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 _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)
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()}