QTG-Finder2: A Generalized Machine-Learning Algorithm for Prioritizing QTL Causal Genes in Plants

Application of machine learning and genomics for orphan crop improvement

Orphan crops are important sources of nutrition in developing regions and many are tolerant to biotic and abiotic stressors; however, modern crop improvement technologies have not been widely applied to orphan crops due to the lack of resources available. There are orphan crop representatives across major crop types and the conservation of genes between these related species can be used in crop improvement. Machine learning (ML) has emerged as a promising tool for crop improvement. Transferring knowledge from major crops to orphan crops and using machine learning to improve accuracy and efficiency can be used to improve orphan crops.

Artificial intelligence in plant breeding

Harnessing cutting-edge technologies to enhance crop productivity is a pivotal goal in modern plant breeding. Artificial intelligence (AI) is renowned for its prowess in big data analysis and pattern recognition, and is revolutionizing numerous scientific domains including plant breeding. We explore the wider potential of AI tools in various facets of breeding, including data collection, unlocking genetic diversity within genebanks, and bridging the genotype-phenotype gap to facilitate crop breeding. This will enable the development of crop cultivars tailored to the projected future environments. Moreover, AI tools also hold promise for refining crop traits by improving the precision of gene-editing systems and predicting the potential effects of gene variants on plant phenotypes. Leveraging AI-enabled precision breeding can augment the efficiency of breeding programs and holds promise for optimizing cropping systems at the grassroots level. This entails identifying optimal inter-cropping and crop-rotation models to enhance agricultural sustainability and productivity in the field.

Agile Genetics: Single gene resolution without the fuss

Gene discovery reveals new biology, expands the utility of marker-assisted selection, and enables targeted mutagenesis. Still, such discoveries can take over a decade. We present a general strategy, "Agile Genetics," that uses nested, structured populations to overcome common limits on gene resolution. Extensive simulation work on realistic genetic architectures shows that, at population sizes of >5000 samples, single gene-resolution can be achieved using bulk segregant pools. At this scale, read depth and technical replication become major drivers of resolution. Emerging enrichment methods to address coverage are on the horizon; we describe one possibility - iterative depth sequencing (ID-seq). In addition, graph-based pangenomics in experimental populations will continue to maximize accuracy and improve interpretation. Based on this merger of agronomic scale with molecular and bioinformatic innovation, we predict a new age of rapid gene discovery.

Integrated Assays of Genome-Wide Association Study, Multi-Omics Co-Localization, and Machine Learning Associated Calcium Signaling Genes with Oilseed Rape Resistance to Sclerotinia sclerotiorum

Sclerotinia sclerotiorum (Ss) is one of the most devastating fungal pathogens, causing huge yield loss in multiple economically important crops including oilseed rape. Plant resistance to Ss pertains to quantitative disease resistance (QDR) controlled by multiple minor genes. Genome-wide identification of genes involved in QDR to Ss is yet to be conducted. In this study, we integrated several assays including genome-wide association study (GWAS), multi-omics co-localization, and machine learning prediction to identify, on a genome-wide scale, genes involved in the oilseed rape QDR to Ss. Employing GWAS and multi-omics co-localization, we identified seven resistance-associated loci (RALs) associated with oilseed rape resistance to Ss. Furthermore, we developed a machine learning algorithm and named it Integrative Multi-Omics Analysis and Machine Learning for Target Gene Prediction (iMAP), which integrates multi-omics data to rapidly predict disease resistance-related genes within a broad chromosomal region. Through iMAP based on the identified RALs, we revealed multiple calcium signaling genes related to the QDR to Ss. Population-level analysis of selective sweeps and haplotypes of variants confirmed the positive selection of the predicted calcium signaling genes during evolution. Overall, this study has developed an algorithm that integrates multi-omics data and machine learning methods, providing a powerful tool for predicting target genes associated with specific traits. Furthermore, it makes a basis for further understanding the role and mechanisms of calcium signaling genes in the QDR to Ss.

Integrating machine learning and genome editing for crop improvement

Genome editing is a promising technique that has been broadly utilized for basic gene function studies and trait improvements. Simultaneously, the exponential growth of computational power and big data now promote the application of machine learning for biological research. In this regard, machine learning shows great potential in the refinement of genome editing systems and crop improvement. Here, we review the advances of machine learning to genome editing optimization, with emphasis placed on editing efficiency and specificity enhancement. Additionally, we demonstrate how machine learning bridges genome editing and crop breeding, by accurate key site detection and guide RNA design. Finally, we discuss the current challenges and prospects of these two techniques in crop improvement. By integrating advanced genome editing techniques with machine learning, progress in crop breeding will be further accelerated in the future.

In silico characterization of five novel disease-resistance proteins in Oryza sativa sp. japonica against bacterial leaf blight and rice blast diseases

In the current study, gene network analysis revealed five novel disease-resistance proteins against bacterial leaf blight (BB) and rice blast (RB) diseases caused by Xanthomonas oryzae pv. oryzae (Xoo) and Magnaporthe oryzae (M. oryzae), respectively. In silico modeling, refinement, and model quality assessment were performed to predict the best structures of these five proteins and submitted to ModelArchive for future use. An in-silico annotation indicated that the five proteins functioned in signal transduction pathways as kinases, phospholipases, transcription factors, and DNA-modifying enzymes. The proteins were localized in the nucleus and plasma membrane. Phylogenetic analysis showed the evolutionary relation of the five proteins with disease-resistance proteins (XA21, OsTRX1, PLD, and HKD-motif-containing proteins). This indicates similar disease-resistant properties between five unknown proteins and their evolutionary-related proteins. Furthermore, gene expression profiling of these proteins using public microarray data showed their differential expression under Xoo and M. oryzae infection. This study provides an insight into developing disease-resistant rice varieties by predicting novel candidate resistance proteins, which will assist rice breeders in improving crop yield to address future food security through molecular breeding and biotechnology.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13205-023-03893-5.

Haplotype analysis of QTLs governing early seedling vigor-related traits under dry-direct-seeded rice (Oryza sativa L.) conditions

BACKGROUND

The eventual shifting of cultivation method from puddle transplanted rice to direct-seeded rice (DSR) to save water prompted researchers to develop DSR-suitable varieties. To achieve this, identification of molecular markers associated with must-have traits for DSR, especially early seedling vigour related traits is crucial.

METHODS AND RESULTS

In the present investigation, the haplotype analysis using flanking markers of three important quantitative trait loci (QTLs) for early seedling vigour-related traits viz., qSV-6a (RM204 and RM402) for root length; qVI (RM20429 and RM3) for seedling vigour index; qGP-6 (RM528 and RM400) for germination percentage revealed that the marker alleles were found to show significant associations with qVI and qGP-6 QTLs. The majority of genotypes with high early seedling vigour are with qVIHap-1 (220 and 160 bp) and qGPHap-1 (290 and 290 bp). The rice genotypes with superior haplotypes for early seedling vigour are BMF536, BMF540, BMF525, MM129 and MDP2.

CONCLUSIONS

In conclusion, here we demonstrated that the markers RM20429 and RM3 are associated with seedling vigour index whereas RM528 and RM400 are associated with germination percentage. Therefore, these markers can be utilized to develop varieties suitable for DSR conditions through haplotype-based breeding. In addition, the rice genotypes with superior haplotypes can be of immense value to use as donors or can be released as varieties also under DSR conditions.

Next-generation bulked segregant analysis for Breeding 4.0

Functional cloning and manipulation of genes controlling various agronomic traits are important for boosting crop production. Although bulked segregant analysis (BSA) is an efficient method for functional cloning, its low throughput cannot satisfy the current need for crop breeding and food security. Here, we review the rationale and development of conventional BSA and discuss its strengths and drawbacks. We then propose next-generation BSA (NG-BSA) integrating multiple cutting-edge technologies, including high-throughput phenotyping, biological big data, and the use of machine learning. NG-BSA increases the resolution of genetic mapping and throughput for cloning quantitative trait genes (QTGs) and optimizes candidate gene selection while providing a means to elucidate the interaction network of QTGs. The ability of NG-BSA to efficiently batch-clone QTGs makes it an important tool for dissecting molecular mechanisms underlying various traits, as well as for the improvement of Breeding 4.0 strategy, especially in targeted improvement and population improvement of crops.

Machine learning bridges omics sciences and plant breeding

Some of the biological knowledge obtained from fundamental research will be implemented in applied plant breeding. To bridge basic research and breeding practice, machine learning (ML) holds great promise to translate biological knowledge and omics data into precision-designed plant breeding. Here, we review ML for multi-omics analysis in plants, including data dimensionality reduction, inference of gene-regulation networks, and gene discovery and prioritization. These applications will facilitate understanding trait regulation mechanisms and identifying target genes potentially applicable to knowledge-driven molecular design breeding. We also highlight applications of deep learning in plant phenomics and ML in genomic selection-assisted breeding, such as various ML algorithms that model the correlations among genotypes (genes), phenotypes (traits), and environments, to ultimately achieve data-driven genomic design breeding.

From Genetic Maps to QTL Cloning: An Overview for Durum Wheat

Durum wheat is one of the most important cultivated cereal crops, providing nutrients to humans and domestic animals. Durum breeding programs prioritize the improvement of its main agronomic traits; however, the majority of these traits involve complex characteristics with a quantitative inheritance (quantitative trait loci, QTL). This can be solved with the use of genetic maps, new molecular markers, phenotyping data of segregating populations, and increased accessibility to sequences from next-generation sequencing (NGS) technologies. This allows for high-density genetic maps to be developed for localizing candidate loci within a few Kb in a complex genome, such as durum wheat. Here, we review the identified QTL, fine mapping, and cloning of QTL or candidate genes involved in the main traits regarding the quality and biotic and abiotic stresses of durum wheat. The current knowledge on the used molecular markers, sequence data, and how they changed the development of genetic maps and the characterization of QTL is summarized. A deeper understanding of the trait architecture useful in accelerating durum wheat breeding programs is envisioned.