Machine Learning-Based Tomato Fruit Shape Classification System.

Fruit shape significantly impacts the quality and commercial value of tomatoes (Solanum lycopersicum L.). Precise grading is essential to elucidate the genetic basis of fruit shape in breeding programs, cultivar descriptions, and variety registration. Despite this, fruit shape classification is still primarily based on subjective visual inspection, leading to time-consuming and labor-intensive processes prone to human error. This study presents a novel approach incorporating machine learning techniques to establish a robust fruit shape classification system. We trained and evaluated seven supervised machine learning algorithms by leveraging a public dataset derived from the Tomato Analyzer tool and considering the current four classification systems as label variables. Subsequently, based on class-specific metrics, we derived a novel classification framework comprising seven discernible shape classes. The results demonstrate the superiority of the Support Vector Machine model in terms of its accuracy, surpassing human classifiers across all classification systems. The new classification system achieved the highest accuracy, averaging 88%, and maintained a similar performance when validated with an independent dataset. Positioned as a common standard, this system contributes to standardizing tomato fruit shape classification, enhancing accuracy, and promoting consensus among researchers. Its implementation will serve as a valuable tool for overcoming bias in visual classification, thereby fostering a deeper understanding of consumer preferences and facilitating genetic studies on fruit shape morphometry.

The genetic architecture of the pepper metabolome and the biosynthesis of its signature capsianoside metabolites.

Capsicum (pepper) is among the most economically important species worldwide, and its fruits accumulate specialized metabolites with essential roles in plant environmental interaction and human health benefits as well as in conferring their unique taste. However, the genetics underlying differences in metabolite presence/absence and/or accumulation remain largely unknown. In this study, we carried out a genome-wide association study as well as generating and characterizing a novel backcross inbred line mapping population to determine the genetic architecture of the pepper metabolome. This genetic analysis provided over 1,000 metabolic quantitative trait loci (mQTL) for over 250 annotated metabolites. We identified 92 candidate genes involved in various mQTLs. Among the identified loci, we described and validated a gene cluster of eleven UDP-glycosyltransferases (UGTs) involved in monomeric capsianoside biosynthesis. We additionally constructed the gene-by-gene-based biosynthetic pathway of pepper capsianoside biosynthesis, including both core and decorative reactions. Given that one of these decorative pathways, namely the glycosylation of acyclic diterpenoid glycosides, contributes to plant resistance, these data provide new insights and breeding resources for pepper. They additionally provide a blueprint for the better understanding of the biosynthesis of species-specific natural compounds in general.

Genomic prediction of morphometric and colorimetric traits in Solanaceous fruits.

Selection of high-performance lines with respect to traits of interest is a key step in plant breeding. Genomic prediction allows to determine the genomic estimated breeding values of unseen lines for trait of interest using genetic markers, e.g. single-nucleotide polymorphisms (SNPs), and machine learning approaches, which can therefore shorten breeding cycles, referring to genomic selection (GS). Here, we applied GS approaches in two populations of Solanaceous crops, i.e. tomato and pepper, to predict morphometric and colorimetric traits. The traits were measured by using scoring-based conventional descriptors (CDs) as well as by Tomato Analyzer (TA) tool using the longitudinally and latitudinally cut fruit images. The GS performance was assessed in cross-validations of classification-based and regression-based machine learning models for CD and TA traits, respectively. The results showed the usage of TA traits and tag SNPs provide a powerful combination to predict morphology and color-related traits of Solanaceous fruits. The highest predictability of 0.89 was achieved for fruit width in pepper, with an average predictability of 0.69 over all traits. The multi-trait GS models are of slightly better predictability than single-trait models for some colorimetric traits in pepper. While model validation performs poorly on wild tomato accessions, the usage as many as one accession per wild species in the training set can increase the transferability of models to unseen populations for some traits (e.g. fruit shape for which predictability in unseen scenario increased from zero to 0.6). Overall, GS approaches can assist the selection of high-performance Solanaceous fruits in crop breeding.

Double Haploid Development and Assessment of Androgenic Competence of Balkan Pepper Core Collection in Bulgaria.

This study was designed to assess the androgenic potential of 180 pepper accessions and 11 progenies (four F1 and seven BC) possessing PMMoV resistance in order to complement an ongoing pepper breeding program. The experiment was carried out in 10 replications with 20 anthers for each accession in two different induction mediums from 2017 to 2019. The highest androgenic response was observed in culture medium 17-2 but differences between two mediums were nonsignificant. From a total of 191 genotypes, 102 genotypes expressed a potential for direct embryogenesis. Embryo induction was seen to be genotype-dependent and decreased in the following order: Pumpkin > Conical > Bell or blocky > Round > Elongate as the most responsive genotypes with over 10% reacted anthers being observed in CAPS-23, CAPS-29, CAPS-127, CAPS-157, CAPS-169, F1 and BC 887 derived from CAPS-23. The number of regenerated plants was higher in the conical group and least in the round varietal group. Regenerated plants were examined visually and by flow cytometry for identification of spontaneous doubled haploids (DH) and haploids. Those originating from F1 and BC progenies were additionally evaluated by a CAPS marker targeting L4 allele for resistance against PMMoV. Obtained results revealed two groups consisting of homozygous susceptible and resistant plants. Therefore, use of anther culture in ongoing breeding will greatly facilitate the pepper genetic improvement.

Genotyping by Sequencing Reveals Genetic Relatedness of Southwestern U.S. Blue Maize Landraces.

Maize has played a key role in the sustenance and cultural traditions of the inhabitants of the southwestern USA for many centuries. Blue maize is an important component of the diverse landraces still cultivated in the region but the degree to which they are related is unknown. This research was designed to ascertain the genotypic, morphological, and phenotypic diversity of six representative southwestern blue maize landraces. Their genotypic diversity was examined using tunable genotyping-by-sequencing (tGBS™). A total of 81,038 high quality SNPs were identified and obtained through tGBS. A total of 45 morphological and biochemical traits were evaluated at two locations in New Mexico. The varieties Los Lunas High and Flor del Rio were genetically less related with other southwestern landraces whereas diffusion between Navajo Blue, Hopi Blue, Yoeme Blue, and Taos Blue demonstrated that these landraces were genetically related. Phenotypic variability was highest for kernel traits and least for plant traits. Plant, ear, and kernel traits were fairly consistent within and across locations. Principal component analysis and tGBS showed that Corn Belt variety 'Ohio Blue' was distinctly different from southwestern landraces. Genotypic analysis displayed that southwestern landraces are genetically closely related, but selection has resulted in differing phenotypes. This study has provided additional insight into the genetic relatedness of southwestern blue maize landraces.

Compositional Analyses Reveal Relationships among Components of Blue Maize Grains.

One aim of this experiment was to develop NIR calibrations for 20-grain components in 143 pigmented maize samples evaluated in four locations across New Mexico during 2013 and 2014. Based on reference analysis, prediction models were developed using principal component regression (PCR) and partial least squares (PLS). The predictive ability of calibrations was generally low, with the calibrations for methionine and glycine performing best by PCR and PLS. The second aim was to explore the relationships among grain constituents. In PCA, the first three PCs explained 49.62, 22.20, and 6.92% of the total variance and tend to align with nitrogen-containing compounds (amino acids), carbon-rich compounds (starch, anthocyanin, fiber, and fat), and sulfur-containing compounds (cysteine and methionine), respectively. Correlations among traits were identified, and these relationships were illustrated by a correlation network. Some relationships among components were driven by common synthetic origins, for example, among amino acids derived from pyruvate. Similarly, anthocyanins, crude fat, and fatty acids all share malonyl CoA in their biosynthetic pathways and were correlated. In contrast, crude fiber and starch have similar biosynthetic origins but were negatively correlated, and this may have been due to their different functional roles in structure and energy storage, respectively.

A step towards Balkan Capsicum annuum L. core collection: Phenotypic and biochemical characterization of 180 accessions for agronomic, fruit quality, and virus resistance traits.

Region-specific local landraces represent a germplasm diversity adapted and acclimatized to local conditions, and are ideal to breed for targeted market niches while maintaining the variability of heirloom traits. A collection of 180 pepper accessions, collected from 62 diverse locations across six Balkan countries, were characterized and evaluated for phenotypic and biochemical variation during a multi-year environment. An assortment of 32 agro-morphological, fruit quality, and virus resistance traits were evaluated, and the top 10% accessions were identified. A wide range of trait variation concerning plant architecture, inflorescence and fruit traits, yield and fruit quality was observed, and appreciable variation was noticed. According to hierarchical clustering, six distinct clusters were established based on pre-defined varietal groups. Divergence among accessions for phenotypic and fruit compositional variability was analyzed, and eight principal components were identified that contributed ~71% of the variation, with fruit shape, width, wall thickness, weight, and fruit quality traits being the most discriminant. Evaluation of the response to tobacco mosaic virus (TMV) and pepper mild mottle mosaic virus (PMMoV) showed that 24 and 1 accession were resistant, respectively while no tomato spotted wilt virus (TSWV) resistance was found. Considerable diversity for agro-bio-morphological traits indicates the Balkan pepper collection as good gene sources for pre-breeding and cultivar development that are locally adapted.

Tomato Phenotypic Diversity Determined by Combined Approaches of Conventional and High-Throughput Tomato Analyzer Phenotyping.

Morphological variation in vegetative and fruit traits is a key determinant in unraveling phenotypic diversity. This study was designed to assess phenotypic diversity in tomatoes and examine intra- and intervarietal groups' variability using 28 conventional descriptors (CDs) and 47 Tomato Analyzer (TA) descriptors related to plant and fruit morphometry. Comprehensive phenotyping of 150 accessions representing 21 countries discerned noticeable variability for CD vegetative traits and TA quantified fruit features, such as shape, size, and color. Hierarchical cluster analysis divided the accessions into 10 distinct classes based on fruit shape and size. Multivariate analysis was used to assess divergence in variable traits among populations. Eight principal components with an eigenvalue >1 were identified by factor analysis, which contributed 87.5% variation to the total cumulative variance with the first two components contributing 32.0% and 18.1% variance, respectively. The relationship between vegetative and fruit descriptors was explained by respective CD and TA correlation networks. There was a strong positive correlation between fruit shape and size whereas negative correlations were between fruit shape index, internal eccentricity, and proximal end shape. The combined approach of CD and TA phenotyping allowed us to unravel the phenotypic diversity of vegetative and reproductive trait variation evaluated at pre- and post-harvest stages.

Quantitative and qualitative evaluation of kernel anthocyanins from southwestern United States blue corn.

BACKGROUND: Anthocyanin-rich blue corn is an emerging specialty crop in the USA. The antioxidant properties of blue corn offer health benefits in the human diet. The objectives of this study were to identify, characterize and quantify the anthocyanins from blue corn. Hypotheses tested were that total anthocyanin content was similar among southwestern US accessions and that it would vary across locations. It was also examined whether different anthocyanin components were unique to certain genotypes. RESULTS: Across all locations and accessions, an average of 0.43 g kg(-1) total anthocyanin content (TAC) was observed. Accessions Santa Clara Blue and Ohio Blue displayed the highest TAC. The TAC of accession Flor del Rio was lower by nearly a factor of six. A total of five anthocyanin components were identified. Cyanidin 3-glucoside was the most abundant, followed by pelargonidin and peonidin 3-glucoside. Succinyl and disuccinyl glycosidic forms of cyanidin were also identified. Cyanidin 3-disuccinylglucoside was newly identified as a novel form of anthocyanin. CONCLUSION: Quantitative and qualitative anthocyanin expression was determined to be relatively stable across multiple southwestern environments. Increased expression of red and purple pigmentation in accession Flor del Rio appeared to be associated more with reduced TAC and cyanidin 3-glucoside than with elevated pelargonidin per se. A previously unreported anthocyanin component in blue corn, cyanidin 3-disuccinylglucoside, is present in southwestern landraces. © 2016 Society of Chemical Industry.