def get_organisms_df(url: Optional[str] = None) -> pd.DataFrame:
"""Convert tab separated txt files to pandas Dataframe.
:param url: url from KEGG tab separated file
:return: dataframe of the file
:rtype: pandas.DataFrame
"""
df = pd.read_csv(
url
or ensure_path(MODULE_NAME, KEGG_ORGANISM_URL, path='organisms.tsv'),
sep='\t',
header=None,
names=[
'kegg_id',
'kegg_code',
'name',
# fourth column is the taxonomy hierarchy
],
usecols=[0, 1, 2],
)
df['common_name'] = df['name'].map(
lambda name: name.replace(')', '').split(' (')[1].capitalize()
if len(name.replace(')', '').split(' (')) > 1 else '')
df['name'] = df['name'].map(
lambda name: name.replace(')', '').split(' (')[0].capitalize())
return df
def _load_file(module_name: str = MODULE_NAME, url: str = URL) -> str:
"""Load the file from the URL and place it into the bio2bel_sophia directory.
:param module_name: name of module (database)
:param url: URL to file from database
:return: path of saved database file
"""
return ensure_path(prefix=module_name, url=url)
def get_entity_pathway_df(url: Optional[str] = None) -> pd.DataFrame:
"""Convert tab separated text files in to DataFrame.
:param url: An optional url from a KEGG TSV file
"""
df = pd.read_csv(
url or ensure_path(MODULE_NAME,
PROTEIN_PATHWAY_HUMAN_URL,
path='protein_pathway.tsv'),
sep='\t',
header=None,
names=['kegg_protein_id', 'kegg_pathway_id'],
)
# df['kegg_pathway_id'] = df['kegg_pathway_id'].map(_remove_path_prefix)
return df
def get_pathway_df(url: Optional[str] = None) -> pd.DataFrame:
"""Convert tab separated txt files to pandpathway = parse_pathway_lines(pathway_lines)as Dataframe.
:param url: url from KEGG tab separated file
:return: dataframe of the file
"""
df = pd.read_csv(
url or ensure_path(
MODULE_NAME, KEGG_HUMAN_PATHWAYS_URL, path='pathways.tsv'),
sep='\t',
header=None,
names=['kegg_pathway_id', 'name'],
)
# df['kegg_pathway_id'] = df['kegg_pathway_id'].map(_remove_path_prefix)
return df
def path(self) -> str: # noqa: D401
"""The (ensured) path to the data."""
return ensure_path(MODULE_NAME, self.url)
'phosphotransfer reaction': 'proteinModification',
'disulfide bond': 'complexAbundance',
'self interaction': '',
'deacetylation reaction': '',
'lipoprotein cleavage reaction': 'proteinAbundance',
'gtpase reaction': 'reaction',
'glycosylation reaction': 'proteinModification(Glyco)',
'palmitoylation reaction': 'proteinModification',
'putative self interaction': '',
'dna cleavage': 'geneAbundance',
'rna cleavage': 'rnaAbundace',
}
MODULE_NAME = 'intact'
URL = 'ftp://ftp.ebi.ac.uk/pub/databases/intact/current/psimitab/intact.zip'
path = ensure_path(MODULE_NAME, URL)
sample_path = '/Users/sophiakrix/Downloads/intact_sample.txt'
ID_INTA = '#ID(s) interactor A'
ID_INTB = 'ID(s) interactor B'
DATABASE_INT_A = 'database_intA'
DATABASE_INT_B = 'database_intB'
ONLY_ID_INT_A = 'id_intA'
ONLY_ID_INT_B = 'id_intB'
UNIPROTKB = 'uniprotkb'
ORIG_ALT_ID_COLUMN_NAMES = [
'Alt. ID(s) interactor A', 'Alt. ID(s) interactor B'
]
NEW_ALT_ID_COLUMN_NAMES = ['alternative_intA', 'alternative_intB']