diff --git a/README.md b/README.md index 5a008679e549994d9587b60690a510f712558400..c6290e7896d5477b3b80c9cf70843021d2f1b880 100644 --- a/README.md +++ b/README.md @@ -67,4 +67,13 @@ snakemake -j 1 -s rewrite-taxonomy.snakefile This will write the merged taxonomy in a format suitable for text projection. +## Resulting taxonomy +### Namespace prefixes + +| Prefix | Domain | URL construct | +|--------|--------|---------------| +| `ncbi` | NCBI Taxonomy | `https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id={ID}` | +| | | `https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=taxonomy&id={ID}` | +| `bd` | BacDive | `https://bacdive.dsmz.de/strain/{ID} | +| | | `https://api.bacdive.dsmz.de/example/fetch/{ID}` (authentication required) | diff --git a/dsmz-match.py b/dsmz-match.py index db0a2744e8876b4659c848f03d82c95f6aa78477..0c06a343e1a302e43792d185e70c5b31b51d5082 100755 --- a/dsmz-match.py +++ b/dsmz-match.py @@ -102,12 +102,7 @@ class BacDiveEntry: self.domain = tax.findtext('./domain') def _get_strain_taxid(self): - for sn in self.strain_number: - if sn.startswith('DSM'): - return sn.lower().replace(' ', ':') - if len(self.strain_number) > 0: - return self.strain_number[0].lower().replace(' ', ':') - return 'bacdive:%s' % os.path.basename(self.filename).replace('.xml', '') + return 'bd:' + self.bacdive_id def _get_canonical(self): for sn in self.strain_number: