Genome structure and molecular phylogeny of the only Eurasian Boechera species,Boechera falcata(Brassicaceae)

Genome structure and molecular phylogeny of the only Eurasian Boechera species, Boechera falcata (Brassicaceae) | 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 Genome structure and molecular phylogeny of the only Eurasian Boechera species, Boechera falcata (Brassicaceae) Danil Zilov , View ORCID Profile Terezie Mandáková , Marina Popova , Michael D. Windham , View ORCID Profile Vladimir Brukhin doi: https://doi.org/10.1101/2025.03.11.642644 Danil Zilov 1 Wellcome Sanger Institute, Wellcome Genome Campus , Hinxton, Cambridge, CB10 1SA, UK 2 ITMO University , Saint Petersburg 197101, Russia Find this author on Google Scholar Find this author on PubMed Search for this author on this site Terezie Mandáková 3 Central European Institute of Technology, Masaryk University , Czech Republic 4 Institute of Experimental Biology, Faculty of Science, Masaryk University , Czech Republic Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Terezie Mandáková For correspondence: vbrukhin{at}gmail.com Marina Popova 5 The Skolkovo Institute of Science and Technology , Moscow Find this author on Google Scholar Find this author on PubMed Search for this author on this site Michael D. Windham 6 Department of Biology, Duke University , Durham, U. S. A Find this author on Google Scholar Find this author on PubMed Search for this author on this site Vladimir Brukhin 7 Department of Molecular Biology and Biotechnology, School of Natural and Environmental Sciences, Newcastle University , NE1 7RU, UK 8 Lab of Embryology and Reproductive Biology, Komarov Botanical Institute , RAS, St. Petersburg, 2 Prof. Popov Str., 197376, Russia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Vladimir Brukhin For correspondence: vbrukhin{at}gmail.com Abstract Full Text Info/History Metrics Preview PDF Abstract Boechera falcata (Turcz.) Al-Shehbaz (earlier known as Arabis turczaninowii Ledeb.) is a herbaceous perennial belonging to the East Siberian, boreal-steppe ecotype. It is the only species of the diverse genus Boechera that grows on the Eurasian continent, all others being endemic to North America and Greenland. In all likelihood, Boechera falcata or its ancestral lineage migrated from North America to Eastern Siberia across the Bering Land Bridge when it was exposed during the height of Pleistocene glaciation. Boechera is interesting in that many species in this genus are allodiploid and triploid apomicts that arose through complex hybridization of sexual species and ecotypes. To date, the genomes of only two American Boechera species, B. stricta and B. retrofracta , have been sequenced, analyzed, and published. In the present study, we sequenced, assembled to the chromosome level, and analyzed the B. falcata genome, which was highly homozygous with a size of 189.36 Mb. Molecular phylogenetic analysis of the nuclear and organelle genomes revealed a high degree of relatedness of B. falcata to North American relatives. Investigation of the structure of pachytene, mitotic, and diakinesis chromosome spreads (n = 14) using cytogenetic analysis and comparative chromosome painting (CCP) allowed us to identify all 22 genomic blocks of crucifers and found that five of the seven B. falcata chromosomes were collinear with their corresponding chromosomes in the ancestral Boechereae genome, and two chromosomes had undergone pericentric and paracentric inversions. Allelic analysis of the apomixis marker APOLLO gene revealed that B. falcata contains only sex alleles of this gene. The availability of the genome of the only Asian Boechera species will facilitate studies of the evolution and phylogeny of Brassicaceae species and apomixis. Introduction As currently defined ( Alexander et al. 2013 ; Hay et al. 2023 ), the genus Boechera Á. Löve & D. Löve (Brassicaceae) comprises c. 75 sexual diploid taxa and c. 355 genetically distinct hybrid lineages with distributions concentrated in western North America. Boechera falcata (Turcz.) ( =Arabis turczaninowii Ledeb.), the sole species found in Eurasia, is endemic to Eastern Siberia and the Far East. Molecular marker data suggest its origin may be linked to the migration of ancestral forms from North America to Siberia over the Bering Land Bridge ( Al-Shehbaz, 2005 ; Windham and Al-Shehbaz, 2007 ; Kiefer et al., 2009 ; Alexander et al., 2013 ; Brukhin et al., 2019 ). Although earlier classifications placed members of Boechera within the genus Arabis L. based on superficially similar morphological traits, karyological studies revealed chromosomal differences, prompting Á. Löve and D. Löve (1975) to separate the genus Arabis (s.l.) into New World species with x = 7 (now classified as Boechera ) and Old World species with x = 8 (retained in Arabis ). Subsequent molecular phylogenetic analyses have confirmed that these two genera belong to distinct clades within the Brassicaceae (Koch et al., 2000; Beilstein et al., 2010 ; Nikolov et al., 2019 ; Hendriks et al., 2023 ), demonstrating that their similarities are convergent rather than indicative of a close evolutionary relationship. Species of the genus Boechera are closely related to the well-studied model plant Arabidopsis of the Brassicaceae family. Boechera is the only genus within the Brassicaceae family where apomixis is well documented ( Böcher, 1951 , 1969 ; Brukhin et al., 2019 ). Apomixis is asexual reproduction of plants through seeds, in which the embryo arises not from the fusion of male and female germ cells, as occurs in sexual reproduction, but is a genetic clone of the maternal plant and develops parthenogenetically. The ability to produce clones of a maternal plant and hence fix the desired genotypes in subsequent generations of various agricultural species will facilitate the development of effective plant breeding strategies based on the knowledge of the genetic aspects of apomixis, and understanding the molecular mechanisms underlying it has a great potential for application in agriculture due to its ability to fix valuable genetic traits of the maternal plant in an indefinite series of generations ( Grossniklaus et al., 2002 ; Bicknell and Koltunow, 2004 ; Van Dijk, 2009; Brukhin, 2017 ). Allodiploid and triploid apomictic accessions of Boechera show signs of hybridogenic origin, due to which changes in their chromosome structure are observed with characteristic occurrence of alloploidy, aneuploidy, substitution of homologous chromosomes and the appearance of aberrant extra chromosomes ( Mandáková et al., 2015 ; Brukhin et al., 2019 ). Therefore, species from the genus Boechera are unique models for molecular genetic studies of apomixis and the influence of hybridization of sexual forms on its occurrence. To date, whole genome assemblies have been published for only two Boechera species: B. stricta (Lee et al., 2017) and B. retrofracta ( Kliver et al., 2018 ). These species are of particular interest because, while they reproduce predominantly sexually, many of their hybrids are apomicts. The Far Eastern Boechera falcata studied here is a key outgroup species for understanding the genome structure of the genus and, possibly, the evolution of genetic loci associated with apomixis. This study aims to: 1) Achieve a chromosome-scale genome assembly of B. falcata . 2) Perform a phylogenetic analysis to explore its relationship with North American Boechera species. 3) Analyze genome structure, perform Hi-C genomic analysis technique, comparative genome analysis, phylogenetic analysis based on nuclear, and chloroplast DNA. 4) Study of the chromosome structure exploiting CCP (comparative chromosome painting) analysis and the location of ACK (Ancestral Crucifer Karyotype) within the chromosomes (as was described in Mandáková et al., 2015 ). 5) Study alleles of the apomixis-associated APOLLO locus (encoding NEN exonuclease) in B. falcata and add to the phylogenetic tree of APOLLO locus isoforms of the Boechera species published earlier ( Kliver et al., 2018 ). Material and Methods 1. Plant Material Seeds of B. falcata were collected from plants ( Figure 1 ) in natural habitats: a petrophytic open community of Artemisia gmelinii Weber ex Stechm. and B. falcata on the southern slope with a steepness of 45° (Tenkinsky district of the Magadan region, 10 km southeast of the village of Orotuk - 62° 01’50.586” N, 148° 38’46.591” E). Download figure Open in new tab Figure 1. Plants of Boechera falcata (leave rosette and blooming plants with siliques) growing in the Kolyma River valley in the Magadan region, from which seeds were collected. Plants were cultivated from seeds in the greenhouse of CEITEC Masaryk University under the standard conditions (16/8 h light/dark, 21/18 °C, 15 µmol/m2/s). Specimens are deposited at the Herbarium of Masaryk University (BRNU): BRNU sheet numbers: 696364 ( https://brnu.jacq.org/BRNU696264 ) and 696267 ( https://brnu.jacq.org/BRNU696267 ) ( Suppl. Figure 1 ). Download figure Open in new tab Suppl. Figure 1 Herbarium specimen of B. falcata investigated, deposited in the herbarium of Masaryk University (BRNU). 2. Microsatellite genotyping Genomic DNA was extracted using the Qiagen DNeasy Plant Mini Kit. Microsatellite allele variation was assessed at 15 previously published loci (A1, A3, B6, Bdru266, BF3, BF9, BF11, BF15, BF18, BF19, BF20, C8, E9, ICE3, ICE14) following Beck et al. (2012) . Forward primers for each locus were labeled with either 6-FAM or HEX. Multiplex polymerase chain reaction (PCR) was performed for sets of three loci simultaneously. Each 50 μl reaction contained 15 μl of 2× Qiagen Multiplex PCR Master Mix, 3 μM of the primer set, and approximately 40 ng of gDNA template. The PCR conditions included an initial denaturation at 95°C for 15 min, followed by 30 cycles of denaturation at 95°C for 30 s, annealing at 53°C for 90 s, and extension at 72°C for 60 s, with a final extension step at 60°C for 30 min. PCR products were first analyzed on a 1–3% agarose gel. Capillary electrophoresis was then performed by Macrogen using a 400HD standard. Electropherograms were analyzed with the Microsatellite plugin of Geneious software, and species identity was determined using the Boechera Microsatellite Website https://windhamlab.biology.duke.edu/ ( Li et al., 2017 ). 3. Chromosome preparation and comparative chromosome painting Mitotic and meiotic (pachytene) chromosome preparations were performed according to the protocol outlined by Mandáková and Lysak (2016) . Before analysis, suitable slides were pre-treated with RNase (100 mg/ml) and pepsin (0.1 mg/ml). Comparative chromosome painting was performed according to Mandáková et al. (2020) . Fluorescent signals were examined and captured using a Zeiss Axioimager epifluorescence microscope equipped with a CoolCube camera (MetaSystems). Images were acquired separately for each of the four fluorochromes using their respective excitation and emission filters (AHF Analysentechnik). The collected images were then pseudocolored and merged using Adobe Photoshop CS6 (Adobe Systems). 4. Whole Genome Sequencing Strategy DNA extraction and prob preparation DNA was extracted following Huang et al. (2023) protocol. The B. falcata genome was sequenced on the three WGS platforms: Illumina NovaSeq with 150bp PE sequencing run, final 75Gb data obtained, with 243x coverage; Pacbio sequel II (HiFi/CCS mode/cell) (1 SMRT cell), genome coverage - 129x; Hi-C genomic analysis technique ∼50M Read-Pairs, genome coverage - 30x. Raw Data Filtration and Pre-Processing Raw Illumina reads and HiC reads trimming were processed using Trimmomatic v0.32 ( Bolger et al., 2014 ) with the following parameters ILLUMINACLIP:2:30:10:2:True LEADING:3 TRAILING:3 MINLEN:36. HiFi reads evaluation of length and quality stats was performed with pauvre tool ( https://github.com/conchoecia/pauvre ). The quality assessment of HiFi reads using the Pauvre tool indicated a mean read length of 13,387 bases and an N50 value of 13,975 bases. The Phred quality scores ranged from 20 to 50, with a peak at 40 ( Suppl. Figure 2 ). Download figure Open in new tab Suppl. Figure 2. Distribution of read length and phred quality scores for the HiFi library. Genome Coverage Estimation Estimation of the genome coverage based on the 23-mer distribution and k -mer based statistics was performed using the a genomic k-mer counter Meryl ( https://github.com/marbl/meryl ), k-mer databases of HiFi and Illumina WGS reads, and GenomeScope2 ( Ranallo-Benavidez et al., 2020 ). 5. Genome Assembly and Quality Control For genome assembly we performed a bake off with four different assemblers: for HiFi reads: flye v2.9.2-b1786 ( Kolmogorov et al., 2019 ), verkko v1.4.1 ( Rautiainen et al., 2023 ), nextdenovo 2.5.2 ( Hu et al., 2023 ), and hifiasm v0.19.6-r595 ( Cheng et al., 2021 ) ( Table 1 ). Flye was run with the --keep-haplotypes option, while verkko and nextdenovo targeted a genome size of 200Mbp. Nextdenovo and hifiasm were executed with standard parameters for HiFi reads. The assembly process was automated using the hifiblender pipeline [ https://github.com/zilov/hifiblender ]. View this table: View inline View popup Download powerpoint Table 1. Comparative statistics of genome assembly by different assemblers Quality of the assembly was assessed using multiple metrics: N50, L50, BUSCO completeness, and QV (Quality Value). QUAST ( Gurevich et al., 2013 ) was utilized for contiguity statistics, BUSCO ( Seppey et al., 2019 ) for completeness assessment, and Merfin ( Formenti et al., 2022 ) for QV (Quality Value) calculation using a Meryl HiFi + Illumina hybrid k-mer database (k=23). Coverage of the genome was calculated with GenomeScope2 ( Ranallo-Benavidez et al., 2020 ). Haplotype phasing was performed using hapdup [ https://github.com/KolmogorovLab/hapdup ] with default parameters. Polishing was conducted with nextpolish ( Hu et al., 2020 ) using Illumina reads, with the number of steps (three for the first pseudo-haplotype, two for the second) determined by QV value progression checked on hybrid HiFi and Illumina Meryl database. Scaffolding and genome curation Hi-C was facilitated by yahs ( Zhou et al., 2023 ), followed by genome curation using juicebox ( Robinson et al., 2018 ). The hic-scaffolder pipeline [ https://github.com/zilov/hic-scaffolder ] streamlined Hi-C read alignment and scaffolding processes. Finally, we aligned the orientation and order of chromosomes to match the Boechera stricta assembly (NCBI GenBank assembly ID: GCA_018361395.1). 6. Organelle DNA Assembly and Annotation Mitochondrial and chloroplast genomes were assembled using contigs from the whole genome assembly after polishing and HiC scaffolding steps. For the mitochondrial genome, we employed MitoHiFi ( Uliano-Silva et al., 2023 ), using the B. stricta mitochondrion as a reference to identify and assemble a complete circular mitochondrial sequence. The chloroplast genome assembly was more complex. MitoHiFi was unable to resolve a circular molecule, so we used a manual approach. The B. stricta chloroplast genome served as a reference for identifying relevant contigs. We then performed a BLAST search to find intersections between these contigs. The chloroplast genome assembly required additional manual steps. While MitoHiFi software typically assembles circular organelle genomes, it failed to automatically reconstruct the complete circular chloroplast genome in our case. Therefore, we developed an alternative approach. First, we used the B. stricta chloroplast genome as a reference to identify chloroplast-derived contigs. Then, we performed BLAST analysis to find overlapping regions between these contigs. Using these overlapping sequences, we manually constructed the complete circular chloroplast genome. Chloroplast and mitochondrial genome annotation and visualization were performed using GeSeq ( Tillich et al., 2017 ) and manually curated by OGDRAW ( Greiner et al., 2019 ), respectively. 7. Nuclear Genome Annotation De novo Repeats Modeling With Repeatmodeler To call for repetitive elements in the genome we used EarlGrey ( Baril et al., 2024 ) repeat masking pipeline. A custom repeat database was created by combining the PlantRep database ( Luo et al., 2022 ) and the nrTEplants dataset ( Contreras-Moreira et al., 2021 ). Initial masking was conducted with the “eukarya” search term. De novo repeat identification performed with RepeatModeler ( Flynn et al., 2020 ). The custom database was then used for subsequent rounds of masking to ensure identification of repetitive elements specific to plant genomes. EarlGrey utilizes a combination of tools, including RepeatModeler ( Flynn et al., 2020 ), RepeatMasker [ https://repeatmasker.org/ ], LTR_FINDER ( Xu and Wang, 2007 ), and others to refine and cluster repeat sequences. For coding gene annotation, we employed BRAKER v3.0.8 (Gabriel et al., 2024) in compleasm (Huang and Li, 2023) mode, utilizing the Viridiplantae OrthoDB ( Kriventseva et al., 2019 ) protein database for homology-based prediction. 8. Comparative analysis of Boechera falcata and Boechera stricta genomes We compared the assembled genome of B. falcata with the published Boechera stricta genome (NCBI GenBank assembly ID: GCA_018361395.1). Both genomes were evaluated using QUAST and BUSCO. QV calculations were performed differently: for B. falcata , k-mer analysis was carried out based on the hybrid HiFi and Illumina reads ( https://github.com/arangrhie/T2T-Polish/tree/master/merqury ), while for B. stricta k-mer analysis performed using only Nanopore reads due to their availability. Repeat masking and annotation were performed on both genomes. Synteny analysis between B. falcata and B. stricta chromosomes was conducted using SyRI ( Goel et al., 2019 ). Whole-genome alignment visualization was generated with the help of D-GENIES (Cabanettes and Klop, 2018) to produce a comparative dotplot. 9. Phylogenetic Analysis of B. falcata Among the Other Boechera and Brassicaceae Species The phylogenetic analysis of B. falcata was conducted in the context of other Boechera and Brassicaceae species using a combination of Angiosperms353 and Brassicaceae764 probe sets, following a methodology similar to that described by Hay et al. (2023) . Loci were assembled using HybPiper version 2.1.7 with Illumina reads. Assembled loci were added to the existing locus files of other Boechera species. Each locus was aligned using MAFFT ( Katoh and Toh, 2008 ) with the L-INS-I method. Alignments were concatenated into a supermatrix using FASconCAT-G ( Kück and Longo, 2014 ) and subsequently trimmed using trimAl ( Capella-Gutiérrez et al., 2009 ) with the -automated1 setting to reduce gaps and missing data. Phylogenetic tree construction was performed using RAxML-NG v1.2.0 ( Kozlov et al., 2019 ), employing the GTR+F+R model and generating 1000 bootstrap replicates. To analyze the phylogeny based on the chloroplast genome, we extracted 47 chloroplasts genes (listed in Suppl. Table 3) from the complete chloroplast assemblies of Boechera species and other Brassicaceae species reported elsewhere ( Zhu et al., 2021 ). Phylogenetic analysis of chloroplast genomes was performed in MEGA (v.11.0.10): ClustalW(Codons) option with default settings was used for alignment of gene sequences. Phylogenetic tree was constructed with the Neighbor-Joining test with bootstrap 1000. 10. Analysis of APOLLO Sex- and Apo-alleles in B. falcata Genome The APOLLO gene ( Corral et al. 2013 ) was identified in the annotated genome using BLAST search. Additional gene sequences for phylogenetic analysis were obtained from Bakin et al. (2022) . Multiple sequence alignment was performed using MUSCLE (Edgar et al., 2004). Phylogenetic tree construction was carried out with RAxML-NG v1.2.0 ( Kozlov et al., 2019 ), employing the following parameters: -all -model JTT+G --bs-trees 1000 --tree pars{10}. 11. Visualization Visualization of HiC-plot was performed with cooler [ https://github.com/open2c/cooler ], with each point on the plot representing 80kbp. Circos plot was built with pyCirclize [ https://github.com/moshi4/pyCirclize ]. The phylogenetic trees were visualized with iTol ( Letunic and Bork, 2021 ). The synteny plots were built with plotsr (Correction to: plotsr: visualizing structural similarities and rearrangements between multiple genomes, 2022), dotplot of genome to genome alignment with dgenies ( Cabanettes and Klopp, 2018 ). Results 1. Chromosome count Chromosome number was determined from young anthers of ten plants cultivated from seeds, confirmed by microsatellite genotyping as B. falcata . All plants were confirmed to be diploid, with a chromosome count of 2 n = 14 ( Figure 2 ). Download figure Open in new tab Figure 2. Karyotype structure of B. falcata inferred from comparative chromosome painting (CCP). The seven chromosomes (BoeFa1–BoeFa7) were visualized through CCP using Arabidopsis BAC contigs as painting probes applied to pachytene, mitotic, and diakinesis chromosome spreads. Painting signals are shown in experimental colors, reflecting the fluorochrome(s) used to label specific genomic blocks (GBs). All chromosomes were counterstained with DAPI and presented as grayscale images. Scale bars, 10 µm. 2. Karyotype structure Bacterial artificial chromosome-based comparative chromosome painting was employed to investigate the genome structure of B. falcata . Probes were arranged according to the ancestral Boechereae genome structure ( Mandáková et al., 2020 ), allowing the mapping of all 22 crucifer genomic blocks ( Mandáková et al., 2019 ) onto B. falcata chromosomes (BoeFa1–BoeFa7) ( Figure 2 ; 3 ). Notably, five of the seven B. falcata chromosomes (BoeFa1, BoeFa2, BoeFa4, BoeFa5, BoeFa7) exhibit collinearity with their corresponding chromosomes in the ancestral Boechereae genome ( Mandáková et al., 2020 ). In contrast, BoeFa3 contains a pericentric inversion involving genomic block W, while BoeFa6 undergoes a paracentric inversion within its short arm, with breakpoints located within genomic blocks O and P ( Figure 2 ; 3 ). Download figure Open in new tab Figure 3. Chromosome evolution of B. falcata from the ancestral Boechereae genome ( Mandáková et al., 2020 ). 3. k-mer Based Statistics Indicates a High Level of B. falcata Genome Homozygosity k -mer spectrum built by GenomeScope2 software ( Ranallo-Benavidez et al., 2020 ) for both Illumina and HiFi reads is shown in Figure 4 . The 23-mer distribution has one major peak at 249× coverage corresponding to diploid 23-mers (shared between homologous chromosomes), also small heterozygous peaks (122× and 64×) were detected ( Figure 4 ). According to the assessment, the genome was highly homozygous with 99,9% of AA k-mers for both Illumina and HiFi reads. The genome size of B. falcata was estimated to be close to 185 Mbp by Illumina k-mers and 219 Mbp by HiFi k-mers, which is in the range of the previous estimations of a minimal genome size of ∼200 Mbp in Boechera ( Anderson et al., 2011 ). Homozygosity of genomes in Boechera is characteristic of sexual reproduction, since all apomicts studied are usually heterozygous, allodiploids or polyploids ( Brukhin et al., 2019 ). Sexuality in B. falcata was also confirmed by cytoembryological studies ( Vinogradova et al., 2023 ). Download figure Open in new tab Figure 4. Distribution of 23-mers for detection genome size and evaluation of homo/heterozygosity (A) for Illumina PE reads and (B) HiFi libraries. Only one major peak is present in both Illumina (at 249x coverage) and HiFi (129x) libraries. 4. Assessment of the Quality of Genome Assembly Performed by Different Assemblers To identify the most efficient and correct Boechera falcata genome construction, we compared four different assemblers: NextDenovo, flye, hifiasm, and verkko ( Table 1 ). The assemblies varied considerably in their contiguity and quality metrics. NextDenovo assembler demonstrated the highest contiguity with only 50 contigs achieving N50 of 12,407,843 bp, L50 of 7. Evaluation of the assembly completeness was performed using BUSCO, complete BUSCO score is 98.8% (95.8% single-copy, 3.0% duplicated). This assembly also exhibited the highest Merqury QV (62.83) and Merfin QV* (32.99) scores, indicating greater accuracy compared to the other assemblies. The hifiasm assembler produced the most contigs (1232) and achieved the highest N50 value of 30,472,172 bp. However, it showed a higher number of overrepresented k- mers and lower QV scores compared to the NextDenovo and flye assemblers. Indeed, all assemblies showed complete BUSCO genes (≥98.7%), indicating high assembly completeness under different assembly strategies. The GC content was similar in all assemblies and ranged from 35.95% to 37.85%. However, based on the obtained metrics, we chose the NextDenovo assembler for further haplotype phasing, polishing, analysis, and improvement of the Hi-C scaffolding due to its favorable balance of continuity, completeness, and accuracy. 5. Genome Polishing After splitting haplotypes to dual assembly with hapdup, both primary and alternate haplotype underwent three rounds of polishing using Illumina reads ( Table 2 ). Each polishing step progressively improved the assembly quality, as evidenced by the decreasing number of missed k-mers and increasing Merqury QV scores. After the final polishing step, the primary haplotype achieved a Merqury QV of 68.04, while the alternative haplotype reached 67.6, indicating high accuracy in both haplotypes. View this table: View inline View popup Download powerpoint Table 2. Genome polishing information 6. Hi-C Scaffolding and Chromosome-Level Assembly Following genome assembly, haplotype phasing, and polishing, we performed Hi-C scaffolding to achieve a chromosome-level assembly. This process resulted in the successful construction of 7 chromosomes, consistent with the known karyotype of Boechera species ( Fig. 5 ). The final assembly contained a total of 32 gaps. The assemblies of the primary and alternate haplotypes are available on the NCBI, BioProjrcts: PRJNA1077252 and PRJNA1100512, respectively. Download figure Open in new tab Figure 5. (A) Hi-C contact matrix of B. falcata genome at 80Kbp resolution. The seven distinct chromosomes are clearly visible along the diagonal, indicating successful chromosome-level assembly. The intensity of red coloration represents the frequency of interactions between genomic regions, with darker red indicating higher interaction frequencies. (B) Circos plot of the genome assembly. HiC map was build with 80kbp bin size, circos plot includes (1) lengths of chromosomes, (2) frequency of genes in 100kbp bin size, (3) frequency of long tandem repeats in 100kbp bin size and (4) frequency of rRNA genes in the same bin size. 7. Analysis of Repetitive Elements The repeat masking analysis revealed that 38.46% of the genome is made up of repetitive elements ( Table 3 ). Long Terminal Repeat (LTR) retrotransposons were the most common class of repeats, accounting for 19.76% of the genome with 24,870 instances identified. DNA transposons represented the second most prevalent class, masking 6.23% of the genome. Long Interspersed Nuclear Elements (LINEs) and Short Interspersed Nuclear Elements (SINEs) accounted for 2.39% and 0.008% of the genome, respectively. Other repetitive elements, including simple repeats, microsatellites, and RNA genes, comprised for a total of 0.65% of the genome. Additionally, 8.82% of the masked regions were classified as uncharacterized repetitive elements. View this table: View inline View popup Download powerpoint Table 3. Repeats revealed by RepeatMasker 8. Prediction of Protein-Coding Genes Homology-based prediction yielded a total of 27,516 protein-coding genes predicted. BUSCO analysis demonstrated completeness of annotation, with 99.2% of the 4,596 BUSCO groups present and complete ( Table 4 ). View this table: View inline View popup Download powerpoint Table 4. Homology-based gene prediction in Boechera falcata genome 9. Comparative analysis of Boechera falcata and Boechera stricta genomes Comparative analysis of the Boechera falcata and Boechera stricta genomes revealed similarities in overall structure, as well as notable differences in assembly quality ( Table 5 ). Both species possess 7 chromosomes and demonstrated highly comparable genome sizes of 189.36 Mb and 190.54 Mb and exhibited similar assembly contiguity metrics N50 of 27.20 Mb and 26.95 Mb for B. falcata and B. stricta correspondingly. BUSCO genome completeness scores are nearly identical for both species 98.8% and 98.7% for B. falcata and B. stricta accordingly, as well as gene counts, 27,516 in B. falcata , 27,538 in B. stricta . However, B. falcata demonstrated higher assembly accuracy with higher Merqury QV (68.04 vs. 27.49) and Merfin QV (33.08 vs. 23.32) scores. Both genomes were assembled to chromosome level as diploid assemblies. Thus, combination of high structural similarity and improved accuracy of the B. falcata genome assembly provides the basis for a detailed comparative analysis of its genome with other species of the genus Boechera . View this table: View inline View popup Table 5. Comparison of genome characteristics of B.falcata and B.stricta Analysis of structural variations between the Boechera falcata and Boechera stricta genomes revealed significant genomic rearrangements ( Figure 6 ). The comparison identified 294 syntenic regions, covering the majority of both genomes ( Table 6 ). A total of 66 inversions were detected, spanning approximately 23.67 Mb in the reference genome ( B. stricta ) and 23.60 Mb in the query genome ( B. falcata ). These inversions represent substantial chromosomal rearrangements among the two species. Large regions of both genomes were found to be non-syntenic: 19.24 Mb are unique to B. stricta and 18.36 Mb are unique to B. falcata , indicating species-specific genomic content. Figure 6 shows these structural variations on synteny plot (A) and dotplot (B). Download figure Open in new tab Figure 6. Illustration of the structural variations between Boechera stricta and Boechera falcata genomes. (A) chromosomal rearrangements, each chromosome of B. falcata is aligned to B. stricta . The orange regions represent inversions. Gray areas indicate syntenic regions. (B) Scatter plot of genome-wide comparison: chromosomes of B. stricta on the x- axis and B. falcata on the y-axis. Diagonal green lines represent syntenic regions with high sequence identity (>70%), and yellow regions indicate areas with lower sequence identity (<70%). Prominent large-scale inversions are visible, especially in chromosomes 1, 3, and 5 in (A) and corresponding off-diagonal patterns in (B). The dot plot highlights the overall conservation of chromosomal structure between the two species and also highlights significant inversions and areas of differing sequence identity across the genomes. View this table: View inline View popup Download powerpoint Table 6. Synteny analysis characteristics 10. B. falcta Falls into the Homozygous Sex Allele Clade on the APOLLO Phylogenetic Tree The APOLLO gene, encoding the NEN3 exonuclease, is an important apomixis- associated gene in Boechera ( Corral et al., 2013 ; Brukhin et al., 2019 ). The APOLLO locus has previously been shown to have multiple alleles ( Corral et al., 2013 ; Kliver et al., 2018 ). All studied apomictic plants carry at least one of the “apo” alleles, and the sexual accessions are homozygous for the “sex” alleles. We decided to further explore the APOLLO locus in the B. falcata genome. The phylogenetic analysis of the APOLLO gene revealed a clear division between two groups of Boechera species, in accordance with their mode of reproduction ( Figure 7 ), as was previously described ( Kliver et al. 2018 ). The tree shows two distinct clades within the Boechera genus, with strong bootstrap support (100) for the split between these groups. One clade comprises apomictic Boechera spp., including apomictic Boechera hybrid M4B, whose genome we assembled to chromosome scale previously (NCBI BioProject PRJNA774175), which forms a well-supported monophyletic group. The other clade comprises B. falcata , B. arcuata , B. retrofracta , B. stricta , and several Boechera spp. , along with multiple B. spatifolia accessions, which reproduce sexually. Notably, B. falcata is positioned within this second clade, clustering closely with sexual B. arcuata and Boechera spp. (KF705572.1). This study demonstrates clear phylogenetic differentiation of the APOLLO gene between the two groups of Boechera species, with the B. falcata group included in the clade that along with B. stricta and other known sexual species. Download figure Open in new tab Figure 7. Phylogenetic tree of APOLLO gene alleles in Boechera and related species. Sequences of Eutrema salsugineum, Arabidopsis thaliana, A. lyrata, A. haleri, Capsella rubella, and C. grandiflora were used as outgroups. The two main clades within Boechera are highlighted: apomictic species in red and sexual species in blue including B. falcata . The numbers in the nodes represent bootstrap support values. 11. Chloroplast and mitochondrial genome assembly and annotation To facilitate further evolutionary relationship study of non-model Boechera species, phylogenetic researches, and species identifications we performed B. falcata chloroplast and mitochondrial genomes assembly and annotation ( Figure 8 ; 9). 79 unique CDS, 30 tRNAs and 4 rRNA were identified in the chloroplast genome. Large single-copy (LSC) part and small single-copy (SSC) part of the chloroplast DNA occupy 84428 bp and 17952 bp respectively. GC contents is 36.41%. All these indicators are consistent with those in the chloroplast genomes of other Boechera species as shown in Table 7 . Download figure Open in new tab Figure 8. Circular representation of B. falcata chloroplast genome. Gray circle inside is GC% content. View this table: View inline View popup Download powerpoint Table 7. Comparison of several Boechera species chloroplast genomes Length of the mitochondrial DNA in B. falcata is 292 083 bp and GC content is 44.90% ( Figure 9 ). Comparative data on the mitochondrial genome size and GC content in B. falcata, B. stricta , and A. thaliana are shown in table 8 . Table 9 indicates the type and functions of the genes identified in mitochondrial DNA of B. falcata, B. stricta , and A. thaliana. All in all 33 protein-coding genes, 17 tRNAs and 3 rRNA were annotated in the mitochondrial genome of B. falcata . Download figure Open in new tab Figure 9. Circular diagram of B. falcata mitochondrial genome. Gray circle inside shows % of GC content. View this table: View inline View popup Download powerpoint Table 8. Comparative data on mitochondrial genome size and GC content in B. falcata, B. stricta , and A. thaliana . View this table: View inline View popup Table 9. Characteristics of the genes identified in mitochondrial DNA of B. falcata, B. stricta , and A. thaliana 12. Phylogeny of B. falcata and Its Relationship with Other Boechera and Brassicaceae species A phylogenetic tree of Brassicacae constructed based on chloroplast DNA ( Figure 10 ) shows that B. falcata is nested among the North American Boechera species, with the closest relatives of B. falcata being B. sufrutescens and B. pulchra . Download figure Open in new tab Figure 10. Phylogenetic tree of Brassicaceae species based on the chloroplast genes. The combination of Angiosperms353 and Brassicaceae764 probe sets revealed a comprehensive evolutionary relationship within the Boechereae tribe ( Figure 11 ). The tree strongly supports the deep divergence between Boechera sensu stricto and the non- Boechera Boechereae (NBB) clade, consistent with previous studies ( Hay et al., 2023 ). Within Boechera s.s., we observed three main core groups (Core Boechera I, II, and III). Boechera falcata , the focus of our study, is positioned within the Core Boechera III, sister to what Hay et al. (2023) called the Boreal clade. This placement provides new insights into the phylogenetic relationships of B. falcata within the broader Boechera genus. The tree topology and strong bootstrap support of many nodes demonstrate the power of combining these probe sets for resolving relationships within this complex group. Download figure Open in new tab Figure 11. Phylogenetic tree of Boechereae and related species based on combined Angiosperms353 and Brassicaceae764 probe sets. The tree is rooted with outgroup species including Arabidopsis thaliana and Schrenkiella parvula . Major clades are highlighted. Boechera falcata is indicated in bold. Numbers at nodes represent bootstrap support values <100. Conclusion To conclude, we present a high-quality genome assembly of the only Boechera species native to Eurasia, (the Far Eastern B. falcata ) to the chromosome level, as well as an assembly of chloroplast and mitochondrial DNA. The highly homozygous genome, the presence of only sex alleles of the APOLLO gene and previously obtained cytoembryological data suggest that this species reproduces only sexually. It likely came to the Eurasian continent from North America across the Bering Land Bridge during the Pleistocene glacial maxima. In terms of genome morphology, structure and size, as well as chromosome arrangement and organelle DNA organization, this species is quite close to its North American sexual relatives from the Boechereae tribe. Using molecular probes, it was possible to confirm the placement of B. falcata within tribe Boechereae, namely in the Core Boechera III group. A phylogenetic tree constructed based on the chloroplast DNA confirmed the phylogenetic analysis using molecular probes. Within our limited sampling for the chloroplast DNA phylogeny, B. falcata appears most closely related to B. suffrutescens and B. pulchra . Finally, the availability of the genome of the only Eurasian Boechera species will help studies of the evolution and phylogeny of Brassicaceae species, as well as apomixis researchers to unravel the complex hybridization events that form Boechera apomicts. Acknowledgement The work was carried out within the framework of the state assignment of the Komarov Botanical Institute RAS No. 124013100862-0 “Polyvariance of morphogenetic programs for the development of plant reproductive structures, regulation of morphological processes in vivo and in vitro” (2024-2028) and RFBR grant No. 20-54-46002 “Phylogenetic and functional analysis of genes associated with apomixis in representatives of the Boechera genus” to VB. This work was further supported by the Czech Science Foundation (project 24- 11371S to TM). Seeds and photographs of B. falcata plants were kindly provided by Dr. N.V. Sinelnikova from the Institute of Biological Problems of the North, Far Eastern Branch RAS. Footnotes Email: zilov.d{at}gmail.com , Email: Terezie.Mandakova{at}ceitec.muni.cz , Email: marina.popova2{at}skoltech.ru , Email: michael.windham{at}duke.edu References ↵ Alexander , P. J. , Windham , M. D. , Beck , J. B. , Al-Shehbaz , I. A. , Allphin , L. , and Bailey , C. D . 2013 . Molecular phylogenetics and taxonomy of the genus Boechera and related genera (Brassicaceae: Boechereae) . Syst. Bot . 38 , 192 – 209 . doi: 10.1600/036364413X661917 OpenUrl CrossRef Web of Science ↵ Al-Shehbaz , I. A . 2005 . Nomenclatural notes on Eurasian Arabis (Brassicaceae) . Novon 15 , 519 – 524 . OpenUrl ↵ Anderson , J.T. ; Willis , J.H. ; Mitchell-Olds , T . ( 2011 ). Evolutionary genetics of plant adaptation . Trends Genet . 27 , 258 – 266 . OpenUrl CrossRef PubMed Web of Science ↵ Bakin E. , Sezer F. , Özbilen A. , Kilic I. , Uner B. , Rayko M. , Taskin K.M. , Brukhin V . ( 2022 ). Phylogenetic and Expression Analysis of CENH3 and APOLLO Genes in Sexual and Apomictic Boechera Species . Plants (Basel ); 11 ( 3 ): 387 . doi: 10.3390/plants11030387 . OpenUrl CrossRef PubMed ↵ Baril T , Galbraith J , Hayward A . Earl Grey: A Fully Automated User-Friendly Transposable Element Annotation and Analysis Pipeline . Mol Biol Evol . 2024 Apr 2; 41 ( 4 ):msae068. doi: 10.1093/molbev/msae068 . OpenUrl CrossRef PubMed ↵ Beck JB , Alexander PJ , Allphin L , Al-Shehbaz IA , Rushworth C , Bailey CD , Windham MD . Does hybridization drive the transition to asexuality in diploid Boechera ? Evolution . 2012 Apr ; 66 ( 4 ): 985 – 95 . doi: 10.1111/j.1558-5646.2011.01507.x . OpenUrl CrossRef PubMed Web of Science ↵ Beilstein MA , Nagalingum NS , Clements MD , Manchester SR , Mathews S . Dated molecular phylogenies indicate a Miocene origin for Arabidopsis thaliana . Proc Natl Acad Sci U S A . 2010 Oct 26; 107 ( 43 ): 18724 – 8 . doi: 10.1073/pnas.0909766107 . OpenUrl Abstract / FREE Full Text ↵ Bicknell , R. A. , and Koltunow , A. M . ( 2004 ). Understanding apomixis: recent advances and remaining conundrums . Plant Cell 16 , 228 – 245 . doi: 10.1105/tpc.017921 OpenUrl FREE Full Text ↵ Böcher , T. W . ( 1951 ). Cytogenetical and embryological studies in the amphiapomictic Arabis holboellii complex . Biol. Skr . 6 , 1 – 58 . OpenUrl ↵ Böcher , T. W . ( 1969 ). Further studies in Arabis holboellii and allied species . Bot. Tidsskr . 64 , 141 – 161 . OpenUrl ↵ Bolger AM , Lohse M , Usadel B . Trimmomatic: a flexible trimmer for Illumina sequence data . Bioinformatics . 2014 Aug 1; 30 ( 15 ): 2114 – 20 . doi: 10.1093/bioinformatics/btu170 . OpenUrl CrossRef PubMed Web of Science ↵ Brukhin , V . ( 2017 ). Molecular and genetic regulation of apomixis. Rus . J. Genet . 9 , 943 – 964 . doi: 10.1134/S1022795417090046 OpenUrl CrossRef ↵ Brukhin V. , Osadtchiy J.V. , Florez-Rueda A.M. , Smetanin D. , Bakin E. , Nobre M.S. , Grossniklaus U . ( 2019 ). The Boechera Genus as a Resource for Apomixis Research . Front Plant Sci . 2 ; 10 : 392 . doi: 10.3389/fpls.2019.00392 . OpenUrl CrossRef ↵ Cabanettes F , Klopp C . D-GENIES: dot plot large genomes in an interactive, efficient and simple way . PeerJ . 2018 Jun 4; 6 : e4958 . doi: 10.7717/peerj.4958 . OpenUrl CrossRef PubMed ↵ Capella-Gutiérrez S , Silla-Martínez JM , Gabaldón T . trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses . Bioinformatics . 2009 Aug 1; 25 ( 15 ): 1972 – 3 . doi: 10.1093/bioinformatics/btp348 . OpenUrl CrossRef PubMed Web of Science ↵ Cheng H , Concepcion GT , Feng X , Zhang H , Li H . Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm . Nat Methods . 2021 Feb ; 18 ( 2 ): 170 – 175 . doi: 10.1038/s41592-020-01056-5 . OpenUrl CrossRef ↵ Contreras-Moreira B , Filippi CV , Naamati G , García Girón C , Allen JE , Flicek P . K-mer counting and curated libraries drive efficient annotation of repeats in plant genomes . Plant Genome . 2021 Nov ; 14 ( 3 ): e20143 . doi: 10.1002/tpg2.20143 . OpenUrl CrossRef PubMed ↵ Corral JM , Vogel H , Aliyu OM , Hensel G , Thiel T , Kumlehn J , Sharbel TF . A conserved apomixis-specific polymorphism is correlated with exclusive exonuclease expression in premeiotic ovules of apomictic boechera species . Plant Physiol . 2013 Dec ; 163 ( 4 ): 1660 – 72 . doi: 10.1104/pp.113.222430 . OpenUrl Abstract / FREE Full Text Correction to: plotsr: visualizing structural similarities and rearrangements between multiple genomes . Bioinformatics . 2022 Nov 30; 38 ( 23 ): 5328 . doi: 10.1093/bioinformatics/btac661 . Erratum for: doi: 10.1093/bioinformatics/btac196. OpenUrl CrossRef PubMed Edgar RC . MUSCLE: multiple sequence alignment with high accuracy and high throughput . Nucleic Acids Res . 2004 Mar 19; 32 ( 5 ): 1792 – 7 . doi: 10.1093/nar/gkh340 . OpenUrl CrossRef PubMed Web of Science ↵ Flynn JM , Hubley R , Goubert C , Rosen J , Clark AG , Feschotte C , Smit AF . RepeatModeler2 for automated genomic discovery of transposable element families . Proc Natl Acad Sci U S A . 2020 Apr 28; 117 ( 17 ): 9451 – 9457 . doi: 10.1073/pnas.1921046117 . OpenUrl Abstract / FREE Full Text ↵ Formenti G , Rhie A , Walenz BP , Thibaud-Nissen F , Shafin K , Koren S , Myers EW , Jarvis ED , Phillippy AM . Merfin: improved variant filtering, assembly evaluation and polishing via k- mer validation . Nat Methods . 2022 Jun ; 19 ( 6 ): 696 – 704 . doi: 10.1038/s41592-022-01445-y . OpenUrl CrossRef Gabriel L , Brůna T , Hoff KJ , Ebel M , Lomsadze A , Borodovsky M , Stanke M . BRAKER3: Fully automated genome annotation using RNA-seq and protein evidence with GeneMark- ETP, AUGUSTUS and TSEBRA . bioRxiv [Preprint]. 2024 Feb 29:2023.06.10.544449. doi: 10.1101/2023.06.10.544449 . OpenUrl Abstract / FREE Full Text ↵ Goel M , Sun H , Jiao WB , Schneeberger K . SyRI: finding genomic rearrangements and local sequence differences from whole-genome assemblies . Genome Biol . 2019 Dec 16; 20 ( 1 ): 277 . doi: 10.1186/s13059-019-1911-0 . OpenUrl CrossRef PubMed ↵ Greiner S , Lehwark P , Bock R . OrganellarGenomeDRAW (OGDRAW) version 1.3.1: expanded toolkit for the graphical visualization of organellar genomes . Nucleic Acids Res . 2019 Jul 2; 47 ( W1 ): W59 – W64 . doi: 10.1093/nar/gkz238 . OpenUrl CrossRef ↵ Vasil IK Grossniklaus , U . Moore , J.M. , Brukhin , V. , Gheyselinck , J. , Baskar , R. , Vielle-Calzada , J-P . Baroux , C. , Page , D.R. , and Spillane , C . ( 2002 ). Engineering of apomixis in crop plants: what can we learn from sexual model systems . In: Vasil IK (Ed) Plant Biotechnology 2002 & Beyond , Kluwer Academic Publishers : Dordrecht , pp 309 – 314 . ↵ Gurevich A. , Saveliev V. , Vyahhi N. , Tesler G ., QUAST: quality assessment tool for genome assemblies, Bioinformatics , Volume 29 , Issue 8 , April 2013 , Pages 1072 – 1075 , doi: 10.1093/bioinformatics/btt086 OpenUrl CrossRef PubMed Web of Science ↵ Hay N.M. , Windham M.D. , Mandáková T. , Lysak M.A. , Hendriks K.P. , Mummenhoff K. , Lens F. , Pryer K.M. , Bailey C.D . ( 2023 ). A Hyb-Seq phylogeny of Boechera and related genera using a combination of Angiosperms353 and Brassicaceae-specific bait sets . Am J Bot . 110 ( 10 ): e16226 . doi: 10.1002/ajb2.16226 . OpenUrl CrossRef PubMed ↵ Hendriks , K. P. , C. Kiefer , I. A . Al-Shehbaz , C. D. , Bailey , A. Hooft van Huysduynen , L. A. Nikolov , L. Nauheimer , et al. 2023 . Global phylogeny of the Brassicaceae provides important insights into gene discordance . Current Biology . doi: 10.1016/j.cub.2023.08.026 OpenUrl CrossRef PubMed ↵ Hu J , Fan J , Sun Z , Liu S . NextPolish: a fast and efficient genome polishing tool for long-read assembly . Bioinformatics . 2020 Apr 1; 36 ( 7 ): 2253 – 2255 . doi: 10.1093/bioinformatics/btz891 . OpenUrl CrossRef ↵ Hu J , Wang Z , Sun Z , et al. An efficient error correction and accurate assembly tool for noisy long reads . bioRxiv ; 2023 . DOI: 10.1101/2023.03.09.531669 . OpenUrl Abstract / FREE Full Text Huang N , Li H. compleasm: a faster and more accurate reimplementation of BUSCO . Bioinformatics . 2023 Oct 3; 39 ( 10 ):btad595. doi: 10.1093/bioinformatics/btad595 . OpenUrl CrossRef PubMed ↵ Huang Y , Guo X , Zhang K , Mandáková T , Cheng F , Lysak MA . The meso-octoploid Heliophila variabilis genome sheds a new light on the impact of polyploidization and diploidization on the diversity of the Cape flora . Plant J . 2023 Oct ; 116 ( 2 ): 446 – 466 . doi: 10.1111/tpj.16383 . OpenUrl CrossRef PubMed ↵ Katoh K , Toh H . Recent developments in the MAFFT multiple sequence alignment program . Brief Bioinform . 2008 Jul ; 9 ( 4 ): 286 – 98 . doi: 10.1093/bib/bbn013 OpenUrl CrossRef PubMed Web of Science ↵ Kiefer , C. , C. Dobeš , and M. A. Koch . 2009 . Boechera or not? Phylogeny and phylogeography of eastern North American Boechera species (Brassicaceae) . Taxon 58 : 1109 – 1121 . doi: 10.1002/tax.584005 OpenUrl CrossRef Web of Science Khokhlov , S.S. ( 1946 ). Seedless plants . Scientific notes from Saratov University . Volume 16 . Issue. 1 . pp. 3 – 74 . OpenUrl ↵ Kliver S. , Rayko M. , Komissarov A. , Bakin E. , Zhernakova D. , Prasad K. , Rushworth C. , Baskar R. , Smetanin D. , Schmutz J. , et al. ( 2018 ). Assembly of the Boechera retrofracta Genome and Evolutionary Analysis of Apomixis-Associated Genes . Genes . 9 ( 4 ): 185 . doi: 10.3390/genes9040185 OpenUrl CrossRef Koch , M. , J. Bishop , T. Mitchell-Olds , and M. Koch . 1999 . Molecular systematics and evolution of Arabidopsis and Arabis . Plant Biology 1 : 529 – 537 . doi: 10.1111/j.1438-8677.1999.tb00779.x OpenUrl CrossRef Web of Science Koch , M. A. , Dobes , C. , and Mitchell-Olds , T . 2003 . Multiple hybrid formation in natural populations: concerted evolution of the internal transcribed spacer of nuclear ribosomal DNA (ITS) in North American Arabis divaricarpa (Brassicaceae) . Mol. Biol. Evol . 20 , 338 – 350 . doi: 10.1093/molbev/msg046 OpenUrl CrossRef PubMed Web of Science ↵ Kolmogorov M , Yuan J , Lin Y , Pevzner PA . Assembly of long, error-prone reads using repeat graphs . Nat Biotechnol . 2019 May ; 37 ( 5 ): 540 – 546 . doi: 10.1038/s41587-019-0072-8 . OpenUrl CrossRef PubMed ↵ Kozlov AM , Darriba D , Flouri T , Morel B , Stamatakis A . RAxML-NG: a fast, scalable and user-friendly tool for maximum likelihood phylogenetic inference . Bioinformatics . 2019 Nov 1; 35 ( 21 ): 4453 – 4455 . doi: 10.1093/bioinformatics/btz305 . OpenUrl CrossRef PubMed ↵ Kriventseva EV , Kuznetsov D , Tegenfeldt F , Manni M , Dias R , Simão FA , Zdobnov EM . OrthoDB v10: sampling the diversity of animal, plant, fungal, protist, bacterial and viral genomes for evolutionary and functional annotations of orthologs . Nucleic Acids Res . 2019 Jan 8; 47 ( D1 ): D807 – D811 . doi: 10.1093/nar/gky1053 . OpenUrl CrossRef PubMed ↵ Kück P , Longo GC . FASconCAT-G: extensive functions for multiple sequence alignment preparations concerning phylogenetic studies . Front Zool . 2014 Nov 18; 11 ( 1 ): 81 . doi: 10.1186/s12983-014-0081-x . OpenUrl CrossRef PubMed ↵ Letunic I , Bork P . Interactive Tree Of Life (iTOL) v5: an online tool for phylogenetic tree display and annotation . Nucleic Acids Res . 2021 Jul 2; 49 ( W1 ): W293 – W296 . doi: 10.1093/nar/gkab301 . OpenUrl CrossRef PubMed ↵ Li F.W. , Rushworth C.A. , Beck J.B. , Windham M.D . ( 2017 ). Boechera microsatellite website: an online portal for species identification and determination of hybrid parentage . Database (Oxford) . 2017 ( 1 ):baw169. doi: 10.1093/database/baw169 . PMID: 28365726 ; PMCID: PMC5467466 . OpenUrl CrossRef PubMed Löve , A. , and Löve , D . ( 1976 ). Nomenclatural notes on arctic plants . Bot. Not . 128 , 497 – 523 . OpenUrl ↵ Luo X , Chen S , Zhang Y . PlantRep: a database of plant repetitive elements . Plant Cell Rep . 2022 Apr ; 41 ( 4 ): 1163 – 1166 . doi: 10.1007/s00299-021-02817-y . OpenUrl CrossRef PubMed ↵ Mandáková T , Lysak MA . Chromosome Preparation for Cytogenetic Analyses in Arabidopsis . Curr Protoc Plant Biol . 2016 May ; 1 ( 1 ): 43 – 51 . doi: 10.1002/cppb.20009 . OpenUrl CrossRef PubMed ↵ Mandáková T , Pouch M , Brock JR , Al-Shehbaz IA , Lysak MA . Origin and Evolution of Diploid and Allopolyploid Camelina Genomes Were Accompanied by Chromosome Shattering . Plant Cell . 2019 Nov ; 31 ( 11 ): 2596 – 2612 . doi: 10.1105/tpc.19.00366 . OpenUrl Abstract / FREE Full Text ↵ Mandáková T. , Price B. , Ashby K. , Hloušková P. , Windham M.D. , Mitchell-Olds T. , Carman J. , Lysak M.A . 2020 . The origin of the Boechereae (Brassicaceae) was preceded by descending dysploidy, whereas intra-tribal cladogenesis was marked by overall genome stasis . Frontiers in Plant Science 11 : 514 . OpenUrl CrossRef PubMed ↵ Mandáková T. , Schranz M. E. , Sharbel T. F. , de Jong H. , Lysak M. A. ( 2015 ) Karyotype evolution in apomictic Boechera and the origin of the aberrant chromosomes . Plant J . 82 : 785 – 793 . doi: 10.1111/tpj.12849 OpenUrl CrossRef PubMed ↵ Nikolov LA , Shushkov P , Nevado B , Gan X , Al-Shehbaz IA , Filatov D , Bailey CD , Tsiantis M . Resolving the backbone of the Brassicaceae phylogeny for investigating trait diversity . New Phytol . 2019 May ; 222 ( 3 ): 1638 – 1651 . doi: 10.1111/nph.15732 . OpenUrl CrossRef PubMed Petrov , D.F . ( 1964 ). Genetically regulated apomixis . Ed. Novosibirsk : Siberian Branch of the USSR Academy of Sciences . 188 pp. Petrov , D.F . ( 1988 ). Apomixis in nature and experiments . Ed. Novosibirsk : Siberian Branch of the USSR Academy of Sciences . 216 pp. ↵ Ranallo-Benavidez TR , Jaron KS , Schatz MC . GenomeScope 2.0 and Smudgeplot for reference-free profiling of polyploid genomes . Nat Commun . 2020 Mar 18; 11 ( 1 ): 1432 . doi: 10.1038/s41467-020-14998-3 . OpenUrl CrossRef PubMed ↵ Rautiainen , M. , Nurk , S. , Walenz , B.P. et al. Telomere-to-telomere assembly of diploid chromosomes with Verkko . Nat Biotechnol 41 , 1474 – 1482 ( 2023 ). doi: 10.1038/s41587-023-01662-6 OpenUrl CrossRef Ranallo-Benavidez TR , Jaron KS , Schatz MC . GenomeScope 2.0 and Smudgeplot for reference-free profiling of polyploid genomes . Nat Commun . 2020 Mar 18; 11 ( 1 ): 1432 . doi: 10.1038/s41467-020-14998-3 . OpenUrl CrossRef PubMed ↵ Robinson JT , Turner D , Durand NC , Thorvaldsdóttir H , Mesirov JP , Aiden EL . Juicebox.js Provides a Cloud-Based Visualization System for Hi-C Data . Cell Syst . 2018 Feb 28; 6 ( 2 ): 256 – 258 .e1. doi: 10.1016/j.cels.2018.01.001 . OpenUrl CrossRef PubMed ↵ Seppey M , Manni M , Zdobnov EM . BUSCO: Assessing Genome Assembly and Annotation Completeness . Methods Mol Biol . 2019 ; 1962 : 227 – 245 . doi: 10.1007/978-1-4939-9173-0_14 . OpenUrl CrossRef PubMed ↵ Tillich M , Lehwark P , Pellizzer T , Ulbricht-Jones ES , Fischer A , Bock R , Greiner S . GeSeq - versatile and accurate annotation of organelle genomes . Nucleic Acids Res . 2017 Jul 3; 45 ( W1 ): W6 – W11 . doi: 10.1093/nar/gkx391 . OpenUrl CrossRef PubMed ↵ Uliano-Silva M , Ferreira JGRN , Krasheninnikova K ; Darwin Tree of Life Consortium ; Formenti G , Abueg L , Torrance J , Myers EW , Durbin R , Blaxter M , McCarthy SA . MitoHiFi: a python pipeline for mitochondrial genome assembly from PacBio high fidelity reads . BMC Bioinformatics . 2023 Jul 18; 24 ( 1 ): 288 . doi: 10.1186/s12859-023-05385-y . OpenUrl CrossRef PubMed Van Dijk , P. , de Jong , H. , Vijverberg , K. , and Biere , A . ( 2009 ). “ An apomixis-gene’s view on dandelions ,” in Lost Sex. The Evolutionary Biology of Parthenogenesis , eds I. Schön , K. Martens , and P. van Dijk ( Dordrecht : Springer ), 475 – 493 . ↵ Vinogradova G.Yu. , Sinelnikova N.V. , Taskin K.M. , Brukhin V.B. ( 2023 ). Development of female reproductive structures in Boechera species (Brassicaceae) during sexual and apomictic modes of reproduction . -Bot. Zhurn . 108 ( 12 ): 1100 – 1118 (In Russ.); DOI: 10.31857/S0006813623120104 , EDN: ZFORQW. OpenUrl CrossRef ↵ Windham , M. D. , Al-Shehbaz , I. A . 2007 . New and noteworthy species of Boechera (Brassicaceae) III: additional sexual diploids and apomictic hybrids . Harv. Papers Bot . 12 , 235 – 257 . doi: 10.3100/1043-4534(2007)12[235:NANSOB]2.0.CO;2 OpenUrl CrossRef ↵ Xu Z , Wang H . LTR_FINDER: an efficient tool for the prediction of full-length LTR retrotransposons . Nucleic Acids Res . 2007 Jul ; 35 ( Web Server issue ): W265 – 8 . doi: 10.1093/nar/gkm286 . OpenUrl CrossRef PubMed Web of Science ↵ Zhou C , McCarthy SA , Durbin R . YaHS: yet another Hi-C scaffolding tool . Bioinformatics . 2023 Jan 1; 39 ( 1 ):btac808. doi: 10.1093/bioinformatics/btac808 . OpenUrl CrossRef PubMed ↵ Zhu B , Qian F , Hou Y , Yang W , Cai M , Wu X . Complete chloroplast genome features and phylogenetic analysis of Eruca sativa (Brassicaceae) . PLoS One . 2021 Mar 12; 16 ( 3 ): e0248556 . doi: 10.1371/journal.pone.0248556 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted March 13, 2025. 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 Genome structure and molecular phylogeny of the only Eurasian Boechera species, Boechera falcata (Brassicaceae) 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 Genome structure and molecular phylogeny of the only Eurasian Boechera species, Boechera falcata (Brassicaceae) Danil Zilov , Terezie Mandáková , Marina Popova , Michael D. Windham , Vladimir Brukhin bioRxiv 2025.03.11.642644; doi: https://doi.org/10.1101/2025.03.11.642644 Share This Article: Copy Citation Tools Genome structure and molecular phylogeny of the only Eurasian Boechera species, Boechera falcata (Brassicaceae) Danil Zilov , Terezie Mandáková , Marina Popova , Michael D. Windham , Vladimir Brukhin bioRxiv 2025.03.11.642644; doi: https://doi.org/10.1101/2025.03.11.642644 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 (7616) Biochemistry (17625) Bioengineering (13852) Bioinformatics (41825) Biophysics (21397) Cancer Biology (18524) Cell Biology (25417) Clinical Trials (138) Developmental Biology (13350) Ecology (19858) Epidemiology (2067) Evolutionary Biology (24277) Genetics (15581) Genomics (22459) Immunology (17698) Microbiology (40278) Molecular Biology (17134) Neuroscience (88400) Paleontology (666) Pathology (2823) Pharmacology and Toxicology (4812) Physiology (7632) Plant Biology (15106) Scientific Communication and Education (2042) Synthetic Biology (4281) Systems Biology (9807) Zoology (2266)