pyobo 0.11.2__py3-none-any.whl → 0.12.1__py3-none-any.whl

pyobo/registries/metaregistry.json

@@ -1,507 +0,0 @@
-{
-  "blacklists": {
-    "full": [
-      "ClinGen:AminoacidopathyGeneCurationPanel",
-      "KEGG",
-      "NIST",
-      "ICD9CM_2005:<new dbxref>",
-      "XX:<new dbxref>",
-      "XX:<new xref>",
-      "STRUCTURE_Formula",
-      "United:Kingdom",
-      "United:States",
-      "Harvard-Oxford:Atlas",
-      "South:Korea",
-      "Codex:\\:260",
-      "Europe:\\:260",
-      "BioGRID:curators",
-      "POC:curators",
-      "CGP:curators",
-      "DiffAvg:",
-      "DiffFormula:",
-      "DiffMono:",
-      "Formula:",
-      "MassAvg:",
-      "MassMono:",
-      "Origin:",
-      "Source:",
-      "TermSpec:",
-      "FormalCharge:",
-      "snap:Quality",
-      "depicted:by",
-      "http:http\\://www.pacificbiosciences.com/pdf/WP_Detecting_DNA_Base_Modifications_Using_SMRT_Sequencing.pdf",
-      "XX:www.ensembl.org/info/genome/variation/predicted_data.html#consequences",
-      "http:www.ensembl.org/info/genome/variation/predicted_data.html#consequences",
-      "EBI:www.ebi.ac.uk/mutations/recommendations/mutevent.html",
-      "\\:has_start_point",
-      "DDB:pf",
-      "TS:0",
-      "CTD:curators",
-      "IEDB:RV",
-      "Tail:fat",
-      "Pituitary:gland",
-      "Compound:eye",
-      "Lymph:node",
-      "Lamina:propria",
-      "Follicular:fluid",
-      "dph:GOC",
-      "gOC:dph",
-      "gOC:dph",
-      "ftp://ftp.ncbi.nih.gov/snp/specs/docsum_3.1.xsd",
-      "HPO:PCS",
-      "HPO:ICE",
-      "IEDB:BP",
-      "PomBane:vw",
-      "PomBase\\:mah",
-      {
-        "type": "group",
-        "from": "mpath",
-        "text": [
-          "Pathbase: Curation",
-          "Pathbase: Pathology Committee"
-        ]
-      },
-      {
-        "type": "group",
-        "from": "hp",
-        "reason": "curator names appearing in definition and synonym provenance strings",
-        "text": [
-          "LMU:mgriese",
-          "HPO:sdoelken",
-          "HPO:curators",
-          "Sanford:krageth",
-          "HPO:probinson",
-          "UToronto:chum",
-          "PhenoTips:CHum"
-        ]
-      },
-      {
-        "type": "group",
-        "text": [
-          "KL:KL",
-          "PT:PT",
-          "EM:EM"
-        ],
-        "reason": "nonsense attribution",
-        "from": "idomal"
-      },
-      {
-        "type": "group",
-        "text": [
-          "NS:NS",
-          "Walter_Reed:taxonomy"
-        ],
-        "from": "miro"
-      },
-      "PLATY:A.H.L.Fischer",
-      "URL:http\\://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1007&context=onlinedictinvertzoology",
-      "NIFSTD:NeuroNames_abbrevSource",
-      {
-        "type": "group",
-        "text": [
-          "OBOL:accepted",
-          "OBOL:automatic",
-          "Follicular:antrum",
-          "Leydig's:organ",
-          "Dermal:denticle",
-          "Serous:membrane",
-          "Pinhole:eye",
-          "Vaginal:fornix",
-          "Duct:(anatomy)",
-          "Organ:(anatomy)"
-        ],
-        "from": "uberon"
-      },
-      "TAIR:TED",
-      "CS:0",
-      "ADL:FTT",
-      "Getty:TGN",
-      {
-        "type": "group",
-        "text": [
-          "USGS:SDTS",
-          "NASA:earthrealm",
-          "Genomes:fissure",
-          "METAR:FZRA",
-          "INTERNAS:WS2",
-          "Uranium:mining"
-        ],
-        "from": "envo"
-      },
-      {
-        "type": "group",
-        "text": [
-          "FlyPNS:PNSdescription0.html",
-          "FlyPNS:PNSdescription.html#lbd",
-          "FlyPNS:PNSdescription.html#ltd",
-          "FlyPNS:PNSnomenclature.html",
-          "FlyPNS:PNSdescription.html#dh1"
-        ],
-        "from": "fbbt"
-      },
-      {
-        "type": "group",
-        "text": [
-          "LifO:0000005"
-        ],
-        "from": "ino",
-        "reason": "random ad-hoc term. should probably just skip this entire ontology"
-      },
-      {
-        "type": "group",
-        "text": [
-          "GeneReviews:NBK331",
-          "GeneReviews:NBK5191",
-          "GeneReveiws:NBK350"
-        ],
-        "from": "maxo",
-        "comment": "these actually correspond to NCBI books"
-      },
-      {
-        "type": "group",
-        "text": [
-          "value-type:xsd\\:string"
-        ],
-        "from": "ms"
-      },
-      {
-        "type": "group",
-        "text": [
-          "POC:Maria_Alejandra_Gandolfo",
-          "NIG:Yukiko_Yamazaki",
-          "NYBG:Brandon_Sinn",
-          "NYBG:Dario_Cavaliere"
-        ],
-        "from": "po"
-      },
-      {
-        "type": "group",
-        "text": [
-          "Gramene:pankaj_jaiswal",
-          "scale:6",
-          "Gramene:cwt6"
-        ],
-        "from": "to"
-      },
-      {
-        "type": "group",
-        "text": [
-          "active:in",
-          "actively:involves",
-          "aggregate:statistic",
-          "associated:with",
-          "affected:by",
-          "base:coordinate",
-          "biomarker:for",
-          "capable:of",
-          "caused:by",
-          "coexpressed:with",
-          "association:type",
-          "association:slot",
-          "close:match",
-          "completed:by",
-          "coexists:with",
-          "colocalizes:with",
-          "available:from"
-        ],
-        "from": "biolink"
-      },
-      {
-        "type": "group",
-        "text": [
-          "TTOCurator:Conway_etal_2008",
-          "TTOCurator:CavenderAndCoburn1992",
-          "TTOCurator:Vari1995"
-        ],
-        "from": "tto"
-      }
-    ],
-    "resource_prefix": {
-      "ogg": [
-        "IMGT/GENE-DB:"
-      ],
-      "vo": [
-        "NCBITaxon_VO"
-      ],
-      "duo": [
-        "topic:"
-      ],
-      "fbbt": [
-        "larvalbrain_axon_tract:",
-        "larvalbrain_neuropil:",
-        "FlyPNS:PNS"
-      ],
-      "envo": [
-        "SPIRE:",
-        "TODO^^^",
-        "IUCN-PACS:",
-        "http://www.britannica.com"
-      ],
-      "mco": [
-        "colombos:"
-      ],
-      "efo": [
-        "Germplasm:",
-        "BilaDO:",
-        "OGES:"
-      ],
-      "idomal": [
-        "IRAC:",
-        "MOSBP"
-      ],
-      "mondo": [
-        "url:https\\://rarediseases.info.nih.gov",
-        "ICD10EXP:"
-      ],
-      "mod": [
-        "Remap:",
-        "UnMod:",
-        "UniMo:"
-      ],
-      "hao": [
-        "DUMMY_TYPDEF:"
-      ],
-      "iceo": [
-        "OTCS:"
-      ],
-      "uberon": [
-        "GAID:",
-        "OpenCyc:",
-        "BM:",
-        "BSA:",
-        "XtroDO:",
-        "nlx_subcell",
-        "OGEM:",
-        "ANISEED:",
-        "BILS:",
-        "ABA:",
-        "MAP:"
-      ],
-      "cellosaurus": [
-        "FCDI",
-        "CCTCC:",
-        "IARC_TP53:",
-        "KCB:",
-        "PharmacoDB:",
-        "MCCL:MCC:",
-        "IBRC",
-        "ISCR",
-        "IZSLER",
-        "MCCL",
-        "NCBI_Iran",
-        "NCI-DTP",
-        "NISES",
-        "RSCB",
-        "SKY/M-FISH/CGH",
-        "LINCS_HMS",
-        "CCLV",
-        "Cosmic-CLP:",
-        "PubChem_Cell_line:CVCL_",
-        "Rockland:",
-        "CancerTools:",
-        "Innoprot:"
-      ],
-      "oba": [
-        "AUTO:patterns"
-      ],
-      "pato": [
-        "ilxtr:"
-      ],
-      "plana": [
-        "Optic:",
-        "NIF:Subcellular\\:sao"
-      ],
-      "po": [
-        "FNA:",
-        "PlantSystematics_image_archive:",
-        "CO_125:",
-        "SOY:",
-        "TAIR:",
-        "OB_SF2_PO:",
-        "OBO-SF2_PO:",
-        "OBO_SF3_PO:",
-        "OBOS_SF_PO:",
-        "OB_SF_PO:",
-        "OBO-SF_PO:",
-        "OBO_PO_SF:",
-        "PO_REF",
-        "Maize",
-        "GO_GIT"
-      ],
-      "pr": [
-        "ImmPort:",
-        "TLR:",
-        "HIstome_ptm_Hs:"
-      ],
-      "to": [
-        "TO_GIT",
-        "GIT_TO",
-        "OBO_S2F_TO",
-        "GCP:GCP_"
-      ],
-      "tto": [
-        "CASGEN:"
-      ],
-      "wb": [
-        "WBPaper:"
-      ],
-      "cl": [
-        "WikipediaVersioned"
-      ]
-    },
-    "prefix": [
-      "Image:",
-      "Category",
-      "http://",
-      "https://",
-      "http://dbpedia.org",
-      "https://github.com",
-      "PERSON",
-      "similar to",
-      "modelled on",
-      "SUBMITTER",
-      "STRUCTURE_ChemicalName_IUPAC",
-      "STRUCTURE_Formula",
-      "stedman",
-      "From_Merriam-Webster's_Online_Dictionary_at_www.Merriam-Webster.com",
-      "value-type:",
-      "binary-data-type:MS\\",
-      "PECO_GIT",
-      "OBO_SF2_PECO",
-      "id-validation-regexp: ",
-      "id-validation-regex: ",
-      "search-url: ",
-      "regexp: ",
-      "Germplasm:",
-      "IUPAC:",
-      "IUPHAR:GPCRListForward?",
-      "GOC:",
-      "goc:",
-      "GIOC:",
-      "MONDORULE:",
-      "MTH:",
-      "FBC:",
-      "RSC:",
-      "DDB:",
-      "http:www",
-      "NCBITaxon_Union",
-      "PhenoScape:",
-      "INFOODs:",
-      "NLCD:",
-      "TEMP:",
-      "PO_GIT:",
-      "URL:http"
-    ],
-    "suffix": [
-      ".jpg",
-      ".svg",
-      ".png"
-    ]
-  },
-  "remappings": {
-    "full": {
-      "CHEBI:133245 MetaCyc:quercetin 3-rhamnoside-7-rhamnoside": "CHEBI:133245",
-      "CHEBI:16531 MetaCyc:renillar luciferin": "CHEBI:16531",
-      "CHEBI:49553 PDBeChem:Copper(II) chloride": "CHEBI:49553",
-      "CHEBI:77450 MetaCyc:dicarboxylic acid monoamide \"SUBMITTER\"": "CHEBI:77450",
-      "CHEBI:84990 MetaCyc:<locant>gamma</locant>-carboxy-<stereo>L</stereo>-glutamate residue \"SUBMITTER\"": "CHEBI:84990",
-      "LIPIDMAPSLMFA01030141": "LIPIDMAPS:LMFA01030141",
-      "LIPIDMAPSLMFA01030152": "LIPIDMAPS:LMFA01030152",
-      "SNOMEDCT274897005": "SNOMEDCT:274897005",
-      "GIOC:vw": "GOC:vw",
-      ":has_start_point": "has_start_point",
-      "dc-creator": "dc:creator",
-      "PMI:17498297": "PMID:17498297",
-      "HPO:SKOEHLER": "orcid:0000-0002-5316-1399",
-      "HPO:skoehler": "orcid:0000-0002-5316-1399",
-      "UBERON:cjm": "orcid:0000-0002-6601-2165",
-      "part:of": "BFO:0000050",
-      "bearer:of": "RO:0000053",
-      "inheres:in": "RO:0000052",
-      "inheres:in-obso": "RO:0000052",
-      "inheres:in_part_of": "RO:0002314",
-      "role:of": "RO:0000081",
-      "unfolds:in": "BFO:0000066",
-      "PATOC:MAH": "orcid:0000-0003-4148-4606",
-      "SBN:9780070316607": "ISBN:9780070316607",
-      "dc-contributor": "dc:contributor",
-      "dc-license": "dc:license",
-      "seeAlso": "rdfs:seeAlso"
-    },
-    "prefix": {
-      "ATCC number: ": "ATCC:",
-      "ATTC: ": "ATCC:",
-      "BAO_": "BAO:",
-      "TKG:TKG ": "TKG:",
-      "KCB:KCB ": "KCB:",
-      "CVCL_": "cellosaurus:CVCL_",
-      "EGA:EGAS": "ega.study:EGAS",
-      "EGA:phs": "ega.study:phs",
-      "EGA:EGAD": "ega.study:EGAD",
-      "KEGG COMPOUND": "KEGG.COMPOUND",
-      "KEGG DRUG": "KEGG.DRUG",
-      "LIPID MAPS:": "LIPIDMAPS:",
-      "MedlinePlus: ": "MedlinePlus:",
-      "NIST Chemistry WebBook": "NIST",
-      "PMID: ": "PMID:",
-      "SNOMEDCT: ": "SNOMEDCT:",
-      "UMLS CUI:": "UMLS:",
-      "http://linkedlifedata.com/resource/umls/id/": "UMLS:",
-      "URL: ": "URL:",
-      "VFB:FBbt_": "FBbt:",
-      "chembl target:CHEMBL": "chembl.target:CHEMBL",
-      "protein ontology:PR\\:": "PR:PR:",
-      "http://orcid.org/": "orcid:",
-      "http:http\\://en.wikipedia.org/wiki/": "wikipedia.en:",
-      "http://en.wikipedia.org/wiki/": "wikipedia.en:",
-      "http:en.wikipedia.org/wiki/": "wikipedia.en:",
-      "http:http\\:en.wikipedia.org/wiki/": "wikipedia.en:",
-      "WIKI:https\\://en.wikipedia.org/wiki/": "wikipedia.en:",
-      "BioRXiv:https\\://doi.org/": "doi:",
-      "NIF_Subcellular:sao": "SAO:",
-      "NIF_Subcellular:nlx_subcell_": "NLXANAT",
-      "NIF_Subcellular:birnlex": "neurolex:birnlex",
-      "NIFSTD:birnlex": "neurolex:birnlex",
-      "NIF_Subcellular:nlx": "neurolex:nlx",
-      "NIFSTD:nifext_": "neurolex:nifext_",
-      "NIFSTD:sao": "SAO:",
-      "NIFSTD:nlx_dys_": "NLXDYS:",
-      "URL:http\\://en.wikipedia.org/wiki/": "wikipedia.en:",
-      "url: \"https://en.wikipedia.org/wiki/": "wikipedia.en:",
-      "url:https\\://www.ncbi.nlm.nih.gov/pubmed/": "pubmed:",
-      "url:https\\://pubmed.ncbi.nlm.nih.gov/": "pubmed:",
-      "URL:http\\://": "http://",
-      "URL: http\\://": "http://",
-      "url:http\\://": "http://",
-      "url:https\\://ghr.nlm.nih.gov/condition/": "ghr:",
-      "NIF_Subcellular:FMA_": "FMA:",
-      "Wikipeda:": "wikipedia:",
-      "has:": "has_",
-      "NSH:D0": "MESH:D0",
-      "MONDOLEX:": "MONDO:",
-      "unirot:": "uniprot:",
-      "http:www": "http://www",
-      "ECGOntology:<new dbxref> \"": "ECGOntology:",
-      "GNOme: \"GNO:": "glygen",
-      "UniProt: \"": "uniprot:",
-      "Unimod: \"Unimod:": "unimod:",
-      "OMIMl:": "OMIM:",
-      "CREDIT_00": "CREDIT:00",
-      "CCLV:CCLV-RIE ": "CCLV:",
-      "APOLLO:SV_": "APOLLO_SV:",
-      "GEMET:http\\://www.eionet.europa.eu/gemet/concept/": "GEMET:",
-      "FBdv_root:": "FBdv:",
-      "NCBI:NBK": "ncbibook:",
-      "MicrO.owl/MICRO:": "MICRO:",
-      "MicrO.owl/TEMP:": "MICRO:",
-      "MicrO.owl/Temp:": "MICRO:",
-      "MicrO.owl/temp:": "MICRO:",
-      "xsd\\:": "xsd:",
-      "OGI.owl:": "ogi:",
-      "PANTHER:PTHR": "panther.family:PTHR",
-      "vo/ontorat/PR:": "PR:",
-      "DC:0000": "diseaseclass:0000",
-      "TS-": "caloha:"
-    }
-  }
-}

pyobo/registries/metaregistry.py

@@ -1,135 +0,0 @@
-"""Load the manually curated metaregistry."""
-
-import itertools as itt
-import json
-import os
-from collections.abc import Iterable, Mapping
-from functools import lru_cache
-from pathlib import Path
-
-import bioregistry
-
-from ..constants import GLOBAL_SKIP, RAW_DIRECTORY
-
-HERE = Path(__file__).parent.resolve()
-CURATED_REGISTRY_PATH = HERE.joinpath("metaregistry.json")
-CURATED_REGISTRY = json.loads(CURATED_REGISTRY_PATH.read_text())
-
-
-def has_no_download(prefix: str) -> bool:
-    """Return if the prefix is not available."""
-    prefix_norm = bioregistry.normalize_prefix(prefix)
-    return prefix_norm is not None and prefix_norm in _no_download()
-
-
-@lru_cache(maxsize=1)
-def _no_download() -> set[str]:
-    """Get the list of prefixes not available as OBO."""
-    return {
-        prefix
-        for prefix in bioregistry.read_registry()
-        if bioregistry.get_obo_download(prefix) is None
-        and bioregistry.get_owl_download(prefix) is None
-    }
-
-
-def curie_has_blacklisted_prefix(curie: str) -> bool:
-    """Check if the CURIE string has a blacklisted prefix."""
-    return any(curie.startswith(x) for x in get_xrefs_prefix_blacklist())
-
-
-@lru_cache(maxsize=1)
-def get_xrefs_prefix_blacklist() -> set[str]:
-    """Get the set of blacklisted xref prefixes."""
-    #: Xrefs starting with these prefixes will be ignored
-    prefixes = set(
-        itt.chain.from_iterable(CURATED_REGISTRY["blacklists"]["resource_prefix"].values())
-    ) | set(CURATED_REGISTRY["blacklists"]["prefix"])
-    nonsense = {
-        prefix
-        for prefix in prefixes
-        if bioregistry.normalize_prefix(prefix.rstrip(":")) is not None
-    }
-    if nonsense:
-        raise ValueError(
-            f"The following prefixes were blacklisted but are in the bioregistry: {nonsense}"
-        )
-    return prefixes
-
-
-def curie_has_blacklisted_suffix(curie: str) -> bool:
-    """Check if the CURIE string has a blacklisted suffix."""
-    return any(curie.endswith(suffix) for suffix in get_xrefs_suffix_blacklist())
-
-
-@lru_cache(maxsize=1)
-def get_xrefs_suffix_blacklist() -> set[str]:
-    """Get the set of blacklisted xref suffixes."""
-    #: Xrefs ending with these suffixes will be ignored
-    return set(CURATED_REGISTRY["blacklists"]["suffix"])
-
-
-def curie_is_blacklisted(curie: str) -> bool:
-    """Check if the full CURIE string is blacklisted."""
-    return curie in get_xrefs_blacklist()
-
-
-@lru_cache(maxsize=1)
-def get_xrefs_blacklist() -> set[str]:
-    """Get the set of blacklisted xrefs."""
-    rv = set()
-    for x in CURATED_REGISTRY["blacklists"]["full"]:
-        if isinstance(x, str):
-            rv.add(x)
-        elif isinstance(x, dict):
-            if x.get("type") == "group":
-                rv.update(x["text"])
-            elif "text" in x:
-                rv.add(x["text"])
-            else:
-                raise ValueError("invalid schema")
-        else:
-            raise TypeError
-    return rv
-
-
-@lru_cache(maxsize=1)
-def get_remappings_full() -> Mapping[str, str]:
-    """Get the remappings for xrefs based on the entire xref database."""
-    return CURATED_REGISTRY["remappings"]["full"]
-
-
-def remap_full(x: str) -> str:
-    """Remap the string if possible otherwise return it."""
-    return get_remappings_full().get(x, x)
-
-
-@lru_cache(maxsize=1)
-def get_remappings_prefix() -> Mapping[str, str]:
-    """Get the remappings for xrefs based on the prefix.
-
-    .. note:: Doesn't take into account the semicolon `:`
-    """
-    return CURATED_REGISTRY["remappings"]["prefix"]
-
-
-def remap_prefix(curie: str) -> str:
-    """Remap a prefix."""
-    for old_prefix, new_prefix in get_remappings_prefix().items():
-        if curie.startswith(old_prefix):
-            return new_prefix + curie[len(old_prefix) :]
-    return curie
-
-
-def iter_cached_obo() -> Iterable[tuple[str, str]]:
-    """Iterate over cached OBO paths."""
-    for prefix in os.listdir(RAW_DIRECTORY):
-        if prefix in GLOBAL_SKIP or has_no_download(prefix) or bioregistry.is_deprecated(prefix):
-            continue
-        d = RAW_DIRECTORY.joinpath(prefix)
-        if not os.path.isdir(d):
-            continue
-        for x in os.listdir(d):
-            if x.endswith(".obo"):
-                p = os.path.join(d, x)
-                yield prefix, p