<?xml version='1.0' encoding='utf-8'?>
<?xml-stylesheet type="text/xsl" href="/v2/static/oai2.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-10-06T09:29:27Z</responseDate>
  <request identifier="oai:figshare.com:article/34037625" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/34037625</identifier>
        <datestamp>2026-10-01T01:38:28Z</datestamp>
        <setSpec>category_24310</setSpec>
        <setSpec>item_type_3</setSpec>
        <setSpec>month_year_10_2026</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>Genome annotation resources for &lt;i&gt;Propomacrus davidi&lt;/i&gt;</dc:title>
          <dc:creator>Xiaobo Xu (21391229)</dc:creator>
          <dc:subject>Genomics</dc:subject>
          <dc:subject>Propomacrus davidi</dc:subject>
          <dc:subject>genome annotation</dc:subject>
          <dc:subject>structural annotation</dc:subject>
          <dc:subject>functional annotation</dc:subject>
          <dc:subject>insect genomics</dc:subject>
          <dc:description>&lt;p dir="ltr"&gt;This dataset provides genome annotation resources for Propomacrus davidi to support gene discovery, functional interpretation, and comparative genomic research. The reference genome was generated from a single wild-collected female larva using PacBio HiFi sequencing and Illumina Hi-C data. Assembly was performed using hifiasm, followed by haplotypic redundancy reduction with purge_dups, scaffolding with HapHiC, and manual curation in Juicebox. The annotated reference assembly spans 498,019,884 bp across 14 scaffolds, including nine chromosome-scale scaffolds.&lt;/p&gt;&lt;p dir="ltr"&gt;The annotation comprises 11,994 protein-coding genes and 15,439 transcript models, with corresponding coding DNA and protein sequences. Multiple transcript isoforms may belong to the same gene.&lt;/p&gt;&lt;p dir="ltr"&gt;The archive contains four annotation directories:&lt;/p&gt;&lt;ol&gt;&lt;li&gt;structural_annotation: Protein-coding gene annotations in GFF3 format, the original BRAKER GTF and protein output, predicted spliced transcript sequences, CDS and protein FASTA files, genomic CDS sequences without artificial boundary padding, transcript-to-gene mappings, transcript quality flags, and reference sequence identifiers, lengths, and checksums.&lt;/li&gt;&lt;li&gt;functional_annotation: Integrated functional annotation tables at both gene and transcript levels, together with the underlying analysis outputs. Annotations incorporate NR and UniRef90 similarity searches, eggNOG-mapper assignments, InterProScan results, and reported HMMER Pfam matches. Available fields include GO terms, KEGG assignments, protein families, and domains. Gene-level annotations combine information across transcript isoforms; transcript-level tables retain isoform-specific assignments.&lt;/li&gt;&lt;li&gt;repeat_annotation: The de novo repeat library and RepeatMasker results describing repetitive sequences in the reference genome.&lt;/li&gt;&lt;li&gt;noncoding_RNA: tRNAscan-SE results, Rfam search outputs, predicted non-coding RNA candidate annotations in GFF3 format, and summary tables.&lt;/li&gt;&lt;/ol&gt;&lt;p dir="ltr"&gt;A README documents file formats, processing details, and interpretation notes. MD5 checksums are supplied for individual files and for the compressed archive. Functional assignments and non-coding RNA annotations are computational predictions; miRNA-related entries represent Rfam family candidates rather than experimentally validated mature miRNAs. Partial gene models and reported Pfam matches should be interpreted according to the README.&lt;/p&gt;&lt;p dir="ltr"&gt;This archive contains annotation resources only. The reference genome FASTA and raw sequencing reads are not included. The annotations must be used with the matching reference assembly identified by the sequence names, lengths, and checksums in structural_annotation/reference_sequences.tsv.gz.&lt;/p&gt;</dc:description>
          <dc:date>2026-10-01T01:38:28Z</dc:date>
          <dc:type>Dataset</dc:type>
          <dc:type>Dataset</dc:type>
          <dc:identifier>10.6084/m9.figshare.34037625.v1</dc:identifier>
          <dc:relation>https://figshare.com/articles/dataset/Genome_annotation_resources_for_i_Propomacrus_davidi_i_/34037625</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
          <dc:rights>Open Access after 2027-10-01</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
