De novo genome assemblies of the dwarf honey bee subgenus Micrapis : Apis andreniformis and Apis florea

preprint OA: closed
📄 Open PDF Full text JSON View at publisher

Abstract

The Micrapis subgenus, which includes the black dwarf honey bee ( Apis andreniformis ) and the red dwarf honey bee ( Apis florea ), remains underrepresented in genomic studies despite its ecological significance. Here, we present high-quality de novo genome assemblies for both species, generated using a hybrid sequencing approach combining Oxford Nanopore Technologies (ONT) long reads with Illumina short reads. The final assemblies are highly contiguous, with contig N50 values of 5.0 Mb ( A. andreniformis ) and 4.3 Mb ( A. florea ), representing a major improvement over the previously published A. florea genome. Genome completeness assessments indicate high quality, with BUSCO scores exceeding 98.5% and k-mer analyses supporting base-level accuracy. Repeat annotation revealed a relatively low repetitive sequence content (∼6%), consistent with other Apis species. Using RNA sequencing data, we annotated 12,232 genes for A. andreniformis and 12,597 genes for A. florea , with >97% completeness in predicted proteomes. These genome assemblies provide a valuable resource for comparative and functional genomic studies, offering new insights into the genetic basis of dwarf honey bee adaptations.
Full text 48,105 characters · extracted from preprint-html · click to expand
De novo genome assemblies of the dwarf honey bee subgenus Micrapis: Apis andreniformis and Apis florea | 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 De novo genome assemblies of the dwarf honey bee subgenus Micrapis : Apis andreniformis and Apis florea View ORCID Profile Atma Ivancevic , Madison Sankovitz , View ORCID Profile Holly Allen , Olivia Joyner , View ORCID Profile Edward B. Chuong , View ORCID Profile Samuel D. Ramsey doi: https://doi.org/10.1101/2025.04.01.646657 Atma Ivancevic 1 BioFrontiers Institute and Department of Molecular, Cellular & Developmental Biology, University of Colorado Boulder , Boulder, CO, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Atma Ivancevic Madison Sankovitz 2 BioFrontiers Institute, University of Colorado Boulder , Boulder, CO, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site Holly Allen 1 BioFrontiers Institute and Department of Molecular, Cellular & Developmental Biology, University of Colorado Boulder , Boulder, CO, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Holly Allen Olivia Joyner 1 BioFrontiers Institute and Department of Molecular, Cellular & Developmental Biology, University of Colorado Boulder , Boulder, CO, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site Edward B. Chuong 1 BioFrontiers Institute and Department of Molecular, Cellular & Developmental Biology, University of Colorado Boulder , Boulder, CO, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Edward B. Chuong For correspondence: s.ramsey{at}colorado.edu edward.chuong{at}colorado.edu Samuel D. Ramsey 3 BioFrontiers Institute and Department of Ecology and Evolutionary Biology, University of Colorado Boulder , Boulder, CO, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Samuel D. Ramsey For correspondence: s.ramsey{at}colorado.edu edward.chuong{at}colorado.edu Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Abstract The Micrapis subgenus, which includes the black dwarf honey bee ( Apis andreniformis ) and the red dwarf honey bee ( Apis florea ), remains underrepresented in genomic studies despite its ecological significance. Here, we present high-quality de novo genome assemblies for both species, generated using a hybrid sequencing approach combining Oxford Nanopore Technologies (ONT) long reads with Illumina short reads. The final assemblies are highly contiguous, with contig N50 values of 5.0 Mb ( A. andreniformis ) and 4.3 Mb ( A. florea ), representing a major improvement over the previously published A. florea genome. Genome completeness assessments indicate high quality, with BUSCO scores exceeding 98.5% and k-mer analyses supporting base-level accuracy. Repeat annotation revealed a relatively low repetitive sequence content (∼6%), consistent with other Apis species. Using RNA sequencing data, we annotated 12,232 genes for A. andreniformis and 12,597 genes for A. florea , with >97% completeness in predicted proteomes. These genome assemblies provide a valuable resource for comparative and functional genomic studies, offering new insights into the genetic basis of dwarf honey bee adaptations. Introduction Honey bees ( Apis spp.) are among the most ecologically and economically significant insects on the planet ( Hristov et al. 2020 ; Khalifa et al. 2021 ; Papa et al. 2022 ). Renowned for their role in pollination, honey production, and as models for studying social behavior, these eusocial insects are indispensable to agricultural systems and natural ecosystems ( Gill 1990 ; Zayed and Robinson 2012 ; Hoover and Ovinge 2018 ). There are eight recognized honey bee species that exhibit varying sizes, nest structures, and ecological niches, though the total number of species is disputed, with some evidence for 11 ( Crane 2009 ). While the western honey bee A. mellifera is the most extensively studied and globally distributed species, other honey bee species, including those in the subgenera Apis, Megapis , and Micrapis , exhibit remarkable diversity in their behaviors and adaptations, many of which remain underexplored. The subgenus Micrapis consists of the dwarf honey bees ( Fig. 1 ), black A. andreniformis and red A. florea , which live throughout south and southeast Asia (Benjamin P. Oldroyd and Wongsiri 2009 ). Red dwarf honey bees have been shown to contribute to the pollination of a diverse range of flora, playing an essential role in maintaining the biodiversity and ecosystem stability of its native regions (Ali, Sajjad, and Saeed 2017; Abrol 2010 ; Shwetha, Bhat, and Neethu 2020 ). Black dwarf honey bees are less studied, likely because they have a smaller distribution than their sister species, although their size and life history are similar and therefore they likely have a comparable ecological impact ( Otis 1996 ). However, despite their ecological importance, both dwarf honey bee species remain underexplored compared to the widely studied western honey bee. Download figure Open in new tab Fig. 1. The dwarf honey bees: (a) black dwarf honey bees and (b) red dwarf honey bees. Photos by Sirachai Shin Arunrugstichai. Dwarf honey bees are morphologically and behaviorally distinct from western honey bees. Dwarf honey bees only live in specific regions in Asia, whereas western honey bees have a cosmopolitan distribution ( Otis 1996 ). Workers of the dwarf honey bees are significantly smaller, about half the size of western honey bee workers (B. P. Oldroyd 2021 ). They also exhibit smaller colony sizes, a simplicity that extends to their nesting behavior; both species construct single, exposed combs in open-air settings, typically hanging from thin branches of low shrubs ( Rinderer et al. 1996 ; B. P. Oldroyd 2021 ). This contrasts with the enclosed nests of western honey bees ( Seeley and Morse 1976 ). Comparative genomics across honey bee species is critical for understanding the genetic basis of their distinctive traits, including morphology and ecological adaptations. Individual genomes of the western honey bee Apis mellifera have led to the identification of new subspecies, a better understanding of evolutionary lineages, and the discovery of a significant number of genes involved with adaptations and colony-level quantitative traits ( Dogantzis and Zayed 2019 ). Genomics can dramatically improve our ability to understand invasive honey bee parasites and mitigate their impacts by selecting stocks with resilient traits, revealing the effect of parasites on bee health, and identifying biomarkers for rapid diagnostics ( Grozinger and Zayed 2020 ). The dwarf honey bees have relatively few parasites that are otherwise invasive and highly damaging to western honey bee colonies worldwide; they are not hosts of Varroa mites, and Tropilaelaps mites have only been observed in red dwarf honey bee colonies in India several decades ago ( Abrol and Kakroo 1997 ). Therefore, dwarf honey bee genomic resources are timely and may be valuable in our collective efforts to control invasive parasites. While a high-quality nuclear genome assembly is available for the western honey bee ( Wallberg et al. 2019 ), the genomes of the dwarf honey bees remain poorly characterized. The nuclear genome of the red dwarf honey bee A. florea was previously sequenced using legacy 454 sequencing technology ( Fouks et al. 2021 ), this assembly has relatively low coverage (20.5x) and is highly fragmented (total length: 211.3 Mb, scaffold N50: 2.9 Mb), making it suboptimal for genomic analysis. The nuclear genome of the black dwarf honey bee A. andreniformis has not been sequenced. To address this gap, we combined Oxford Nanopore Technologies (ONT) long-read sequencing with Illumina short-read sequencing to sequence both species’ nuclear genomes and transcriptomes, generating high-quality genome assemblies and transcript-level gene annotations for both dwarf honey bees. These assemblies provide a valuable resource for comparative genomic analyses and offer new insights into the genetic underpinnings of traits unique to dwarf honey bees. Materials and Methods Sample collection Genome sequencing was performed using specimens of A. andreniformis and A. florea collected from managed colonies in Singapore. Specifically, one female worker A. andreniformis pupa (Aa1SG1, diploid) was collected from a colony in Frankel, and one female worker A. florea pupa (Af1SG1, diploid) was collected from a colony in Admiralty. To complement genome sequencing, additional samples from the same colonies were collected for RNA sequencing. These included: Two female worker A. andreniformis pupae (diploid, samples Aa1SG2 and Aa1SG3). One female worker A. florea pupa (diploid, Af1SG2) and one male A. florea pupa (haploid, Af1SG3). Pupae were extracted from comb cells with forceps after removing the wax cell capping with forceps. After collection, all specimens were flash-frozen in liquid nitrogen and stored at -80°C until extraction. They were then shipped in a cryo-shipper from Singapore to Colorado. DNA extraction and sequencing Genomic DNA was extracted from one female A. andreniformis pupa and one female A. florea pupa using the Quick-DNA Tissue/Insect Kit (Zymo Research), according to the manufacturer’s instructions. For ONT long-read sequencing, a genomic library was prepared with the Native Barcoding Kit 24 V14 kit (SQK-NBD114.24) and sequenced on an R10.4.1 PromethION flow cell (FLO-PRO114M). For Illumina sequencing, a genomic library was prepared using the Ovation Ultralow System V2 kit (Tecan) and sequenced on an Illumina NovaSeq 6000 (University of Colorado Genomics Core) at the University of Colorado, Anschutz. Paired-end 2 × 150 bp reads were generated. RNA extraction and sequencing RNA was extracted from two female A. andreniformis pupae, one female A. florea pupa, and one male A. florea pupa using a TRIzol/column-based method. In brief, whole pupa (30-110 mg) were homogenized in 1 ml TRIzol (ThermoFisher) and then centrifuged at 12,000 xg for 5 minutes at 4°C to remove the cell debris. The supernatant was incubated for 5 minutes at room temperature, mixed with 200 µL chloroform, incubated for a further 3 minutes, and then centrifuged at 12,000 xg for 5 minutes at 4°C. The upper, aqueous phase was combined with a 1:1 ratio of 100% ethanol and then purified according to the Direct-zol RNA Miniprep Kit (Zymo Research). For ONT sequencing, an RNA library was prepared with the PCR cDNA Barcoding Kit (SQK-PCB111.24) and sequenced on an R9.4.1 PromethION flow cell (FLO-PRO002). For Illumina sequencing, an RNA library was prepared using the KAPA mRNA HyperPrep kit (KK8581) and sequenced on an Illumina NovaSeq 6000 (University of Colorado Genomics Core) at the University of Colorado, Anschutz. Paired-end 2 × 150 bp reads were generated. Genome assembly and polishing High-quality genome assemblies for A. andreniformis and A. florea were generated using a combination of ONT long reads and Illumina short reads. The assembly process was conducted in several steps, including base-calling, demultiplexing, de novo assembly, initial polishing, and additional polishing using the short reads. ONT raw signals in POD5 format were base-called using Dorado v0.7.2 (ONT Public License v1.0) using the super high accuracy model (SUP) to ensure high-quality basecalls, and --kit-name SQK-NBD114-24 to enable barcode classification in-line with basecalling. Reads were demultiplexed using Dorado’s demux function and flags --no-classify and --emit-fastq to produce FASTQ files for each barcode. Read statistics for demultiplexed reads were obtained using NanoStat v1.6.0 ( De Coster et al. 2018 ). De novo assemblies of the draft genomes for A. andreniformis and A. florea were conducted using Flye v2.9.5 ( Kolmogorov et al. 2019 ) with options --nano-hq to indicate high-quality reads and the genome size estimate set to 230 Mb (--genome-size 230m) for both bees. The mean coverage of each genome was derived from Flye v2.9.5 ( Kolmogorov et al. 2019 ). Draft assemblies were polished using Medaka v2.0.0 (ONT Public License v1.0), providing the raw ONT reads for each bee and the model r1041_e82_400bps_sup_v5.0.0 as input. Further polishing was conducted with Pilon v1.24 ( Walker et al. 2014 ), leveraging Illumina short reads to correct small indels and base call mismatches. Illumina short reads were first trimmed for adapter sequences, low-quality bases, and contaminants using the bbduk.sh script from BBMap v38.05 ( https://sourceforge.net/projects/bbmap ) and the following parameters: -Xmx32g ktrim=r k=31 mink=11 hdist=1 tpe tbo qtrim=r trimq=10. Trimmed reads were aligned to their corresponding long-read draft assemblies using BWA-MEM v0.7.5 ( Li and Durbin 2009 ), with alignments filtered to exclude low-quality and unmapped reads (-q 10 -F 4) and sorted with Samtools v1.16.1 ( Danecek et al. 2021 ; Li et al. 2009 ). The resulting BAM files were used in Pilon v1.24, as described above, to polish assemblies at the per-base level, correcting small base pair errors and indels. All software was executed using default settings unless otherwise specified. After polishing, VSEARCH v2.14.1 (Rognes et al. 2016) was used with function --sortbylength to sort all contigs by length, and parameters --maxseqlength 1000000000 --minseqlength 3000 to remove contigs shorter than 3 kb for each genome. Before submission to GenBank, the final assemblies underwent contamination screening using NCBI’s Foreign Contamination Screen Tool Suite v0.5.4 ( Astashyn et al. 2024 ). This process consisted of two sequential steps: (1) screening for vector and adapter contamination using FCS-adaptor, and (2) identifying and removing foreign contaminants such as bacterial and viral sequences using FCS-GX, with Apis-specific taxonomic filtering (NCBI taxonomy ID 7464 for A. andreniformis and taxonomy ID 7463 for A. florea ). The cleaned assemblies were then submitted to GenBank. Quality assessment The quality of each genome was assessed based on three criteria: assembly contiguity, genome completeness, and k-mer comparison to short reads. Assembly contiguity was evaluated using QUAST v5.2.0 ( Mikheenko et al. 2018 ) to generate metrics such as N50, L50, total assembly length, and the number of contigs. Genome completeness was assessed using BUSCO v5.7.1 (Manni et al. 2021) with OrthoDB v10 ( Kriventseva et al. 2019 ) to evaluate the presence or absence of universal single-copy orthologous genes. Detected BUSCO genes were classified as single-copy, duplicated, or fragmented. The following lineage-specific OrthoDB databases were used: hymenoptera_odb10 (creation date: 2024-01-08; 40 genomes; 5991 BUSCOs) insecta_odb10 (creation date: 2024-01-08; 75 genomes; 1367 BUSCOs) arthropoda_odb10 (creation date: 2024-01-08; 90 genomes; 1013 BUSCOs) metazoa_odb10 (creation date: 2024-01-08; 65 genomes; 954 BUSCOs) Completeness statistics were compared to two existing Apis genome assemblies: A. mellifera Amel_HAv3.1 (NCBI RefSeq assembly accession GCF_003254395.2) ( Wallberg et al. 2019 ) and A. florea Aflo_1.1 (NCBI RefSeq assembly accession GCF_000184785.3) ( Fouks et al. 2021 ). K-mer analysis was performed using Meryl v1.4.1 ( Rhie et al. 2020 ) and Merqury v1.3 ( Rhie et al. 2020 ) to compare k-mers between the short-read data and polished genome assemblies. Meryl was used to generate k-mer databases from the Illumina paired-end short reads. Merqury was used to compare these k-mer databases to the genome assemblies, providing estimates of k-mer completeness (i.e. the percentage of short-read k-mers present in the assembly) and assembly quality values. While the short reads in this study were only used for genome polishing, this approach nonetheless highlighted the concordance between the Illumina data and the final assemblies. All software was executed using default settings. Repeat annotation RepeatMasker v4.1.7 (Smit et al. 2013, www.repeatmasker.org ) was used to softmask repeats in the polished assemblies and generate repeat statistics for each genome. RepeatMasker was configured with Tandem Repeats Finder v4.0.9 ( Benson 1999 ), RMBlast v2.14.0 ( www.repeatmasker.org/rmblast ), and all nine library partitions from Dfam Database v3.8 ( Storer et al. 2021 ). RepeatMasker was executed with default parameters except -pa 8 -species Eukaryota - noisy -xsmall. Transcriptome assembly and annotation The transcriptomes of A. andreniformis and A. florea were characterized using long-read ONT cDNA sequencing data and short-read Illumina RNA sequencing data. Long-read cDNA sequencing data was base-called using Dorado v0.7.2 (ONT Public License v1.0) with the super high accuracy (SUP) model and the --no-trim option to retain untrimmed reads necessary for cDNA-specific downstream analyses. Demultiplexing was performed using Dorado’s demux function with --no-trim enabled. Read quality and length distributions were assessed using NanoStat v1.6.0 ( De Coster et al. 2018 ). To refine the ONT reads, Pychopper v2.5.0 (ONT Public License v2.0) was used to identify and trim full-length cDNA reads, with -k PCB111 specified for the barcode kit. High-confidence full-length reads were merged with rescued reads to generate the final processed cDNA dataset. ONT reads from the male A. florea sample (Af1SG3) were excluded from further analyses due to poor sequencing quality, an N50 of only 196 bp, and high barcode retention. The remaining three samples—two A. andreniformis females and one A. florea female—demonstrated sufficient quality and coverage for downstream analyses, with N50 values exceeding 1,100 bp and total yields ranging from 31 to 40 Gb. Processed cDNA reads were aligned to the genome using Minimap2 v2.22 with the -x splice option. Illumina RNA-seq reads were preprocessed using the bbduk.sh script from BBMap v38.05 ( https://sourceforge.net/projects/bbmap ) and the following parameters: -Xmx32g ktrim=r k=31 mink=11 hdist=1 tpe tbo qtrim=r trimq=10, to remove adapter sequences and low-quality bases. A Hisat2 genome index was generated for each species using Hisat2 v2.1.0 ( Kim et al. 2019 ), and preprocessed reads were mapped to the genome assembly with default sensitivity and the --dta flag to optimize alignments for transcript assembly. BAM files were sorted and indexed using Samtools v1.16.1 ( Danecek et al. 2021 ; Li et al. 2009 ), and the two Illumina RNA-seq BAM files were merged for each species. Genome annotation was performed using BRAKER3 ( Gabriel et al. 2024 ), an automated gene prediction pipeline that integrates RNA-seq and protein homology evidence to generate gene models. Gene prediction was carried out using GeneMark-ETP (Brůna, Lomsadze, and Borodovsky 2024) and AUGUSTUS ( Stanke et al. 2008 ), incorporating extrinsic evidence to refine gene structures. TSEBRA ( Gabriel et al. 2021 ) was used to select the most well-supported transcript isoforms. StringTie2 ( Kovaka et al. 2019 ) was used for transcriptome assembly. To improve homology-based predictions, we provided the Arthropoda protein dataset from OrthoDB v12 ( Tegenfeldt et al. 2025 ), downloaded from https://bioinf.uni-greifswald.de/bioinf/partitioned_odb12/Arthropoda.fa.gz . DIAMOND ( Buchfink, Xie, and Huson 2015 ) was used to incorporate and align the Arthropoda protein sequences. Gene annotation outputs were further processed with GffRead ( Pertea and Pertea 2020 ) for format conversion and filtering. For A. andreniformis , BRAKER3 was run using two ONT cDNA BAM files (one per sample), a single merged Illumina RNA-seq BAM file, and protein sequences from Arthropoda as extrinsic evidence. For A. florea , BRAKER3 was run with one ONT cDNA BAM file (from sample Af1SG2), a single merged Illumina RNA-seq BAM file, and protein sequences. All software was executed using default settings unless otherwise specified. Results and Discussion Genome sequence data summary Sequencing statistics are summarized in Table 1 . In brief, for A. andreniformis , long-read sequencing using ONT (Native Barcoding V14 Kit sequenced on R10.4.1 PromethION flow cells) yielded 54.0 Gb of raw reads (read length N50 of 6,657 bp; mean read quality of 15.9). Using an estimated genome size of ∼230 Mb gave an initial coverage estimate of 235x. De novo assembly using Flye ( Kolmogorov et al. 2019 ) resulted in a reported mean coverage of 235x. Whole genome sequencing using Illumina yielded 16.4 Gb (54,425,614 150 bp read pairs; mean quality score of 38.5), producing an estimated short read coverage of 71x. Pilon ( Walker et al. 2014 ) was used to polish the long-read genome assembly with these Illumina short reads. All raw sequencing reads were uploaded to the NCBI Sequence Read Archive (SRA), which revealed that the ONT reads contained <0.01% bacteria and other contaminants. In contrast, the Illumina reads contained many unidentified reads (32.43%, likely derived from adapter sequences) and contaminants (e.g. 6.84% bacteria). Therefore, the bbduk.sh script from BBMap was used to filter and trim the short reads before alignment to the long-read assembly. View this table: View inline View popup Download powerpoint Table 1. Sequencing statistics of raw reads for A. andreniformis and A. florea . Shows the number of raw reads (or read pairs for Illumina) and the total number of gigabases generated. For Illumina reads, estimated coverage is based on the number of sequence bases and an assumed genome size of ∼230 Mb. For ONT long reads, estimated coverage is based on the mean coverage reported by Flye during the initial assembly step. All reads have been uploaded to NCBI SRA and can be downloaded using the listed accession numbers. For A. florea , we generated 42.6 Gb of long reads using ONT sequencing (read length N50 of 6,132 bp; mean read quality of 15.7). This amount gave us a coverage estimate of 185x based on the assumed genome size of ∼230 Mb. De novo assembly using Flye ( Kolmogorov et al. 2019 ) resulted in a reported mean coverage of 176x, slightly less than our initial estimate. Whole genome sequencing using Illumina yielded 15.4 Gb (50,980,281 read pairs; mean quality score of 38.4), producing an estimated short read coverage of 67x, which we used for base-level polishing of the long-read assembly. As observed with A. andreniformis , the ONT reads for A. florea showed <0.01 contaminants, whereas the Illumina reads contained 2.47% bacteria and required trimming prior to alignment. Final assemblies were additionally screened using NCBI’s Foreign Contamination Screen ( Astashyn et al. 2024 ) to remove any remaining vector or microbial contaminants before submission to GenBank. Assembly quality and completeness We generated high-quality genome assemblies for A. andreniformis and A. florea using ONT long-read sequencing, followed by Illumina short-read polishing. The final A. andreniformis assembly (Aa1SG1) consisted of 333 contigs totaling 216.8 Mb, a contig N50 of 5.0 Mb, and a GC content of 33.7% ( Table 2 ). The A. florea assembly (Af1SG1) had a slightly larger total length of 221.6 Mb, with 601 contigs and a contig N50 of 4.3 Mb. Compared to the previously published A. florea assembly, Aflo_1.1 ( Fouks et al. 2021 ), which was sequenced using 454 shotgun sequencing, our assemblies show significant improvements in contiguity and completeness. The Aflo_1.1 assembly contains 6,983 scaffolds and 18,378 contigs, with a contig N50 of 24.9 kb–orders of magnitude lower than our assemblies ( Table 2 ). View this table: View inline View popup Download powerpoint Table 2. Assembly contiguity statistics for the A. andreniformis and A. florea genomes compared to previously published Apis genomes. Assembly statistics for our genomes (Aa1SG1 for A. andreniformis and Af1SG1 for A. florea ) were generated using QUAST on the polished assemblies. For the published assemblies (Aflo_1.1 and Amel_HAv3.1), assembly statistics were obtained from their publicly available NCBI genome pages. Genome completeness estimates using BUSCO confirm the high quality of our assemblies. When evaluated against the Hymenoptera dataset, A. andreniformis (Aa1SG1) and A. florea (Af1SG1) achieved completeness scores of 98.5% and 98.6%, respectively, with low levels of fragmentation (0.6–0.7%) or missing genes (0.8%; Table 3 ). BUSCO analysis using the broader Insecta dataset showed even higher completeness estimates of 99.7% for both species ( Table 3 ). K-mer analysis using Merqury further supported the completeness and base-level accuracy of our assemblies. View this table: View inline View popup Download powerpoint Table 3. Genome completeness statistics for the A. andreniformis and A. florea genomes compared to previously published Apis genomes. BUSCO analysis was performed using the OrthoDB v10 datasets for Hymenoptera (5,991 genes) and Insecta (1,367 genes), with results shown below. Additional analyses using datasets for Arthropoda (1,013 genes) and Metazoa (954 genes) are summarized in Supp Table 1 . Since Illumina short reads were used exclusively for polishing rather than assembly, the k-mer completeness estimates primarily reflect how well the short-read data aligns with the final genomes. K-mer completeness was estimated at ∼93% for both species ( Supp Table 2, Supp Figures 1–2 ), suggesting that some genomic regions, such as highly repetitive sequences, may be underrepresented in the short-read data. However, the low estimated per-base error rates (∼0.0002, Supp Table 2 ) indicate a high base-level accuracy, consistent with the strong BUSCO scores. Finally, repeat analysis identified a diverse set of repetitive elements ( Supp Tables 3 & 4 ), with total repeat content estimated at ∼6% for both bee species. This content is consistent with previous findings in A. dorsata ( Oppenheim et al. 2020 ) and A. mellifera ( Wallberg et al. 2019 ). Altogether, our results indicate that these genome assemblies represent the highest-quality Micrapis dwarf honey bee genomes published to date. Gene annotation RNA from two pupae per species was extracted and sequenced using a combination of ONT long-read cDNA sequencing and Illumina short-read RNA-seq. For A. andreniformis , we generated 70,960,146 ONT long reads with read length N50s exceeding 1 kb (1,178 bp N50 for sample Aa1SG2; 1,145 bp N50 for sample Aa1SG3; Supp Table 5 ), along with 25.6 million high-quality Illumina read pairs. Similarly, for A. florea , we obtained 34,084,378 Nanopore reads with read length N50s of 1,098 bp (sample Af1SG2) and 196 bp (sample Af1SG3, excluded from downstream analyses), as well as 21.1 million Illumina read pairs ( Supp Table 5 ). Previous annotations for A. florea ( Fouks et al. 2021 ) and A. mellifera ( Wallberg et al. 2019 ) identified 12,573 and 12,398 genes, respectively. Our BRAKER3 annotation yielded similar numbers, with 12,232 putative genes for A. andreniformis and 12,597 genes for A. florea ( Table 4 ). BUSCO analysis of the predicted proteomes identified 97.8% of orthologs using the Hymenoptera database and 99.5% of orthologs using the broader Insecta database ( Table 5 ), indicating that our annotation successfully captured nearly all expected genes for these species. View this table: View inline View popup Download powerpoint Table 4. Summary statistics of BRAKER3 gene annotation for both genome assemblies. View this table: View inline View popup Download powerpoint Table 5. BUSCO completeness statistics for the predicted proteomes of A. andreniformis and A. florea , assessed using OrthoDB v10 datasets for Hymenoptera (5,991 genes) and Insecta (1,367 genes). Results indicate the percentage of complete, fragmented, and missing orthologs in each assembly, with complete genes further categorized as single-copy or duplicated. Notably, we observed a relatively high proportion of duplicated BUSCO genes (∼23–26%; Table 5 ), which may reflect uncollapsed heterozygosity, as these diploid female bee genomes were assembled without Hi-C or haplotype resolution. Some alleles may have been retained as separate sequences rather than phased, leading to apparent gene duplications. However, the low fraction of missing BUSCOs (∼0.4–1.6%; Table 5 ) suggests that the assemblies are highly complete, supporting the idea that duplication inflation is due to heterozygosity rather than misassembly and highlighting the need for haplotype-aware approaches in future diploid assemblies. Conclusion Here, we report new high-quality reference genome assemblies for the black dwarf bee A. andreniformis , sampled from Frankel, Singapore, and the red dwarf bee A. florea , sampled from Admiralty, Singapore. These genomes will provide a crucial resource for further biological, population, and evolutionary studies of dwarf honey bees. Our assemblies were generated using a hybrid sequencing approach combining Oxford Nanopore Technology long reads (with R10.4.1 flowcells) and Illumina short reads. While we sequenced diploid female individuals to enable us to call heterozygous sites, given our relatively modest contig N50 values (5.0 Mb for A. andreniformis ; 4.3 Mb for A. florea ), we did not conduct haplotype resolution for these initial assemblies. Ultra-long reads and/or Hi-C data would be necessary to achieve haplotype-resolved and chromosome-level assemblies. Future work sequencing additional individuals from other populations will be critical for developing a comprehensive catalog of genomic variation, including structural variants. A key strength of our approach is its efficiency, as it required only a single pupa per species to generate genome assemblies with over 98.5% completeness. This approach contrasts with previous studies, such as Aflo_1.1 ( Fouks et al. 2021 ) and Amel_HAv3.1 ( Wallberg et al. 2019 ), which pooled multiple adult drones to achieve similar assembly quality. Our results underscore the potential of using hybrid sequencing to study rare or endangered species, such as these dwarf honey bees, where access to adult specimens is limited or unavailable and even pupae are considered extremely precious. Data availability All raw sequencing data used for genome and transcriptome sequencing are available on the NCBI Sequence Read Archive ( www.ncbi.nlm.nih.gov/sra ) under the following BioProjects: Apis andreniformis Genome sequencing and assembly; NCBI BioProject PRJNA1217036 Transcriptome sequencing; NCBI BioProject PRJNA1217108 Apis florea Genome sequencing and assembly; NCBI BioProject PRJNA1217041 Transcriptome sequencing; NCBI BioProject PRJNA1217110 Genome assemblies have been deposited in GenBank under accession GCA_048593525.1 for Apis andreniformis and GCA_048593485.1 for Apis florea . Gene annotations generated using BRAKER3 are available on Zenodo ( https://doi.org/10.5281/zenodo.15048194 ). Source code and workflows are available on GitHub ( https://github.com/atmaivancevic/Micrapis_genome_project ). Conflict of interest The authors declare no competing interests. Funding MS and SDR were funded by grant ID AP23PPQS&T00C157, “Study of Honey Bee Pest Diversity to Support Development of Emergency Response Plan”, from the United States Department of Agriculture Animal Plant Health Inspection Service. AI, HA, OJ, and EBC were funded by NIGMS grant ID 2R35GM128822. Footnotes ↵ * co-first authors ↵ + co-last authors https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA1217036 https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA1217108 https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA1217041 https://www.ncbi.nlm.nih.gov/bioproject/?term=PRJNA1217110 https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_048593525.1/ https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_048593485.1/ https://zenodo.org/records/15048194 References ↵ Abrol , D. P. 2010 . “ Foraging Behaviour of Apis Florea F., an Important Pollinator of Allium Cepa L .” Journal Apicultural Research 49 ( 4 ): 318 – 25 . OpenUrl CrossRef ↵ Abrol , D. P. , and S. K. Kakroo . 1997 . “ Observations on Concurrent Parasitism by Mites on Four Honeybee Species in India .” Tropical Agriculture 74 ( 2 ). Ali , M. , Sajjad, and S. Saeed . 2017 . “ Yearlong Association of Apis Dorsata and Apis Florea with Flowering Plants: Planted Forest vs. Agricultural Landscape .” Sociobiology 64 ( 1 ): 18 – 25 . OpenUrl CrossRef ↵ Astashyn , Alexander , Eric S. Tvedte , Deacon Sweeney , Victor Sapojnikov , Nathan Bouk , Victor Joukov , Eyal Mozes , et al. 2024 . “ Rapid and Sensitive Detection of Genome Contamination at Scale with FCS-GX .” Genome Biology 25 ( 1 ): 60 . OpenUrl CrossRef PubMed ↵ Benson , G. 1999 . “ Tandem Repeats Finder: A Program to Analyze DNA Sequences .” Nucleic Acids Research 27 ( 2 ): 573 – 80 . OpenUrl CrossRef PubMed Web of Science Brůna , Tomáš , Alexandre Lomsadze , and Mark Borodovsky . 2024 . “ GeneMark-ETP Significantly Improves the Accuracy of Automatic Annotation of Large Eukaryotic Genomes .” Genome Research 34 ( 5 ): 757 – 68 . OpenUrl Abstract / FREE Full Text ↵ Buchfink , Benjamin , Chao Xie , and Daniel H. Huson . 2015 . “ Fast and Sensitive Protein Alignment Using DIAMOND .” Nature Methods 12 ( 1 ): 59 – 60 . OpenUrl CrossRef PubMed ↵ Crane , E. 2009 . “ Apis Species:(Honey Bees ).” In Encyclopedia of Insects , 31 – 32 . Academic Press . ↵ Danecek , Petr , James K. Bonfield , Jennifer Liddle , John Marshall , Valeriu Ohan , Martin O. Pollard , Andrew Whitwham , et al. 2021 . “ Twelve Years of SAMtools and BCFtools .” GigaScience 10 ( 2 ). doi: 10.1093/gigascience/giab008 . OpenUrl CrossRef PubMed ↵ De Coster , Wouter , Svenn D’Hert , Darrin T. Schultz , Marc Cruts , and Christine Van Broeckhoven . 2018 . “ NanoPack: Visualizing and Processing Long-Read Sequencing Data .” Bioinformatics (Oxford, England) 34 ( 15 ): 2666 – 69 . OpenUrl CrossRef PubMed ↵ Dogantzis , Kathleen A. , and Amro Zayed . 2019 . “ Recent Advances in Population and Quantitative Genomics of Honey Bees .” Current Opinion in Insect Science 31 ( February ): 93 – 98 . OpenUrl CrossRef PubMed ↵ Fouks , Bertrand , Philipp Brand , Hung N. Nguyen , Jacob Herman , Francisco Camara , Daniel Ence , Darren E. Hagen , et al. 2021 . “ The Genomic Basis of Evolutionary Differentiation among Honey Bees .” Genome Research 31 ( 7 ): 1203 – 15 . OpenUrl Abstract / FREE Full Text ↵ Gabriel , Lars , Tomáš Brůna , Katharina J. Hoff , Matthis Ebel , Alexandre Lomsadze , Mark Borodovsky , and Mario Stanke . 2024 . “ BRAKER3: Fully Automated Genome Annotation Using RNA-Seq and Protein Evidence with GeneMark-ETP, AUGUSTUS, and TSEBRA .” Genome Research 34 ( 5 ): 769 – 77 . OpenUrl Abstract / FREE Full Text ↵ Gabriel , Lars , Katharina J. Hoff , Tomáš Brůna , Mark Borodovsky , and Mario Stanke . 2021 . “ TSEBRA: Transcript Selector for BRAKER .” BMC Bioinformatics 22 ( 1 ): 566 . OpenUrl CrossRef PubMed ↵ Gill , R. A. 1990 . “ The Value of Honeybee Pollination to Society .” In VI International Symposium on Pollination 288 , 62 – 68 . OpenUrl ↵ Grozinger , Christina M. , and Amro Zayed . 2020 . “ Improving Bee Health through Genomics .” Nature Reviews. Genetics 21 ( 5 ): 277 – 91 . OpenUrl CrossRef PubMed ↵ Hoover , Shelley E. , and Lynae P. Ovinge . 2018 . “ Pollen Collection, Honey Production, and Pollination Services: Managing Honey Bees in an Agricultural Setting .” Journal of Economic Entomology 111 ( 4 ): 1509 – 16 . OpenUrl CrossRef PubMed ↵ Hristov , Peter , Boyko Neov , Rositsa Shumkova , and Nadezhda Palova . 2020 . “ Significance of Apoidea as Main Pollinators. Ecological and Economic Impact and Implications for Human Nutrition .” Diversity 12 ( 7 ): 280 . OpenUrl CrossRef ↵ Khalifa , Shaden A. M. , Esraa H. Elshafiey , Aya A. Shetaia , Aida A. Abd El-Wahed , Ahmed F. Algethami , Syed G. Musharraf , Mohamed F. AlAjmi , et al. 2021 . “ Overview of Bee Pollination and Its Economic Value for Crop Production .” Insects 12 ( 8 ): 688 . OpenUrl CrossRef PubMed ↵ Kim , Daehwan , Joseph M. Paggi , Chanhee Park , Christopher Bennett , and Steven L. Salzberg . 2019 . “ Graph-Based Genome Alignment and Genotyping with HISAT2 and HISAT-Genotype .” Nature Biotechnology 37 ( 8 ): 907 – 15 . OpenUrl CrossRef PubMed ↵ Kolmogorov , Mikhail , Jeffrey Yuan , Yu Lin , and Pavel A. Pevzner . 2019 . “ Assembly of Long, Error-Prone Reads Using Repeat Graphs .” Nature Biotechnology 37 ( 5 ): 540 – 46 . OpenUrl CrossRef PubMed ↵ Kovaka , Sam , Aleksey V. Zimin , Geo M. Pertea , Roham Razaghi , Steven L. Salzberg , and Mihaela Pertea . 2019 . “ Transcriptome Assembly from Long-Read RNA-Seq Alignments with StringTie2 .” Genome Biology 20 ( 1 ): 278 . OpenUrl CrossRef PubMed ↵ Kriventseva , Evgenia V. , Dmitry Kuznetsov , Fredrik Tegenfeldt , Mosè Manni Renata Dias , Felipe A. Simão , and Evgeny M. Zdobnov . 2019 . “ OrthoDB v10: Sampling the Diversity of Animal, Plant, Fungal, Protist, Bacterial and Viral Genomes for Evolutionary and Functional Annotations of Orthologs .” Nucleic Acids Research 47 ( D1 ): D807 – 11 . OpenUrl CrossRef PubMed ↵ Li , Heng , and Richard Durbin . 2009 . “ Fast and Accurate Short Read Alignment with Burrows-Wheeler Transform .” Bioinformatics (Oxford, England) 25 ( 14 ): 1754 – 60 . OpenUrl CrossRef PubMed Web of Science ↵ Li , Heng , Bob Handsaker , Alec Wysoker , Tim Fennell , Jue Ruan , Nils Homer , Gabor Marth , Goncalo Abecasis , Richard Durbin , and 1000 Genome Project Data Processing Subgroup . 2009 . “ The Sequence Alignment/Map Format and SAMtools .” Bioinformatics (Oxford, England) 25 ( 16 ): 2078 – 79 . OpenUrl CrossRef PubMed Web of Science Manni , Mosè , Matthew R. Berkeley , Mathieu Seppey , Felipe A. Simão , and Evgeny M. Zdobnov . 2021 . “ BUSCO Update: Novel and Streamlined Workflows along with Broader and Deeper Phylogenetic Coverage for Scoring of Eukaryotic, Prokaryotic, and Viral Genomes .” Molecular Biology and Evolution 38 ( 10 ): 4647 – 54 . OpenUrl CrossRef PubMed ↵ Mikheenko , Alla , Andrey Prjibelski , Vladislav Saveliev , Dmitry Antipov , and Alexey Gurevich . 2018 . “ Versatile Genome Assembly Evaluation with QUAST-LG .” Bioinformatics (Oxford, England) 34 ( 13 ): i142 – 50 . OpenUrl CrossRef PubMed ↵ Oldroyd , Benjamin P. , and Siriwat Wongsiri . 2009 . Asian Honey Bees: Biology, Conservation, and Human Interactions . Harvard University Press . ↵ Oldroyd , B. P. 2021 . “ Dwarf Honey Bees (Apis (Micrapis )).” In Encyclopedia of Social Insects , 333 – 39 . Cham : Springer International Publishing . ↵ Oppenheim , Sara , Xiaolong Cao , Olav Rueppel , Sasiprapa Krongdang , Patcharin Phokasem , Rob DeSalle , Sara Goodwin , Jinchuan Xing , Panuwan Chantawannakul , and Jeffrey A. Rosenfeld . 2020 . “ Whole Genome Sequencing and Assembly of the Asian Honey Bee Apis Dorsata .” Genome Biology and Evolution 12 ( 1 ): 3677 – 83 . OpenUrl CrossRef PubMed ↵ Otis , G. W. 1996 . “ Distributions of Recently Recognized Species of Honey Bees (Hymenoptera: Apidae; Apis) in Asia .” Journal of the Kansas Entomological Society , 311 – 33 . ↵ Papa , Giulia , Roberto Maier , Alessandra Durazzo , Massimo Lucarini , Ioannis K. Karabagias , Manuela Plutino , Elisa Bianchetto , et al. 2022 . “ The Honey Bee Apis Mellifera: An Insect at the Interface between Human and Ecosystem Health .” Biology 11 ( 2 ): 233 . OpenUrl CrossRef PubMed ↵ Pertea , Geo , and Mihaela Pertea . 2020 . “ GFF Utilities: GffRead and GffCompare .” F1000Research 9 ( April ). doi: 10.12688/f1000research.23297.2 . OpenUrl CrossRef ↵ Rhie , Arang , Brian P. Walenz , Sergey Koren , and Adam M. Phillippy . 2020 . “ Merqury: Reference-Free Quality, Completeness, and Phasing Assessment for Genome Assemblies .” Genome Biology 21 ( 1 ): 245 . OpenUrl CrossRef PubMed ↵ Rinderer , Thomas E. , Siriwat Wongsiri , Bangyu Kuang , Jisheng Liu , Benjamin P. Oldroyd , H. Allen Sylvester , and Lilia de Guzman . 1996 . “ Comparative Nest Architecture of the Dwarf Honey Bees .” Journal of Apicultural Research 35 ( 1 ): 19 – 26 . OpenUrl CrossRef Rognes , Torbjørn , Tomáš Flouri , Ben Nichols , Christopher Quince , and Frédéric Mahé . 2016 . “ VSEARCH: A Versatile Open Source Tool for Metagenomics .” PeerJ 4 ( October ): e2584 . OpenUrl CrossRef PubMed ↵ Seeley , T. D. , and R. A. Morse . 1976 . “ The Nest of the Honey Bee (Apis Mellifera L .).” Insectes Sociaux 23 ( 4 ): 495 – 512 . OpenUrl CrossRef ↵ Shwetha , B. V. , N. S. Bhat , and T. Neethu . 2020 . “ Utilization of Apis Florea in Crop Pollination .” In The Future Role of Dwarf Honey Bees in Natural and Agricultural Systems , 107 – 23 . CRC Press . ↵ Stanke , Mario , Mark Diekhans , Robert Baertsch , and David Haussler . 2008 . “ Using Native and Syntenically Mapped cDNA Alignments to Improve de Novo Gene Finding .” Bioinformatics (Oxford, England) 24 ( 5 ): 637 – 44 . OpenUrl CrossRef PubMed Web of Science ↵ Storer , Jessica , Robert Hubley , Jeb Rosen , Travis J. Wheeler , and Arian F. Smit . 2021 . “ The Dfam Community Resource of Transposable Element Families, Sequence Models, and Genome Annotations .” Mobile DNA 12 ( 1 ): 2 . OpenUrl CrossRef PubMed ↵ Tegenfeldt , Fredrik , Dmitry Kuznetsov , Mosè Manni Matthew Berkeley , Evgeny M. Zdobnov , and Evgenia V. Kriventseva . 2025 . “ OrthoDB and BUSCO Update: Annotation of Orthologs with Wider Sampling of Genomes .” Nucleic Acids Research 53 ( D1 ): D516 – 22 . OpenUrl CrossRef PubMed ↵ Walker , Bruce J. , Thomas Abeel , Terrance Shea , Margaret Priest , Amr Abouelliel , Sharadha Sakthikumar , Christina A. Cuomo , et al. 2014 . “ Pilon: An Integrated Tool for Comprehensive Microbial Variant Detection and Genome Assembly Improvement .” PloS One 9 ( 11 ): e112963 . OpenUrl CrossRef PubMed ↵ Wallberg , Andreas , Ignas Bunikis , Olga Vinnere Pettersson , Mai-Britt Mosbech , Anna K. Childers , Jay D. Evans , Alexander S. Mikheyev , Hugh M. Robertson , Gene E. Robinson , and Matthew T. Webster . 2019 . “ A Hybrid de Novo Genome Assembly of the Honeybee, Apis Mellifera, with Chromosome-Length Scaffolds .” BMC Genomics 20 ( 1 ): 275 . OpenUrl CrossRef PubMed ↵ Zayed , Amro , and Gene E. Robinson . 2012 . “ Understanding the Relationship between Brain Gene Expression and Social Behavior: Lessons from the Honey Bee .” Annual Review of Genetics 46 ( September ): 591 – 615 . OpenUrl CrossRef PubMed Web of Science View the discussion thread. Back to top Previous Next Posted April 06, 2025. Download PDF Supplementary Material 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 De novo genome assemblies of the dwarf honey bee subgenus Micrapis: Apis andreniformis and Apis florea 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 De novo genome assemblies of the dwarf honey bee subgenus Micrapis : Apis andreniformis and Apis florea Atma Ivancevic , Madison Sankovitz , Holly Allen , Olivia Joyner , Edward B. Chuong , Samuel D. Ramsey bioRxiv 2025.04.01.646657; doi: https://doi.org/10.1101/2025.04.01.646657 Share This Article: Copy Citation Tools De novo genome assemblies of the dwarf honey bee subgenus Micrapis : Apis andreniformis and Apis florea Atma Ivancevic , Madison Sankovitz , Holly Allen , Olivia Joyner , Edward B. Chuong , Samuel D. Ramsey bioRxiv 2025.04.01.646657; doi: https://doi.org/10.1101/2025.04.01.646657 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 (7642) Biochemistry (17715) Bioengineering (13907) Bioinformatics (42005) Biophysics (21472) Cancer Biology (18624) Cell Biology (25534) Clinical Trials (138) Developmental Biology (13390) Ecology (19935) Epidemiology (2067) Evolutionary Biology (24356) Genetics (15617) Genomics (22529) Immunology (17753) Microbiology (40437) Molecular Biology (17200) Neuroscience (88697) Paleontology (667) Pathology (2840) Pharmacology and Toxicology (4829) Physiology (7653) Plant Biology (15171) Scientific Communication and Education (2046) Synthetic Biology (4304) Systems Biology (9827) Zoology (2272)

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00