A first look at the genome structure of hexaploid 'Black Mitcham' peppermint (Mentha piperita L.)

A first look at the genome structure of hexaploid ‘Black Mitcham’ peppermint (Mentha piperita L.) | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results A first look at the genome structure of hexaploid ‘Black Mitcham’ peppermint (Mentha piperita L.) View ORCID Profile Samuel Talbot , Iovanna Pandelova , B. Markus Lange , View ORCID Profile Kelly Vining doi: https://doi.org/10.1101/2024.03.15.585188 Samuel Talbot 1 Department of Horticulture, Oregon State University , Corvallis, Oregon, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Samuel Talbot For correspondence: talbots{at}oregonstate.edu Iovanna Pandelova 1 Department of Horticulture, Oregon State University , Corvallis, Oregon, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site B. Markus Lange 2 Institute of Biological Chemistry, Washington State University , Pullman, Washington, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Kelly Vining 1 Department of Horticulture, Oregon State University , Corvallis, Oregon, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Kelly Vining Abstract Full Text Info/History Metrics Preview PDF Abstract Peppermint, Mentha xpiperita L., is a hexaploid (2n = 6x = 72) and the predominant cultivar of commercial mint oil production in the US. This cultivar is threatened because of high susceptibility to the fungal disease Verticillium wilt, caused by Verticillium dahliae . This report details the first draft polyploid chromosome-level genome assembly for this mint species. The ‘Black Mitcham’ genome resource will broaden comparative studies of disease resistance, essential oil biosynthesis, and hybridization events within the genus Mentha . It will also be a valuable contribution to the body of phylogenetic studies involving Mentha and other genera that contain species with varying ploidy levels. Introduction Mints ( Mentha spp.) are commercially grown for their distilled monoterpene-rich essential oils. Extracts are used for aroma and flavoring in a wide variety of consumer products ranging from cosmetics to candies, medicine and dental care. The major species of import to industry are spearmints M. spicata (Native spearmint), M . ×gracilis (Scotch spearmint) and peppermint ( M . × piperita ). The peppermint cultivar ‘Black Mitcham’ has been the most widely-grown mint for much of the history of commercial production in the United States. First grown in England in the 1750s, then in colonial New England ( Landing 1969 ), ‘Black Mitcham’ is highly prized for its oil quality and yield. However, this clonally-propagated herbaceous perennial is highly susceptible to the vascular wilt fungus Verticillium dahliae . ‘Black Mitcham’ is also male-sterile and not amenable to traditional crossing, meaning introgression of resistance from other mints is not an option. Irradiation of ‘Black Mitcham’ resulted in the release of two cultivars in the 1970s that showed higher field resistance to Verticillium wilt, Todd’s Mitcham and Murray Mitcham ( Murray and Todd 1972 ; Todd et al . 1977 ), but these cultivars are not grown widely, and ‘Black Micham’ continues to dominate the acreage for a crop with peppermint-like oil characteristics. M . × piperita has a complex allohexaploid genome. It was first determined to be a natural hybrid of M. aquatica and M. spicata based on karyotype data ( Harley and Brighton 1977 ), where chromosome numbers of M . × piperita were either 2n=6x=66 or 2n=6x=72. Molecular marker studies have indicated that M. spicata is itself a hybrid of M. longifolia and M. suaveolens ( Gobert et al . 2002 , 2006 ). ‘Black Mitcham’s chromosome composition is 2n=6x=72. With advances in long-read DNA sequencing technology, plus concurrent advances in chromatin-based methods for chromosome scaffolding, larger, more complex plant genomes are being assembled to whole-chromosome level, often including telomeres. This has been done for the accession of the diploid mint species used for genetic studies, Mentha longifolia CMEN 585 (PI 557767) ( Vining et al . 2022 ). In that genome assembly, genes encoding key enzymes in the monoterpene biosynthesis pathway have been located on chromosomes. Still, polyploidy remains a challenge for chromosome scaffolding and haplotype phasing of plant genomes. As a sterile allohexaploid, the genome of ‘Black Mitcham’ is presumed to have not undergone meiotic recombination since it was first cultivated. Therefore, its subgenome structure is expected to be preserved. Here, we present the first draft genome assembly and gene annotation of ‘Black Mitcham’ peppermint. It was produced through a combination of Pacific Biosciences HiFi sequencing and Omni-C-based scaffolding, and contains partially-resolved haplotypes. Materials and Methods Plant material Clonally-propagated plant material from ‘Black Mitcham’ peppermint (PI 557937, local ID CMEN 133) was obtained from the USDA National Clonal Germplasm Repository in Corvallis, Oregon, USA. It was maintained at the Oregon State University West greenhouse complex by regularly transplanting a small wedge of soil containing stem and root material into fresh potting soil. Genome sequencing and assembly High molecular weight genomic DNA was isolated from young, unexpanded leaf tissue using a modified cetyl trimethyl ammonium bromide method ( Healey et al . 2014 ). Library preparation and sequencing on a Pacific Biosciences Sequel II instrument were done at Oregon CBD (Independence, OR). For high-throughput chromosome conformation capture (Hi-C), young, unexpanded leaf tissue was sent to Cantata Bio (Santa Cruz, CA, USA) for tissue processing, chromatin isolation and Omni-C library preparation. Libraries were sequenced as 150bp PE reads on an Illumina HiSeqX platform. An initial genome size was estimated with a K-mer analysis of raw HiFi reads using jellyfish (version 2.3.0, RRID: SCR_005491) and the web version of GenomeScope (version 2.0, RRID: SCR_017014) with settings: k-mer length of 31, read length of 15,000 bp, and ploidy of six. Raw PacBio HiFi reads were assembled using hifiasm (version 0.16.1-r375, RRID: SCR_0121069) ( Cheng et al., 2021 ). ‘Black Mitcham’ was assembled using the --primary flag. The Arima HiC mapping pipeline ( https://github.com/Armia/Genomics/mapping_pipeline ) was followed to map Omni-C reads to the respective genome assembly. To scaffold the contig assemblies into pseudo-chromosomal scaffolds, YaHs (version 1.1, RRID: SCR_021172) was run using the Hi-C aligned, read name sorted bam file (Zhao et al., 2022). A Hi-C contact map was generated and manually curated by contig merging and rearrangement within JuiceBox (version 1.11.08). This was done to obtain an accurate number of pseudomolecules for the species based on expected pseudomolecule size according to alignments of M. longifolia and suggested protocols by Aiden et al. (2021). Final assembly metrics were generated by a custom script; assembly completeness was assessed with BUSCO (version 5.5.2, RRID: SCR_015008) in genome mode, using the Embryophyta_odb10 dataset ( Manni et al., 2021 ). To assess long-range structural variations, ‘Black Mitcham’ was compared to the collapsed diploid assembly of M. longifolia V3 using minimap2 with divergence rate set to 20 percent (version 2.23-r1111, RRID: SCR_018550), SyRI (version 1.6.3, RRID: SCR_023008) and visualized by plotsR ( Goel et al . 2019 ; Li et al . 2021; Goel and Schneeberger 2022 ). Repeat identification To create a repeat library of transposable element families, EDTA (version 2.1, RRID: SCR_XYZ) was used on the finalized genome assembly with parameters: --anno 1 --sensitive ( Ou et al., 2019 ). EDTA is composed of a number of tools, including TIR-Learner, Generic Repeat Finder, HelitronScanner and TEsorter. Low complexity DNA sequences and repetitive regions identified by EDTA were soft masked prior to gene annotation. The quality of the genomes assembled repetitive regions were assessed using the long terminal repeat (LTR) assembly index (LAI); this pipeline was composed of LTRharvest in GenomeTools (version 1.6.1, RRID: SCR_016120), LTR_FINDER (version 1.2, RRID: SCR_015247), and LTR_retriever (version 2.9.6, RRID: SCR_017623) using suggested parameters to predict and combine likely full length candidate LTR-RTs (retrotransposons) (Gremme et al., 2013; Ellinghaus et al., 2008 ; Xu and Wang, 2007 ; Ou and Jiang 2019 ; Su et al., 2019 ; Shi and Liang, 2019 ; Xiong et al., 2014 ; Zhang et al.., 2022 ; Ou et al., 2018 ). Calculation of the LAI index was based on the formula: Structural gene annotation Gene prediction and annotation was facilitated by 150bp PE Illumina RNA-Seq data derived from ‘Black Mitcham’ root and stem tissue (unpublished), and concatenated with glandular trichome from M. xpiperita ( Ahkami et al., 2015 ) and flower tissue (Boachon et al., 2018) for a total of ∼380 million reads. Structural annotation of protein-coding genes were identified using the gene prediction software AUGUSTUS and GeneMark-ETP+, integrated by BRAKER3 ( Stanke et al., 2006 , 2008 ; Gotoh 2008 ; Buchfink et al., 2015 ; Hoff et al., 2016 , 2019 ; Kovaka et al., 2019 ; Pertea and Pertea 2020 ; Brůna et al., 2021 , 2023 ). First, RNA-Seq reads were aligned to the chromosome-level assembly using the splice-aware aligner Hisat2 ( Kim et al., 2019 ) to generate a bam file. Second, BRAKER3 was run using the soft masked genome output from EDTA, the RNA-Seq bam file, and a curated Viridiplantae odb11 protein set. For homology-based annotation, a protein set derived from the previous M. longifolia genome assembly ( Vining et al., 2022 ) and two unpublishe d Mentha diploid species assemblies consisted of 187,098 proteins, and was used as input to BRAKER2 with GenomeThreader (Gremme 2013) with AUGUSTUS ab-initio and GALBA ( Brůna et al., 2023 ; Li 2023 ), separately. Gene predictions of the respective BRAKER3 and homology-based annotation runs were assessed for quality, deduplicated, and combined using TSEBRA with default settings (-c braker3.config) (Gabriel et al., 2021). Completeness of the predicted annotation sets were assessed using BUSCO protein mode with the Embryophyta odb10 data set. The proteome set was additionally vetted with OMArk (version 0.3.0) using default settings, the OMAmer Viridipla ntae v2.0.0.h5 database, and a .splice file representing all alternatively spliced variants of transcripts ( Nevers et al., 2024 ). Functional gene annotation A single “best” haplotype was selected for functional analysis, consisting of 12 pseudo-chromosomal scaffolds with the highest quality alignment to M. longifolia V3. This set of chromosomes and their respective annotated gene models were subject to predictive functional analysis using within OmicsBox (version 3.1); the OmicsBox pipeline included CloudBLAST using BLASTx, InterPro, GO Merge, GO Mapping, and GO Annotation plus validation (Götz et al., 2008; Paysan-Lafosse et al., 2023 ). Conservation of putative high confidence gene models between assemblies was assessed using OrthoFinder (version 2.5.4, RRID: SCR_017118) (Emms and Kelly 2019). Results and Discussion Genome assembly A total of 1.9 million PacBio HiFi reads with an average length of 18,304 bp were generated from one 8M SMRT cell, resulting in 34.8 Gb of sequencing data for M . ×piperita ‘Black Mitcham’ (Supplement Table S1). K-mer counts of the hexaploid ‘Black Mitcham’ identified three peaks and a haplotype genome size estimate of 342 Mb (Supplement Figure S1). ‘Black Mitcham’ was assembled using hifiasm and the --primary flag, generating 610 contigs for a total of 2,040 Mb and an N50 of 27.7 Mb ( Table 1 ), representing 84% coverage of the 2.4 Gb expected genome size. View this table: View inline View popup Download powerpoint Table 1. Summary statistics for the M. longifolia and ‘Black Mitcham’ peppermint genome assemblies. The hifiasm haplotype assemblies were inputs to the chromosome scaffolding process. The Omni-C protocol (Cantata Biosciences) was used to generate the sequencing library which was then scaffolded using YaHs (version 1.1), and manually curated within JuiceBox. Approximately 40 million PE 150 bp reads were generated for Hi-C, for a total yield of ∼12 Gb (6x coverage) (Table S1). The scaffolded chromosome-level assembly spans 1,974 Mb, capturing 96% of the hifiasm primary assembly. Following manual-curation within JuiceBox based on minimap2 alignments to M. longifolia V3, 72 pseudo-chromosomal scaffolds were generated. BUSCO results in genome mode showed that the assembly was high quality and captured >98% of conserved genes in the embryophyta odb10 dataset ( Table 1 ). Characterization of repeats To further vet the genome assembly, the LTR Assembly Index was calculated, wherein a LAI score less than 10 indicates draft quality, 10-20 as reference quality, and gold standard with an LAI score greater than 20 (Ou et al., 2022). Subsequent LAI analysis of the reference M. longifolia V3 was estimated at 17.9, whereas the LAI score of ‘Black Mitcham’ was 10.13 and indicative of a draft genome assembly ( Table 1 ). Prior to gene annotation, genomic repeats were identified on all assemblies for downstream masking. The proportion of repeats and unknown elements identified by EDTA resulted in ‘Black Mitcham’ having ∼62% of its genome masked (Supplement Table S2). This proportion of repeats in ‘Black Mitcham’ is significantly higher than M. longifolia V3 which had ∼45% of the genome masked. The majority of repeats were Class I Long Terminal Repeats (LTRs), with 32.3% of the genome composed of the Copia or Gypsy superfamily. A significant proportion of the genome (12.5%) consisted of helitron elements. Helitrons are unique transposable elements that are thought to significantly contribute to genome rearrangements, gene fragment duplications, exon shuffling and chimeric transcript generation ( Barro-Trastoy and Köhler, 2024 ). Published helitron content estimates vary widely among plant species and between genotypes within a species; in the hexaploid wheat cultivar ‘AK58’, helitrons made up 6% of total genome size whereas in ‘Chinese Spring’ they made up only 0.047% ( Wang et al . 2022 ). Such a difference in helitron density could be attributed to computational difficulty in distinguishing helitron elements that are embedded in other repetitive sequences. Genome annotation For ‘Black Mitcham’, 247,493 protein-coding genes were annotated in the genome assembly, representing roughly ∼41,200 genes per haplotype. The number of gene models in ‘Black Mitcham’, when considering an individua l haplotype, is comparable to the unphased M. longifolia V3 diploid assembly annotation of 42,107 genes. Translated coding sequences of putative gene models were subject to BUSCO analysis and revealed that the annotation set was 99.4% complete, although nearly all complete copies were duplications, which is expected due to polyploidy ( Table 2 ). As an additional check, OMARK was used to compare M. longifolia V3 to ‘Black Mitcham’. The analysis showed that the majority of conserved hierarchical orthologous groups derived from the lamiids clade were duplicated in M. x piperita , with ∼36% of proteins having unknown lineage placement ( Figure 1 ). A set of twelve Black Mitcham scaffolds with the best alignment to the twelve M. longifolia V3 chromosomes was chosen to represent one Black Mitcham haplotype. This haplotype contained 43,758 gene models, which were then used as input to OmicsBox for functional annotation. A total of 32,765 (∼75%) gene models was given a functional description (Supplement Figure 2 ). View this table: View inline View popup Download powerpoint Table 2. Assessment of annotation completeness in M. longifolia and ‘Black Mitcham’. Download figure Open in new tab Figure 1. OMArk results of Gene annotation sets of M. longifolia and ‘Black Mitcham’. Download figure Open in new tab Figure 2. SyRI plot of twelve ‘Black Mitcham’ pseudo-chromosomes against the M. longifolia V3 genome assembly. To assess gene models with shared homology, OrthoFinder (version 2.5.4, RRID: ) was run with the annotated amino acid sequences derived from M. longifolia V3 and the ‘Black Mitcham’ gene set. Approximately 77% (223,735) gene models were assigned orthogroups were categorized into orthogroups, with ∼63% of these being orthogroups with both species present (Supplement Table S3). Of the species-specific orthogroups, the large majority (67%) of these orthogroups were composed of a single gene model. Nearly 66,000 (23%) gene models were unassigned. The large number of single copy orthogroups and unassigned gene models is indicative of both novel gene models and highly fragmented genes. Synteny between ‘Black Mitcham’ and M. longifolia As an initial step to identify syntenous regions between ‘Black Mitcham’ and its hypothesized ancestral species, the twelve highest-quality ‘Black Mitcham’ pseudo-chromosome scaffolds were aligned to those of M. longifolia V3 using minimap2 and SyRI, then pairwise alignments were plotted using plotsr. Only ∼40% of the total length of the ‘Black Mitcham’ scaffolds aligned meaningfully to those of M. longifolia (Supplement Table S4, S5). Of the syntenous regions between the two genomes, the majority of alignments contained inversions ( Figure 2 ). These results were expected for several reasons. First, the ‘Black Mitcham’ subgenome haplotypes are only partially resolved, and are not defined in any way based on hypothesized ancestry. Second, the specific representatives of the hypothesized ancestral species subgenome contributors are unknown. Third, the M. longifolia diploid ‘CMEN 585’ is from South Africa and is assumed to not be a direct ancestor of ‘Black Mitcham’ which reportedly arose in Europe. The results reported here open the door to further exploration of the origin of ‘Black Mitcham’ peppermint, including definition of subgenomes by species-of-origin, as has been done for the allo-octoploid cultivated strawberry, Fragaria × annanassa ( Edger et al . 2019 ). However, unlike the sexually fertile cultivated strawberry, the chromosomes in the subgenomes of ‘Black Mitcham’ are presumed to be frozen in time, awaiting discovery. Data Availability The primary assembly and related annotation will be available through mintgenomes.oregonstate.edu as a fully accessible genome browser (in progress). These files with additional scripts that were used to assemble the genome are also accessible through our Github at https://github.com/ViningLab/ViningLab_code/blob/3289b81866d0e01c4fa824e460c42e2f0c5b126e/G3_BM_AssemblyPipeline . Acknowle dge ments We thank Cantata Biosciences for their collaboration on genome scaffolding for this project. This work was partially funded by the Mint Industry Research Council. References ↵ Ahkami , A. , S. Johnson , N. Srividya , and B. Lange , 2015 . Multiple levels of regulation determine monoterpenoid essential oil compositional variation in the mint family . Mol. Plant 8 : 188 – 191 . OpenUrl CrossRef ↵ Barro-Trastoy , D. , and C. Köhler , 2024 . Helitrons: genomic parasites that generate developmental novelties . Trends in Genetics . Boachon , B. , 2018 . Phylogenomic Mining of the Mints Reveals Multiple Mechanisms Contributing to the Evolution of Chemical Diversity in Lamiaceae . Molecular Plant 11 : 1084 – 1096 . OpenUrl CrossRef PubMed ↵ Brůna , T. , K. J. Hoff , A. Lomsadze , M. Stanke , and M. Borodovsky , 2021 . BRAKER2: automatic eukaryotic genome annotation with GeneMark-EP+ and AUGUSTUS supported by a protein database . NAR Genomics and Bioinformatics 3 : lqaa108. ↵ Brůna , T. , H. Li , J. Guhlin , D. Honsel , S. Herbold et al. , 2023 . GALBA: Genome Annotation with Miniprot and AUGUSTUS: Bioinformatics preprint . Bruna , T. , A. Lomsadze , and M. Borodovsky , 2023 . GeneMark-ETP: Automatic Gene Finding in Eukaryotic Genomes in Consistency with Extrinsic Data: Bioinformatics preprint . ↵ Buchfink , B. , C. Xie , and D. H. Huson , 2015 . Fast and sensitive protein alignment using DIAMOND . Nat Methods 12 : 59 – 60 . OpenUrl CrossRef PubMed ↵ Cheng , H. , G. T. Concepcion , X. Feng , H. Zhang , and H. Li , 2021 . Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm . Nat Methods 18 : 170 – 175 . OpenUrl CrossRef ↵ Edger , P. P. , T. J. Poorten , R. VanBuren , M. A. Hardigan , M. Colle et al. , 2019 . Origin and evolution of the octoploid strawberry genome . Nat Genet 51 : 541 – 547 . OpenUrl CrossRef ↵ Ellinghaus , D. , S. Kurtz , and U. Willhoeft , 2008 . LTRharvest, an efficient and flexible software for de novo detection of LTR retrotransposons . BMC Bioinformatics 9 : 18 . OpenUrl CrossRef PubMed ↵ Gobert , V. , S. Moja , M. Colson , and P. Taberlet , 2002 . Hybridization in the section Mentha (Lamiaceae) inferred from AFLP markers . Am. J. Bot . 89 : 2017 – 2023 . OpenUrl Abstract / FREE Full Text ↵ Gobert , V. , S. Moja , P. Taberlet , and M. Wink , 2006 . Heterogeneity of Three Molecular Data Partition Phylogenies of Mints Related to M . × piperita ( Mentha; Lamiaceae) . Plant Biology 8 : 470 – 485 . OpenUrl PubMed ↵ ( P. Robinson Goel , M. , and K. Schneeberger , 2022 . plotsr: visualizing structural similarities and rearrangements between multiple genomes ( P. Robinson , Ed.). Bioinformatics 38 : 2922 – 2926 . OpenUrl CrossRef ↵ Goel , M. , H. Sun , W.-B. Jiao , and K. Schneeberger , 2019 . SyRI: finding genomic rearrangements and local sequence differences from whole-genome assemblies . Genome Biol 20 : 277 . OpenUrl CrossRef PubMed ↵ Gotoh , O. , 2008 A space-efficient and accurate method for mapping and aligning cDNA sequences onto genomic sequence . Nucleic Acids Research 36 : 2630 – 2638 . OpenUrl CrossRef PubMed Web of Science Gotz , S. , J. M. Garcia-Gomez , J. Terol , T. D. Williams , S. H. Nagaraj et al. , 2008 . High-throughput functional annotation and data mining with the Blast2GO suite . Nucleic Acids Research 36 : 3420 – 3435 . OpenUrl CrossRef PubMed Web of Science ↵ Harley , R. M. , and C. A. Brighton , 1977 . Chromosome numbers in the genus Mentha L . Botanical Journal of the Linnean Society 74 : 71 – 96 . OpenUrl Web of Science ↵ Healey , A. , A. Furtado , T. Cooper , and R. J. Henry , 2014 . Protocol: a simple method for extracting next-generation sequencing quality genomic DNA from recalcitrant plant species . Plant Methods 10 : 21 . OpenUrl CrossRef PubMed ↵ Hoff , K. J. , S. Lange , A. Lomsadze , M. Borodovsky , and M. Stanke , 2016 . BRAKER1: Unsupervised RNA-Seq-Based Genome Annotation with GeneMark-ET and AUGUSTUS . Bioinformatics 32 : 767 – 769 . OpenUrl CrossRef PubMed ↵ M. Kollmar Hoff , K. J. , A. Lomsadze , M. Borodovsky , and M. Stanke , 2019 . Whole-Genome Annotation with BRAKER , pp. 65 – 95 in Gene Prediction, edited by M. Kollmar . Methods in Molecular Biology , Springer New York , New York, NY. Hoff , K. J. , and M. Stanke , 2019 . Predicting Genes in Single Genomes with AUGUSTUS . CP in Bioinformatics 65 : e57 . OpenUrl Iwata , H. , and O. Gotoh , 2012 . Benchmarking spliced alignment programs including Spaln2, an extended version of Spaln that incorporates additional species-specific features . Nucleic Acids Research 40 : e161 – e161 . OpenUrl CrossRef PubMed ↵ Kim , D. , J. M. Paggi , C. Park , C. Bennett , and S. L. Salzberg , 2019 . Graph-based genome alignment and genotyping with HISAT2 and HISAT-genotype . Nat Biotechnol 37 : 907 – 915 . OpenUrl CrossRef PubMed ↵ Kovaka , S. , A. V. Zimin , G. M. Pertea , R. Razaghi , S. L. Salzberg et al. , 2019 . Transcriptome assembly from long-read RNA-seq alignments with StringTie2 . Genome Biol 20 : 278 . OpenUrl CrossRef PubMed ↵ Landing , J. E. , 1969 . American Essence: A History of the Peppermint and Spearmint Industry in the United States . A.M. Todd Foundation, Kalamazoo, Michigan, U.S . I. Birol Li , H. , 2018 . Minimap2: pairwise alignment for nucleotide sequences ( I. Birol , Ed.). Bioinformatics 34 : 3094 – 3100 . OpenUrl CrossRef PubMed ↵ A. Valencia Li , H. , 2023 . Protein-to-genome alignment with miniprot ( A. Valencia , Ed.). Bioinformatics 39 : btad014 . OpenUrl ↵ J. Kelley Manni , M. , M. R. Berkeley , M. Seppey , F. A. Simão , and E. M. Zdobnov , 2021 . BUSCO Update: Novel and Streamlined Workflows along with Broader and Deeper Phylogenetic Coverage for Scoring of Eukaryotic, Prokaryotic, and Viral Genomes ( J. Kelley , Ed.). Molecular Biology and Evolution 38 : 4647 – 4654 . OpenUrl CrossRef ↵ Murray , M. J. , and W. A. Todd , 1972 . Registration of Todd’s Mitcham peppermint . Crop Science 12 : 128 . OpenUrl ↵ Nevers , Y. , A. Warwick Vesztrocy , V. Rossier , C.-M. Train , A. Altenhoff et al. , 2024 . Quality assessment of gene repertoire annotations with OMArk . Nat Biotechnol . ↵ Ou , S. , J. Chen , and N. Jiang , 2018 . Assessing genome assembly quality using the LTR Assembly Index (LAI) . Nucleic Acids Research . ↵ Ou , S. , and N. Jiang , 2019 . LTR_FINDER_parallel: parallelization of LTR_FINDER enabling rapid identification of long terminal repeat retrotransposons . Mobile DNA 10 : 48 . OpenUrl Ou , S. , and N. Jiang , 2018 . LTR_retriever: A Highly Accurate and Sensitive Program for Identification of Long Terminal Repeat Retrotransposons . Plant Physiol . 176 : 1410 – 1422 . OpenUrl Abstract / FREE Full Text ↵ Ou , S. , W. Su , Y. Liao , K. Chougule , J. R. A. Agda et al. , 2019 . Benchmarking transposable element annotation methods for creation of a streamlined, comprehensive pipeline . Genome Biol 20 : 275 . OpenUrl CrossRef PubMed ↵ Paysan-Lafosse , T. , M. Blum , S. Chuguransky , T. Grego , B. L. Pinto et al. , 2023 . InterPro in 2022 . Nucleic Acids Research 51 : D418 – D427 . OpenUrl CrossRef ↵ Pertea , G. , and M. Pertea , 2020 . GFF Utilities: GffRead and GffCompare . F1000Res 9 : 304 . OpenUrl ↵ Shi , J. , and C. Liang , 2019 . Generic Repeat Finder: A High-Sensitivity Tool for Genome-Wide De Novo Repeat Detection . Plant Physiol . 180 : 1803 – 1815 . OpenUrl Abstract / FREE Full Text ↵ Stanke , M. , M. Diekhans , R. Baertsch , and D. Haussler , 2008 . Using native and syntenically mapped cDNA alignments to improve de novo gene finding . Bioinformatics 24 : 637 – 644 . OpenUrl CrossRef PubMed Web of Science ↵ Stanke , M. , O. Schöffmann , B. Morgenstern , and S. Waack , 2006 . Gene prediction in eukaryotes with a generalized hidden Markov model that uses hints from external sources . BMC Bioinformatics 7 : 62 . OpenUrl CrossRef PubMed ↵ Su , W. , X. Gu , and T. Peterson , 2019 . TIR-Learner, a New Ensemble Method for TIR Transposable Element Annotation, Provides Evidence for Abundant New Transposable Elements in the Maize Genome . Molecular Plant 12 : 447 – 460 . OpenUrl CrossRef PubMed ↵ Todd , W. A. , R. J. Green , and C. E. Horner , 1977 . Registration of Murray Mitcham Peppermint1(Reg. No. 2) . Crop Science 17 : 188 – 188 . OpenUrl ↵ J. Udall Vining , K. J. , I. Pandelova , I. Lange , A. N. Parrish , A. Lefors et al. , 2022 . Chromosome-level genome assembly of Mentha longifolia L. reveals gene organization underlying disease resistance and essential oil traits ( J. Udall , Ed.). G3 Genes|Genomes|Genetics 12 : jkac112 . OpenUrl ↵ Wang , Z. , G. Zhao , Q. Yang , L. Gao , C. Liu et al. , 2022 . Helitron and CACTA DNA transposons actively reshape the common wheat - AK58 genome . Genomics 114 : 110288 . OpenUrl ↵ Xiong , W. , L. He , J. Lai , H. K. Dooner , and C. Du , 2014 . HelitronScanner uncovers a large overlooked cache of Helitron transposons in many plant genomes . Proc. Natl. Acad. Sci. U.S.A . 111 : 10263 – 10268 . OpenUrl Abstract / FREE Full Text ↵ Xu , Z. , and H. Wang , 2007 . LTR_FINDER: an efficient tool for the prediction of full-length LTR retrotransposons . Nucleic Acids Research 35 : W265 – W268 . OpenUrl CrossRef PubMed Web of Science ↵ Zhang , R.-G. , G.-Y. Li , X.-L. Wang , J. Dainat , Z.-X. Wang et al. , 2022 . TEsorter: An accurate and fast method to classify LTR-retrotransposons in plant genomes . Horticulture Research 9 : uhac017 . OpenUrl ( C. Alkan Zhou , C. , S. A. McCarthy , and R. Durbin , 2023 . YaHS: yet another Hi-C scaffolding tool ( C. Alkan , Ed.). Bioinformatics 39 : btac808 . OpenUrl CrossRef View the discussion thread. Back to top Previous Next Posted March 16, 2024. Download PDF Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following A first look at the genome structure of hexaploid ‘Black Mitcham’ peppermint (Mentha piperita L.) Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share A first look at the genome structure of hexaploid ‘Black Mitcham’ peppermint (Mentha piperita L.) Samuel Talbot , Iovanna Pandelova , B. Markus Lange , Kelly Vining bioRxiv 2024.03.15.585188; doi: https://doi.org/10.1101/2024.03.15.585188 Share This Article: Copy Citation Tools A first look at the genome structure of hexaploid ‘Black Mitcham’ peppermint (Mentha piperita L.) Samuel Talbot , Iovanna Pandelova , B. Markus Lange , Kelly Vining bioRxiv 2024.03.15.585188; doi: https://doi.org/10.1101/2024.03.15.585188 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Genomics Subject Areas All Articles Animal Behavior and Cognition (7643) Biochemistry (17717) Bioengineering (13910) Bioinformatics (42018) Biophysics (21480) Cancer Biology (18629) Cell Biology (25537) Clinical Trials (138) Developmental Biology (13392) Ecology (19935) Epidemiology (2067) Evolutionary Biology (24356) Genetics (15617) Genomics (22531) Immunology (17755) Microbiology (40438) Molecular Biology (17200) Neuroscience (88706) Paleontology (667) Pathology (2840) Pharmacology and Toxicology (4832) Physiology (7657) Plant Biology (15171) Scientific Communication and Education (2046) Synthetic Biology (4304) Systems Biology (9828) Zoology (2272)