literature references, they can be organized into collections. A number
of operations are available on evidences and their collections, for
example they can be combined or filtered.
"""
from future.utils import iteritems
import importlib as imp
import copy
import pypath.internals.refs as refs
import pypath.share.common as common
import pypath.share.session as session_mod
import pypath.core.entity as entity
_logger = session_mod.Logger(name = 'evidence')
_log = _logger._log
class Evidence(object):
"""
Represents an evidence supporting a relationship such as molecular
interaction, molecular complex, enzyme-PTM interaction, annotation, etc.
The evidence consists of two main parts: the database and the literature
references. If a relationship is supported by multiple databases, for
each one `Evidence` object should be created and
:arg pypath.resource.ResourceAttributes resource:
An object derived from :py:class:`pypath.resource.ResourceAttributes`.
:arg str,list,set,NoneType references:
# See accompanying file LICENSE.txt or copy at
# http://www.gnu.org/licenses/gpl-3.0.html
#
# Website: http://pypath.omnipathdb.org/
#
import os
import re
import itertools
import pypath.share.curl as curl
import pypath.share.session as session
import pypath.resources.urls as urls
import pypath.inputs.common as inputs_common
_logger = session.Logger(name='inputs.kirouac2010')
_log = _logger._log
def kirouac2010_interactions():
"""
Returns tuples of ligand-receptor genesymbol pairs.
"""
rename = re.compile(r'[A-Z]{2}[A-Z0-9][-A-Z0-9]*')
rerange = re.compile(r'([0-9])-([0-9])')
reslash = re.compile(r'.*?([A-Z0-9]{1,3}/[/A-Z0-9]+)')
def get_names(s):
names = set()
#
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import os
import collections
import pypath.share.curl as curl
import pypath.resources.urls as urls
import pypath.share.settings as settings
import pypath.share.session as session
import pypath.utils.mapping as mapping
_logger = session.Logger(name='inputs.msigdb')
_log = _logger._log
def msigdb_download(
registered_email=None,
collection='msigdb',
id_type='symbols',
force_download=False,
):
"""
Downloads and preprocesses a collection of gmt format gene sets from
MSigDB. Returns dict of sets with gene set names as keys and molecular
identifiers as values.
:arg str,NoneType registered_email:
# See accompanying file LICENSE.txt or copy at
# http://www.gnu.org/licenses/gpl-3.0.html
#
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
from past.builtins import xrange, range
import sys
import xlrd
from xlrd.biffh import XLRDError
import pypath.share.session as session_mod
_logger = session_mod.Logger(name='dataio')
_log = _logger._log
_console = _logger._console
if 'unicode' not in __builtins__: unicode = str
def read_xls(xls_file, sheet='', csv_file=None, return_table=True):
"""
Generic function to read MS Excel XLS file, and convert one sheet
to CSV, or return as a list of lists
"""
try:
if hasattr(xls_file, 'read'):
book = xlrd.open_workbook(
file_contents=xls_file.read(),
# Olga Ivanova
#
# Distributed under the GPLv3 License.
# See accompanying file LICENSE.txt or copy at
# http://www.gnu.org/licenses/gpl-3.0.html
#
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import pypath.omnipath.server._html as _html
import pypath.resources.urls as urls
import pypath.share.session as session_mod
_logger = session_mod.Logger(name='generate_about_page')
_log = _logger._log
__all__ = ['generate_about_html', 'write_html']
if 'long' not in __builtins__:
long = int
if 'unicode' not in __builtins__:
unicode = str
pypath_methods = {
'data': 'Data source (URLs and files)',
'format': 'Data format definition',
'intr': 'Interactions',
'input': 'Data input methods',
# See accompanying file LICENSE.txt or copy at
# http://www.gnu.org/licenses/gpl-3.0.html
#
# Website: http://pypath.omnipathdb.org/
#
import re
import os
import collections
import pypath.share.session as session_mod
import pypath.share.common as common
import pypath.share.curl as curl
import pypath.resources.urls as urls
_logger = session_mod.Logger(name='biomart_input')
# for mouse homologues: Filter name = "with_mmusculus_homolog"
_filter_xml_template = '<Filter name="%s" excluded="0"/>'
_attr_xml_template = '<Attribute name="%s" />'
def biomart_query(
attrs,
filters=None,
transcript=False,
gene=False,
dataset='hsapiens_gene_ensembl',
):
"""
Use https://www.ensembl.org/biomart/martview/ to check for attribute
# File author(s): Dénes Türei ([email protected]) # Nicolàs Palacio # Olga Ivanova # # Distributed under the GPLv3 License. # See accompanying file LICENSE.txt or copy at # http://www.gnu.org/licenses/gpl-3.0.html # # Website: http://pypath.omnipathdb.org/ # from future.utils import iteritems import pypath.share.session as session_mod _logger = session_mod.Logger(name = 'db_categories') _log = _logger._log categories = { 'Vidal HI-III': 'i', 'CancerCellMap': 'p', 'InnateDB': 'i', 'SPIKE': 'p', 'LMPID': 'm', 'DIP': 'i', 'HPRD': 'i', 'HPRD-phos': 'm', 'PDZBase': 'p', 'dbPTM': 'm', 'MatrixDB': 'i',
from future.utils import iteritems
import os
import itertools
import collections
import pypath.inputs.common as inputs_common
import pypath.resources.urls as urls
import pypath.utils.mapping as mapping
import pypath.utils.homology as homology
import pypath.share.curl as curl
import pypath.share.common as common
import pypath.share.session as session
_logger = session.Logger(name='inputs.embrace')
_log = _logger._log
def embrace_raw():
"""
Returns Supplementary Table S11 from 10.1016/j.isci.2019.10.026
(Sheikh et al. 2019) as a list of tuples.
"""
url = urls.urls['embrace']['url']
c_nocall = curl.Curl(
url,
call=False,
setup=False,
process=False,
#
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import re
import bs4
import warnings
import pypath.resources.urls as urls
import pypath.share.curl as curl
import pypath.share.session as session
import pypath.share.settings as settings
_logger = session.Logger(name = 'inputs.genecards')
_log = _logger._log
_respace = re.compile(r'\s+')
_summary_sources = {
'Gene Wiki': 'GeneWiki',
'UniProtKB/Swiss-Prot': 'UniProt',
}
def genecards_datasheet(gene):
"""
Retrieves a gene (protein) datasheet from GeneCards.
Returns HTML as string.
Website: http://pypath.omnipathdb.org/
"""
from future.utils import iteritems
import itertools
import sys
from typing import Optional, Set, Union
import click
import pypath.share.progress as progress
import pypath.share.common as common
import pypath.share.session as session_mod
_logger = session_mod.Logger(name='bel')
try:
import pybel
if hasattr(pybel, 'ob'):
_logger._log(
'You have the `openbabel` module installed '
'instead of `pybel`. '
'To be able to use `pybel`, create a virtual env and install '
'it by `pip install pybel`.')
# unimport openbabel
del sys.modules['pybel']
pybel = None
# See accompanying file LICENSE.txt or copy at
# http://www.gnu.org/licenses/gpl-3.0.html
#
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import copy
import pypath.internals.resource as resource
import pypath.resources.data_formats as data_formats
import pypath.share.session as session_mod
import pypath.share.settings as settings
_logger = session_mod.Logger(name='network_resources')
_log = _logger._log
_data_models = {
'interaction': 'interaction',
'interaction_misc': 'interaction',
'interaction_htp': 'interaction',
'ligand_receptor': 'ligand_receptor',
'pathway': 'activity_flow',
'pathway_all': 'activity_flow',
'pathway_noref': 'activity_flow',
'activity_flow': 'activity_flow',
'dorothea': 'activity_flow',
'transcription': 'activity_flow',
'transcription_dorothea': 'activity_flow',
'transcription_onebyone': 'activity_flow',
import pypath.utils.mapping as mapping
import pypath.share.common as common
import pypath.internals.intera as intera
import pypath.resources.urls as urls
import pypath.share.curl as curl
import pypath.inputs.uniprot as uniprot_input
import pypath.utils.seq as _se
import pypath.share.session as session_mod
import pypath.utils.taxonomy as taxonomy
import pypath.share.cache as cache_mod
timeloop.app.logging.disable(level=9999)
_homology_cleanup_timeloop = timeloop.Timeloop()
_logger = session_mod.Logger(name='homology')
_log = _logger._log
class HomologyManager(session_mod.Logger):
def __init__(self, cleanup_period=10, lifetime=300):
session_mod.Logger.__init__(self, name='homology')
@_homology_cleanup_timeloop.job(
interval=datetime.timedelta(seconds=cleanup_period))
def _cleanup():
self._remove_expired()
_homology_cleanup_timeloop.start(block=False)
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import time
import datetime
import timeloop
timeloop.app.logging.disable(level = 9999)
import pypath.share.common as common
import pypath.share.session as session
import pypath.share.settings as settings
import pypath.inputs.uniprot as uniprot_input
_logger = session.Logger(name = 'taxonomy')
_log = _logger._log
db = {}
_cleanup_period = settings.get('mapper_cleanup_interval')
_lifetime = 300
_last_used = {}
# XXX: Shouldn't we keep all functions and variables separated
# (together among them)?
taxids = {
9606: 'human',
10090: 'mouse',
10116: 'rat',
9031: 'chicken',
9913: 'cow',
#
from future.utils import iteritems
import re
import csv
import collections
import itertools
import functools
import pyreadr
import pypath.share.curl as curl
import pypath.resources.urls as urls
import pypath.share.session as session
_logger = session.Logger(name='dorothea_input')
DorotheaInteraction = collections.namedtuple('DorotheaInteraction', [
'tf',
'target',
'effect',
'level',
'curated',
'chipseq',
'predicted',
'coexp',
'curated_sources',
'chipseq_sources',
'predicted_sources',
'coexp_sources',
'all_sources',
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import json
import os
import copy
import importlib as imp
import pypath.share.session as session_mod
import pypath.share.common as common
import pypath.internals.resource as resource_base
import pypath.resources.licenses as licenses
_logger = session_mod.Logger(name='resources.controller')
class ResourceController(session_mod.Logger):
"""
Resource controller is aimed to be the central part of pypath
communication with resources.
14.01.2020: the initial step for resource controller development:
used for /info page generating for the server.
14.02.2020: storing and reading enzyme-substrate resource definitions
from the JSON; class inherits from session.Logger
"""
def __init__(
self,
resource_info_path=(
# File author(s): Dénes Türei ([email protected]) # Nicolàs Palacio # Olga Ivanova # # Distributed under the GPLv3 License. # See accompanying file LICENSE.txt or copy at # http://www.gnu.org/licenses/gpl-3.0.html # # Website: http://pypath.omnipathdb.org/ # import importlib import pypath.share.session as session _logger = session.Logger(name='inputs') _log = _logger._log def get_method(module_name, method_name=None): """ Retrieves a method from a submodule of this module (``inputs``) by its name. E.g. for ``'uniprot.all_uniprots'`` it returns the ``all_uniprots`` method from the ``pypath.inputs.uniprot`` module. """ _log('Selecting input method (step 1): module `%s`, method `%s`.' % ( module_name, method_name, ))
#
# Distributed under the GPLv3 License.
# See accompanying file LICENSE.txt or copy at
# http://www.gnu.org/licenses/gpl-3.0.html
#
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import os
import pypath.share.curl as curl
import pypath.share.session as session
_logger = session.Logger(name='inputs.cell')
_log = _logger._log
def cell_supplementary(supp_url, article_url):
"""
Downloads a supplementary material from the Cell journal webpage.
:param str supp_url:
URL of the supplementary material.
:param str article_url:
URL of the article page.
:return:
The path of the downloaded file.
"""
import re
import time
import datetime
import collections
import itertools
import timeloop
timeloop.app.logging.disable(level=9999)
import pypath.resources.urls as urls
import pypath.share.curl as curl
import pypath.share.common as common
import pypath.share.session as session_mod
import pypath.share.settings as settings
_logger = session_mod.Logger(name='uniprot_input')
db = {}
_cleanup_period = settings.get('mapper_cleanup_interval')
_lifetime = 300
_last_used = {}
_redatasheet = re.compile(r'([A-Z\s]{2})\s*([^\n\r]+)[\n\r]+')
# regex for matching UniProt AC format
# from https://www.uniprot.org/help/accession_numbers
reac = re.compile(r'[OPQ][0-9][A-Z0-9]{3}[0-9]|'
r'[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}')
_rename = re.compile(r'Name=([\w\(\)-]+)\W')
_retaxid = re.compile(r'=(\d+)[^\d]')
# Olga Ivanova
#
# Distributed under the GPLv3 License.
# See accompanying file LICENSE.txt or copy at
# http://www.gnu.org/licenses/gpl-3.0.html
#
# Website: http://pypath.omnipathdb.org/
import os
import copy
from pypath.share import session as _session_mod
from pypath.share import settings as _settings_mod
from pypath.omnipath import app as _app_mod
_logger = _session_mod.Logger(name='omnipath.init')
_log = _logger._log
_log('Welcome to the OmniPath database manager app.')
def init(**kwargs):
param = (copy.deepcopy(globals()['OP_DB_ARGS'])
if 'OP_DB_ARGS' in globals() else {})
_log('You can customize the database building process by '
'setting parameters in the `OP_DB_ARGS` global variable '
'or by calling `init` again with keyword arguments or after '
'setting values in the `pypath.share.settings` module.'
'You can define your own databases following the examples in '
# Website: http://pypath.omnipathdb.org/
#
from future.utils import iteritems
import os
import bs4
import pickle
import pypath.share.curl as curl
import pypath.resources.urls as urls
import pypath.share.settings as settings
import pypath.share.session as session
import pypath.share.common as common
_logger = session.Logger(name='inputs.trip')
_log = _logger._log
def take_a_trip(cachefile=None):
"""
Downloads TRIP data from webpage and preprocesses it.
Saves preprocessed data into `cachefile` and next
time loads from this file.
:arg cachefile str:
Path to pickle dump of preprocessed TRIP database. If does not exist
the database will be downloaded and saved to this file. By default
the path queried from the ``settings`` module.
"""
