis (Nagasubramanian et al., 2022), computer vision for maize ear phenotyping (Gonzalez et al., 2022), and image‐based oat panicle phenotyping (Berro et al., 2022). The advances in genomic prediction have also only been possible with new machine‐learning tools (Barbosa et al., 2021), and they are now being powerfully used to characterize genomic diversity measures using more data (da Costa et al., 2022).…”

Complete Issue

“…It is exciting to see the first uses of deep learning tools for stress analysis (Nagasubramanian et al, 2022), computer vision for maize ear phenotyping (Gonzalez et al, 2022), and image-based oat panicle phenotyping (Berro et al, 2022). The advances in genomic prediction have also only been possible with new machine-learning tools (Barbosa et al, 2021), and they are now being powerfully used to characterize genomic diversity measures using more data (da Costa et al, 2022).…”