A roadmap for gene functional characterisation in crops with large genomes: Lessons from polyploid wheat

Abstract

Understanding the function of genes within staple crops will accelerate crop improvement by allowing targeted breeding approaches. Despite their importance, a lack of genomic information and resources has hindered the functional characterisation of genes in major crops. The recent release of high-quality reference sequences for these crops underpins a suite of genetic and genomic resources that support basic research and breeding. For wheat, these include gene model annotations, expression atlases and gene networks that provide information about putative function. Sequenced mutant populations, improved transformation protocols and structured natural populations provide rapid methods to study gene function directly. We highlight a case study exemplifying how to integrate these resources. This review provides a helpful guide for plant scientists, especially those expanding into crop research, to capitalise on the discoveries made in Arabidopsis and other plants. This will accelerate the improvement of crops of vital importance for food and nutrition security.

Keywords: crop genetics; genomics; plant biology; polyploidy; wheat.

Figure 1.. Gene homology within polyploid wheat.

Due to two separate hybridisation events, genes in polyploid wheat will be present in multiple copies called homoeologs, which usually have similar chromosome locations. In the example of hexaploid bread wheat illustrated here, Gene X has homoeologs on chromosomes 1A, 1B and 1D. Duplicated genes, called paralogs (e.g. two copies of Gene Y on chromosome 7A), have evolved either within wheat or in one of its ancestral species. Most paralogs arise from intra-chromosomal duplications, although inter-chromosomal duplications can also occur.

Figure 2.. The roadmap for gene characterisation in wheat.

Overview of a proposed strategy to take a gene from any plant species, identify the correct wheat ortholog(s) using Ensembl Plants (https://plants.ensembl.org) and determine gene expression using expression browsers and gene networks. Suggestions for functional characterisation are provided including induced variation such as mutants, transgenics or Virus-Induced Gene Silencing (VIGs). In addition, publicly available populations incorporating natural variation are available. Finally steps for growing, genotyping and crossing plants are outlined. Links to detailed tutorials and further information are provided and can be found on www.wheat-training.com. (1) www.wheat-training.com/wp-content/uploads/Genomic_resources/pdfs/EnsemblPlants-primer.pdf (2) www.wheat-training.com/wp-content/uploads/Genomic_resources/pdfs/Finding-wheat-orthologs.pdf (3) www.wheat-training.com/wp-content/uploads/Genomic_resources/pdfs/Genome_assemblies.pdf (4) www.wheat-training.com/wp-content/uploads/Genomic_resources/pdfs/Gene-models.pdf (5) www.wheat-training.com/wp-content/uploads/Genomic_resources/pdfs/Expression-browsers.pdf (6) www.wheat-training.com/wp-content/uploads/Genomic_resources/pdfs/Gene-networks.pdf (7) www.wheat-training.com/wp-content/uploads/Functional_studies/PDFs/Selecting-TILLING-mutants.pdf (8) www.wheat-training.com/wp-content/uploads/Functional_studies/PDFs/Transgenics.pdf (9) www.wheat-training.com/wp-content/uploads/Functional_studies/PDFs/Virus_Induced_Gene_Silencing.pdf (10) www.wheat-training.com/wp-content/uploads/Functional_studies/PDFs/Populations.pdf (11) www.wheat-training.com/wp-content/uploads/Genomic_resources/Variation-data.pdf (2) www.wheat-training.com/wp-content/uploads/Wheat_growth/pdfs/Growing_Wheat_final.pdf (13) www.wheat-training.com/wp-content/uploads/Wheat_growth/pdfs/Speed_breeding.pdf (14) www.wheat-training.com/wp-content/uploads/Functional_studies/PDFs/Designing-genome-specific-primers.pdf (15) https://www.biosearchtech.com/support/education/kasp-genotyping-reagents/running-kasp-genotyping-reactions (16) http://www.wheat-training.com/wp-content/uploads/Wheat_growth/pdfs/How-to-cross-wheat-pdf.pdf (17) www.wheat-training.com/wp-content/uploads/Functional_studies/PDFs/Designing-crossing-schemes.pdf.

Figure 3.. Gene model ID nomenclature description from the five available gene annotations for domesticated polyploid wheat.

Here, one gene is used as an example to highlight the differences in gene ID nomenclature. Fields represented in the nomenclature are shown at the top with matching colours for the corresponding features in the gene names. Yellow background shows the CSS gene names with dark grey arrows pointing towards the corresponding field in the TGAC gene annotation (TGACv1, green background). Blue backgrounds show the gene nomenclatures for RefSeqv1.0 and v1.1 annotations (as used in Ensembl Plants), while the lilac background shows the nomenclature for Svevo v1.0 (modern durum wheat). (1) Two annotation versions are available for the RefSeqv1.0 genome assembly: RefSeqv1.0 (release annotation) and RefSeqv1.1 (improved annotation). These are differentiated by the annotation version number; ‘01’ for RefSeqv1.0 and ‘02’ for RefSeqv1.1. Otherwise, the annotations follow the same rules. (2) In the RefSeq and Svevo annotations, the biotype is represented by an additional identifier, where G = gene. (3) In the RefSeqv1.0 and v1.1 annotation, identifiers are progressive numbers in steps of 100 reflecting the relative position between gene models. For example, gene TraesCS5B02G236400 would be adjacent to gene TraesCS5B02G236500. However, it is important to note that the relative positions of genes may change in future genome releases as the assembly is improved, for example, if scaffolds are rearranged. In these cases, the gene order would no longer be retained. In the gene annotation for the tetraploid durum wheat cv. Svevo, the species name is TRITD (TRITicum Durum) and gene identifiers increase in steps of 10, rather than by steps of 100 as in the RefSeq hexaploid wheat annotation. Note that RefSeqv1.0 and v1.1 comprises High Confidence (HC) and Low Confidence (LC) gene models. Low Confidence gene models are flagged by the ‘LC’ at the end (not shown). HC and LC genes which otherwise display the same unique identifier are not the same locus and are not in sequential order. Hence, TraesCS5B02G236400 and TraesCS5B02G236400LC are both located on chromosome 5B, but are not the same gene nor are they physically adjacent. Similarly, genes from homoeologous chromosomes with the same subsequent numeric identifier are not necessarily homoeologous genes. For example, TraesCS5A02G236400, TraesCS5B02G236400 and TraesCS5D02G236400 are not homoeologous genes.

Figure 4.. Crossing scheme to combine TILLING or CRISPR/Cas9 single mutants in wheat.

In tetraploid wheat, mutations in the A and B genome homoeologs can be combined through a single cross. The F₁ plants are self-pollinated to produce a segregating F₂ population which contains homozygous double and single mutants, as well as wild type plants (screening using molecular markers required; only four genotypes shown). These F₂ progeny can be characterised for the phenotype of interest. The use of ‘speed breeding’ (Watson et al., 2018), reduces the time taken to reach this phenotyping stage from 12 (yellow) to 7.5 months (green). In hexaploid wheat, a second round of crossing is required to combine the mutant alleles from all three homoeologs. The F₂ progeny segregating for the three mutant alleles can be genotyped using molecular markers to select the required combination of mutant alleles (only five genotypes shown; all factorial combinations are possible). Speed breeding reduces the time taken to generate triple homozygous mutants for phenotyping to 10 months (green), compared to 16 months in conventional conditions (yellow). Self-pollination is represented by an X inside a circle. Combinations of wild type alleles from the A (AA), B (BB) and D (DD) genomes, as well as the mutant alleles from each genome (aa, bb and dd, respectively) are indicated.

Figure 5.. Case study exemplifying use of available resources for gene functional characterisation in wheat.

(A). The Ensembl Plants Gene Tree illustrates the identification of the wheat triad (green bar) most closely related to AtHSFB1 (shown in purple). (B) Using Os09g0456800 (the rice ortholog of AtHSFB1) as a BLASTp query against wheat predicted proteins independently identifies the same wheat triad. (C) Examination of RNA expression data from www.wheat-expression.com shows that the wheat triad is most highly expressed in the spike, with differential expression in abiotic and disease stress conditions. The samples are identified by tissue of origin (spike, green; grain, purple; leaves/shoots, orange; roots, yellow) and stress (none, light blue; abiotic, green; disease, dark blue) as they are on the website. (D) After identification of suitable wheat TILLING mutants, A and B genome homoeologs are combined via this example crossing scheme, demonstrating the four crosses required between the two selected mutations in each homoeolog. Note that the functional validation proposed in (D) is carried out using the tetraploid mutant population.

Figure 6.. The KnetMiner network illustrates the putative role of the wheat TBF1 orthologs in responding to abiotic stress.

The wheat orthologs of the Arabidopsis gene TBF1, here depicted as three copies of the gene HSFB1 (light blue triangles) fall in expression module three (brown arrow; WGCNA module 3). The genes in this module are enriched for GO terms such as ‘Response to Stress’ and ‘Response to Abiotic Stimulus’ (dark green pentagons). The HFSB1 homoeologs are predicted to regulate other genes (blue triangles) in the GENIE3 network (purple connecting arrows) which are associated with the drought tolerance trait ontology terms (light green pentagon). PTC mutations are available for all three HFSB1 homoeologs (dark green stars connecting with STOP GAINED SNP effect) in the Cadenza population.