<?xml version="1.0" encoding="UTF-8"?>

<?xml-stylesheet type="text/xsl" href="/static/oaitohtml.xsl"?>

<!--
<?xml-stylesheet type="text/xsl" href="/oaitohtml.xsl"?>
-->

<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
    <responseDate>2026-10-14T17:16:02Z</responseDate>
    <request verb="GetRecord" metadataPrefix="oai_dc" identifier="10.57760/sciencedb.35748" >https://www.scidb.cn/oai</request>
<GetRecord>
    <record>
    <header >
    <identifier>10.57760/sciencedb.35748</identifier>
    <datestamp>2026-07-12T15:29:13Z</datestamp>
</header>
    <metadata>
        
<oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:date>2026-07-12</dc:date>
  <dc:title>Data for: DNRA horizontal gene transfer (HGT) analysis of nrfA genes</dc:title>
  <dc:identifier>doi:10.57760/sciencedb.35748</dc:identifier>
  <dc:language>en</dc:language>
  <dc:description>This dataset supports the manuscript on DNRA (dissimilatory nitrate reduction to ammonium) and horizontal gene transfer (HGT) analysis of nrfA genes.## Dataset Summary- **Total files**: 90 files- **Last updated**: 2026-05-13## Folder Structure| Folder | Content | File Count ||--------|---------|------------|| `01_sequences/` | FASTA sequence files with subdirectories (raw/, processed/, aligned/) and combined dataset | 10 files || `03_tree/` | Phylogenetic tree files (IQ-TREE outputs: .nwk, .fasta alignment) | 3 files || `04_hgt/` | HGT analysis results (GC content, ENC, delta GC, candidate lists, IQ-TREE outputs, metadata) | 14 files || `05_script/` | Python/Shell scripts for data retrieval, analysis, and figure generation (includes sub-modules: easy_fig/, flanking_mobile_elements/, generax_scripts/, reconciliation/) | 51 files || `06_figures/` | Raw CSV data used to generate figures and tables | 15 files |### Detailed Directory Tree```文件关联数据/│├── Readme.md│├── 01_sequences/│&amp;nbsp;&amp;nbsp;├── all_sequences.fasta│&amp;nbsp;&amp;nbsp;├── aligned/│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── nrfA_alignment.fasta│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── nrfA_all_for_phylogeny.fasta│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;└── nrfA_merged_alignment.fasta│&amp;nbsp;&amp;nbsp;├── processed/│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── mobile_element_proteins.fasta│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── nrfA_hgt.fasta│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── nrfA_reference.fasta│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;└── nrfA_sequences.fasta│&amp;nbsp;&amp;nbsp;└── raw/│&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;├── nrfA_from_eutils.fasta│&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;└── PRJNA1204190_nrfA_candidates.fasta│├── 03_tree/│&amp;nbsp;&amp;nbsp;├── nrfA_alignment.fasta│&amp;nbsp;&amp;nbsp;├── nrfA_merged_tree.nwk│&amp;nbsp;&amp;nbsp;└── nrfA_tree.nwk│├── 04_hgt/│&amp;nbsp;&amp;nbsp;├── delta_gc_analysis.json│&amp;nbsp;&amp;nbsp;├── enc_analysis_complete.json│&amp;nbsp;&amp;nbsp;├── gc_analysis_results_corrected.json│&amp;nbsp;&amp;nbsp;├── nrfA_hgt_candidates.csv│&amp;nbsp;&amp;nbsp;├── nrfA_hgt_meta.csv│&amp;nbsp;&amp;nbsp;├── nrfA_hgt_results.csv│&amp;nbsp;&amp;nbsp;├── nrfA_ML.contree│&amp;nbsp;&amp;nbsp;├── nrfA_ML.iqtree│&amp;nbsp;&amp;nbsp;├── nrfA_ML.treefile│&amp;nbsp;&amp;nbsp;├── Table2_HGT_candidates.csv│&amp;nbsp;&amp;nbsp;├── wwtp_nrfA_delta_gc.csv│&amp;nbsp;&amp;nbsp;├── wwtp_nrfA_enc_results.csv│&amp;nbsp;&amp;nbsp;├── wwtp_nrfA_gc_results.csv│&amp;nbsp;&amp;nbsp;└── wwtp_nrfA_HGT_summary.csv│├── 05_script/│&amp;nbsp;&amp;nbsp;├── 05_script_README_scripts.txt│&amp;nbsp;&amp;nbsp;├── 05_script_requirements.txt│&amp;nbsp;&amp;nbsp;├── cross_phylum_clusters.json│&amp;nbsp;&amp;nbsp;├── [analysis scripts *.py &amp;times; 28]│&amp;nbsp;&amp;nbsp;├── easy_fig/&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;larr; EasyFig synteny visualization│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── download_genbank_files.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── run_easyfig_v2.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── search_geobacter.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── search_kuenenia.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;└── synteny_final.py│&amp;nbsp;&amp;nbsp;├── flanking_mobile_elements/&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;larr; Flanking region &amp;amp; mobile element analysis│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── step1_fetch_flanking.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── step1b_diagnose_accessions.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── step2_flanking_corrected.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── step3_deep_flanking.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── step4_blast_mobile_elements.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;└── step5_visualization.py│&amp;nbsp;&amp;nbsp;├── generax_scripts/&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;larr; GeneRax ML-DTL reconciliation│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── build_family_file.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── extract_plausible_trees.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;├── pargenes_to_family_file.py│&amp;nbsp;&amp;nbsp;│&amp;nbsp;&amp;nbsp;└── scalasca_build.sh│&amp;nbsp;&amp;nbsp;└── reconciliation/&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;larr; DTL reconciliation &amp;amp; bootstrap│&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;├── inspect_json.py│&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;├── step1_build_species_tree.py│&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;├── step2_reconciliation_core.py│&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;├── step3_bootstrap_reconciliation.py│&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;└── step4_visualization_v2.py│└── 06_figures/&amp;nbsp;&amp;nbsp;├── Figure7_metadata.csv&amp;nbsp;&amp;nbsp;├── nrfA_dist_matrix_new.csv&amp;nbsp;&amp;nbsp;├── nrfA_flanking_analysis.csv&amp;nbsp;&amp;nbsp;├── nrfA_gc_analysis.csv&amp;nbsp;&amp;nbsp;├── nrfA_gc_codon_results.csv&amp;nbsp;&amp;nbsp;├── nrfA_metadata.csv&amp;nbsp;&amp;nbsp;├── nrfA_reference_analysis.csv&amp;nbsp;&amp;nbsp;├── sequences_table.csv&amp;nbsp;&amp;nbsp;├── Table1_complete_metrics.csv&amp;nbsp;&amp;nbsp;├── TableS1_sequence_metadata.csv&amp;nbsp;&amp;nbsp;├── TableS2_lineage_summary.csv&amp;nbsp;&amp;nbsp;├── wwtp_nrfA_delta_gc.csv&amp;nbsp;&amp;nbsp;├── wwtp_nrfA_enc_results.csv&amp;nbsp;&amp;nbsp;├── wwtp_nrfA_gc_results.csv&amp;nbsp;&amp;nbsp;└── wwtp_nrfA_HGT_summary.csv## Software Requirements- Python 3.9+ (see `05_script/05_script_requirements.txt`)- IQ-TREE v2.2.0- MAFFT v7.5- GeneRax (Linux/WSL; `conda install generax -c bioconda`)## ContactFor questions: 434934032@qq.com</dc:description>
  <dc:subject>DNRA; nrfA; horizontal gene transfer; phylogenetic analysis; HGT; functional gene; nitrogen cycle; bioinformatics</dc:subject>
  <dc:creator>王昌稳</dc:creator>
  <dc:creator>高明昌</dc:creator>
  <dc:creator>裘娜</dc:creator>
  <dc:creator>丁祥伟</dc:creator>
  <dc:rights>EMBARGO</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/</dc:rights>
  <dc:type>dataset</dc:type>
  <dc:publisher>Science Data Bank</dc:publisher>
</oai_dc:dc>

    </metadata>
</record>
</GetRecord>
</OAI-PMH>