pyobo 0.11.2__py3-none-any.whl → 0.12.0__py3-none-any.whl

pyobo/xrefdb/sources/compath.py

@@ -1,82 +0,0 @@
-"""Import ComPath mappings between pathways."""
-
-from collections.abc import Iterable
-
-import pandas as pd
-from pystow.utils import get_commit
-
-from pyobo.constants import (
-    PROVENANCE,
-    SOURCE_ID,
-    SOURCE_PREFIX,
-    TARGET_ID,
-    TARGET_PREFIX,
-    XREF_COLUMNS,
-)
-
-__all__ = [
-    "iter_compath_dfs",
-]
-
-
-def _get_df(name: str, *, sha: str, sep: str = ",") -> pd.DataFrame:
-    url = f"https://raw.githubusercontent.com/ComPath/compath-resources/{sha}/mappings/{name}"
-    df = pd.read_csv(
-        url,
-        sep=sep,
-        usecols=["Source Resource", "Source ID", "Mapping Type", "Target Resource", "Target ID"],
-    )
-    df.rename(
-        columns={
-            "Source Resource": SOURCE_PREFIX,
-            "Source ID": SOURCE_ID,
-            "Target Resource": TARGET_PREFIX,
-            "Target ID": TARGET_ID,
-        },
-        inplace=True,
-    )
-    df = df[df["Mapping Type"] == "equivalentTo"]
-    del df["Mapping Type"]
-    df[PROVENANCE] = url
-    df = df[XREF_COLUMNS]
-
-    df[SOURCE_PREFIX] = df[SOURCE_PREFIX].map(_fix_kegg_prefix)
-    df[TARGET_PREFIX] = df[TARGET_PREFIX].map(_fix_kegg_prefix)
-    df[SOURCE_ID] = [
-        _fix_kegg_identifier(prefix, identifier)
-        for prefix, identifier in df[[SOURCE_PREFIX, SOURCE_ID]].values
-    ]
-    df[TARGET_ID] = [
-        _fix_kegg_identifier(prefix, identifier)
-        for prefix, identifier in df[[TARGET_PREFIX, TARGET_ID]].values
-    ]
-
-    return df
-
-
-def _fix_kegg_identifier(prefix, identifier) -> str:
-    if prefix == "kegg.pathway":
-        return identifier[len("path:") :]
-    return identifier
-
-
-def _fix_kegg_prefix(s):
-    return s if s != "kegg" else "kegg.pathway"
-
-
-def iter_compath_dfs() -> Iterable[pd.DataFrame]:
-    """Iterate over all ComPath mappings."""
-    sha = get_commit("ComPath", "compath-resources")
-
-    yield _get_df("kegg_reactome.csv", sha=sha)
-    yield _get_df("kegg_wikipathways.csv", sha=sha)
-    yield _get_df("pathbank_kegg.csv", sha=sha)
-    yield _get_df("pathbank_reactome.csv", sha=sha)
-    yield _get_df("pathbank_wikipathways.csv", sha=sha)
-    yield _get_df("special_mappings.csv", sha=sha)
-    yield _get_df("wikipathways_reactome.csv", sha=sha)
-
-
-def get_compath_xrefs_df() -> pd.DataFrame:
-    """Iterate over all ComPath mappings."""
-    return pd.concat(iter_compath_dfs())

pyobo/xrefdb/sources/famplex.py

@@ -1,64 +0,0 @@
-"""Get FamPlex xrefs."""
-
-import logging
-from collections.abc import Mapping
-from functools import lru_cache
-
-import bioregistry
-import pandas as pd
-
-from ...constants import (
-    PROVENANCE,
-    SOURCE_ID,
-    SOURCE_PREFIX,
-    TARGET_ID,
-    TARGET_PREFIX,
-    XREF_COLUMNS,
-)
-from ...utils.path import ensure_df
-
-__all__ = [
-    "get_famplex_xrefs_df",
-]
-
-logger = logging.getLogger(__name__)
-
-URL = "https://github.com/sorgerlab/famplex/raw/master/equivalences.csv"
-
-
-def _get_famplex_df(force: bool = False) -> pd.DataFrame:
-    return ensure_df(
-        prefix="fplx",
-        url=URL,
-        force=force,
-        header=None,
-        names=[TARGET_PREFIX, TARGET_ID, SOURCE_ID],
-        sep=",",
-    )
-
-
-def get_famplex_xrefs_df(force: bool = False) -> pd.DataFrame:
-    """Get xrefs from FamPlex."""
-    df = _get_famplex_df(force=force)
-    df[TARGET_PREFIX] = df[TARGET_PREFIX].map(bioregistry.normalize_prefix)
-    df = df[df[TARGET_PREFIX].notna()]
-    df[SOURCE_PREFIX] = "fplx"
-    df[PROVENANCE] = "https://github.com/sorgerlab/famplex/raw/master/equivalences.csv"
-    df = df[XREF_COLUMNS]
-    return df
-
-
-@lru_cache
-def get_remapping(force: bool = False) -> Mapping[tuple[str, str], tuple[str, str, str]]:
-    """Get a mapping from database/identifier pairs to famplex identifiers."""
-    df = _get_famplex_df(force=force)
-    rv = {}
-    for target_ns, target_id, source_id in df.values:
-        if target_ns.lower() == "medscan":
-            continue  # MEDSCAN is proprietary and Ben said to skip using these identifiers
-        remapped_prefix = bioregistry.normalize_prefix(target_ns)
-        if remapped_prefix is None:
-            logger.warning("could not remap %s", target_ns)
-        else:
-            rv[remapped_prefix, target_id] = "fplx", source_id, source_id
-    return rv

pyobo/xrefdb/sources/gilda.py

@@ -1,50 +0,0 @@
-"""Cross references from Gilda.
-
-.. seealso:: https://github.com/indralabs/gilda
-"""
-
-import bioregistry
-import pandas as pd
-
-from pyobo.constants import (
-    PROVENANCE,
-    SOURCE_ID,
-    SOURCE_PREFIX,
-    TARGET_ID,
-    TARGET_PREFIX,
-)
-
-__all__ = [
-    "get_gilda_xrefs_df",
-]
-
-GILDA_MAPPINGS = (
-    "https://raw.githubusercontent.com/indralab/gilda/master/gilda/resources/mesh_mappings.tsv"
-)
-
-
-def get_gilda_xrefs_df() -> pd.DataFrame:
-    """Get xrefs from Gilda."""
-    df = pd.read_csv(
-        GILDA_MAPPINGS,
-        sep="\t",
-        header=None,
-        usecols=[0, 1, 3, 4],
-        names=[SOURCE_PREFIX, SOURCE_ID, TARGET_PREFIX, TARGET_ID],
-    )
-    df[PROVENANCE] = GILDA_MAPPINGS
-
-    for k in SOURCE_PREFIX, TARGET_PREFIX:
-        df[k] = df[k].map(bioregistry.normalize_prefix)
-
-    for k in SOURCE_ID, TARGET_ID:
-        df[k] = df[k].map(_fix_gogo)
-
-    return df
-
-
-def _fix_gogo(s):
-    for prefix in ("CHEBI:", "DOID:", "HP:", "GO:"):
-        if s.startswith(prefix):
-            return s[len(prefix) :]
-    return s

pyobo/xrefdb/sources/intact.py

@@ -1,113 +0,0 @@
-"""Get the xrefs from IntAct."""
-
-from collections.abc import Mapping
-
-import pandas as pd
-
-from pyobo.api.utils import get_version
-from pyobo.constants import PROVENANCE, SOURCE_PREFIX, TARGET_PREFIX, XREF_COLUMNS
-from pyobo.utils.cache import cached_mapping
-from pyobo.utils.path import prefix_cache_join
-
-__all__ = [
-    "COMPLEXPORTAL_MAPPINGS",
-    "get_intact_complex_portal_xrefs_df",
-    "get_complexportal_mapping",
-    "get_intact_reactome_xrefs_df",
-    "get_reactome_mapping",
-]
-
-COMPLEXPORTAL_MAPPINGS = (
-    "ftp://ftp.ebi.ac.uk/pub/databases/intact/current/various/cpx_ebi_ac_translation.txt"
-)
-REACTOME_MAPPINGS = "ftp://ftp.ebi.ac.uk/pub/databases/intact/current/various/reactome.dat"
-
-
-def _get_complexportal_df():
-    return pd.read_csv(
-        COMPLEXPORTAL_MAPPINGS, sep="\t", header=None, names=["source_id", "target_id"]
-    )
-
-
-def get_intact_complex_portal_xrefs_df() -> pd.DataFrame:
-    """Get IntAct-Complex Portal xrefs."""
-    df = _get_complexportal_df()
-    df[SOURCE_PREFIX] = "intact"
-    df[TARGET_PREFIX] = "complexportal"
-    df[PROVENANCE] = COMPLEXPORTAL_MAPPINGS
-    df = df[XREF_COLUMNS]
-    return df
-
-
-def get_complexportal_mapping() -> Mapping[str, str]:
-    """Get IntAct to Complex Portal mapping.
-
-    Is basically equivalent to:
-
-    .. code-block:: python
-
-        from pyobo import get_filtered_xrefs
-
-        intact_complexportal_mapping = get_filtered_xrefs("intact", "complexportal")
-    """
-
-    @cached_mapping(
-        path=prefix_cache_join(
-            "intact", "xrefs", name="complexportal.tsv", version=get_version("intact")
-        ),
-        header=["intact_id", "complexportal_id"],
-    )
-    def _cache():
-        df = _get_complexportal_df()
-        return dict(df.values)
-
-    return _cache()
-
-
-def _get_reactome_df():
-    return pd.read_csv(REACTOME_MAPPINGS, sep="\t", header=None, names=["source_id", "target_id"])
-
-
-def get_intact_reactome_xrefs_df() -> pd.DataFrame:
-    """Get IntAct-Reactome xrefs."""
-    df = _get_reactome_df()
-    df[SOURCE_PREFIX] = "intact"
-    df[TARGET_PREFIX] = "reactome"
-    df[PROVENANCE] = REACTOME_MAPPINGS
-    df = df[XREF_COLUMNS]
-    return df
-
-
-def get_reactome_mapping() -> Mapping[str, str]:
-    """Get IntAct to Reactome mapping.
-
-    Is basically equivalent to:
-
-    .. code-block:: python
-
-        from pyobo import get_filtered_xrefs
-
-        intact_complexportal_mapping = get_filtered_xrefs("intact", "reactome")
-    """
-
-    @cached_mapping(
-        path=prefix_cache_join(
-            "intact", "xrefs", name="reactome.tsv", version=get_version("intact")
-        ),
-        header=["intact_id", "reactome_id"],
-    )
-    def _cache():
-        df = _get_complexportal_df()
-        return dict(df.values)
-
-    return _cache()
-
-
-def get_xrefs_df() -> pd.DataFrame:
-    """Get IntAct xrefs."""
-    return pd.concat(
-        [
-            get_intact_complex_portal_xrefs_df(),
-            get_intact_reactome_xrefs_df(),
-        ]
-    )

pyobo/xrefdb/sources/ncit.py

@@ -1,133 +0,0 @@
-"""Import NCIT mappings."""
-
-from collections.abc import Iterable
-
-import pandas as pd
-
-from ...constants import (
-    PROVENANCE,
-    SOURCE_ID,
-    SOURCE_PREFIX,
-    TARGET_ID,
-    TARGET_PREFIX,
-    XREF_COLUMNS,
-)
-from ...utils.path import ensure_df
-
-__all__ = [
-    "iter_ncit_dfs",
-    "get_ncit_go_df",
-    "get_ncit_chebi_df",
-    "get_ncit_hgnc_df",
-    "get_ncit_uniprot_df",
-]
-
-PREFIX = "ncit"
-
-HGNC_MAPPINGS_URL = (
-    "https://ncit.nci.nih.gov/ncitbrowser/ajax?action="
-    + "export_mapping&dictionary=NCIt_to_HGNC_Mapping&version=1.0"
-)
-
-GO_MAPPINGS_URL = (
-    "https://ncit.nci.nih.gov/ncitbrowser/ajax?action="
-    + "export_mapping&dictionary=GO_to_NCIt_Mapping&version=1.1"
-)
-
-CHEBI_MAPPINGS_URL = (
-    "https://ncit.nci.nih.gov/ncitbrowser/ajax?action="
-    + "export_mapping&dictionary=NCIt_to_ChEBI_Mapping&version=1.0"
-)
-
-# url_swissprot = 'https://ncit.nci.nih.gov/ncitbrowser/ajax?action=' \
-#                 'export_mapping&uri=https://evs.nci.nih.gov/ftp1/' \
-#                 'NCI_Thesaurus/Mappings/NCIt-SwissProt_Mapping.txt'
-
-UNIPROT_MAPPINGS_URL = (
-    "https://evs.nci.nih.gov/ftp1/NCI_Thesaurus/Mappings/NCIt-SwissProt_Mapping.txt"
-)
-
-
-def get_ncit_xrefs_df() -> pd.DataFrame:
-    """Get all NCIT mappings in a single dataframe."""
-    return pd.concat(iter_ncit_dfs())
-
-
-def iter_ncit_dfs() -> Iterable[pd.DataFrame]:
-    """Iterate all NCIT mappings dataframes."""
-    yield get_ncit_hgnc_df()
-    yield get_ncit_chebi_df()
-    yield get_ncit_uniprot_df()
-    yield get_ncit_go_df()
-
-
-def get_ncit_hgnc_df() -> pd.DataFrame:
-    """Get NCIT-HGNC mappings.
-
-    In this file, the only association type was mapsTo.
-    """
-    df = ensure_df(
-        PREFIX,
-        url=HGNC_MAPPINGS_URL,
-        name="ncit_hgnc.csv",
-        sep=",",
-        usecols=["Source Code", "Target Code"],
-    )
-    df.rename(columns={"Source Code": SOURCE_ID, "Target Code": TARGET_ID}, inplace=True)
-    df[TARGET_ID] = df[TARGET_ID].map(lambda s: s[len("HGNC:") :])
-    df.dropna(inplace=True)
-
-    df[SOURCE_PREFIX] = "ncit"
-    df[TARGET_PREFIX] = "hgnc"
-    df[PROVENANCE] = HGNC_MAPPINGS_URL
-    df = df[XREF_COLUMNS]
-    return df
-
-
-def get_ncit_go_df() -> pd.DataFrame:
-    """Get NCIT-GO mappings.
-
-    In this file, the only association type was mapsTo.
-    """
-    df = ensure_df(PREFIX, url=GO_MAPPINGS_URL, name="ncit_go.csv", sep=",")
-    # The data is flipped here
-    df.rename(columns={"Source Code": TARGET_ID, "Target Code": SOURCE_ID}, inplace=True)
-    df[TARGET_ID] = df[TARGET_ID].map(lambda s: s[len("GO:")])
-    df.dropna(inplace=True)
-
-    df[SOURCE_PREFIX] = "ncit"
-    df[TARGET_PREFIX] = "go"
-    df[PROVENANCE] = GO_MAPPINGS_URL
-    df = df[XREF_COLUMNS]
-    return df
-
-
-def get_ncit_chebi_df() -> pd.DataFrame:
-    """Get NCIT-ChEBI mappings.
-
-    In this file, the only association type was mapsTo.
-    """
-    df = ensure_df(PREFIX, url=CHEBI_MAPPINGS_URL, name="ncit_chebi.csv", sep=",")
-    df.rename(columns={"Source Code": SOURCE_ID, "Target Code": TARGET_ID}, inplace=True)
-    df[TARGET_ID] = df[TARGET_ID].map(lambda s: s[len("CHEBI:")])
-    df.dropna(inplace=True)
-
-    df[SOURCE_PREFIX] = "ncit"
-    df[TARGET_PREFIX] = "chebi"
-    df[PROVENANCE] = CHEBI_MAPPINGS_URL
-    df = df[XREF_COLUMNS]
-    return df
-
-
-def get_ncit_uniprot_df() -> pd.DataFrame:
-    """Get NCIT-UniProt mappings.
-
-    In this file, the only association type was mapsTo.
-    """
-    df = ensure_df(PREFIX, url=UNIPROT_MAPPINGS_URL, name="ncit_uniprot.csv")
-    df.rename(columns={"NCIt Code": SOURCE_ID, "SwissProt ID": TARGET_ID}, inplace=True)
-    df[SOURCE_PREFIX] = "ncit"
-    df[TARGET_PREFIX] = "uniprot"
-    df[PROVENANCE] = UNIPROT_MAPPINGS_URL
-    df = df[XREF_COLUMNS]
-    return df

pyobo/xrefdb/sources/pubchem.py

@@ -1,27 +0,0 @@
-"""Get xrefs from PubChem Compound to MeSH."""
-
-from typing import Optional
-
-import pandas as pd
-
-from ...api.utils import safe_get_version
-from ...constants import XREF_COLUMNS
-from ...sources.pubchem import _get_pubchem_extras_url, get_pubchem_id_to_mesh_id
-
-__all__ = [
-    "get_pubchem_mesh_df",
-]
-
-
-def get_pubchem_mesh_df(version: Optional[str] = None) -> pd.DataFrame:
-    """Get PubChem Compound-MeSH xrefs."""
-    if version is None:
-        version = safe_get_version("pubchem")
-    cid_mesh_url = _get_pubchem_extras_url(version, "CID-MeSH")
-    return pd.DataFrame(
-        [
-            ("pubchem.compound", k, "mesh", v, cid_mesh_url)
-            for k, v in get_pubchem_id_to_mesh_id(version=version).items()
-        ],
-        columns=XREF_COLUMNS,
-    )

pyobo/xrefdb/sources/wikidata.py

@@ -1,116 +0,0 @@
-"""Get Wikidata xrefs.
-
-Run with ``python -m pyobo.xrefdb.sources.wikidata``.
-"""
-
-import json
-import logging
-from collections.abc import Iterable
-
-import bioregistry
-import click
-import pandas as pd
-import requests
-from more_click import verbose_option
-from tqdm.auto import tqdm
-
-from ...constants import RAW_MODULE, XREF_COLUMNS
-from ...version import get_version
-
-logger = logging.getLogger(__name__)
-
-#: WikiData SPARQL endpoint. See https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service#Interfacing
-URL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql"
-
-WIKIDATA_MAPPING_DIRECTORY = RAW_MODULE.module("wikidata", "mappings")
-
-
-def get_wikidata_xrefs_df(*, use_tqdm: bool = True) -> pd.DataFrame:
-    """Get all Wikidata xrefs."""
-    return pd.concat(iterate_wikidata_dfs(use_tqdm=use_tqdm))
-
-
-def iterate_wikidata_dfs(*, use_tqdm: bool = True) -> Iterable[pd.DataFrame]:
-    """Iterate over WikiData xref dataframes."""
-    wikidata_properties = {
-        prefix: entry.wikidata["prefix"]
-        for prefix, entry in bioregistry.read_registry().items()
-        if entry.wikidata and "prefix" in entry.wikidata
-    }
-
-    it = tqdm(sorted(wikidata_properties.items()), disable=not use_tqdm, desc="Wikidata properties")
-    for prefix, wikidata_property in it:
-        if prefix in {"pubmed", "pmc", "orcid", "inchi", "smiles"}:
-            continue  # too many
-        it.set_postfix({"prefix": prefix})
-        try:
-            yield get_wikidata_df(prefix, wikidata_property)
-        except json.decoder.JSONDecodeError as e:
-            logger.warning(
-                "[%s] Problem decoding results from %s: %s", prefix, wikidata_property, e
-            )
-
-
-def get_wikidata_df(prefix: str, wikidata_property: str) -> pd.DataFrame:
-    """Get Wikidata xrefs."""
-    df = pd.DataFrame(
-        [
-            ("wikidata", wikidata_id, prefix, external_id, "wikidata")
-            for wikidata_id, external_id in iter_wikidata_mappings(wikidata_property)
-        ],
-        columns=XREF_COLUMNS,
-    )
-    logger.debug("got wikidata (%s; %s): %d rows", prefix, wikidata_property, len(df.index))
-    return df
-
-
-def iter_wikidata_mappings(
-    wikidata_property: str, *, cache: bool = True
-) -> Iterable[tuple[str, str]]:
-    """Iterate over Wikidata xrefs."""
-    path = WIKIDATA_MAPPING_DIRECTORY.join(name=f"{wikidata_property}.json")
-    if path.exists() and cache:
-        with path.open() as file:
-            rows = json.load(file)
-    else:
-        query = f"SELECT ?wikidata_id ?id WHERE {{?wikidata_id wdt:{wikidata_property} ?id}}"
-        rows = _run_query(query)
-        with path.open("w") as file:
-            json.dump(rows, file, indent=2)
-
-    for row in rows:
-        wikidata_id = _removeprefix(row["wikidata_id"]["value"], "http://www.wikidata.org/entity/")
-        wikidata_id = _removeprefix(wikidata_id, "http://wikidata.org/entity/")
-        entity_id = row["id"]["value"]
-        yield wikidata_id, entity_id
-
-
-def _removeprefix(s, prefix):
-    if s.startswith(prefix):
-        return s[len(prefix) :]
-    return s
-
-
-HEADERS = {
-    "User-Agent": f"pyobo/{get_version()}",
-}
-
-
-def _run_query(query, base: str = URL):
-    logger.debug("running query: %s", query)
-    res = requests.get(base, params={"query": query, "format": "json"}, headers=HEADERS)
-    res.raise_for_status()
-    res_json = res.json()
-    return res_json["results"]["bindings"]
-
-
-@click.command()
-@verbose_option
-def _main():
-    """Summarize xrefs."""
-    for _ in iterate_wikidata_dfs():
-        pass
-
-
-if __name__ == "__main__":
-    _main()