Multi-trait and multi-environment genomic prediction for flowering traits in maize: a deep learning approach.

Maize (Zea mays L.), the third most widely cultivated cereal crop in the world, plays a critical role in global food security. To improve the efficiency of selecting superior genotypes in breeding programs, researchers have aimed to identify key genomic regions that impact agronomic traits. In this study, the performance of multi-trait, multi-environment deep learning models was compared to that of Bayesian models (Markov Chain Monte Carlo generalized linear mixed models (MCMCglmm), Bayesian Genomic Genotype-Environment Interaction (BGGE), and Bayesian Multi-Trait and Multi-Environment (BMTME)) in terms of the prediction accuracy of flowering-related traits (Anthesis-Silking Interval: ASI, Female Flowering: FF, and Male Flowering: MF). A tropical maize panel of 258 inbred lines from Brazil was evaluated in three sites (Cambira-2018, Sabaudia-2018, and Iguatemi-2020 and 2021) using approximately 290,000 single nucleotide polymorphisms (SNPs). The results demonstrated a 14.4% increase in prediction accuracy when employing multi-trait models compared to the use of a single trait in a single environment approach. The accuracy of predictions also improved by 6.4% when using a single trait in a multi-environment scheme compared to using multi-trait analysis. Additionally, deep learning models consistently outperformed Bayesian models in both single and multiple trait and environment approaches. A complementary genome-wide association study identified associations with 26 candidate genes related to flowering time traits, and 31 marker-trait associations were identified, accounting for 37%, 37%, and 22% of the phenotypic variation of ASI, FF and MF, respectively. In conclusion, our findings suggest that deep learning models have the potential to significantly improve the accuracy of predictions, regardless of the approach used and provide support for the efficacy of this method in genomic selection for flowering-related traits in tropical maize.

Application of Near-Infrared Reflectance Spectroscopy for Predicting Damage Severity in a Diverse Panel of Tectona grandis Caused by Ceratocystis fimbriata.

Tectona grandis Linn., also known as teak, is a highly valued species with adaptability to a wide range of climatic conditions and high tolerance to soil variations, making it an attractive option for both commercial and conservation purposes. In this sense, the classification of cultivated teak genotypes is crucial for both breeding programs and conservation efforts. This study examined the relationship between traits related to damage in the stem of teak plants caused by Ceratocystis fimbriata (a soil-borne pathogen that negatively impacts the productivity of teak plantations) and the spectral reflectance of 110 diverse clones, using near-infrared spectroscopy (NIRS) data and partial least squares regression (PLSR) analysis. Cross-validation models had R2 = 0.894 (ratio of standard error of prediction to standard deviation: RPD = 3.1), R2 = 0.883 (RPD = 2.7), and R2 = 0.893 (RPD = 2.8) for predicting stem lesion area, lesion length, and severity of infection, respectively. Teak genotypes (clones) can benefit from the creation of a calibration model utilizing NIRS-generated data paired with PLSR, which can effectively screen the magnitude of damage caused by the fungus. Overall, while the study provides valuable information for teak breeding and conservation efforts, a long-term perspective would be essential to evaluate the sustainability of teak genotypes over various growth stages and under continuous pathogen pressure.

Saponins: Research Progress and Their Potential Role in the Post-COVID-19 Pandemic Era.

In the post-COVID-19 pandemic era, the new global situation and the limited therapeutic management of the disease make it necessary to take urgent measures in more effective therapies and drug development in order to counteract the negative global impacts caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and its new infectious variants. In this context, plant-derived saponins-glycoside-type compounds constituted from a triterpene or steroidal aglycone and one or more sugar residues-may offer fewer side effects and promising beneficial pharmacological activities. This can then be used for the development of potential therapeutic agents against COVID-19, either as a therapy or as a complement to conventional pharmacological strategies for the treatment of the disease and its prevention. The main objective of this review was to examine the primary and current evidence in regard to the therapeutic potential of plant-derived saponins against the COVID-19 disease. Further, the aim was to also focus on those studies that highlight the potential use of saponins as a treatment against SARS-CoV-2. Saponins are antiviral agents that inhibit different pharmacological targets of the virus, as well as exhibit anti-inflammatory and antithrombotic activity in relieving symptoms and clinical complications related to the disease. In addition, saponins also possess immunostimulatory effects, which improve the efficacy and safety of vaccines for prolonging immunogenicity against SARS-CoV-2 and its infectious variants.

Spectral-Based Classification of Genetically Differentiated Groups in Spring Wheat Grown under Contrasting Environments.

The global concern about the gap between food production and consumption has intensified the research on the genetics, ecophysiology, and breeding of cereal crops. In this sense, several genetic studies have been conducted to assess the effectiveness and sustainability of collections of germplasm accessions of major crops. In this study, a spectral-based classification approach for the assignment of wheat cultivars to genetically differentiated subpopulations (genetic structure) was carried out using a panel of 316 spring bread cultivars grown in two environments with different water regimes (rainfed and fully irrigated). For that, different machine-learning models were trained with foliar spectral and genetic information to assign the wheat cultivars to subpopulations. The results revealed that, in general, the hyperparameters ReLU (as the activation function), adam (as the optimizer), and a size batch of 10 give neural network models better accuracy. Genetically differentiated groups showed smaller differences in mean wavelengths under rainfed than under full irrigation, which coincided with a reduction in clustering accuracy in neural network models. The comparison of models indicated that the Convolutional Neural Network (CNN) was significantly more accurate in classifying individuals into their respective subpopulations, with 92 and 93% of correct individual assignments in water-limited and fully irrigated environments, respectively, whereas 92% (full irrigation) and 78% (rainfed) of cultivars were correctly assigned to their respective classes by the multilayer perceptron method and partial least squares discriminant analysis, respectively. Notably, CNN did not show significant differences between both environments, which indicates stability in the prediction independent of the different water regimes. It is concluded that foliar spectral variation can be used to accurately infer the belonging of a cultivar to its respective genetically differentiated group, even considering radically different environments, which is highly desirable in the context of crop genetic resources management.

Challenges for a Massive Implementation of Phenomics in Plant Breeding Programs.

Due to climate change and expected food shortage in the coming decades, not only will it be necessary to develop cultivars with greater tolerance to environmental stress, but it is also imperative to reduce breeding cycle time. In addition to yield evaluation, plant breeders resort to many sensory assessments and some others of intermediate complexity. However, to develop cultivars better adapted to current/future constraints, it is necessary to incorporate a new set of traits, such as morphophysiological and physicochemical attributes, information relevant to the successful selection of genotypes or parents. Unfortunately, because of the large number of genotypes to be screened, measurements with conventional equipment are unfeasible, especially under field conditions. High-throughput plant phenotyping (HTPP) facilitates collecting a significant amount of data quickly; however, it is necessary to transform all this information (e.g., plant reflectance) into helpful descriptors to the breeder. To the extent that a holistic characterization of the plant (phenomics) is performed in challenging environments, it will be possible to select the best genotypes (forward phenomics) objectively but also understand why the said individual differs from the rest (reverse phenomics). Unfortunately, several elements had prevented phenomics from developing as desired. Consequently, a new set of prediction/validation methodologies, seasonal ambient information, and the fusion of data matrices (e.g., genotypic and phenotypic information) need to be incorporated into the modeling. In this sense, for the massive implementation of phenomics in plant breeding, it will be essential to count an interdisciplinary team that responds to the urgent need to release material with greater capacity to tolerate environmental stress. Therefore, breeding programs should (i) be more efficient (e.g., early discarding of unsuitable material), (ii) have shorter breeding cycles (fewer crosses to achieve the desired cultivar), and (iii) be more productive, increasing the probability of success at the end of the breeding process (percentage of cultivars released to the number of initial crosses).

Variation in Root-Related Traits Is Associated With Water Uptake in Lagenaria siceraria Genotypes Under Water-Deficit Conditions.

In many agricultural areas, crop production has decreased due to a lack of water availability, which is having a negative impact on sustainability and putting food security at risk. In plants, the plasticity of the root system architecture (RSA) is considered to be a key trait driving the modification of the growth and structure of roots in response to water deficits. The purpose of this study was to examine the plasticity of the RSA traits (mean root diameter, MRD; root volume, RV; root length, RL; and root surface area, SA) associated with drought tolerance in eight Lagenaria siceraria (Mol. Standl) genotypes, representing three different geographical origins: South Africa (BG-58, BG-78, and GC), Asia (Philippines and South Korea), and Chile (Illapel, Chepica, and Osorno). The RSA changes were evaluated at four substrate depths (from 0 to 40 cm). Bottle gourd genotypes were grown in 20 L capacity pots under two contrasting levels of irrigation (well-watered and water-deficit conditions). The results showed that the water productivity (WP) had a significant effect on plasticity values, with the Chilean accessions having the highest values. Furthermore, Illapel and Chepica genotypes presented the highest WP, MRD, and RV values under water-deficit conditions, in which MRD and RV were significant in the deeper layers (20-30 and 30-40 cm). Biplot analysis showed that the Illapel and Chepica genotypes presented a high WP, MRD, and RV, which confirmed that these may be promising drought-tolerant genotypes. Consequently, increased root diameter and volume in bottle gourd may constitute a response to a water deficit. The RSA traits studied here can be used as selection criteria in bottle gourd breeding programs under water-deficit conditions.

Heritable Variation of Foliar Spectral Reflectance Enhances Genomic Prediction of Hydrogen Cyanide in a Genetically Structured Population of Eucalyptus.

Plants produce a wide diversity of specialized metabolites, which fulfill a wide range of biological functions, helping plants to interact with biotic and abiotic factors. In this study, an integrated approach based on high-throughput plant phenotyping, genome-wide haplotypes, and pedigree information was performed to examine the extent of heritable variation of foliar spectral reflectance and to predict the leaf hydrogen cyanide content in a genetically structured population of a cyanogenic eucalyptus (Eucalyptus cladocalyx F. Muell). In addition, the heritable variation (based on pedigree and genomic data) of more of 100 common spectral reflectance indices was examined. The first profile of heritable variation along the spectral reflectance curve indicated the highest estimate of genomic heritability ( h g 2 =0.41) within the visible region of the spectrum, suggesting that several physiological and biological responses of trees to environmental stimuli (ex., light) are under moderate genetic control. The spectral reflectance index with the highest genomic-based heritability was leaf rust disease severity index 1 ( h g 2 =0.58), followed by the anthocyanin reflectance index and the Browning reflectance index ( h g 2 =0.54). Among the Bayesian prediction models based on spectral reflectance data, Bayes B had a better goodness of fit than the Bayes-C and Bayesian ridge regression models (in terms of the deviance information criterion). All models that included spectral reflectance data outperformed conventional genomic prediction models in their predictive ability and goodness-of-fit measures. Finally, we confirmed the proposed hypothesis that high-throughput phenotyping indirectly capture endophenotypic variants related to specialized metabolites (defense chemistry), and therefore, generally more accurate predictions can be made integrating phenomics and genomics.

Revealing the differential protein profiles behind the nitrogen use efficiency in popcorn (Zea mays var. everta).

We investigated the proteomic profiles of two popcorn inbred lines, P2 (N-efficient and N-responsive) and L80 (N-inefficient and nonresponsive to N), under low (10% of N supply) and high (100% of N supply) nitrogen environments, associated with agronomic- and physiological-related traits to NUE. The comparative proteomic analysis allowed the identification of 79 differentially accumulated proteins (DAPs) in the comparison of high/low N for P2 and 96 DAPs in the comparison of high/low N for L80. The NUE and N uptake efficiency (NUpE) presented high means in P2 in comparison to L80 at both N levels, but the NUE, NUpE, and N utilization efficiency (NUtE) rates decreased in P2 under a high N supply. DAPs involved in energy and carbohydrate metabolism suggested that N regulates enzymes of alternative pathways to adapt to energy shortages and that fructose-bisphosphate aldolase may act as one of the key primary nitrate responsive proteins in P2. Proteins related to ascorbate biosynthesis and nitrogen metabolism increased their regulation in P2, and the interaction of L-ascorbate peroxidase and Fd-NiR may play an important role in the NUE trait. Taken together, our results provide new insights into the proteomic changes taking place in contrasting inbred lines, providing useful information on the genetic improvement of NUE in popcorn.

Exploring plant responses to abiotic stress by contrasting spectral signature changes.

In this study, daily changes over a short period and diurnal progression of spectral reflectance at the leaf level were used to identify spring wheat genotypes (Triticum aestivum L.) susceptible to adverse conditions. Four genotypes were grown in pots experiments under semi-controlled conditions in Chile and Spain. Three treatments were applied: i) control (C), ii) water stress (WS), and iii) combined water and heat shock (WS+T). Spectral reflectance, gas exchange and chlorophyll fluorescence measurements were performed on flag leaves for three consecutive days at anthesis. High canopy temperature ( H CT ) genotypes showed less variability in their mean spectral reflectance signature and chlorophyll fluorescence, which was related to weaker responses to environmental fluctuations. While low canopy temperature ( L CT ) genotypes showed greater variability. The genotypes spectral signature changes, in accordance with environmental fluctuation, were associated with variations in their stomatal conductance under both stress conditions (WS and WS+T); L CT genotypes showed an anisohydric response compared that of H CT , which was isohydric. This approach could be used in breeding programs for screening a large number of genotypes through proximal or remote sensing tools and be a novel but simple way to identify groups of genotypes with contrasting performances.

Antiviral Activities of Eucalyptus Essential Oils: Their Effectiveness as Therapeutic Targets against Human Viruses.

Given the limited therapeutic management of infectious diseases caused by viruses, such as influenza and SARS-CoV-2, the medicinal use of essential oils obtained from Eucalyptus trees has emerged as an antiviral alternative, either as a complement to the treatment of symptoms caused by infection or to exert effects on possible pharmacological targets of viruses. This review gathers and discusses the main findings on the emerging role and effectiveness of Eucalyptus essential oil as an antiviral agent. Studies have shown that Eucalyptus essential oil and its major monoterpenes have enormous potential for preventing and treating infectious diseases caused by viruses. The main molecular mechanisms involved in the antiviral activity are direct inactivation, that is, by the direct binding of monoterpenes with free viruses, particularly with viral proteins involved in the entry and penetration of the host cell, thus avoiding viral infection. Furthermore, this review addresses the coadministration of essential oil and available vaccines to increase protection against different viruses, in addition to the use of essential oil as a complementary treatment of symptoms caused by viruses, where Eucalyptus essential oil exerts anti-inflammatory, mucolytic, and spasmolytic effects in the attenuation of inflammatory responses caused by viruses, in particular respiratory diseases.

Achievements and Challenges of Genomics-Assisted Breeding in Forest Trees: From Marker-Assisted Selection to Genome Editing.

Forest tree breeding efforts have focused mainly on improving traits of economic importance, selecting trees suited to new environments or generating trees that are more resilient to biotic and abiotic stressors. This review describes various methods of forest tree selection assisted by genomics and the main technological challenges and achievements in research at the genomic level. Due to the long rotation time of a forest plantation and the resulting long generation times necessary to complete a breeding cycle, the use of advanced techniques with traditional breeding have been necessary, allowing the use of more precise methods for determining the genetic architecture of traits of interest, such as genome-wide association studies (GWASs) and genomic selection (GS). In this sense, main factors that determine the accuracy of genomic prediction models are also addressed. In turn, the introduction of genome editing opens the door to new possibilities in forest trees and especially clustered regularly interspaced short palindromic repeats and CRISPR-associated protein 9 (CRISPR/Cas9). It is a highly efficient and effective genome editing technique that has been used to effectively implement targetable changes at specific places in the genome of a forest tree. In this sense, forest trees still lack a transformation method and an inefficient number of genotypes for CRISPR/Cas9. This challenge could be addressed with the use of the newly developing technique GRF-GIF with speed breeding.

Regional Heritability Mapping of Quantitative Trait Loci Controlling Traits Related to Growth and Productivity in Popcorn (Zea mays L.).

The method of regional heritability mapping (RHM) has become an important tool in the identification of quantitative trait loci (QTLs) controlling traits of interest in plants. Here, RHM was first applied in a breeding population of popcorn, to identify the QTLs and candidate genes involved in grain yield, plant height, kernel popping expansion, and first ear height, as well as determining the heritability of each significant genomic region. The study population consisted of 98 S1 families derived from the 9th recurrent selection cycle (C-9) of the open-pollinated variety UENF-14, which were genetically evaluated in two environments (ENV1 and ENV2). Seventeen and five genomic regions were mapped by the RHM method in ENV1 and ENV2, respectively. Subsequent genome-wide analysis based on the reference genome B73 revealed associations with forty-six candidate genes within these genomic regions, some of them are considered to be biologically important due to the proteins that they encode. The results obtained by the RHM method have the potential to contribute to knowledge on the genetic architecture of the growth and yield traits of popcorn, which might be used for marker-assisted selection in breeding programs.

Advantage of Nanotechnology-Based Genome Editing System and Its Application in Crop Improvement.

Agriculture is an important source of human food. However, current agricultural practices need modernizing and strengthening to fulfill the increasing food requirements of the growing worldwide population. Genome editing (GE) technology has been used to produce plants with improved yields and nutritional value as well as with higher resilience to herbicides, insects, and diseases. Several GE tools have been developed recently, including clustered regularly interspaced short palindromic repeats (CRISPR) with nucleases, a customizable and successful method. The main steps of the GE process involve introducing transgenes or CRISPR into plants via specific gene delivery systems. However, GE tools have certain limitations, including time-consuming and complicated protocols, potential tissue damage, DNA incorporation in the host genome, and low transformation efficiency. To overcome these issues, nanotechnology has emerged as a groundbreaking and modern technique. Nanoparticle-mediated gene delivery is superior to conventional biomolecular approaches because it enhances the transformation efficiency for both temporal (transient) and permanent (stable) genetic modifications in various plant species. However, with the discoveries of various advanced technologies, certain challenges in developing a short-term breeding strategy in plants remain. Thus, in this review, nanobased delivery systems and plant genetic engineering challenges are discussed in detail. Moreover, we have suggested an effective method to hasten crop improvement programs by combining current technologies, such as speed breeding and CRISPR/Cas, with nanotechnology. The overall aim of this review is to provide a detailed overview of nanotechnology-based CRISPR techniques for plant transformation and suggest applications for possible crop enhancement.

Isolation and characterization of microsatellites for the endangered endemic tree Nothofagus alessandrii (Nothofagaceae).

Nothofagus alessandrii (Nothofagaceae) is one of the most endangered trees from Chile due to high rates of habitat disturbance caused by human activities. Despite its conservation status, few molecular markers are available to study its population genetic, connectivity and to assist reproduction programs. Thus, the species needs urgent actions to restore its original distribution. Novel polymorphic microsatellites from the genome of N. alessandrii were isolated and characterized using high-through sequencing. A total of 30 primer pairs were synthesized and 18 microsatellites were amplified correctly. Polymorphism and genetic diversity was evaluated in 58 individuals from three populations of N. alessandrii. Sixteen of them were polymorphic and the number of alleles in the pooled sample ranged from 2 to 14, the mean number of alleles was 4.81. The mean values of observed heterozigosity (HO) and excepted heterozygosity (HE) are similar in all studied populations. Linkage disequilibrium was found between a few pairs of loci (five out of 263 tests) suggesting that most of the markers can be considered as independent. Significant deviations from Hardy-Weinberg equilibrium (P < 0.05) were found in four loci probably due to low sampling size. Transferability to the congeneric N. pumilio was successful in only four out of the sixteen polymorphic markers. The microsatellite markers developed in this study will be useful to study the genetic diversity and structure and to develop integrated management plans for the conservation of this endangered species.

Jasmonates and Plant Salt Stress: Molecular Players, Physiological Effects, and Improving Tolerance by Using Genome-Associated Tools.

Soil salinity is one of the most limiting stresses for crop productivity and quality worldwide. In this sense, jasmonates (JAs) have emerged as phytohormones that play essential roles in mediating plant response to abiotic stresses, including salt stress. Here, we reviewed the mechanisms underlying the activation and response of the JA-biosynthesis and JA-signaling pathways under saline conditions in Arabidopsis and several crops. In this sense, molecular components of JA-signaling such as MYC2 transcription factor and JASMONATE ZIM-DOMAIN (JAZ) repressors are key players for the JA-associated response. Moreover, we review the antagonist and synergistic effects between JA and other hormones such as abscisic acid (ABA). From an applied point of view, several reports have shown that exogenous JA applications increase the antioxidant response in plants to alleviate salt stress. Finally, we discuss the latest advances in genomic techniques for the improvement of crop tolerance to salt stress with a focus on jasmonates.

Haplotype- and SNP-Based GWAS for Growth and Wood Quality Traits in Eucalyptus cladocalyx Trees under Arid Conditions.

The agricultural and forestry productivity of Mediterranean ecosystems is strongly threatened by the adverse effects of climate change, including an increase in severe droughts and changes in rainfall distribution. In the present study, we performed a genome-wide association study (GWAS) to identify single-nucleotide polymorphisms (SNPs) and haplotype blocks associated with the growth and wood quality of Eucalyptus cladocalyx, a tree species suitable for low-rainfall sites. The study was conducted in a progeny-provenance trial established in an arid site with Mediterranean patterns located in the southern Atacama Desert, Chile. A total of 87 SNPs and 3 haplotype blocks were significantly associated with the 6 traits under study (tree height, diameter at breast height, slenderness coefficient, first bifurcation height, stem straightness, and pilodyn penetration). In addition, 11 loci were identified as pleiotropic through Bayesian multivariate regression and were mainly associated with wood hardness, height, and diameter. In general, the GWAS revealed associations with genes related to primary metabolism and biosynthesis of cell wall components. Additionally, associations coinciding with stress response genes, such as GEM-related 5 and prohibitin-3, were detected. The findings of this study provide valuable information regarding genetic control of morphological traits related to adaptation to arid environments.

Genome-wide association study of cyanogenic glycosides, proline, sugars, and pigments in Eucalyptus cladocalyx after 18 consecutive dry summers.

Natural variation of cyanogenic glycosides, soluble sugars, proline, and nondestructive optical sensing of pigments (chlorophyll, flavonols, and anthocyanins) was examined in ex situ natural populations of Eucalyptus cladocalyx F. Muell. grown under dry environmental conditions in the southern Atacama Desert, Chile. After 18 consecutive dry seasons, considerable plant-to-plant phenotypic variation for all the traits was observed in the field. For example, leaf hydrogen cyanide (HCN) concentrations varied from 0 (two acyanogenic individuals) to 1.54 mg cyanide g-1 DW. Subsequent genome-wide association study revealed associations with several genes with a known function in plants. HCN content was associated robustly with genes encoding Cytochrome P450 proteins, and with genes involved in the detoxification mechanism of HCN in cells (ß-cyanoalanine synthase and cyanoalanine nitrilase). Another important finding was that sugars, proline, and pigment content were linked to genes involved in transport, biosynthesis, and/or catabolism. Estimates of genomic heritability (based on haplotypes) ranged between 0.46 and 0.84 (HCN and proline content, respectively). Proline and soluble sugars had the highest predictive ability of genomic prediction models (PA = 0.65 and PA = 0.71, respectively). PA values for HCN content and flavonols were relatively moderate, with estimates ranging from 0.44 to 0.50. These findings provide new understanding on the genetic architecture of cyanogenic capacity, and other key complex traits in cyanogenic E. cladocalyx.

Genome-Wide Prediction of Complex Traits in Two Outcrossing Plant Species Through Deep Learning and Bayesian Regularized Neural Network.

Genomic selection models were investigated to predict several complex traits in breeding populations of Zea mays L. and Eucalyptus globulus Labill. For this, the following methods of Machine Learning (ML) were implemented: (i) Deep Learning (DL) and (ii) Bayesian Regularized Neural Network (BRNN) both in combination with different hyperparameters. These ML methods were also compared with Genomic Best Linear Unbiased Prediction (GBLUP) and different Bayesian regression models [Bayes A, Bayes B, Bayes Cπ, Bayesian Ridge Regression, Bayesian LASSO, and Reproducing Kernel Hilbert Space (RKHS)]. DL models, using Rectified Linear Units (as the activation function), had higher predictive ability values, which varied from 0.27 (pilodyn penetration of 6 years old eucalypt trees) to 0.78 (flowering-related traits of maize). Moreover, the larger mini-batch size (100%) had a significantly higher predictive ability for wood-related traits than the smaller mini-batch size (10%). On the other hand, in the BRNN method, the architectures of one and two layers that used only the pureline function showed better results of prediction, with values ranging from 0.21 (pilodyn penetration) to 0.71 (flowering traits). A significant increase in the prediction ability was observed for DL in comparison with other methods of genomic prediction (Bayesian alphabet models, GBLUP, RKHS, and BRNN). Another important finding was the usefulness of DL models (through an iterative algorithm) as an SNP detection strategy for genome-wide association studies. The results of this study confirm the importance of DL for genome-wide analyses and crop/tree improvement strategies, which holds promise for accelerating breeding progress.

A Deep Learning Approach to Population Structure Inference in Inbred Lines of Maize.

Analysis of population genetic variation and structure is a common practice for genome-wide studies, including association mapping, ecology, and evolution studies in several crop species. In this study, machine learning (ML) clustering methods, K-means (KM), and hierarchical clustering (HC), in combination with non-linear and linear dimensionality reduction techniques, deep autoencoder (DeepAE) and principal component analysis (PCA), were used to infer population structure and individual assignment of maize inbred lines, i.e., dent field corn (n = 97) and popcorn (n = 86). The results revealed that the HC method in combination with DeepAE-based data preprocessing (DeepAE-HC) was the most effective method to assign individuals to clusters (with 96% of correct individual assignments), whereas DeepAE-KM, PCA-HC, and PCA-KM were assigned correctly 92, 89, and 81% of the lines, respectively. These findings were consistent with both Silhouette Coefficient (SC) and Davies-Bouldin validation indexes. Notably, DeepAE-HC also had better accuracy than the Bayesian clustering method implemented in InStruct. The results of this study showed that deep learning (DL)-based dimensional reduction combined with ML clustering methods is a useful tool to determine genetically differentiated groups and to assign individuals into subpopulations in genome-wide studies without having to consider previous genetic assumptions.