Merge branch 'release/0.16.1'

Author: siebrenf

CHANGELOG.md

@@ -6,6 +6,11 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ## [Unreleased]
 
+## [0.16.1] - 2023-06-14
+
+### Fixed
+- fix for NCBI's assembly report header "asm_submitter" instead of "submitter"
+
 ## [0.16.0] - 2023-05-31
 
 ### Added
@@ -473,6 +478,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Added `-r` and `--match/--no-match` option to select sequences by regex.
 
 [Unreleased]: https://github.com/vanheeringen-lab/genomepy/compare/master...develop
+[0.16.0]: https://github.com/vanheeringen-lab/genomepy/compare/0.16.0...0.16.1
 [0.16.0]: https://github.com/vanheeringen-lab/genomepy/compare/0.15.0...0.16.0
 [0.15.0]: https://github.com/vanheeringen-lab/genomepy/compare/0.14.0...0.15.0
 [0.14.0]: https://github.com/vanheeringen-lab/genomepy/compare/0.13.1...0.14.0

genomepy/__about__.py

@@ -1,5 +1,5 @@
 """Metadata"""
-__version__ = "0.16.0"
+__version__ = "0.16.1"
 __author__ = (
     "Siebren Frölich, Maarten van der Sande, Tilman Schäfers and Simon van Heeringen"
 )

genomepy/providers/base.py

@@ -331,7 +331,7 @@ def _search_text(self, term: str, exact=False) -> Iterator[str]:
 
         pattern = re.compile(term, re.I)  # case insensitive
         for name, metadata in self.genomes.items():
-            texts = [name] + [str(metadata[f]) for f in self.description_fields]
+            texts = [name] + [str(metadata.get(f, "")) for f in self.description_fields]
             if any(pattern.search(t) for t in texts):
                 yield name
 
@@ -340,7 +340,7 @@ def _search_accession(self, term: str, exact=False) -> Iterator[str]:
         # cut off prefix (GCA/GCF) and suffix (version numbers, e.g. '.3')
         term = term.upper() if exact else term[3:].split(".")[0]
         for name, metadata in self.genomes.items():
-            if any(term in str(metadata[f]) for f in self.accession_fields):
+            if any(term in str(metadata.get(f, "")) for f in self.accession_fields):
                 yield name
 
     def _search_taxonomy(self, term: str, exact=False) -> Iterator[str]:
@@ -354,7 +354,7 @@ def exact_match(md, t):
 
         func = exact_match if exact else fuzzy_match
         for name, metadata in self.genomes.items():
-            if any(func(metadata[f], term) for f in self.taxid_fields):
+            if any(func(metadata.get(f, ""), term) for f in self.taxid_fields):
                 yield name
 
     def search(self, term: str or int, exact=False, size=False):

genomepy/providers/ncbi.py

@@ -39,7 +39,8 @@ class NcbiProvider(BaseProvider):
     accession_fields = ["assembly_accession", "gbrs_paired_asm"]
     taxid_fields = ["species_taxid", "taxid"]
     description_fields = [
-        "submitter",
+        "submitter",  # replaced with "asm_submitter" in 2023
+        "asm_submitter",
         "organism_name",
         "assembly_accession",
         "gbrs_paired_asm",
@@ -65,7 +66,7 @@ def _genome_info_tuple(self, name, size=False):
         taxid = self.genome_taxid(name)
         annotations = bool(self.annotation_links(name))
         species = self.genomes[name].get("organism_name")
-        other = self.genomes[name].get("submitter")
+        other = self.genomes[name].get("asm_submitter")
         if size:
             length = get_genome_size(accession)
             return name, accession, taxid, annotations, species, length, other
@@ -224,14 +225,14 @@ def load_summary(url):
     ]
     # filter summaries to these keys (to reduce the size of the cached data)
     summary_keys_to_keep = [
-        0,  # 'assembly_accession',
-        5,  # 'taxid',
-        6,  # 'species_taxid',
-        7,  # 'organism_name',
-        16,  # 'submitter',
-        17,  # 'gbrs_paired_asm',
-        18,  # 'paired_asm_comp',
-        19,  # 'ftp_path',
+        0,  # "assembly_accession",
+        5,  # "taxid",
+        6,  # "species_taxid",
+        7,  # "organism_name",
+        16,  # "asm_submitter",
+        17,  # "gbrs_paired_asm",
+        18,  # "paired_asm_comp",
+        19,  # "ftp_path",
     ]
     for fname in names:
         lines = load_summary(f"{assembly_url}/{fname}")

genomepy/providers/ucsc.py

@@ -97,7 +97,7 @@ def _search_accession(self, term: str, exact=False) -> Iterator[str]:
         term = term.upper() if exact else term[3:].split(".")[0]
         hits = False
         for name, metadata in self.genomes.items():
-            if any([term in str(metadata[f]) for f in self.accession_fields]):
+            if any([term in str(metadata.get(f, "")) for f in self.accession_fields]):
                 hits = True
                 yield name
 

tests/test_07_provider_ncbi.py

@@ -72,7 +72,11 @@ def test__get_genomes(ncbi):
     genome = ncbi.genomes["ASM2732v1"]
     assert isinstance(genome, dict)
     for field in ncbi.accession_fields + ncbi.taxid_fields + ncbi.description_fields:
-        assert field in genome
+        if field.endswith("submitter"):
+            # "submitter" or "asm_submitter" must be present
+            assert sum([k.endswith("submitter") for k in genome.keys()]) == 1
+        else:
+            assert field in genome.keys()
     assert genome["species_taxid"] == "2097"
     assert genome["taxid"] == "243273"