def make_goa_df_getter(url, path):
return make_df_getter(
url,
path,
sep='\t',
names=GAF_COLUMNS,
skiprows=15,
)
IS_PART_OF, KEGG, KEGG_REACTOME_PATH, KEGG_REACTOME_URL, KEGG_WP_PATH, KEGG_WP_URL, MAPPING_TYPE, SOURCE_ID,
SOURCE_RESOURCE, SPECIAL_MAPPINGS_PATH, SPECIAL_MAPPINGS_URL, TARGET_ID, TARGET_RESOURCE, WP_REACTOME_PATH,
WP_REACTOME_URL,
)
__all__ = [
'get_mapping_dict',
'get_equivalent_pairs',
'load_compath_mapping_dfs',
'get_equivalent_mappings_dict',
]
Identifier = Tuple[str, str]
EquivalenceMapping = Mapping[Identifier, List[Identifier]]
get_kegg_reactome_df = make_df_getter(KEGG_REACTOME_URL, KEGG_REACTOME_PATH)
get_wp_reactome_df = make_df_getter(WP_REACTOME_URL, WP_REACTOME_PATH)
get_kegg_wp_df = make_df_getter(KEGG_WP_URL, KEGG_WP_PATH)
get_special_mappings_df = make_df_getter(SPECIAL_MAPPINGS_URL, SPECIAL_MAPPINGS_PATH)
def get_mapping_dict(df: pd.DataFrame, mapping_type: str) -> Mapping[Identifier, List[Identifier]]:
"""Create a dictionary with ComPath mappings for each pathway."""
mapping_dict = defaultdict(list)
for index, row in df.iterrows():
if row[MAPPING_TYPE] != mapping_type:
continue
if row[SOURCE_RESOURCE] != KEGG and row[TARGET_RESOURCE] != KEGG:
mapping_dict[(row[SOURCE_RESOURCE], row[SOURCE_ID])].append((row[TARGET_RESOURCE], row[TARGET_ID]))
# -*- coding: utf-8 -*-
"""Downloaders for Bio2BEL HMDD"""
from bio2bel.downloading import make_df_getter
from .constants import HMDD_COLUMNS, HMDD_PATH, HMDD_URL
__all__ = ['get_hmdd_df']
get_hmdd_df = make_df_getter(
HMDD_URL,
HMDD_PATH,
sep='\t',
)
"""Loads the HMDD into a data frame
1) Index
2) miRNA ID
3) MeSHDisease term
4) PubMed ID
5) Description
"""
SPECIES_URL,
)
__all__ = [
'get_species_df',
'download_definitions',
'get_aliases_df',
'get_mirbase_alias_to_id',
]
logger = logging.getLogger(__name__)
get_species_df = make_df_getter(
SPECIES_URL,
SPECIES_PATH,
sep='\t',
names=SPECIES_HEADER,
skiprows=1,
)
download_definitions = make_downloader(DEFINITIONS_URL, DEFINITIONS_PATH)
get_aliases_df = make_df_getter(
ALIASES_URL,
ALIASES_PATH,
sep='\t',
)
def get_mirbase_alias_to_id(
) -> Tuple[Mapping[str, str], Mapping[str, List[str]]]:
import os
import pickle
from typing import Optional
import pandas as pd
from bio2bel.downloading import make_df_getter
from .constants import MAPPINGS_PATH, MAPPINGS_URL, SLIM_MAPPINGS_PATH
__all__ = [
'get_mappings_df',
'get_slim_mappings_df',
]
get_mappings_df = make_df_getter(MAPPINGS_URL,
MAPPINGS_PATH,
sep='\t',
header=None)
"""Returns a file with the following columns:
1. UniProtKB-AC
2. UniProtKB-ID
3. GeneID (EntrezGene)
4. RefSeq
5. GI
6. PDB
7. GO
8. UniRef100
9. UniRef90
10. UniRef50
11. UniParc
12. PIR
13. NCBI-taxon
# -*- coding: utf-8 -*-
"""Parsers for FlyBase."""
from bio2bel.downloading import make_df_getter
from .constants import GENE_MAPPING_PATH, GENE_MAPPING_URL
__all__ = [
'get_mapping_df',
]
get_mapping_df = make_df_getter(
GENE_MAPPING_URL,
GENE_MAPPING_PATH,
sep='\t',
comment='#',
compression='gzip',
names=[
'symbol',
'flybase_id',
],
usecols=[
1,
2,
],
na_filter=False,
)
GENE2REFSEQ_COLUMNS, GENE2REFSEQ_DATA_PATH, GENE2REFSEQ_HUMAN_DATA_PATH, GENE2REFSEQ_HUMAN_SLIM_DATA_PATH,
GENE2REFSEQ_URL, GENE_INFO_COLUMNS, GENE_INFO_DATA_PATH, GENE_INFO_URL, HOMOLOGENE_COLUMNS, HOMOLOGENE_DATA_PATH,
HOMOLOGENE_URL,
)
__all__ = [
'get_gene_info_df',
'get_homologene_df',
'get_refseq_df',
'get_human_refseq_slim_df',
]
get_gene_info_df = make_df_getter(
GENE_INFO_URL,
GENE_INFO_DATA_PATH,
sep='\t',
na_values=['-', 'NEWENTRY'],
usecols=GENE_INFO_COLUMNS,
)
get_homologene_df = make_df_getter(
HOMOLOGENE_URL,
HOMOLOGENE_DATA_PATH,
sep='\t',
names=HOMOLOGENE_COLUMNS,
)
"""Download the HomoloGene data.
Columns:
1) HID (HomoloGene group id)
from bio2bel.downloading import make_df_getter
from .constants import GENES_PATH, GENES_URL
__all__ = [
'get_genes_df',
]
get_genes_df = make_df_getter(
GENES_URL,
GENES_PATH,
sep='\t',
usecols=[
0, # RGD identifier
1, # Symbol
2, # Name
3, # Description
20, # NCBI_GENE_ID
36, # Gene type
],
names=[
'rgd_id',
'symbol',
'name',
'description',
'entrez_id',
'gene_type',
],
header=0,
comment='#',
)
# -*- coding: utf-8 -*-
from bio2bel.downloading import make_df_getter
from ..constants import MARKERS_PATH, MARKERS_URL
__all__ = [
'get_marker_df',
]
get_marker_df = make_df_getter(
MARKERS_URL,
MARKERS_PATH,
sep='\t',
usecols=[
0, # MGI ID
6, # SYMBOL
8, # name
9, # marker type
10, # feature type
],
names=[
'mgi_id',
'symbol',
'name',
'marker_type',
'feature_type',
],
skiprows=[0],
)
# -*- coding: utf-8 -*-
"""Parsers and downloaders for Bio2BEL Antibody Registry."""
from bio2bel.downloading import make_df_getter
from .constants import HEADER, PATH, URL
__all__ = [
'df_getter',
]
df_getter = make_df_getter(
URL,
PATH,
names=HEADER[:3],
skiprows=1,
usecols=[0, 1, 2],
chunksize=250_000,
)
from .constants import (
GENE_PERTURBATIONS_DATA_PATH,
GENE_PERTURBATIONS_DATA_URL,
GENE_PERTURBATIONS_METADATA_PATH,
GENE_PERTURBATIONS_METADATA_URL,
)
__all__ = [
'get_gene_perturbations_metadata_df',
'get_gene_perturbations_json',
'get_gene_perturbations_metadata_preprocessed_df',
'get_gene_perturbations_preprocessed_df',
]
get_gene_perturbations_metadata_df = make_df_getter(
GENE_PERTURBATIONS_METADATA_URL,
GENE_PERTURBATIONS_METADATA_PATH,
)
get_gene_perturbations_json = make_json_getter(
GENE_PERTURBATIONS_DATA_URL,
GENE_PERTURBATIONS_DATA_PATH,
)
hgnc_gene_symbol_update = {
'PARK2': 'PRKN',
'ERO1L': 'ERO1A',
'RFWD2': 'COP1',
'CYR61': 'CCN1',
'FAM60A': 'SINHCAF',
'PRKCDBP': 'CAVIN3',
'VPRBP': 'DCAF1',
# -*- coding: utf-8 -*-
"""Parsers and downloaders for Bio2BEL GWAS Catalog."""
from bio2bel.downloading import make_df_getter
from .constants import PATH, URL
__all__ = [
'df_getter',
]
df_getter = make_df_getter(URL,
PATH,
sep='\t',
usecols=[
'PUBMEDID',
'MAPPED_GENE',
'SNPS',
'CONTEXT',
'INTERGENIC',
'RISK ALLELE FREQUENCY',
'PVALUE_MLOG',
'OR or BETA',
'95% CI (TEXT)',
'MAPPED_TRAIT',
'MAPPED_TRAIT_URI',
])