High-quality haplotype-resolved genome assembly and annotation of Malus baccata ‘Jackii’

High-quality haplotype-resolved genome assembly and annotation of Malus baccata ‘Jackii’ | 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 High-quality haplotype-resolved genome assembly and annotation of Malus baccata ‘Jackii’ Matthias Pfeifer , View ORCID Profile Ofere Francis Emeriewen , View ORCID Profile Henryk Flachowsky , View ORCID Profile Monika Höfer , View ORCID Profile Jens Keilwagen , View ORCID Profile Fang-Shiang Lim , Andreas Peil , Holger Zetzsche , View ORCID Profile Thomas Wöhner doi: https://doi.org/10.1101/2025.07.27.667097 Matthias Pfeifer 1 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Breeding Research on Fruit Crops , Dresden-Pillnitz, Germany 2 Institute of Plant Genetics, Department of Molecular Plant Breeding, Leibniz University Hannover , Hannover, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ofere Francis Emeriewen 1 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Breeding Research on Fruit Crops , Dresden-Pillnitz, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Ofere Francis Emeriewen Henryk Flachowsky 1 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Breeding Research on Fruit Crops , Dresden-Pillnitz, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Henryk Flachowsky Monika Höfer 1 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Breeding Research on Fruit Crops , Dresden-Pillnitz, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Monika Höfer Jens Keilwagen 3 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Biosafety in Plant Biotechnology , Quedlinburg, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jens Keilwagen Fang-Shiang Lim 3 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Biosafety in Plant Biotechnology , Quedlinburg, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Fang-Shiang Lim Andreas Peil 1 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Breeding Research on Fruit Crops , Dresden-Pillnitz, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site Holger Zetzsche 4 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Resistance Research and Stress Tolerance , Quedlinburg, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site Thomas Wöhner 1 Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Breeding Research on Fruit Crops , Dresden-Pillnitz, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Thomas Wöhner For correspondence: thomas.woehner{at}julius-kuehn.de Abstract Full Text Info/History Metrics Preview PDF Abstract Malus baccata ‘Jackii’ has been observed to exhibit multiple disease resistances, thus rendering it a promising source for breeding new disease-resistant apple cultivars. Here, we present the first haplotype-resolved genome assembly and annotation of this genotype, achieved by integrating PacBio HiFi sequencing, Hi-C, and mRNA sequencing data with a range of bioinformatic tools and databases. The genome assembly comprises 17 pseudochromosomes with total scaffold lengths of 654.6 Mb and 637.5 Mb for the two haplotypes, respectively. Both haplotypes have scaffold N50 values exceeding 30 Mb, with 42,441 and 46,507 predicted genes, of which 99.9% were successfully annotated. The high quality of this genome is supported by BUSCO analysis values exceeding 97.5% for both haplotypes. This comprehensive dataset is well suited for a wide range of future genomic analyses and is anticipated to benefit apple breeding, particularly in the context of enhancing disease resistance. Background & Summary The apple ( Malus domestica Borkh.) is among the most popular and important fruits in the world. Different closely related species of apple ( Malus spp.) can hybridize easily, and the domesticated apple of today contains genomic contributions from e.g. Malus sieversii, Malus sylvestris, Malus orientalis and Malus baccata 1 . M. baccata is native to Asia and is used for breeding cultivars and rootstocks due to its distinct cold hardiness and disease resistance 2 . Breeding of new apple varieties is a complex process that takes several years 3 . Sequencing the genomes of apple genotypes provides insights into genetic diversity, evolutionary history, and genotype-phenotype relationships. The availability of whole genome sequences facilitates the development of marker-assisted selection (MAS), which aids breeding by enabling more efficient and targeted selection strategies. Recently, many genomes from various apple cultivars and individual accessions of different Malus species have been sequenced and published 4 , including that of M. baccata 2 . However, until now, no genome sequence has been available for M. baccata ‘Jackii’, an ornamental genotype collected in 1905 by J. G. Jack in Seoul 5 , which exhibits resistance to several fungal diseases such as apple scab ( Venturia inaequalis ) 6 , powdery mildew ( Podosphaera leucotricha ) 7 and apple blotch ( Diplocarpon coronariae) 8 . In addition, M. baccata ‘Jackii’ is resistant to fire blight 9 , 10 , caused by the Gram-negative bacterium Erwinia amylovora , which is one of the most destructive bacterial diseases affecting the genus Malus 11 . Breeding resistant apple cultivars is a promising and desirable strategy against fire blight and would require pyramiding the different resistance gene (R-gene) candidates due to the fact that resistance is strain-dependent, with some R-gene donors already overcome by virulent strains of E. amylovora 11,12 . The first fire blight R-gene to be isolated and functionally characterized using a transgenic approach was FB_Mr5 , which underlies the resistance QTL region at the top of chromosome 3 of Malus × robusta 5 13 , 14 . FB_Mr5 encodes a CC-NBS-LRR resistance protein that interacts with the cysteine protease AvrRpt2 Ea from E. amylovora , demonstrating a gene-for-gene relationship 9 , 13 – 16 . Moreover, sequence analysis of avrRpt2 Ea from various E. amylovora strains, along with inoculation experiments using avrRpt2 Ea knock-out mutants, revealed that FB_Mr5 -mediated resistance in Malus × robusta 5 is lost when inoculated with knockout mutants and strains carrying a cysteine-to-serine substitution at amino acid position 156 in the bacterial effector avrRpt2 Ea . Furthermore, it was shown that fire blight resistance in M. baccata ‘Jackii’ likely functions in a similar manner to that of Malus × robusta 5 9 , 16 . Additionally, a closely related homologue of FB_Mr5 was identified in M. baccata ‘Jackii’ 17 . However, as it has been demonstrated that even a single amino acid substitution in specific regions of FB_Mr5 can have a significant impact and trigger autoactivity 18 , it is important to know the exact sequences of resistance genes and whether there are other candidate genes at an R-gene locus that show a very high sequence similarity. In this study, we generated a high-quality, haplotype-resolved genome assembly and annotation of M. baccata ‘Jackii’ by combining PacBio HiFi sequencing with Hi-C and mRNA sequencing. Targeted genotyping-by-sequencing (tGBS) 19 data of an F 1 biparental population derived from an ‘Idared’ × M. baccata ‘Jackii’ cross were generated, and single-nucleotide polymorphisms (SNPs) were identified by mapping the sequences to the newly assembled genome. By additionally mapping the sequences of the tGBS analysis to the HFTH1 reference genome, chromosome names were assigned based on the HFTH1 assembly 20 . The genome assembly and annotation presented here for this multi-resistant genotype are of significant value and can be utilised directly for various resistance analyses and other applications. Methods Sampling, DNA and RNA extraction Leaves from M. baccata ‘Jackii’ were collected at the Fruit Genebank of the Julius Kühn-Institut (JKI) in Dresden-Pillnitz, Germany. The QIAGEN Genomic-tip 20/G kit (QIAGEN, Hilden, Germany) was used for DNA extraction, while the RNAprep Pure Plant Plus Kit (Tiangen, Beijing, China) was employed for RNA extraction, with both procedures conducted in accordance with the manufacturer’s protocols. Genome size estimation using Illumina sequencing Genomic DNA from diploid M. baccata ‘Jackii’ was sequenced using the Illumina NovaSeq 6000 platform (Illumina, Inc., San Diego, CA, USA) with a paired-end read length of 150 bp and a 350 bp sequencing library. Subsequently, the reads were quality-filtered (polyG tails trimmed, minimum length ≥ 100 bp, average read quality ≥ Q20, homopolymer filter ≤ 10% consecutive identical bases, ≤ 50% of bases with Q < 10). After filtering, a total of 80.14 GB of sequencing data was obtained, corresponding to an estimated sequencing depth of ~135.19×. The GC content was 37.22%, with Q20 exceeding 97.85% and Q30 surpassing 93.87%. Genome analysis was conducted using the Jellyfish 2.1.4 21 and GenomeScope 2.0 22 software. The k -mer distribution map with k = 19 was generated, the haploid genome size of M. baccata was estimated to be 592,786,100 bp and the heterozygosity rate was calculated to be ~1.57% ( Fig. 1 ). The repeat sequence content was estimated at ~52.78%. Download figure Open in new tab Fig. 1. K -mer distribution map ( k =19) of Malus baccata ‘Jackii’ Haplotype-resolved genome assembly with PacBio and Hi-C DNA from M. baccata ‘Jackii’ was used for PacBio HiFi sequencing on the PacBio Revio platform (Pacific Biosciences, Menlo Park, CA, USA) following the standard protocol. The DNA molecules were sequenced in zero-mode waveguides (ZMWs) over multiple cycles, and repeated subreads were combined to generate highly accurate, self-corrected circular consensus sequencing (CCS) reads. In total, 6,149,970 CCS reads were produced, yielding 101,342,658,289 bp of sequence data. The average CCS read length was 16,479 bp, with an N50 of 16,808 bp, and the longest CCS read measured 61,744 bp. In addition, an in situ Hi-C experiment was conducted 23 . To preserve DNA-DNA interactions and maintain the 3D genome structure, cross-linking was performed with formaldehyde and subsequently DNA was digested with the Hin dIII restriction enzyme generating sticky ends that were filled in with biotin-labeled nucleotides. Blunt-end ligation was performed to form circular structures. After reversing the cross-linking, the DNA was purified and sheared into fragments between 300-700 bp. Biotinylated junctions were isolated using streptavidin beads, and purified fragments were utilised for library preparation and sequencing on an Illumina NovaSeq 6000 PE150 (Illumina, Inc., San Diego, CA, USA). This process generated 689,199,106 read pairs, corresponding to 206,283,188,268 bp of sequence data, with an average GC content of 39.54%, a Q20 value of 97.98%, and a Q30 value of 94.70%. The Hi-C data were processed using HiC-Pro v2.10.0 24 , and the paired-end reads were aligned using BWA (v0.7.10-r789; mode: aln; default settings) 25 to the preliminary assemblies of haplotype 1 and haplotype 2 derived from the CCS reads generated with Hifiasm (v0.19.9-r616) 26 . Of the total 1,378,398,212 reads, 1,174,709,293 and 1,175,354,792 reads were mapped to the preliminary assemblies of haplotype 1 and 2, respectively. Among these, 538,129,731 and 538,891,702 reads were uniquely mapped, resulting in 196,878,252 (36.59%) and 196,590,135 (36.48%) valid interaction pairs for haplotype 1 and 2, respectively. The preliminary assembly was segmented into 50-kb fragments and reassembled using the Hi-C data. Haplotype-resolved chromosome assembly was performed with LACHESIS 27 . A summary of the Hi-C-based haplotype-resolved genome assembly is presented in Table 1 . View this table: View inline View popup Download powerpoint Table 1. Summary of the Hi-C-based haplotype-resolved genome assembly (only scaffolds > 1 kb were included). The assembled genome sequence was cut into 300 kb bins, and the signal intensity between corresponding bins was visualized as a heatmap in Fig. 2 . The signal intensity was stronger within the 17 chromosome groups than between them, indicating a high-quality genome assembly. Download figure Open in new tab Fig. 2. Heatmap of the assembled haplotype-resolved genomes. (a) Haplotype 1. (b) Haplotype mRNA sequencing and genome annotation The assembled genome was then used for genome annotation, with transposable element prediction performed using the following programs and databases: RepeatModeler2 v2.0.1 28 , RECON v1.0.8 29 , RepeatScout v1.0.6 30 , LTR_retriever v2.8 31 , LTRharvest v1.5.9 32 , LTR_FINDER v1.1 33 , RepeatMasker v4.1.0 34 , Repbase v19.06 35 , REXdb v3.0 36 and Dfam v3.2 37 . Tandem repeats were predicted using the Microsatellite identification tool (MISA v2.1) 38 and the Tandem Repeat Finder (TRF, v409) 39 . The results of the aforementioned analyses are presented in Tables 2 and 3 . View this table: View inline View popup Download powerpoint Table 2. Summary of predicted transposable elements. View this table: View inline View popup Download powerpoint Table 3. Summary of tandem repeat analysis. The coding gene prediction was performed using three complementary approaches: ab initio , homology-based, and transcriptome-based methods (with and without reference genomes). Ab initio coding gene prediction was carried out using Augustus v2.4 40 and SNAP (2006-07-28) 41 . Homology-based predictions were performed with GeMoMa v1.7 42 , and for transcriptome-based predictions, mRNA sequencing was performed on Illumina Novaseq 6000 platform (Illumina, Inc., San Diego, CA, USA) with a paired-end read length of 150 bp. This yielded a total of 40,279,131 reads (12.07 Gb), corresponding to 12,065,202,432 bp. The Q30 and Q20 values were 94.57% and 98.01%, respectively, and the GC content was 48.16%. Transcripts were predicted using HISAT v2.0.4 43 and StringTie v1.2.3 44 with different reference genomes 20 , 45 – 47 . Coding genes were then identified using GeneMarkS-T v5.1 48 . Additionally, transcripts were assembled without the use of a reference genome with Trinity v2.11 49 , and coding genes were predicted with PASA v2.0.2 50 . Finally, the genes predicted by the different methods were integrated using EVM v1.1.1 51 and finalized by PASA v2.0.2 50 . The total number of coding genes predicted for haplotype 1 and 2 was 42,441 and 46,507, respectively. Detailed results are presented in Tables 4 and 5 and in Fig. 3 . View this table: View inline View popup Download powerpoint Table 4. Predicted coding genes using different software tools. View this table: View inline View popup Download powerpoint Table 5. Statistics of predicted coding genes of Malus baccata ‘Jackii’. Download figure Open in new tab Fig. 3. Venn diagram of integrated predicted coding genes. (a) Haplotype 1. (b) Haplotype 2. Created with Venny 52 Non-coding RNA prediction was conducted with tRNAscan-SE v1.3.1 53 for tRNA, with barrnap v0.9 54 based on Rfam v12.0 55 for rRNA, with miRBase 56 for miRNA, and with Infernal 1.1 57 based on Rfam v12.0 55 for snoRNA and snRNA. The results are summarised in Table 6 . View this table: View inline View popup Download powerpoint Table 6. Predicted numbers of non-coding RNAs. Homologous gene sequences without a complete gene locus were identified using GenBlastA v1.0.4 58 and GeneWise v2.4.1 59 was used to detect premature stop codons and frameshift mutations, resulting in the identification of 228 and 308 pseudogenes, respectively ( Table 7 ). View this table: View inline View popup Download powerpoint Table 7. Predicted pseudogenes in Malus baccata ‘Jackii’. The predicted coding genes were functionally annotated using multiple databases, including GenBank Non-Redundant (NR, 20200921), eggNOG 5.0 60 , Gene Ontology (GO, 20200615) 61 , 62 , Kyoto Encyclopedia of Genes and Genomes (KEGG, 20191220) 63 , SWISS-PROT and TrEMBL (202005) 64 , Pfam v33 65 and eukaryotic orthologous groups (KOG, 20110125). Overall, more than 99.9% of coding genes were successfully annotated. The statistics on gene function annotation are presented in Table 8 . View this table: View inline View popup Download powerpoint Table 8. Statistics of gene function annotation. In the final step, InterProScan (5.34-73.0) 66 was utilised for the prediction of motifs and domains. A total of 1,876 motifs and 45,003 domains were predicted in haplotype 1, and 1,820 motifs and 44,973 domains in haplotype 2. Chromosome assignment according to HFTH1 DNA of the F 1 population (‘Idared’ × M. baccata ‘Jackii’), including the parental genotypes, was analysed using tGBS 19 by Data2Bio (Ames, IA, USA). The restriction enzyme Bsp 12861 was used and sequencing was carried out on an Illumina HiSeq X instrument (Illumina, Inc., San Diego, CA, USA). Polymorphic sites were first identified, and in a second step, final SNP calling was performed. In the initial step, individual sequence reads were scanned for low-quality regions (PHRED score ≤ 15), and quality-trimmed sequence reads were aligned to the genome sequences of haplotypes 1 and 2 of M. baccata ‘Jackii’ reported here using GSNAP 67 . Only confidently mapped reads with ≤ 2 mismatches per 36 bp and no more than 4 bases as tails per 75 bp that aligned to a single location were used for SNP identification, based on the following criteria: for homozygous SNPs, the most common allele had to be supported by at least 5 unique reads and 80% of all aligned reads. For heterozygous SNPs, each of the two most common alleles had to be supported by at least 5 unique reads and at least 30% of all aligned reads. For both homozygous and heterozygous SNPs, polymorphisms in the first and last 3 bp of each quality-trimmed read were ignored, and a PHRED base quality value of 20 (≤ 1% error rate) was set as the threshold for each polymorphic base. In the second step, SNPs were classified for tGBS genotyping as follows: a SNP was classified as homozygous if ≥ 5 reads supported the major allele and ≥ 90% of all reads at that site matched, and heterozygous if ≥ 2 reads supported each of two alleles, both alleles individually made up > 20%, and their combined reads were ≥ 5, covering ≥ 90% of all reads at that site. SNPs were then filtered based on a minimum calling rate of 50%, the allele number was set to 2, the number of genotypes ≥ 2, the minor allele frequency ≥ 10%, and the heterozygosity rate range between 0% and (2 × Frequency allele1 × Frequency allele2 + 20%). In a final step, imputation was used on chromosome-based SNPs that lacked a sufficient number of reads to make genotype calls using Beagle v5.4 68 with 50 phasing iterations and default parameters. A total of 321,733 and 319,620 SNPs for haplotypes 1 and 2 were identified, with each site genotyped in at least 50% of the samples. SNP sequences from the tGBS data were then mapped to the HFTH1 genome sequence 20 using BWA-MEM2 69 on the JKI Galaxy Server (Galaxy v2.2.1+galaxy1) 70 and the data presented in this study were assigned and oriented according to the HFTH1 reference 20 . A Circos plot 71 illustrating key genomic features and alignments between the two haplotypes is shown in Fig. 4 . Download figure Open in new tab Fig. 4. Circos plot of the Malus baccata ‘Jackii’ haplotype-resolved genome assembly. (a) Chromosome names and lengths in Mb. (b) Frequency of tandem repeats in 50 kb windows. (c) Frequency of transposable elements in 50 kb windows. (d) Frequency of genes in 50 kb windows. (e) Sequences from the tGBS analysis of haplotype 1 mapped onto haplotype 2. kb: kilobase, Mb: million base pairs, tGBS: targeted genotyping-by-sequencing. Data records The raw data and assembled sequences and annotations can be accessed from the European Nucleotide Archive (ENA) under the BioProject accession number PRJEB89942 and study number ERP172974. Technical validation To assess the completeness of the genome assembly, a BUSCO analysis with BUSCO v4.0 72 was performed using the Embryophyta database containing 1,614 core genes. The results, presented in Table 9 , demonstrate the high integrity of the haplotype-resolved genome assembly, with 97.58% and 97.52% of the core genes identified in haplotype 1 and 2, respectively. View this table: View inline View popup Download powerpoint Table 9. BUSCO analysis results using the Embryophyta database (1,614 core genes). To functionally assess the quality of the genome assembly for downstream applications, the F 1 population and both parents were grafted onto rootstock MM111 and up to five replicates per genotype were phenotyped for fire blight incidence i.e., length of shoot tip necrosis after artificial inoculation using E. amylovora strain Ea 222, as described in Peil et al. (2007) 14 . Mean percent lesion length (PLL) was calculated for each F 1 genotype by dividing the length of necrotic shoot by the total shoot length and averaging data from experiments conducted in 2024 and 2025. To identify potential associations between SNPs and fire blight incidence, each SNP with a minor allele frequency (MAF) ≥ 0.05 was analysed using the following procedure: genotypes were divided into two groups according to the observed allele. Using ‘Idared’ as a reference for the susceptible allele, phenotypic values of the two groups were used for a non-parametric Wilcoxon rank-sum test performed in R v4.4.2 73 . The genome-wide significance threshold was determined using Bonferroni correction as -log 10 (0.01/number of SNPs tested). A Manhattan plot was generated using the ggplot2 package 74 and it showed a significant association of SNP markers at the top of chromosome 3 with the fire blight phenotypic data of the F 1 progeny, shown for haplotype 2 in Fig. 5 . Haplotype 1 produced a comparable plot (not shown). The sequence of the FB_Mr5 homolog in M. baccata ‘Jackii’ (GenBank accession KT013244 .1 17 ) was found to be 100% identical over 4,164 bp to a region at the top of chromosome 3 of haplotype 2 between positions 598,337 and 602,501 bp, and this homolog is only 43,365 bp distant from the SNP marker with the highest -log 10 (p) value and the strongest association with fire blight resistance. This supports the accuracy of the haplotype-resolved genome assembly, the correctness of chromosome assignment and orientation, as FB_Mr5 has been described to be located on the distal part of chromosome 3 14 , and the reliability and usability of the genomic data presented here for further analyses. Download figure Open in new tab Fig. 5. PLL in the F 1 biparental (‘Idared’ × M. baccata ‘Jackii’) population after artificial fire blight inoculation. (a) Mean necrosis (%) across 2024 and 2025. (b) Correlation of necrosis between years across F 1 genotypes. (c) Manhattan plot of the genome-wide association for mean PLL in the F 1 population with newly generated SNP markers of haplotype 2. The dashed line indicates the Bonferroni-corrected significance threshold. Mb: million base pairs, PLL: percent lesion length, SNP: single-nucleotide polymorphism. Code availability A custom R script was used to perform association mapping and is available from the corresponding author upon request. Author information Authors and Affiliations Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Breeding Research on Fruit Crops, Dresden-Pillnitz, Germany M. Pfeifer, O. F. Emeriewen, H. Flachowsky, M. Höfer, A. Peil & T. Wöhner Institute of Plant Genetics, Department of Molecular Plant Breeding, Leibniz University Hannover, Hannover, Germany M. Pfeifer Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Biosafety in Plant Biotechnology, Quedlinburg, Germany J. Keilwagen & F.-S. Lim Julius Kühn-Institut (JKI) - Federal Research Centre for Cultivated Plants, Institute for Resistance Research and Stress Tolerance, Quedlinburg, Germany H. Zetzsche Contributions Conception: Henryk Flachowsky, Andreas Peil and Thomas Wöhner. Strategy and design: Matthias Pfeifer, Ofere Francis Emeriewen and Thomas Wöhner. Analyses and writing: Matthias Pfeifer. Plant material: Monika Höfer and Andreas Peil. Fire blight phenotyping: Holger Zetzsche. Association mapping and analysis: Matthias Pfeifer, Ofere Francis Emeriewen, Jens Keilwagen, Fang-Shiang Lim and Thomas Wöhner. Data curation and upload: Jens Keilwagen and Fang-Shiang Lim. Funding: Thomas Wöhner. Supervision: Henryk Flachowsky and Thomas Wöhner. Revision: All authors. All authors read and approved the final manuscript. Corresponding authors Correspondence to T. Wöhner (thomas.woehner{at}julius-kuehn.de). Ethics declarations Competing interests The authors declare no competing interests. Acknowledgements Parts of this work were supported by the Federal Ministry of Agriculture, Food and Regional Identity by decision of the German Bundestag (funding reference number: 281D108×21). Funder Information Declared Federal Ministry of Agriculture, Food and Regional Identity , 281D108X21 References 1. Cornille , A. , Giraud , T. , Smulders , M. J. M. , Roldán-Ruiz , I. & Gladieux , P. The domestication and evolutionary ecology of apples . Trends Genet . 30 , 57 – 65 , doi: 10.1016/j.tig.2013.10.002 ( 2014 ). OpenUrl CrossRef PubMed 2. ↵ Chen , X. et al. Sequencing of a Wild Apple (Malus baccata) Genome Unravels the Differences Between Cultivated and Wild Apple Species Regarding Disease Resistance and Cold Tolerance . G3: Genes Genomes Genet . 9 , 2051 – 2060 , doi: 10.1534/g3.119.400245 ( 2019 ). OpenUrl Abstract / FREE Full Text 3. ↵ Flachowsky , H. et al. Application of a high-speed breeding technology to apple (Malus × domestica) based on transgenic early flowering plants and marker-assisted selection . New Phytol . 192 , 364 – 377 , doi: 10.1111/j.1469-8137.2011.03813.x ( 2011 ). OpenUrl CrossRef PubMed Web of Science 4. ↵ Genome Database for Rosaceae . https://www.rosaceae.org/species/malus/all ( 2025 ). 5. ↵ Fiala , J.L. Flowering crabapples: The genus Malus ( Timber Press , Portland , 1994 ). 6. ↵ Gygax , M. , Gianfranceschi , L. , Liebhard , R. , Kellerhals , M. & Patocchi , A. Molecular markers linked to the apple scab resistance gene Vbj derived from Malus baccata jackii . Theor. Appl. Genet . 109 , 1702 – 1709 , doi: 10.1007/s00122-004-1803-9 ( 2004 ) OpenUrl CrossRef PubMed Web of Science 7. ↵ Dunemann , F. & Schuster , M. Genetic characterization and mapping of the major powdery mildew resistance gene Plbj from Malus baccata jackii . Acta Hortic . 814 , 791 – 798 , doi: 10.17660/ActaHortic.2009.814.134 ( 2009 ). OpenUrl CrossRef 8. ↵ Wöhner , T. , Emeriewen , O. F. & Höfer , M. Evidence of apple blotch resistance in wild apple germplasm (Malus spp.) accessions . Eur. J. Plant Pathol . 159 , 441 – 448 , doi: 10.1007/s10658-020-02156-w ( 2021 ). OpenUrl CrossRef 9. ↵ Vogt , I. et al. A. Gene-for-gene relationship in the host-pathogen system Malus × robusta 5-Erwinia amylovora . New Phytol . 197 , 1262 – 1275 , doi: 10.1111/nph.12094 ( 2013 ). OpenUrl CrossRef PubMed 10. ↵ Wöhner , T. et al. Inoculation of Malus genotypes with a set of Erwinia amylovora strains indicates a gene-for-gene relationship between the effector gene eop1 and both Malus floribunda 821 and Malus ‘Evereste’ . Plant Pathol . 67 , 938 – 947 , doi: 10.1111/ppa.12784 ( 2017 ). OpenUrl CrossRef 11. Peil , A. , Emeriewen , O. F. , Khan , A. , Kostick , S. & Malnoy , M. Status of fire blight resistance breeding in Malus . J. Plant Pathol . 103 , 3 – 12 , doi: 10.1007/s42161-020-00581-8 ( 2021 ). OpenUrl CrossRef 12. Emeriewen , O. F. , Wöhner , T. , Flachowsky , H. & Peil , A. Malus Hosts-Erwinia amylovora Interactions: Strain Pathogenicity and Resistance Mechanisms . Front. Plant Sci . 10 , 551 , doi: 10.3389/fpls.2019.00551 ( 2019 ). OpenUrl CrossRef PubMed 13. ↵ Fahrentrapp , J. et al. A candidate gene for fire blight resistance in Malus × robusta 5 is coding for a CC–NBS–LRR . Tree Genet. Genomes 9 , 237 – 251 , doi: 10.1007/s11295-012-0550-3 ( 2013 ). OpenUrl CrossRef 14. ↵ Peil , A. et al. Strong evidence for a fire blight resistance gene of Malus robusta located on linkage group 3 . Plant Breed . 126 , 470 – 475 , doi: 10.1111/j.1439-0523.2007.01408.x ( 2007 ). OpenUrl CrossRef Web of Science 15. Broggini , G. A. L. et al. Engineering fire blight resistance into the apple cultivar ’Gala’ using the FB_MR5 CC-NBS-LRR resistance gene of Malus × robusta 5 . Plant Biotechnol. J . 12 , 728 – 733 , doi: 10.1111/pbi.12177 ( 2014 ). OpenUrl CrossRef PubMed 16. ↵ Wöhner , T. W. et al. QTL mapping of fire blight resistance in Malus ×robusta 5 after inoculation with different strains of Erwinia amylovora . Mol. Breed . 34 , 217 – 230 , doi: 10.1007/s11032-014-0031-5 ( 2014 ). OpenUrl CrossRef 17. ↵ Wöhner , T. et al. Homologs of the FB_MR5 fire blight resistance gene of Malus ×robusta 5 are present in other Malus wild species accessions . Tree Genet. Genomes 12 , 2 , doi: 10.1007/s11295-015-0962-y ( 2016 ). OpenUrl CrossRef 18. ↵ Kim , H. , Kim , J. , Kim , M. , Park , J. T. & Sohn , K. H. Comparative analysis on natural variants of fire blight resistance protein FB_MR5 indicates distinct effector recognition mechanisms . Mol. Cells 47 , 100094 , doi: 10.1016/j.mocell.2024.100094 ( 2024 ). OpenUrl CrossRef PubMed 19. ↵ Ott , A. , Schnable , J. C. , Yeh , C.-T. , Wang , K.-S. & Schnable , P. S. tGBS® genotyping-by-sequencing enables reliable genotyping of heterozygous loci . Nucleic Acids Res . 45 , e178 , doi: 10.1093/nar/gkx853 ( 2017 ). OpenUrl CrossRef PubMed 20. ↵ Zhang , L. et al. A high-quality apple genome assembly reveals the association of a retrotransposon and red fruit colour . Nat. Commun . 10 , 1494 , doi: 10.1038/s41467-019-09518-x ( 2019 ). OpenUrl CrossRef PubMed 21. ↵ Marçais , G. & Kingsford , C. A fast, lock-free approach for efficient parallel counting of occurrences of k-mers . Bioinformatics 27 , 764 – 770 , doi: 10.1093/bioinformatics/btr011 ( 2011 ). OpenUrl CrossRef PubMed Web of Science 22. ↵ Ranallo-Benavidez , T. R. , Jaron , K. S. & Schatz , M. C. GenomeScope 2.0 and Smudgeplot for reference-free profiling of polyploid genomes . Nat. Commun . 11 , 1432 , doi: 10.1038/s41467-020-14998-3 ( 2020 ). OpenUrl CrossRef PubMed 23. ↵ Rao , S. S. P. et al. A 3D map of the human genome at kilobase resolution reveals principles of chromatin looping . Cell 159 , 1665 – 1680 , doi: 10.1016/j.cell.2014.11.021 ( 2014 ). OpenUrl CrossRef PubMed Web of Science 24. ↵ Servant , N. et al. HiC-Pro: an optimized and flexible pipeline for Hi-C data processing . Genome Biol . 16 , 259 , doi: 10.1186/s13059-015-0831-x ( 2015 ). OpenUrl CrossRef PubMed 25. ↵ Li , H. & Durbin , R. Fast and accurate short read alignment with Burrows-Wheeler transform . Bioinformatics 25 , 1754 – 1760 , doi: 10.1093/bioinformatics/btp324 ( 2009 ). OpenUrl CrossRef PubMed Web of Science 26. ↵ Cheng , H. , Concepcion , G. T. , Feng , X. , Zhang , H. & Li , H. Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm . Nat. Methods 18 , 170 – 175 , doi: 10.1038/s41592-020-01056-5 ( 2021 ). OpenUrl CrossRef 27. ↵ Burton , J. N. et al. Chromosome-scale scaffolding of de novo genome assemblies based on chromatin interactions . Nat. Biotechnol . 31 , 1119 – 1125 , doi: 10.1038/nbt.2727 ( 2013 ). OpenUrl CrossRef PubMed 28. ↵ Flynn , J. M. et al. RepeatModeler2 for automated genomic discovery of transposable element families . Proc. Natl. Acad. Sci. U. S. A . 117 , 9451 – 9457 , doi: 10.1073/pnas.1921046117 ( 2020 ). OpenUrl Abstract / FREE Full Text 29. ↵ Bao , Z. & Eddy , S. R. Automated de novo identification of repeat sequence families in sequenced genomes . Genome Res . 12 , 1269 – 1276 , doi: 10.1101/gr.88502 ( 2002 ). OpenUrl Abstract / FREE Full Text 30. ↵ Price , A. L. , Jones , N. C. & Pevzner , P. A. De novo identification of repeat families in large genomes . Bioinformatics 21 , i351 – i358 , doi: 10.1093/bioinformatics/bti1018 ( 2005 ). 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 Physiol . 176 , 1410 – 1422 , doi: 10.1104/pp.17.01310 ( 2018 ). OpenUrl Abstract / FREE Full Text 32. ↵ Ellinghaus , D. , Kurtz , S. & Willhoeft , U. LTRharvest, an efficient and flexible software for de novo detection of LTR retrotransposons . BMC Bioinform . 9 , 18 ; doi: 10.1186/1471-2105-9-18 ( 2008 ). OpenUrl CrossRef PubMed 33. ↵ Xu , Z. & Wang , H. LTR_FINDER: an efficient tool for the prediction of full-length LTR retrotransposons . Nucleic Acids Res . 35 , W265 – W268 , doi: 10.1093/nar/gkm286 ( 2007 ). OpenUrl CrossRef PubMed Web of Science 34. ↵ Tarailo-Graovac , M. & Chen , N. Using RepeatMasker to identify repetitive elements in genomic sequences . Current Protoc. Bioinform . 25 , 4.10.1-4.10.14 , doi: 10.1002/0471250953.bi0410s25 ( 2009 ) OpenUrl CrossRef PubMed 35. ↵ Jurka , J. et al. Repbase Update, a database of eukaryotic repetitive elements . Cytogenet. Genome Res . 110 , 462 – 467 , doi: 10.1159/000084979 ( 2005 ). OpenUrl CrossRef PubMed Web of Science 36. ↵ Neumann , P. , Novák , P. , Hoštáková , N. & Macas , J. Systematic survey of plant LTR-retrotransposons elucidates phylogenetic relationships of their polyprotein domains and provides a reference for element classification . Mob. DNA 10 , 1 , doi: 10.1186/s13100-018-0144-1 ( 2019 ). OpenUrl CrossRef PubMed 37. ↵ Wheeler , T. J. et al. Dfam: a database of repetitive DNA based on profile hidden Markov models . Nucleic Acids Res . 41 , D70 – D82 , doi: 10.1093/nar/gks1265 ( 2013 ). OpenUrl CrossRef PubMed Web of Science 38. ↵ Beier , S. , Thiel , T. , Münch , T. , Scholz , U. & Mascher , M. MISA-web: a web server for microsatellite prediction . Bioinformatics 33 , 2583 – 2585 , doi: 10.1093/bioinformatics/btx198 ( 2017 ). OpenUrl CrossRef PubMed 39. ↵ Benson , G. Tandem repeats finder: a program to analyze DNA sequences . Nucleic Acids Res . 27 , 573 – 580 , doi: 10.1093/nar/27.2.573 ( 1999 ). OpenUrl CrossRef PubMed Web of Science 40. ↵ Stanke , M. , Diekhans , M. , Baertsch , R. & Haussler , D. Using native and syntenically mapped cDNA alignments to improve de novo gene finding . Bioinformatics 24 , 637 – 644 , doi: 10.1093/bioinformatics/btn013 ( 2008 ). OpenUrl CrossRef PubMed Web of Science 41. ↵ Stanke , M. , Diekhans , M. , Baertsch , R. & Haussler , D. Using native and syntenically mapped cDNA alignments to improve de novo gene finding . Bioinformatics 24 , 637 – 644 , doi: 10.1093/bioinformatics/btn013 ( 2008 ). OpenUrl CrossRef PubMed Web of Science 42. ↵ Korf , I. Gene finding in novel genomes . BMC Bioinform . 5 , 59 ; doi: 10.1186/1471-2105-5-59 ( 2004 ). OpenUrl CrossRef PubMed 43. ↵ Keilwagen , J. et al. Using intron position conservation for homology-based gene prediction . Nucleic Acids Res . 44 , e89 , doi: 10.1093/nar/gkw092 ( 2016 ). OpenUrl CrossRef PubMed 44. ↵ Kim , D. , Langmead , B. & Salzberg , S. L. HISAT: a fast spliced aligner with low memory requirements . Nat. Methods 12 , 357 – 360 , doi: 10.1038/nmeth.3317 ( 2015 ). OpenUrl CrossRef PubMed 45. ↵ Pertea , M. et al. StringTie enables improved reconstruction of a transcriptome from RNA-seq reads . Nat. Biotechnol . 33 , 290 – 295 , doi: 10.1038/nbt.3122 ( 2015 ). OpenUrl CrossRef PubMed 46. Daccord , N. et al. High-quality de novo assembly of the apple genome and methylome dynamics of early fruit development . Nat. Genet . 49 , 1099 – 1106 , doi: 10.1038/ng.3886 ( 2017 ). OpenUrl CrossRef PubMed 47. ↵ Lamesch , P. et al. The Arabidopsis Information Resource (TAIR): improved gene annotation and new tools . Nucleic Acids Res . 40 , D1202 – D1210 , doi: 10.1093/nar/gkr1090 ( 2012 ). OpenUrl CrossRef PubMed Web of Science 48. ↵ Li , Z. et al. Chromosome-scale reference genome provides insights into the genetic origin and grafting-mediated stress tolerance of Malus prunifolia . Plant Biotechnol. J . 20 , 1015 – 1017 , doi: 10.1111/pbi.13817 ( 2022 ). OpenUrl CrossRef PubMed 49. ↵ Tang , S. , Lomsadze , A. & Borodovsky , M. Identification of protein coding regions in RNA transcripts . Nucleic Acids Res . 43 , e78 ; doi: 10.1093/nar/gkv227 ( 2015 ). OpenUrl CrossRef PubMed 50. ↵ Grabherr , M. G. et al. A. Full-length transcriptome assembly from RNA-Seq data without a reference genome . Nat. Biotechnol . 29 , 644 – 652 , doi: 10.1038/nbt.1883 ( 2011 ). OpenUrl CrossRef PubMed 51. ↵ Haas , B. J. et al. Improving the Arabidopsis genome annotation using maximal transcript alignment assemblies . Nucleic Acids Res . 31 , 5654 – 5666 , doi: 10.1093/nar/gkg770 ( 2003 ). OpenUrl CrossRef PubMed Web of Science 52. ↵ Haas , B. J. et al. Automated eukaryotic gene structure annotation using EVidenceModeler and the Program to Assemble Spliced Alignments . Genome Biol . 9 , R7 , doi: 10.1186/gb-2008-9-1-r7 ( 2008 ). OpenUrl CrossRef PubMed 53. ↵ Oliveros , J.C. Venny: An interactive tool for comparing lists with Venn’s diagrams . https://bioinfogp.cnb.csic.es/tools/venny/index.html (2007-2015). 54. ↵ Lowe , T. M. & Eddy , S. R. tRNAscan-SE: a program for improved detection of transfer RNA genes in genomic sequence . Nucleic Acids Res . 25 , 955 – 964 , doi: 10.1093/nar/25.5.955 ( 1997 ). OpenUrl CrossRef PubMed 55. ↵ Loman , T. A Novel Method for Predicting Ribosomal RNA Genes in Prokaryotic Genomes . MSc thesis, Lund University ( 2017 ). 56. ↵ Griffiths-Jones , S. et al. A. Rfam: annotating non-coding RNAs in complete genomes . Nucleic Acids Res . 33 , D121 – D124 , doi: 10.1093/nar/gki081 ( 2005 ). OpenUrl CrossRef PubMed Web of Science 57. ↵ Griffiths-Jones , S. , Grocock , R. J. , van Dongen , S. , Bateman , A. & Enright , A. J. miRBase: microRNA sequences, targets and gene nomenclature . Nucleic Acids Res . 34 , D140 – D144 , doi: 10.1093/nar/gkj112 ( 2006 ). OpenUrl CrossRef PubMed Web of Science 58. ↵ Nawrocki , E. P. & Eddy , S. R. Infernal 1.1: 100-fold faster RNA homology searches . Bioinformatics 29 , 2933 – 2935 , doi: 10.1093/bioinformatics/btt509 ( 2013 ). OpenUrl CrossRef PubMed Web of Science 59. ↵ She , R. , Chu , J. S.-C. , Wang , K. , Pei , J. & Chen , N. GenBlastA: enabling BLAST to identify homologous gene sequences . Genome Res . 19 , 143 – 149 , doi: 10.1101/gr.082081.108 ( 2009 ). OpenUrl Abstract / FREE Full Text 60. ↵ Birney , E. , Clamp , M. & Durbin , R. GeneWise and Genomewise . Genome Res . 14 , 988 – 995 , doi: 10.1101/gr.1865504 ( 2004 ). OpenUrl Abstract / FREE Full Text 61. ↵ Huerta-Cepas , J. et al. eggNOG 5.0: a hierarchical, functionally and phylogenetically annotated orthology resource based on 5090 organisms and 2502 viruses . Nucleic Acids Res . 47 , D309 – D314 , doi: 10.1093/nar/gky1085 ( 2019 ). OpenUrl CrossRef PubMed 62. ↵ Ashburner , M. et al. Gene ontology: tool for the unification of biology . Nat. Genet . 25 , 25 – 29 , doi: 10.1038/75556 ( 2000 ). OpenUrl CrossRef PubMed Web of Science 63. ↵ The Gene Ontology Consortium et al. The Gene Ontology knowledgebase in 2023 . Genetics 224, iyad031 , doi: 10.1093/genetics/iyad031 ( 2023 ). OpenUrl CrossRef PubMed 64. ↵ Kanehisa , M. , Sato , Y. , Kawashima , M. , Furumichi , M. & Tanabe , M. KEGG as a reference resource for gene and protein annotation . Nucleic Acids Res . 44 , D457 – D462 , doi: 10.1093/nar/gkv1070 ( 2016 ). OpenUrl CrossRef PubMed 65. ↵ Boeckmann , B. et al. The SWISS-PROT protein knowledgebase and its supplement TrEMBL in 2003 . Nucleic Acids Res . 31 , 365 – 370 , doi: 10.1093/nar/gkg095 ( 2003 ). OpenUrl CrossRef PubMed Web of Science 66. ↵ Finn , R. D. et al. Pfam: clans, web tools and services . Nucleic Acids Res . 34 , D247 – D251 , doi: 10.1093/nar/gkj149 ( 2006 ). OpenUrl CrossRef PubMed Web of Science 67. ↵ Jones , P. et al. InterProScan 5: genome-scale protein function classification . Bioinformatics 30 , 1236 – 1240 , doi: 10.1093/bioinformatics/btu031 ( 2014 ). OpenUrl CrossRef PubMed Web of Science 68. ↵ Wu , T. D. & Nacu , S. Fast and SNP-tolerant detection of complex variants and splicing in short reads . Bioinformatics 26 , 873 – 881 , doi: 10.1093/bioinformatics/btq057 ( 2010 ). OpenUrl CrossRef PubMed Web of Science 69. ↵ Browning , B. L. , Zhou , Y. & Browning , S. R. A One-Penny Imputed Genome from Next-Generation Reference Panels . Am. J. Hum. Genet . 103 , 338 – 348 , doi: 10.1016/j.ajhg.2018.07.015 ( 2018 ). OpenUrl CrossRef PubMed 70. ↵ Li , H. Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM . Preprint at arXiv doi: 10.48550/arXiv.1303.3997 ( 2013 ). OpenUrl CrossRef 71. ↵ Afgan , E. et al. The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2016 update . Nucleic Acids Res . 44 , W3 – W10 , doi: 10.1093/nar/gkw343 ( 2016 ). OpenUrl CrossRef PubMed 72. ↵ Krzywinski , M. et al. Circos: an information aesthetic for comparative genomics . Genome Res . 19 , 1639 – 1645 , doi: 10.1101/gr.092759.109 ( 2009 ). OpenUrl Abstract / FREE Full Text 73. ↵ 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 , doi: 10.1093/bioinformatics/btv351 ( 2015 ). OpenUrl CrossRef PubMed 74. ↵ R Core Team . R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing , Vienna, Austria . https://www.R-project.org/ ( 2023 ). 75. Wickham , H. ggplot2: Elegant Graphics for Data Analysis . ( Springer-Verlag New York , 2016 ) View the discussion thread. Back to top Previous Next Posted July 31, 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 High-quality haplotype-resolved genome assembly and annotation of Malus baccata ‘Jackii’ 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 High-quality haplotype-resolved genome assembly and annotation of Malus baccata ‘Jackii’ Matthias Pfeifer , Ofere Francis Emeriewen , Henryk Flachowsky , Monika Höfer , Jens Keilwagen , Fang-Shiang Lim , Andreas Peil , Holger Zetzsche , Thomas Wöhner bioRxiv 2025.07.27.667097; doi: https://doi.org/10.1101/2025.07.27.667097 Share This Article: Copy Citation Tools High-quality haplotype-resolved genome assembly and annotation of Malus baccata ‘Jackii’ Matthias Pfeifer , Ofere Francis Emeriewen , Henryk Flachowsky , Monika Höfer , Jens Keilwagen , Fang-Shiang Lim , Andreas Peil , Holger Zetzsche , Thomas Wöhner bioRxiv 2025.07.27.667097; doi: https://doi.org/10.1101/2025.07.27.667097 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 (7640) Biochemistry (17707) Bioengineering (13903) Bioinformatics (41980) Biophysics (21465) Cancer Biology (18613) Cell Biology (25528) Clinical Trials (138) Developmental Biology (13387) Ecology (19920) Epidemiology (2067) Evolutionary Biology (24332) Genetics (15615) Genomics (22519) Immunology (17747) Microbiology (40424) Molecular Biology (17194) Neuroscience (88664) Paleontology (667) Pathology (2839) Pharmacology and Toxicology (4827) Physiology (7650) Plant Biology (15160) Scientific Communication and Education (2046) Synthetic Biology (4302) Systems Biology (9826) Zoology (2271)