Chromosome-level genome assembly and annotation of the chaetognath Flaccisagitta enflata

Chromosome-level genome assembly and annotation of the chaetognath Flaccisagitta enflata | 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 Chromosome-level genome assembly and annotation of the chaetognath Flaccisagitta enflata View ORCID Profile Nadège Guiglielmoni , View ORCID Profile Michael Eitel , View ORCID Profile Pierrick Moreau , Stefan Krebs , View ORCID Profile Mark Vermeij , View ORCID Profile Romain Koszul , View ORCID Profile Jean-François Flot doi: https://doi.org/10.1101/2025.03.14.643333 Nadège Guiglielmoni 1 Service Evolution Biologique et Ecologie, Universitélibre de Bruxelles (ULB) , 1050 Brussels, Belgium 2 Institut für Zoologie, Universität zu Köln , 50674 Cologne, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Nadège Guiglielmoni For correspondence: nguiglie{at}uni-koeln.de Michael Eitel 3 Department of Earth and Environmental Sciences, Paleontology & Geobiology, Ludwig-Maximilians-Universität München , 80333 Munich, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Michael Eitel Pierrick Moreau 4 Institut Pasteur, UnitéRégulation Spatiale des Génomes, UMR 3525, CNRS , 75015 Paris, France Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Pierrick Moreau Stefan Krebs 5 Laboratory for Functional Genome Analysis, Gene Center, Ludwig-Maximilians-Universität München , 81377 Munich, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site Mark Vermeij 6 Institute for Biodiversity and Ecosystem Dynamics, University of Amsterdam , Amsterdam, The Netherlands Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Mark Vermeij Romain Koszul 4 Institut Pasteur, UnitéRégulation Spatiale des Génomes, UMR 3525, CNRS , 75015 Paris, France Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Romain Koszul Jean-François Flot 1 Service Evolution Biologique et Ecologie, Universitélibre de Bruxelles (ULB) , 1050 Brussels, Belgium 7 2 , 1050 Brussels, Belgium Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jean-François Flot Abstract Full Text Info/History Metrics Data/Code Preview PDF Abstract Chaetognaths, a phylum of enigmatic marine predators, present a significant challenge to phylogenetic reconstruction due to their uncertain evolutionary placement. While transcriptome analyses have suggested affinities with the Gnathifera clade, genomic data for this group remain scarce, hindering a comprehensive understanding of their evolution. Here, we present the first chromosome-level genome assembly of Flaccisagitta enflata, a species within the Aphragmophora order. The genome assembly includes 9 chromosome candidates with a total size of 794 Mb and a BUSCO score of 91.3% against the Metazoa lineage. This high-quality genome assembly provides a crucial resource for comparative genomic analyses within Chaetognatha and the broader Gnathifera clade, and it will facilitate investigations into chaetognath evolution and their phylogenetic relationships, addressing long-standing questions regarding their placement within the animal kingdom. Background Chaetognaths, or arrow worms, are transparent marine predators found at various depths across all oceans, though most species prefer shallow waters [ 1 ]. They have an elongated, transparent body with one or two pairs of lateral fins, a caudal fin, a distinctive head equipped with hooks, and their size ranges from a few millimeters to several centimeters [ 2 ]. Chaetognaths are classified into two orders based on the presence of transverse muscles, or phragms: Phragmophora and Aphragmophora [ 3 ]. The phylum comprises approximately 150 known species and represents an enigmatic clade with an uncertain phylogenetic position. Initially, chaetognaths were thought to be deuterostomes due to their developmental characteristics, but 18S rDNA analyses disproved this hypothesis [ 4 , 5 ] and further supported the division into Phragmophora and Aphragmophora [ 6 ]. Later, Nielsen proposed that chaetognaths belong to the Gnathifera clade, which includes Gnathostomulida, Micrognathozoa, and Rotifera [ 7 ]. This hypothesis has recently been reinforced by transcriptome analysis of ten chaetognath species [ 8 ], yet no high-quality genome assembly was generated so far for this group due to the challenge of sequencing and assembling non-model species [ 9 ], and only one chromosome-level genome assembly of the rotifer Adineta vaga is available for Gnathifera [ 10 ]. We present a first and chromosome-level genome assembly of a species belonging to the phylum Chaetognatha, namely Flaccisagitta enflata . This species was initially described by Grassi in 1881, and is classified in the order Aphragmophora and the family Sagittidae. This species is found at low depth and in seas at more elevated temperatures [ 11 ] and has some large specimens reaching up to 2.5 cm. Its genome size is moderate, estimated at 0.71 pg using Feulgen Image Analysis Densitometry [ 12 ]. Methods Sample collection and fixation Chaetognaths were collected in Snake bay, Curacao, on November 2nd 2019 after sunset. Individuals were identified as Flaccisaggita enflata following the key provided in [ 11 ] and based on the following criteria: length up to 2.5 cm; body transparent, soft and inflated-looking; 8-10 hooks ( Figure 1.A1 ); no collarette; anterior position of the ganglion ( Figure 1.A2 ); pair of lateral fins; short rounded fins; ovaries not extending till the anterior fins ( Figure 1.B3 ); round vesicles close to the tail ( Figure 1.B4 ). Download figure Open in new tab Figure 1: Crosslinked individual C2 used for Hi-C sequencing. One 2-cm individual C1 was preserved in 96% ethanol and kept at 4°C for high-molecular-weight DNA extraction. One 1.5-cm individual C2 was crosslinked in 3% formaldehyde for 45 minutes, quenched in 250 mM glycine, then frozen at -80°C for Hi-C. Two individuals C3 and C4 of 1.5 and 1.2 cm were preserved in RNAlater and kept at 4°C for RNA extraction. High-molecular-weight DNA extraction and sequencing C1 was extracted following a modified version of the protocol described in [ 13 ]. The whole individual was incubated in 180 µL of cetyltrimethylammonium bromide (CTAB) buffer (polyvinylpyrrolidone 2%, tris(hydroxymethyl)aminometha HCl 100 mM, ethylenediaminetetraacetic acid 25 mM, NaCl 2 M, CTAB 2%, β -mercaptoethanol 1/100) and 25 µL of proteinase K for 3 hours at 60°C and 300 rpm. The lysed sample was purified with phenol-chloroform-isoamyl alcohol 25:24:1, chloroform-isoamyl alcohol 24:1 and with AMPure XP beads, which yielded 2.5 µg of DNA with OD260/280=1.95 and OD260/230=1.95. A long-read library was prepared for C1 with the Nanopore SQK-LSK109 Ligation sequencing kit and sequenced using a PromethION flow cell (with pore proteins R9.4.1), which ran for 72 hours with 3 nuclease flushes and reloads, and gave an output of 40.5 Gb with an N50=6.1 kb. Basecalling was done with Guppy v4. 168 Gb of paired-end 150-bp Illumina reads were additionally sequenced for C1 by Novogene on a NovaSeq. Hi-C sequencing The crosslinked individual C2 was used to prepare a Hi-C library with the Arima Hi-C kit (including the restriction enzymes DpnII and HinfI), and resulted in 466 ng of DNA. The DNA was fragmented with a Covaris (300 bp) and biotinylated fragments were selected with streptavidin beads. The library was prepared for Illumina sequencing using the Invitrogen TM Collibri TM PS DNA Library Prep Kit and following manufacturer instructions. Sequencing by Novogene resulted in 489 millions pairs of 150-bp reads. RNA extraction and sequencing RNA was extracted by Novogene using a Trizol-based protocol. Samples were sequenced on a NovaSeq platform and yielded 320 and 122 millions pairs of 150-bp reads for C3 and C4 respectively. Pre-assembly analysis The genome size was estimated with BBtools v38.79 [ 14 ] using the script kmercountexact.sh and the shotgun Illumina reads. As this tool is based on k -mers, three values of k were tested with k = { 27, 29, 31 } . A k -mer histogram of the Illumina dataset was built using KAT hist v2.4.2 [ 15 ] (with k =27). Genome assembly Shotgun Illumina and Hi-C reads were trimmed using cutadapt v2.9 with parameter -m 10 [ 16 ]. Nanopore reads were trimmed using Porechop v0.2.4 [ 17 ] with default parameters, corrected using the Illumina reads and Ratatosk v0.7.5 [ 18 ] with default parameters, and assembled de novo using Canu v1.9 [ 19 ] with parameter genomeSize=700m and the reads passed with --nanopore-corrected . Nanopore reads were mapped to the contigs using minimap2 v2.17 [ 20 ] with parameter -x map-ont and uncollapsed haplotypes were purged with purge dups [ 21 ] twice with default parameters. Hi-C reads were mapped to the draft assembly using hicstuff v2.3.0 [ 22 ] and bowtie2 v2.3.5.1 [ 23 ] with parameters --enzyme DpnII,HinfI --iterative . instaGRAAL v0.1.6 no-opengl branch [ 24 ] was run with the parameters --level 5 --cycles 150 . The scaffolds were post-processed with instaGRAAL-polish to reduce misassemblies and 10 Ns were added as gaps. Gaps in the chromosome candidates were filled using TGS-GapCloser [ 25 ] and the Ratatosk-corrected Nanopore reads with parameter --ne , and the scaffolds were further polished using HyPo [ 26 ] with parameters -c 240 -s 700 after mapping the Illumina reads with bowtie2. Assembly evaluation Assemblies were assessed using BUSCO v5.8.0 [ 27 ] against the lineage Metazoa odb10 with parameter -m genome and using KAT comp v2.4.2 [ 15 ] against the Illumina dataset (with k =27) with default parameters. The Hi-C contact map was built using the tool hicstuff with hicstuff pipeline as described previously and hicstuff view with the parameter --binning 2000 . Genome annotation Transposable elements (TE) were annotated with the EDTA pipeline v1.9.8 [ 28 ] with parameters --sensitive 1 --anno 1 --overwrite 1 --force 1 : first, long-terminal repeat (LTR) candidates detected by LTRharvest v1.6.1 [ 29 ] and LTR FINDER v1.07 [ 30 ] were filtered with LTR retriever v2.9.0 [ 31 ]; Helitron transposons were searched for with HelitronScanner [ 32 ], while other repeats were detected by Generic Repeat Finder v1.0 [ 33 ] and TIR-learner [ 34 ]; a final TE library was produced after further filtering and repetition annotation with RepeatModeler v2.0.1 [ 35 ]. The output hardmasked assembly was converted into a softmasked assembly. RNA-seq reads were trimmed with cutadapt v2.9 [ 16 ] with parameter -m 10 . C3 reads were assembled with Trinity v2.12.0 [ 36 ]. This transcriptome and the C3 and C4 reads were provided as input to Funannotate [ 37 ]. funannotate train was run with parameters --no trimmomatic --no normalize reads to map the transcripts to the softmasked assembly using minimap2 v2.17 [ 20 ] and produce a first annotation with PASA v2.4.1 [ 38 ]. These files were used by funannotate predict for gene prediction with GeneMark-ES [ 39 ] and Augustus [ 40 ], and a consensus gene set was produced by Evidence Modeler [ 41 ]. Annotation was evaluated using BUSCO v5.8.0 [ 27 ] against the lineage Metazoa odb10 with parameter -m proteins . Genome quality The full assembly pipeline is presented in Figure 2a . Genome size was estimated to 695-699 Mb (haploid) with BBTools, matching the cytological estimation of 0.71 pg. Initial contigs were obtained by assembling Ratatosk-corrected Nanopore reads with Canu and reached 1.48 Gb, close to the expected size for a diploid genome assembly, with an N50 of 195 kb. Contigs were purged using purge dups and resulted in an assembly of 946 Mb with an N50 of 215 kb. The assembly was scaffolded using instaGRAAL and yielded 9 chromosome candidates ranging from 71.5 to 112.6 Mb. Gaps were filled using TGS-GapCloser and the final scaffolds were polished using HyPo, to obtain a final assembly of 794 Mb with an overall BUSCO score of 91.3% against the Metazoa odb10 lineage ( Table 1 ). Sequences not anchored to the main scaffolds were removed from the assembly to prevent contamination, which is expected as the samples were preserved directly after collection and not starved nor cleaned. Plankton on which chaetognaths feed would hardly be distinguishable from the host using typical decontamination strategies, as they have linear genomes, a GC content similar to chaetognaths, and are likely poorly documented in public databases. The k -mer plot ( Figure 2b ) shows two peaks, as is expected for a diploid species. Erroneous k -mers at low multiplicity are not included in the assembly (0X, in black). Limited artefactual duplications are shown in the homozygous peak (2X, purple). The 9 chromosome candidates can be identified on the contact map ( Figure 2c ) based on their heightened intrachromosomal contacts. 64.2% of the assembly was identified as repetitive and 35,833 genes were predicted with a BUSCO score of 87.8% (77.0% single-copy, 10.8% duplicated features) against the Metazoa odb10 lineage. View this table: View inline View popup Download powerpoint Table 1: Assembly statistics. Download figure Open in new tab Figure 2: a) Assembly workflow. Nanopore reads were corrected using Ratatosk with Illumina reads. Both Nanopore and Illumina reads were generated from a DNA extraction of individual C1. Corrected reads were assembled using Canu and haplotigs were removed using purge dups. The assembly was scaffolded using instaGRAAL and Hi-C reads from individual C2. The scaffolds were gap filled using TGS-GapCloser and the Nanopore reads, and polished using HyPo and the Illumina reads. b) k -mer analysis using KAT comp with k =27. The spectrum shows two peaks, the first one for heterozygous k -mers and the second one for homozygous k -mers. c) Hi-C contact map of the final scaffolds. 9 chromosome candidates with heightened intrachromosomal contacts can be identified. Perspectives The chromosome-level assembly of Flaccisagitta enflata provides a first reference for the phylum Chaetognatha, and shall be employed in comparative and phylogenomic studies. This genome assembly posed a challenge due to the high heterozygosity between haplotypes of the species, and accordingly we strived to use few individuals. Nanopore and shotgun Illumina reads were obtained from a single individual and can be used to generate a draft phased assembly. With the improvements of long-read sequencing technologies, it would be possible to obtain both long reads and Hi-C reads from a single individual of similar size by using a portion for low-input PacBio HiFi sequencing and the rest for Hi-C sequencing. The high-accuracy of PacBio HiFi reads and Hi-C would be an adequate combination to produce a haplotype-resolved assembly. A phased assembly would be most appropriate for this species due to its high heterozygosity and the difficulty of collapsing divergent regions [ 42 ]. DNA extraction may additionally be optimized by flash-freezing and crushing the sample prior to chemical lysis, and incubating the powder in CTAB buffer and proteinase K for 30 minutes to 1 hour maximum, as prolonged lysis in CTAB may explain suboptimal fragment length. Supplementary information Command lines are listed in github.com/nadegeguiglielmoni/Flaccisagitta enflata methods. Data availability Sequencing datasets and assembly were submitted to European Nucleotide Archive under the accession number PRJEB83807. Funding This project was funded by the Horizon 2020 research and innovation program of the European Union under the Marie Sklodowska-Curie grant agreement No 764840 (ITN IGNITE, www.itn-ignite.eu ) and a complementary fellowship from the David and Alice Van Buuren fund and the Jaumotte-Demoulin foundation. Computational resources were provided by the Leibniz-Rechenzentrum (LRZ) and the Consortium des Équipements de Calcul Intensif (CÉCI), funded by the Belgian Fund for Scientific Research-FNRS (F.R.S.-FNRS; grant No. 2.5020.11). Conflict of interest NG received a travel grant of 500$ from Oxford Nanopore to present their work at the conference of the European Society for Evolutionary Biology in Prague, 2022. Acknowledgements We thank Christophe Chapard for his help in preparing the Hi-C library. Footnotes https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_965153355.1/ References [1]. ↵ Alvarino , A. Bathymetric distribution of chaetognaths . Pacific Science XVIII ( 1964 ). [2]. ↵ Ghirardelli , E. Some aspects of the biology of the chaetognaths . Advances in Marine Biology 6 , 271 – 375 ( 1969 ). OpenUrl CrossRef [3]. ↵ Tokioka , T. The taxonomical outline of chaetognatha . Publications of the Seto Marine Biological Laboratory 12 , 335 – 357 ( 1965 ). OpenUrl CrossRef [4]. ↵ Telford , M. J. & Holland , P. W. The Phylogenetic Affinities of the Chaetognaths: A Molecular Analysis . Molecular Biology and Evolution 10 , 660 – 676 ( 1993 ). OpenUrl CrossRef PubMed Web of Science [5]. ↵ Wada , H. & Satoh , N. Details of the evolutionary history from invertebrates to vertebrates, as deduced from the sequences of 18S rDNA . Proceedings of the National Academy of Sciences 91 , 1801 – 1804 ( 1994 ). OpenUrl Abstract / FREE Full Text [6]. ↵ Telford , M. J. & Holland , P. W. Evolution of 28S Ribosomal DNA in Chaetognaths: Duplicate Genes and Molecular Phylogeny . Journal of Molecular Evolution 44 , 135 – 144 ( 1997 ). OpenUrl CrossRef PubMed Web of Science [7]. ↵ Nielsen , C. Animal evolution: interrelationships of the living phyla ( Oxford University Press on Demand , 2011 ). [8]. ↵ Marlétaz , F. , Peijnenburg , K. T. , Goto , T. , Satoh , N. & Rokhsar , D. S. A new spiralian phylogeny places the enigmatic arrow worms among gnathiferans . Current Biology 29 , 312 – 318 ( 2019 ). OpenUrl CrossRef PubMed [9]. ↵ Guiglielmoni , N. , Rivera-Vicéns , R. , Koszul , R. & Flot , J.-F. A deep dive into genome assemblies of non-vertebrate animals . Peer Community Journal 2 ( 2022 ). [10]. ↵ Simion , P. et al. Chromosome-level genome assembly reveals homologous chromosomes and recombination in asexual rotifer adineta vaga . Science Advances 7 , eabg4216 ( 2021 ). OpenUrl CrossRef PubMed [11]. ↵ Michel , H. B. Chaetognatha of the Caribbean Sea and adjacent areas , vol. 15 ( National Oceanic and Atmospheric Administration, National Marine Fisheries , 1984 ). [12]. ↵ Gregory , T. R. Animal Genome Size Database , http://www.genomesize.com , unpublished data ( 2021 ). [13]. ↵ Guiglielmoni , N. , Villegas , L. I. , Kirangwa , J. & Schiffer , P. H. Revisiting genomes of non-model species with long reads yields new insights into their biology and evolution . Frontiers in Genetics 15 , 1308527 ( 2024 ). OpenUrl CrossRef PubMed [14]. ↵ Joint Genome Institute . BBtools , https://sourceforge.net/projects/bbmap/ ( 2014 ). [15]. ↵ Mapleson , D. , Garcia Accinelli , G. , Kettleborough , G. , Wright , J. & Clavijo , B. J. KAT: a K-mer analysis toolkit to quality control NGS datasets and genome assemblies . Bioinformatics 33 , 574 – 576 ( 2016 ). OpenUrl [16]. ↵ Martin , M. Cutadapt removes adapter sequences from high-throughput sequencing reads . EMBnet. Journal 17 , 10 – 12 ( 2011 ). OpenUrl [17]. ↵ Wick , R. R. Porechop , https://github.com/rrwick/Porechop ( 2017 ). [18]. ↵ Holley , G. et al. Ratatosk: hybrid error correction of long reads enables accurate variant calling and assembly . Genome Biology 22 , 1 – 22 ( 2021 ). OpenUrl CrossRef PubMed [19]. ↵ Koren , S. et al. Canu: scalable and accurate long-read assembly via adaptive k -mer weighting and repeat separation . Genome Research 25 , 1 – 11 ( 2017 ). OpenUrl [20]. ↵ Li , H. Minimap2: pairwise alignment for nucleotide sequences . Bioinformatics 34 , 3094 – 3100 ( 2018 ). OpenUrl CrossRef PubMed [21]. ↵ Guan , D. et al. Identifying and removing haplotypic duplication in primary genome assemblies . Bioinformatics 36 , 2896 – 2898 ( 2020 ). OpenUrl CrossRef PubMed [22]. ↵ Matthey-Doret , C. et al. koszullab/hicstuff ( 2020 ). [23]. ↵ Langmead , B. & Salzberg , S. L. Fast gapped-read alignment with Bowtie 2 . Nature Methods 9 , 357 – 359 ( 2012 ). OpenUrl CrossRef PubMed [24]. ↵ Baudry , L. et al. instaGRAAL: chromosome-level quality scaffolding of genomes using a proximity ligation-based scaffolder . Genome Biology 21 , 1 – 22 ( 2020 ). OpenUrl CrossRef PubMed [25]. ↵ Xu , M. et al. TGS-GapCloser: a fast and accurate gap closer for large genomes with low coverage of error-prone long reads . GigaScience 9 ( 2020 ). [26]. ↵ Kundu , R. , Casey , J. & Sung , W.-k. HyPo : super fast & accurate polisher for long read assemblies . bioRxiv ( 2019 ). [27]. ↵ Simão , F. A. , Waterhouse , R. M. , Ioannidis , P. , Kriventseva , E. V. & Zdobnov , E. M. BUSCO: assessing genome assembly and annotation completeness with single-copy orthologs . Bioinformatics 31 , 3210 – 3212 ( 2015 ). OpenUrl CrossRef PubMed [28]. ↵ Ou , S. et al. Benchmarking transposable element annotation methods for creation of a streamlined, comprehensive pipeline . Genome Biology 20 , 1 – 18 ( 2019 ). OpenUrl CrossRef PubMed [29]. ↵ Gremme , G. , Steinbiss , S. & Kurtz , S. GenomeTools: a comprehensive software library for efficient processing of structured genome annotations . IEEE/ACM Transactions on Computational Biology and Bioinformatics 10 , 645 – 656 ( 2013 ). OpenUrl CrossRef [30]. ↵ Xu , Z. & Wang , H. LTR FINDER: an efficient tool for the prediction of full-length LTR retrotransposons . Nucleic Acids Research 35 , W265 – W268 ( 2007 ). OpenUrl CrossRef PubMed Web of Science [31]. ↵ Ou , S. & Jiang , N. LTR retriever: a highly accurate and sensitive program for identification of long terminal repeat retrotransposons . Plant Physiology 176 , 1410 – 1422 ( 2018 ). OpenUrl Abstract / FREE Full Text [32]. ↵ Xiong , W. , He , L. , Lai , J. , Dooner , H. K. & Du , C. HelitronScanner uncovers a large overlooked cache of Helitron transposons in many plant genomes . Proceedings of the National Academy of Sciences 111 , 10263 – 10268 ( 2014 ). OpenUrl Abstract / FREE Full Text [33]. ↵ Shi , J. & Liang , C. Generic Repeat Finder: a high-sensitivity tool for genome-wide de novo repeat detection . Plant Physiology 180 , 1803 – 1815 ( 2019 ). OpenUrl Abstract / FREE Full Text [34]. ↵ Su , W. , Gu , X. & Peterson , T. 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 ( 2019 ). OpenUrl CrossRef PubMed [35]. ↵ Flynn , J. M. et al. RepeatModeler2 for automated genomic discovery of transposable element families . Proceedings of the National Academy of Sciences 117 , 9451 – 9457 ( 2020 ). OpenUrl Abstract / FREE Full Text [36]. ↵ Grabherr , M. G. et al. Full-length transcriptome assembly from RNA-Seq data without a reference genome . Nature Biotechnology 29 , 644 – 652 ( 2011 ). OpenUrl CrossRef PubMed [37]. ↵ Palmer , J. M. & Stajich , J. Funannotate v1.8.1: Eukaryotic genome annotation ( 2020 ). [38]. ↵ Haas , B. J. et al. Improving the Arabidopsis genome annotation using maximal transcript alignment assemblies . Nucleic Acids Research 31 , 5654 – 5666 ( 2003 ). OpenUrl CrossRef PubMed Web of Science [39]. ↵ Ter-Hovhannisyan , V. , Lomsadze , A. , Chernoff , Y. O. & Borodovsky , M. Gene prediction in novel fungal genomes using an ab initio algorithm with unsupervised training . Genome Research 18 , 1979 – 1990 ( 2008 ). OpenUrl Abstract / FREE Full Text [40]. ↵ Stanke , M. et al. AUGUSTUS: ab initio prediction of alternative transcripts . Nucleic Acids Research 34 , W435 – W439 ( 2006 ). OpenUrl CrossRef PubMed Web of Science [41]. ↵ Haas , B. J. et al. Automated eukaryotic gene structure annotation using EVidenceModeler and the Program to Assemble Spliced Alignments . Genome Biology 9 , 1 – 22 ( 2008 ). OpenUrl CrossRef PubMed [42]. ↵ Guiglielmoni , N. , Houtain , A. , Derzelle , A. , Van Doninck , K. & Flot , J.-F. Overcoming uncollapsed haplo-types in long-read assemblies of non-model organisms . BMC Bioinformatics 22 , 303 ( 2021 ). OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted March 17, 2025. Download PDF Data/Code 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 Chromosome-level genome assembly and annotation of the chaetognath Flaccisagitta enflata 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 Chromosome-level genome assembly and annotation of the chaetognath Flaccisagitta enflata Nadège Guiglielmoni , Michael Eitel , Pierrick Moreau , Stefan Krebs , Mark Vermeij , Romain Koszul , Jean-François Flot bioRxiv 2025.03.14.643333; doi: https://doi.org/10.1101/2025.03.14.643333 Share This Article: Copy Citation Tools Chromosome-level genome assembly and annotation of the chaetognath Flaccisagitta enflata Nadège Guiglielmoni , Michael Eitel , Pierrick Moreau , Stefan Krebs , Mark Vermeij , Romain Koszul , Jean-François Flot bioRxiv 2025.03.14.643333; doi: https://doi.org/10.1101/2025.03.14.643333 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 (7637) Biochemistry (17705) Bioengineering (13899) Bioinformatics (41968) Biophysics (21460) Cancer Biology (18603) Cell Biology (25526) Clinical Trials (138) Developmental Biology (13385) Ecology (19910) Epidemiology (2067) Evolutionary Biology (24327) Genetics (15614) Genomics (22513) Immunology (17741) Microbiology (40423) Molecular Biology (17193) Neuroscience (88646) Paleontology (667) Pathology (2835) Pharmacology and Toxicology (4825) Physiology (7647) Plant Biology (15160) Scientific Communication and Education (2046) Synthetic Biology (4302) Systems Biology (9825) Zoology (2271)