def wrpy_pwy2pmids(self, fout_py):
"""Write Publications(LiteratureReference, Book, URL) into a Python module."""
pw2pmids = self.pubs['pw2pubs']
if not pw2pmids:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
with open(fout_py, 'w') as prt:
# prt = sys.stdout
prt_docstr_module('PubMed IDs for each Pathway', prt)
prt.write(
'\n# {N} of {M} Pathways are associated with PubMed IDs\n'.
format(N=len(pw2pmids), M=len(self.pw2info)))
prt.write(
'# pylint: disable=line-too-long,too-many-lines,bad-continuation\n'
)
prt.write('PWY2PMIDS = {\n')
for pwy, pmid_nts in sorted(pw2pmids.items(), key=self._sortby):
pmids = sorted(set(pmid for pmid, _ in pmid_nts))
prt.write(" '{PW}' : {{{PMIDS}}},\n".format(
PW=pwy, PMIDS=", ".join(str(i) for i in pmids)))
prt.write('}\n\n')
prt_copyright_comment(prt)
print(" {N:5} items WROTE: {PY}".format(N=len(pw2pmids),
PY=fout_py))
return pw2pmids
def wrpy_pubmeds(self, fout_py):
"""Write Publications(LiteratureReference, Book, URL) into a Python module."""
pmid2nt = self._get_pmid2nt()
if not pmid2nt:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
keys = ' '.join(next(iter(pmid2nt.values()))._fields)
with open(fout_py, 'w') as prt:
prt.write('# coding=utf-8\n')
# prt = sys.stdout
prt_docstr_module(
'Publications including Pubmed papers, Books, and URLs', prt)
prt.write('from collections import namedtuple\n')
prt.write('\n# {N} PubMed IDs assc. w/{M} Pathways\n'.format(
N=len(pmid2nt), M=len(self.pubs['pw2pubs'])))
prt.write(
"Ntlit = namedtuple('ntlit', '{KEYS}')\n".format(KEYS=keys))
prt.write(
'# pylint: disable=line-too-long,too-many-lines,bad-continuation\n'
)
prt.write('PMID2NT = {\n')
for pmid, ntd in sorted(pmid2nt.items(),
key=lambda t: [t[1].year, t[0]]):
prt.write(' {PMID:>8} : Ntlit._make({VALS}),\n'.format(
PMID=pmid, VALS=list(ntd)))
prt.write('}\n\n')
prt_copyright_comment(prt)
print(" {N:5} items WROTE: {PY}".format(N=len(pmid2nt),
PY=fout_py))
return pmid2nt
def wrpy_gons(self, fout_py, name='GO_BiologicalProcess'):
"""Write Gene Ontology information for a Pathway's Biological Processes."""
pwy2ns = self._get_pwy2ns(name)
if not pwy2ns:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
with open(fout_py, 'w') as prt:
# prt = sys.stdout
prt_docstr_module(
'Gene Ontology {NS} for each Pathway'.format(NS=name), prt)
prt.write(
'\n# {N} of {M} Pathways are associated with {NS}\n'.format(
N=len(pwy2ns), M=len(self.pw2info), NS=name))
prt.write(
'# pylint: disable=line-too-long,too-many-lines,bad-continuation\n'
)
prt.write('PWY2GOS = {\n')
for pwy, goids in sorted(pwy2ns.items(), key=self._sortby):
goids_str = ", ".join(
sorted(set("'{GO}'".format(GO=go) for go in goids)))
prt.write(" '{PW}' : {{{GOS}}},\n".format(PW=pwy,
GOS=goids_str))
prt.write('}\n\n')
prt_copyright_comment(prt)
print(" {N:5} items WROTE: {PY}".format(N=len(pwy2ns),
PY=fout_py))
return pwy2ns
def wrpy_figure(self, fpat_py):
"""Write pathway figure information to a Python file."""
fout_py = fpat_py.format(ABC=self.taxnt.abc)
pw2ntfig = self._get_ntfig()
if not pw2ntfig:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
keys = ' '.join(next(iter(pw2ntfig.values()))._fields)
with open(os.path.join(REPO, fout_py), 'w') as prt:
prt_docstr_module(
'{N} of {T} Pathway have figures'.format(N=len(pw2ntfig),
T=len(self.pw2info)),
prt)
prt.write('from collections import namedtuple\n')
prt.write(
"Ntfig = namedtuple('ntfig', '{KEYS}')\n".format(KEYS=keys))
prt.write("PW2FIGS = {\n")
for pwy, ntfig in sorted(pw2ntfig.items(), key=self._sortby):
prt.write(" '{PWY}' : Ntfig._make({VALS}),\n".format(
PWY=pwy, VALS=list(ntfig)))
prt.write("}\n")
prt_copyright_comment(prt)
print(' {N:5} items WROTE: {PY}'.format(N=len(pw2ntfig),
PY=fout_py))
return pw2ntfig
def wrpy_pwy2nt(self, fout_py):
"""Write all pathways into a Python module in a condensed format."""
pwy2nt = self.get_pwy2nt()
if not pwy2nt:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
keys = ' '.join(next(iter(pwy2nt.values()))._fields)
with open(fout_py, 'w') as prt:
prt.write('# coding=utf-8\n')
prt_docstr_module('Pathway information', prt)
prt.write('from collections import namedtuple\n')
prt.write('from datetime import date\n')
prt.write('\n# Keys:\n{KEY}\n'.format(KEY=self._get_pwmarkdoc()))
prt.write('\n# Keys:\n{KEY}\n'.format(KEY=self._get_nsdoc()))
prt.write(
"\nNto = namedtuple('ntpwy', '{KEYS}')\n".format(KEYS=keys))
prt.write('# {N} {SPECIES} Pathways\n'.format(
N=len(pwy2nt), SPECIES=self.taxnt.displayName))
prt.write('# pylint: disable=line-too-long,too-many-lines\n')
prt.write('PWYNTS = [\n')
for dct in pwy2nt.values():
ntstr = '{}'.format(list(dct)).replace('datetime.date', 'date')
prt.write(' Nto._make({VALS}),\n'.format(VALS=ntstr))
prt.write(']\n')
prt_copyright_comment(prt)
print(" {N:5} pathways WROTE: {TXT}".format(N=len(self.pw2info),
TXT=fout_py))
return pwy2nt
def wrpy_info(self, fout_py):
"""Print Reactome species main information."""
fields = ['abc', 'abbreviation', 'taxId', 'displayName']
with open(os.path.join(REPO, fout_py), 'w') as prt:
prt_docstr_module('Species in Reactome', prt)
prt.write('import collections as cx\n\n')
prt_namedtuple(self.dcts, 'SPECIES', fields, prt)
prt_copyright_comment(prt)
print(' WROTE: {PY}'.format(PY=fout_py))
def main():
"""Print Reactome version in downloaded DAG."""
fout_py = 'src/reactomepy/data/reactome_version.py'
with open(fout_py, 'w') as prt:
prt_docstr_module('Reactome version in DAG', prt)
# CYPHER: MATCH (v:DBInfo) RETURN v
version = get_version(get_gdbdr())
prt.write('VERSION = {V}\n'.format(V=version))
prt_copyright_comment(prt)
print(' Version {V} WROTE: {PY}\n'.format(PY=fout_py, V=version))
def wrpy_common_names(self, fout_py):
"""Print species common names."""
taxid2namesalt = self._get_taxid2commonnames()
with open(os.path.join(fout_py), 'w') as prt:
prt_docstr_module('Common name for the species in Reactome', prt)
prt.write('# pylint: disable=line-too-long\n')
taxid_names = sorted(taxid2namesalt.items())
prt_dict(taxid_names,
'TAXID2NAMES',
afmt='{A}',
bfmt=None,
prt=prt)
prt_copyright_comment(prt)
print(' WROTE: {PY}'.format(PY=fout_py))
def wrpy_referencedatabase_nts(self, fout_py):
"""Print referencedatabase common names."""
# Find all referencedatabases which have definitions
id_nt_lst = sorted(self.referencedatabases.items(),
key=lambda t: t[1].displayName)
with open(os.path.join(REPO, fout_py), 'w') as prt:
docstr = '{N} ReferenceDatabases in Reactome'.format(
N=len(id_nt_lst))
prt_docstr_module(docstr, prt)
prt.write('from collections import namedtuple\n\n')
prt.write('# pylint: disable=line-too-long\n')
prt_id2nt(id_nt_lst, prt)
prt_copyright_comment(prt)
print(' WROTE: {PY}'.format(PY=fout_py))
def wrpy_disease2fld(self, fout_py, field, varname):
"""Print disease common names."""
# Find all diseases which have definitions
dis2val = self._get_dis2fldval(field)
with open(os.path.join(REPO, fout_py), 'w') as prt:
docstr = '{N} of {M} diseases in Reactome have definitions'.format(
M=self.num_dis, N=len(dis2val))
prt_docstr_module(docstr, prt)
prt.write('# pylint: disable=line-too-long\n')
disease_names = sorted(dis2val.items())
prt_dict(disease_names,
varname,
afmt='"{A}"',
bfmt='"{B}"',
prt=prt)
prt_copyright_comment(prt)
print(' WROTE: {PY}'.format(PY=fout_py))
def wrpy_pw2molecules(self, fout_py, database='UniProt'):
"""Print the Participating molecules for a pathway."""
pw2molecules = self.get_pw2molecules(database)
molecules = set(m for ms in pw2molecules.values() for m in ms)
hms = get_hms(TIC)
msg = '{N:4} Pathways contain {M:5} items from {DB}'.format(
N=len(pw2molecules), M=len(molecules), DB=database)
with open(os.path.join(REPO, fout_py), 'w') as prt:
prt_docstr_module(msg, prt)
prt.write('# pylint: disable=line-too-long, too-many-lines\n')
prt.write('PWY2{ITEM}S = {{\n'.format(ITEM=database.upper()))
for pwy, molecules in sorted(pw2molecules.items(), key=lambda t: [int(t[0].split('-')[2]), t[0]]):
prt.write(" '{PWY}':".format(PWY=pwy))
mstrs = ["'{V}'".format(V=m) for m in sorted(molecules)]
prt.write("{{{SET}}},\n".format(SET=", ".join(mstrs)))
# prt_namedtuple(self.dcts, 'SPECIES', fields, prt)
prt.write('}\n')
prt_copyright_comment(prt)
filesize = int(os.stat(os.path.join(REPO, fout_py)).st_size/1000000.0)
print(" {HMS} {MB} Mbytes {MSG} WROTE: {PY}".format(HMS=hms, MB=filesize, MSG=msg, PY=fout_py))
def wrpy_pwy2disease(self, fout_py):
"""Write all pathways that have associated diseases."""
pwy_dis = [(p, d['disease']) for p, d in self.pw2info.items()
if 'disease' in d]
if not pwy_dis:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
num_pwy = len(pwy_dis)
num_dis = len(set(d for _, ds in pwy_dis for d in ds))
with open(fout_py, 'w') as prt:
msg = '{N} Pathways have {M} diseases'.format(N=num_pwy, M=num_dis)
prt_docstr_module(msg, prt)
prt.write('# pylint: disable=line-too-long\n')
prt.write('PWY2DIS = {\n')
for pwy, dis in pwy_dis:
prt.write(" '{PWY}': {DIS},\n".format(PWY=pwy, DIS=dis))
prt.write('}\n')
prt_copyright_comment(prt)
print(" {MSG} WROTE: {PY}".format(MSG=msg, PY=fout_py))
return pwy_dis
def wrpy_relatedspecies(self, fout_py):
"""Write related species for a pathway, if it exists."""
pwy2taxids = self._get_pwy2relatedspecies()
if not pwy2taxids:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
with open(fout_py, 'w') as prt:
prt_docstr_module('Related species.', prt)
prt.write('\n# {N} of {M} Pathways have related species\n'.format(
N=len(pwy2taxids), M=len(self.pw2info)))
# prt.write('# pylint: disable=line-too-long,too-many-lines,bad-continuation\n')
prt.write('PWY2TAXIDS = {\n')
for pwy, taxids in sorted(pwy2taxids.items(), key=self._sortby):
prt.write(" '{PW}' : {TAXIDS},\n".format(PW=pwy,
TAXIDS=taxids))
prt.write('}\n\n')
prt_copyright_comment(prt)
print(" {N:5} items WROTE: {PY}".format(N=len(pwy2taxids),
PY=fout_py))
return pwy2taxids
def wrpy_pwy2summation(self, fpat_py):
"""Write pathway summation to a Python file."""
fout_py = fpat_py.format(ABC=self.taxnt.abc)
pwy2summation = self.objqu.get_pwy2summation(self.log)
if not pwy2summation:
print(" NO items. Not writing {PY}".format(PY=fout_py))
return
with open(os.path.join(REPO, fout_py), 'w') as prt:
prt.write('# coding=utf-8\n')
prt_docstr_module('Summations for pathways', prt)
prt.write('# pylint: disable=line-too-long,too-many-lines\n')
prt.write("PW2SUMS = {\n")
for pwy, summation in sorted(pwy2summation.items(),
key=self._sortby):
# Get the summation from the original pathway
prt.write(" '{KEY}': {VAL},\n".format(KEY=pwy,
VAL=summation))
prt.write("}\n")
prt_copyright_comment(prt)
print(' {N:5} items WROTE: {PY}'.format(N=len(pwy2summation),
PY=fout_py))
return pwy2summation
