def write(self, fout_xlsx=None, fout_txt=None, verbose=False):
"""Command-line interface for go_draw script."""
sortby = self._get_fncsortnt(self.objgrpd.grprobj.gosubdag.prt_attr['flds'])
kws_sort = {'sortby' if verbose else 'section_sortby': sortby}
sortobj = Sorter(self.objgrpd.grprobj, **kws_sort)
# KWS: hdrgo_prt=True section_prt=None top_n=None use_sections=True
# RET: {sortobj, sections, hdrgo_prt} or {sortobj flat hdrgo_prt}
desc2nts = sortobj.get_desc2nts_fnc(
hdrgo_prt=verbose,
section_prt=True,
top_n=None,
use_sections=True)
# print('FFFF', desc2nts['flds'])
# Write user GO IDs in sections
objgowr = WrXlsxSortedGos("init", sortobj, self.objgrpd.ver_list)
if fout_xlsx is not None:
kws_xlsx = {'shade_hdrgos':verbose}
if not verbose:
kws_xlsx['prt_flds'] = [f for f in desc2nts['flds'] if f not in self.excl_flds]
objgowr.wr_xlsx_nts(fout_xlsx, desc2nts, **kws_xlsx)
fout_desc = '{BASE}_desc.txt'.format(BASE=os.path.splitext(fout_xlsx)[0])
self._wr_ver_n_key(fout_desc, verbose)
if fout_txt is not None:
self._wr_txt_nts(fout_txt, desc2nts, objgowr, verbose)
if fout_xlsx is None and fout_txt is None:
self._prt_ver_n_key(sys.stdout, verbose)
prtfmt = self._get_prtfmt(objgowr, verbose)
summary_dct = objgowr.prt_txt_desc2nts(sys.stdout, desc2nts, prtfmt)
self._prt_ver_n_key(sys.stdout, verbose)
if summary_dct:
print("\n{N} GO IDs in {S} sections".format(
N=desc2nts['num_items'], S=desc2nts['num_sections']))
def write(self, fout_xlsx=None, fout_txt=None, verbose=False):
"""Command-line interface for go_draw script."""
sortby = self._get_fncsortnt(self.objgrpd.grprobj.gosubdag.prt_attr['flds'])
kws_sort = {'sortby' if verbose else 'section_sortby': sortby}
sortobj = Sorter(self.objgrpd.grprobj, **kws_sort)
# KWS: hdrgo_prt=True section_prt=None top_n=None use_sections=True
# RET: {sortobj, sections, hdrgo_prt} or {sortobj flat hdrgo_prt}
desc2nts = sortobj.get_desc2nts_fnc(
hdrgo_prt=verbose,
section_prt=True,
top_n=None,
use_sections=True)
# print('FFFF', desc2nts['flds'])
# Write user GO IDs in sections
objgowr = WrXlsxSortedGos("init", sortobj, self.objgrpd.ver_list)
if fout_xlsx is not None:
kws_xlsx = {'shade_hdrgos':verbose}
if not verbose:
kws_xlsx['prt_flds'] = [f for f in desc2nts['flds'] if f not in self.excl_flds]
objgowr.wr_xlsx_nts(fout_xlsx, desc2nts, **kws_xlsx)
fout_desc = '{BASE}_desc.txt'.format(BASE=os.path.splitext(fout_xlsx)[0])
self._wr_ver_n_key(fout_desc, verbose)
if fout_txt is not None:
self._wr_txt_nts(fout_txt, desc2nts, objgowr, verbose)
if fout_xlsx is None and fout_txt is None:
self._prt_ver_n_key(sys.stdout, verbose)
prtfmt = self._get_prtfmt(objgowr, verbose)
summary_dct = objgowr.prt_txt_desc2nts(sys.stdout, desc2nts, prtfmt)
self._prt_ver_n_key(sys.stdout, verbose)
if summary_dct:
print("\n{N} GO IDs in {S} sections".format(
N=desc2nts['num_items'], S=desc2nts['num_sections']))
def _wr_xlsx(name, grprobj, **kws):
"""Group, sort, and print xlsx file."""
# Exclude ungrouped "Misc." section of sections var(sec_rd)
fout_xlsx = "{NAME}.xlsx".format(NAME=name)
# kws Sorter: hdrgo_prt section_prt top_n use_sections
sortobj = Sorter(grprobj)
desc2nts = sortobj.get_desc2nts(**kws)
objwr = WrXlsxSortedGos(name, sortobj)
# kws WrXlsxSortedGos wr_xlsx_nts: title hdrs
objwr.wr_xlsx_nts(fout_xlsx, desc2nts, **kws)
def __init__(self, name, goea_results, obj):
self.name = name
self.datobj = obj # AArtGeneProductSetsAll
_ini = _Init(obj)
self.go2nt = _ini.get_go2nt(goea_results)
_grprobj = Grouper("grp", self.go2nt, obj.hdrobj, obj.grprdflt.gosubdag, go2nt=self.go2nt)
self.sortobj = Sorter(_grprobj)
self.sec2gos = _ini.get_sec2gos(self.sortobj)
self.sec2chr = cx.OrderedDict([(s, obj.sec2chr[s]) for s in self.sec2gos.keys()])
self.go2chrs = _ini.get_go2chrs(self.sec2gos, self.sec2chr)
self.gene2gos = _ini.get_gene2gos(self.go2nt)
self.gene2section2gos = _ini.get_gene2section2gos(self.gene2gos, self.sec2gos)
self.gene2aart = _ini.get_gene2aart(self.gene2section2gos, self.sec2chr)
def _wr_xlsx(name, grprobj, **kws):
"""Group, sort, and print xlsx file."""
# print('\nTEST {} kws_sortobj: {}'.format(name, kws))
# KWS SORT OBJ
kws_sort = {'sortby', 'hdrgo_sortby', 'section_sortby'}
# KWS SORT FUNC: hdrgo_prt section_prt top_n use_sections prtfmt
# Exclude ungrouped "Misc." section of sections var(sec_rd)
fout_xlsx = "{NAME}.xlsx".format(NAME=name)
# kws Sorter: hdrgo_prt section_prt top_n use_sections
sortobj = Sorter(grprobj, **{k:v for k, v in kws.items() if k in kws_sort})
desc2nts = sortobj.get_desc2nts(**kws)
objwr = WrXlsxSortedGos(name, sortobj)
# kws WrXlsxSortedGos wr_xlsx_nts: title hdrs
objwr.wr_xlsx_nts(fout_xlsx, desc2nts, **kws)
def cli(self, prt=sys.stdout):
"""Command-line interface for go_draw script."""
kws = self.objdoc.get_docargs(prt=None)
godag = get_godag(kws['obo'], prt=None, loading_bar=False, optional_attrs=['relationship'])
usrgos = GetGOs(godag, max_gos=200).get_usrgos(kws.get('GO_FILE'), prt)
tcntobj = self._get_tcntobj(usrgos, godag, **kws) # Gets TermCounts or None
self.gosubdag = GoSubDag(usrgos, godag, relationships=True, tcntobj=tcntobj, prt=None)
grprdflt = GrouperDflts(self.gosubdag, kws['slims'])
ver_list = [godag.version, grprdflt.ver_goslims]
prt.write("{VER}\n".format(VER="\n".join(ver_list)))
sections = self._read_sections(kws['ifile'])
# print("SECSECSEC", sections)
hdrobj = HdrgosSections(self.gosubdag, grprdflt.hdrgos_dflt, sections)
grprobj = Grouper("init", usrgos, hdrobj, self.gosubdag)
# Write sections
objsecwr = WrSectionsTxt(grprobj, ver_list)
if not os.path.exists(kws['ifile']):
objsecwr.wr_txt_section_hdrgos(kws['ifile'])
objsecwr.wr_txt_section_hdrgos(kws['ofile'])
objsecpy = WrSectionsPy(grprobj, ver_list)
if 'py' in kws:
objsecpy.wr_py_sections(kws['py'], sections, doc=godag.version)
# Write user GO IDs in sections
sortobj = Sorter(grprobj)
objgowr = WrXlsxSortedGos("init", sortobj, ver_list)
objgowr.wr_txt_gos(kws['txt'], sortby=objsecpy.fncsortnt)
#objwr.wr_txt_section_hdrgos(kws['ofile'], sortby=objwr.fncsortnt)
self._prt_cnt_usrgos(usrgos, sys.stdout)
def _get_sortobj():
"""Get object for grouping GO IDs."""
godag = get_godag("go-basic.obo", prt=None, loading_bar=False, optional_attrs=['relationship'])
gosubdag = GoSubDag(USER_GOS, godag, relationships=True, tcntobj=None)
grprdflt = GrouperDflts(gosubdag)
hdrobj = HdrgosSections(gosubdag, grprdflt.hdrgos_dflt, SECTIONS)
grprobj = Grouper("wrusrgos", USER_GOS, hdrobj, gosubdag)
return Sorter(grprobj)
def get_sortobj(self, goea_results, **kws):
"""Return a Grouper object, given a list of GOEnrichmentRecord."""
nts_goea = MgrNtGOEAs(goea_results).get_goea_nts_prt(**kws)
goids = set(nt.GO for nt in nts_goea)
go2nt = {nt.GO:nt for nt in nts_goea}
grprobj = Grouper("GOEA", goids, self.hdrobj, self.grprdflt.gosubdag, go2nt=go2nt)
grprobj.prt_summary(sys.stdout)
# hdrgo_prt", "section_prt", "top_n", "use_sections"
sortobj = Sorter(grprobj, section_sortby=lambda nt: getattr(nt, self.pval_fld))
return sortobj
def __init__(self, name, goea_results, obj):
self.name = name
self.datobj = obj # AArtGeneProductSetsAll
_ini = _Init(obj)
self.go2nt = _ini.get_go2nt(goea_results)
_grprobj = Grouper("grp", self.go2nt, obj.hdrobj, obj.grprdflt.gosubdag, go2nt=self.go2nt)
self.sortobj = Sorter(_grprobj)
self.sec2gos = _ini.get_sec2gos(self.sortobj)
self.sec2chr = cx.OrderedDict([(s, obj.sec2chr[s]) for s in self.sec2gos.keys()])
self.go2chrs = _ini.get_go2chrs(self.sec2gos, self.sec2chr)
self.gene2gos = _ini.get_gene2gos(self.go2nt)
self.gene2section2gos = _ini.get_gene2section2gos(self.gene2gos, self.sec2gos)
self.gene2aart = _ini.get_gene2aart(self.gene2section2gos, self.sec2chr)
def run(grprobj, hdrobj, exp_hdrs, hdrgo_prt=True):
"""Load sorter. Check results."""
chk_hdrs(grprobj, hdrobj)
act_hdrs = grprobj.get_hdrgos()
print("ACTUAL")
grprobj.gosubdag.prt_goids(sorted(act_hdrs))
print("EXPECTED")
grprobj.gosubdag.prt_goids(sorted(exp_hdrs))
# assert act_hdrs == exp_hdrs
sortobj = Sorter(grprobj, hdrgo_prt=hdrgo_prt)
sys.stdout.write("\n{NAME} PRINT GOs hdrgo_prt({H}):\n".format(
H=hdrgo_prt, NAME=grprobj.grpname))
sortobj.prt_gos()
nts = sortobj.get_nts_flat(hdrgo_prt)
nts_go = set([nt.GO for nt in nts])
usrgos = grprobj.usrgos
assert nts_go.intersection(usrgos) == usrgos, \
"ONLY {N} of {U} user gos found in grouped sorted GOs. MISSING: {GOs}".format(
N=len(nts_go.intersection(usrgos)),
GOs=" ".join(usrgos.difference(nts_go.intersection(usrgos))),
U=len(usrgos))
return sortobj, nts, nts_go, act_hdrs
def run(grprobj, hdrobj, exp_hdrs, hdrgo_prt=True):
"""Load sorter. Check results."""
chk_hdrs(grprobj, hdrobj)
act_hdrs = grprobj.get_hdrgos()
print("ACTUAL")
grprobj.gosubdag.prt_goids(sorted(act_hdrs))
print("EXPECTED")
grprobj.gosubdag.prt_goids(sorted(exp_hdrs))
# assert act_hdrs == exp_hdrs
sortobj = Sorter(grprobj, hdrgo_prt=hdrgo_prt)
sys.stdout.write("\n{NAME} PRINT GOs hdrgo_prt({H}):\n".format(
H=hdrgo_prt, NAME=grprobj.grpname))
sortobj.prt_gos()
nts = sortobj.get_nts_flat(hdrgo_prt)
nts_go = set([nt.GO for nt in nts])
usrgos = grprobj.usrgos
assert nts_go.intersection(usrgos) == usrgos, \
"ONLY {N} of {U} user gos found in grouped sorted GOs. MISSING: {GOs}".format(
N=len(nts_go.intersection(usrgos)),
GOs=" ".join(usrgos.difference(nts_go.intersection(usrgos))),
U=len(usrgos))
return sortobj, nts, nts_go, act_hdrs
class AArtGeneProductSetsOne(object):
"""Product gene lists with ASCII art sections and GO IDs for each gene product."""
# nts need: nt.GO and nt.study_items
def __init__(self, name, goea_results, obj):
self.name = name
self.datobj = obj # AArtGeneProductSetsAll
_ini = _Init(obj)
self.go2nt = _ini.get_go2nt(goea_results)
_grprobj = Grouper("grp",
self.go2nt,
obj.hdrobj,
obj.grprdflt.gosubdag,
go2nt=self.go2nt)
self.sortobj = Sorter(_grprobj)
self.sec2gos = _ini.get_sec2gos(self.sortobj)
self.sec2chr = cx.OrderedDict([(s, obj.sec2chr[s])
for s in self.sec2gos.keys()])
self.go2chrs = _ini.get_go2chrs(self.sec2gos, self.sec2chr)
self.gene2gos = _ini.get_gene2gos(self.go2nt)
self.gene2section2gos = _ini.get_gene2section2gos(
self.gene2gos, self.sec2gos)
self.gene2aart = _ini.get_gene2aart(self.gene2section2gos,
self.sec2chr)
def prt_report_grp0(self, prt=sys.stdout):
"""Print full GO/gene report without grouping."""
summaryline = self.str_summaryline()
kws_grp = {
'use_sections': False,
'hdrgo_prt': False,
'sortby': lambda nt: [-1 * nt.dcnt, nt.depth]
}
# Print grouped GO IDs
prt.write("{SUMMARY}\n".format(SUMMARY=summaryline))
self.prt_gos_grouped(sys.stdout, **kws_grp)
# genes
genes = sorted(self.gene2gos.keys())
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_gene_aart(genes, prt)
# Sort genes
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_gene_aart_details(genes, prt)
return (self.name, self.get_section_marks())
def prt_report_grp1(self, prt=sys.stdout, **kws_grp):
"""Print full GO/gene report with grouping."""
summaryline = self.str_summaryline()
# Print grouped GO IDs
prt.write("{SUMMARY}\n".format(SUMMARY=summaryline))
self.prt_gos_grouped(prt, **kws_grp)
# genes
genes = sorted(self.gene2gos.keys())
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_section_key(prt)
self.prt_gene_aart(genes, prt)
# Sort genes
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_gene_aart_details(genes, prt)
return (self.name, self.get_section_marks())
def str_summaryline(self):
"""Print: 47 GOs, 262 genes described by 10 of 19 sections consistent_increase."""
return "{N} GOs, {M} genes described by {X} of {Y} sections {NM}".format(
N=len(self.go2nt),
M=len(self.gene2gos),
X=len(self.sec2chr),
Y=len(self.datobj.sec2chr),
NM=self.name)
def prt_gos_grouped(self, prt, **kws_grp):
"""Print grouped GO list."""
prtfmt = self.datobj.kws['fmtgo']
wrobj = WrXlsxSortedGos(self.name, self.sortobj)
# Keyword arguments: control content: hdrgo_prt section_prt top_n use_sections
desc2nts = self.sortobj.get_desc2nts(**kws_grp)
wrobj.prt_txt_desc2nts(prt, desc2nts, prtfmt)
def prt_gos_flat(self, prt):
"""Print flat GO list."""
prtfmt = self.datobj.kws['fmtgo']
_go2nt = self.sortobj.grprobj.go2nt
go2nt = {go: _go2nt[go] for go in self.go2nt}
prt.write("\n{N} GO IDs:\n".format(N=len(go2nt)))
_sortby = self._get_sortgo()
for ntgo in sorted(go2nt.values(), key=_sortby):
prt.write(prtfmt.format(**ntgo._asdict()))
#print("FFFMMMTTT", prtfmt)
def _get_sortgo(self):
"""Get function for sorting GO terms in a list of namedtuples."""
if 'sortgo' in self.datobj.kws:
return self.datobj.kws['sortgo']
return self.datobj.grprdflt.gosubdag.prt_attr['sort'] + "\n"
def prt_gene_aart(self, geneids, prt=sys.stdout):
"""For each gene, print ASCII art which represents its associated GO IDs."""
patgene = self.datobj.kws["fmtgene"]
itemid2name = self.datobj.kws.get("itemid2name")
prt.write("\n{HDR}\n".format(HDR=self.str_hdr()))
for geneid in geneids:
symbol = "" if itemid2name is None else itemid2name.get(geneid, "")
prt.write(
patgene.format(AART=self.gene2aart[geneid],
ID=geneid,
NAME=symbol))
def prt_gene_aart_details(self, geneids, prt=sys.stdout):
"""For each gene, print ASCII art which represents its associated GO IDs."""
_go2nt = self.sortobj.grprobj.go2nt
patgene = self.datobj.kws["fmtgene2"]
patgo = self.datobj.kws["fmtgo2"]
itemid2name = self.datobj.kws.get("itemid2name")
chr2i = self.datobj.get_chr2idx()
for geneid in geneids:
gos_gene = self.gene2gos[geneid]
symbol = "" if itemid2name is None else itemid2name.get(geneid, "")
prt.write("\n")
prt.write(
patgene.format(AART=self.gene2aart[geneid],
ID=geneid,
NAME=symbol))
go2nt = {
go: (_go2nt[go], "".join(self.go2chrs[go]))
for go in gos_gene
}
for ntgo, abc in sorted(
go2nt.values(),
key=lambda t: [chr2i[t[1][:1]], t[0].NS, -1 * t[0].dcnt]):
prt.write("{ABC} ".format(ABC=abc))
prt.write(patgo.format(**ntgo._asdict()))
def prt_section_key(self, prt=sys.stdout):
"""Print the section name and its alias."""
for section_name, letter in self.datobj.sec2chr.items():
mrk = '*' if section_name in self.sec2chr else ""
prt.write("{M:1} {ABC} {SECT}\n".format(M=mrk,
ABC=letter,
SECT=section_name))
def str_hdr(self):
"""Return a string representing the section headers: """
return "".join([c for _, c in self.sec2chr.items()])
def get_section_marks(self):
"""For each section in AArtGeneProducts, return '*' or "" ."""
return [
abc if s in self.sec2chr else "."
for s, abc in self.datobj.sec2chr.items()
]
def get_gene2binvec(self):
"""Return a boolean vector for each gene representing GO section membership."""
_sec2chr = self.sec2chr
return {
g: [s in s2gos for s in _sec2chr]
for g, s2gos in self.gene2section2gos.items()
}
class AArtGeneProductSetsOne(object):
"""Product gene lists with ASCII art sections and GO IDs for each gene product."""
# nts need: nt.GO and nt.study_items
def __init__(self, name, goea_results, obj):
self.name = name
self.datobj = obj # AArtGeneProductSetsAll
_ini = _Init(obj)
self.go2nt = _ini.get_go2nt(goea_results)
_grprobj = Grouper("grp", self.go2nt, obj.hdrobj, obj.grprdflt.gosubdag, go2nt=self.go2nt)
self.sortobj = Sorter(_grprobj)
self.sec2gos = _ini.get_sec2gos(self.sortobj)
self.sec2chr = cx.OrderedDict([(s, obj.sec2chr[s]) for s in self.sec2gos.keys()])
self.go2chrs = _ini.get_go2chrs(self.sec2gos, self.sec2chr)
self.gene2gos = _ini.get_gene2gos(self.go2nt)
self.gene2section2gos = _ini.get_gene2section2gos(self.gene2gos, self.sec2gos)
self.gene2aart = _ini.get_gene2aart(self.gene2section2gos, self.sec2chr)
def prt_report_grp0(self, prt=sys.stdout):
"""Print full GO/gene report without grouping."""
summaryline = self.str_summaryline()
kws_grp = {'use_sections':False,
'hdrgo_prt':False,
'sortby':lambda nt: [-1*nt.dcnt, nt.depth]}
# Print grouped GO IDs
prt.write("{SUMMARY}\n".format(SUMMARY=summaryline))
self.prt_gos_grouped(sys.stdout, **kws_grp)
# genes
genes = sorted(self.gene2gos.keys())
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_gene_aart(genes, prt)
# Sort genes
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_gene_aart_details(genes, prt)
return (self.name, self.get_section_marks())
def prt_report_grp1(self, prt=sys.stdout, **kws_grp):
"""Print full GO/gene report with grouping."""
summaryline = self.str_summaryline()
# Print grouped GO IDs
prt.write("{SUMMARY}\n".format(SUMMARY=summaryline))
self.prt_gos_grouped(prt, **kws_grp)
# genes
genes = sorted(self.gene2gos.keys())
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_section_key(prt)
self.prt_gene_aart(genes, prt)
# Sort genes
prt.write("\n\n{SUMMARY}\n\n".format(SUMMARY=summaryline))
self.prt_gene_aart_details(genes, prt)
return (self.name, self.get_section_marks())
def str_summaryline(self):
"""Print: 47 GOs, 262 genes described by 10 of 19 sections consistent_increase."""
return "{N} GOs, {M} genes described by {X} of {Y} sections {NM}".format(
N=len(self.go2nt), M=len(self.gene2gos),
X=len(self.sec2chr), Y=len(self.datobj.sec2chr), NM=self.name)
def prt_gos_grouped(self, prt, **kws_grp):
"""Print grouped GO list."""
prtfmt = self.datobj.kws['fmtgo']
wrobj = WrXlsxSortedGos(self.name, self.sortobj)
# Keyword arguments: control content: hdrgo_prt section_prt top_n use_sections
desc2nts = self.sortobj.get_desc2nts(**kws_grp)
wrobj.prt_txt_desc2nts(prt, desc2nts, prtfmt)
def prt_gos_flat(self, prt):
"""Print flat GO list."""
prtfmt = self.datobj.kws['fmtgo']
_go2nt = self.sortobj.grprobj.go2nt
go2nt = {go:_go2nt[go] for go in self.go2nt}
prt.write("\n{N} GO IDs:\n".format(N=len(go2nt)))
_sortby = self._get_sortgo()
for ntgo in sorted(go2nt.values(), key=_sortby):
prt.write(prtfmt.format(**ntgo._asdict()))
#print("FFFMMMTTT", prtfmt)
def _get_sortgo(self):
"""Get function for sorting GO terms in a list of namedtuples."""
if 'sortgo' in self.datobj.kws:
return self.datobj.kws['sortgo']
return self.datobj.grprdflt.gosubdag.prt_attr['sort'] + "\n"
def prt_gene_aart(self, geneids, prt=sys.stdout):
"""For each gene, print ASCII art which represents its associated GO IDs."""
patgene = self.datobj.kws["fmtgene"]
itemid2name = self.datobj.kws.get("itemid2name")
prt.write("\n{HDR}\n".format(HDR=self.str_hdr()))
for geneid in geneids:
symbol = "" if itemid2name is None else itemid2name.get(geneid, "")
prt.write(patgene.format(AART=self.gene2aart[geneid], ID=geneid, NAME=symbol))
def prt_gene_aart_details(self, geneids, prt=sys.stdout):
"""For each gene, print ASCII art which represents its associated GO IDs."""
_go2nt = self.sortobj.grprobj.go2nt
patgene = self.datobj.kws["fmtgene2"]
patgo = self.datobj.kws["fmtgo2"]
itemid2name = self.datobj.kws.get("itemid2name")
chr2i = self.datobj.get_chr2idx()
for geneid in geneids:
gos_gene = self.gene2gos[geneid]
symbol = "" if itemid2name is None else itemid2name.get(geneid, "")
prt.write("\n")
prt.write(patgene.format(AART=self.gene2aart[geneid], ID=geneid, NAME=symbol))
go2nt = {go:(_go2nt[go], "".join(self.go2chrs[go])) for go in gos_gene}
for ntgo, abc in sorted(go2nt.values(),
key=lambda t: [chr2i[t[1][:1]], t[0].NS, -1*t[0].dcnt]):
prt.write("{ABC} ".format(ABC=abc))
prt.write(patgo.format(**ntgo._asdict()))
def prt_section_key(self, prt=sys.stdout):
"""Print the section name and its alias."""
for section_name, letter in self.datobj.sec2chr.items():
mrk = '*' if section_name in self.sec2chr else ""
prt.write("{M:1} {ABC} {SECT}\n".format(M=mrk, ABC=letter, SECT=section_name))
def str_hdr(self):
"""Return a string representing the section headers: """
return "".join([c for _, c in self.sec2chr.items()])
def get_section_marks(self):
"""For each section in AArtGeneProducts, return '*' or "" ."""
return [abc if s in self.sec2chr else "." for s, abc in self.datobj.sec2chr.items()]
def get_gene2binvec(self):
"""Return a boolean vector for each gene representing GO section membership."""
_sec2chr = self.sec2chr
return {g:[s in s2gos for s in _sec2chr] for g, s2gos in self.gene2section2gos.items()}