Digital descriptors sharpen classical descriptors, for improving genebank accession management: A case study on Arachis spp. and Phaseolus spp.

Abstract

High-throughput phenotyping brings new opportunities for detailed genebank accessions characterization based on image-processing techniques and data analysis using machine learning algorithms. Our work proposes to improve the characterization processes of bean and peanut accessions in the CIAT genebank through the identification of phenomic descriptors comparable to classical descriptors including methodology integration into the genebank workflow. To cope with these goals morphometrics and colorimetry traits of 14 bean and 16 forage peanut accessions were determined and compared to the classical International Board for Plant Genetic Resources (IBPGR) descriptors. Descriptors discriminating most accessions were identified using a random forest algorithm. The most-valuable classification descriptors for peanuts were 100-seed weight and days to flowering, and for beans, days to flowering and primary seed color. The combination of phenomic and classical descriptors increased the accuracy of the classification of Phaseolus and Arachis accessions. Functional diversity indices are recommended to genebank curators to evaluate phenotypic variability to identify accessions with unique traits or identify accessions that represent the greatest phenotypic variation of the species (functional agrobiodiversity collections). The artificial intelligence algorithms are capable of characterizing accessions which reduces costs generated by additional phenotyping. Even though deep analysis of data requires new skills, associating genetic, morphological and ecogeographic diversity is giving us an opportunity to establish unique functional agrobiodiversity collections with new potential traits.

Plant phenotyping relevance

画像処理・形態計測・色彩計測と機械学習を用いて遺伝資源の表現型記述子を開発・比較し、遺伝資源管理ワークフローへ統合することが中心であるため。

Code and data availability

The paper's Data Availability statement explicitly points to a public GitHub repository containing the phenomics and traditional descriptor data underlying the study, which directly reproduces the paper's plant-phenotyping measurements. Figures and tables in the article are not treated as separate assets.