def prt_txt(self, prt, goea_results, prtfmt=None, **kws):
"""Print GOEA results in text format."""
if prtfmt is None:
prtfmt = "{GO} {NS} {p_uncorrected:5.2e} {study_count:>5} {name}\n"
prtfmt = self.adjust_prtfmt(prtfmt)
prt_flds = RPT.get_fmtflds(prtfmt)
data_nts = get_goea_nts_prt(goea_results, prt_flds, **kws)
RPT.prt_txt(prt, data_nts, prtfmt, prt_flds, **kws)
return data_nts
def prt_sections(prt, sections, prtfmt, secspc=False):
"""Print GO namedtuples in their sections."""
num_goids = 0
for section, nts_flat in sections:
# Add an empty line between sections, if desired
if secspc:
prt.write("\n")
prt.write("{SECTION}\n".format(SECTION=section))
num_nts = len(nts_flat)
num_goids += num_nts
prt_txt(prt, nts_flat, prtfmt=prtfmt)
def prt_txt(prt, goea_results, prtfmt=None, **kws):
"""Print GOEA results in text format."""
objprt = PrtFmt()
if prtfmt is None:
flds = ['GO', 'NS', 'p_uncorrected',
'ratio_in_study', 'ratio_in_pop', 'depth', 'name', 'study_items']
prtfmt = objprt.get_prtfmt_str(flds)
prtfmt = objprt.adjust_prtfmt(prtfmt)
prt_flds = RPT.get_fmtflds(prtfmt)
data_nts = MgrNtGOEAs(goea_results).get_goea_nts_prt(prt_flds, **kws)
RPT.prt_txt(prt, data_nts, prtfmt, prt_flds, **kws)
return data_nts
def prt_nts(self, desc2nts, prt=sys.stdout, prtfmt=None):
"""Print grouped and sorted GO IDs."""
# deprecated
# Set print format string
if prtfmt is None:
prtfmt = "{{hdr1usr01:2}} {FMT}\n".format(FMT=self.grprobj.gosubdag.prt_attr['fmt'])
# 1-D: data to print is a flat list of namedtuples
if 'flat' in desc2nts:
prt_txt(prt, desc2nts['flat'], prtfmt=prtfmt)
# 2-D: data to print is a list of [(section, nts), ...
else:
WrSectionsTxt.prt_sections(prt, desc2nts['sections'], prtfmt)
def prt_txt(prt, goea_results, prtfmt=None, **kws):
"""Print GOEA results in text format."""
objprt = PrtFmt()
if prtfmt is None:
flds = ['GO', 'NS', 'p_uncorrected',
'ratio_in_study', 'ratio_in_pop', 'depth', 'name', 'study_items']
prtfmt = objprt.get_prtfmt_str(flds)
prtfmt = objprt.adjust_prtfmt(prtfmt)
prt_flds = RPT.get_fmtflds(prtfmt)
data_nts = MgrNtGOEAs(goea_results).get_goea_nts_prt(prt_flds, **kws)
RPT.prt_txt(prt, data_nts, prtfmt, prt_flds, **kws)
return data_nts
def prt_nts(self, desc2nts, prt=sys.stdout, prtfmt=None):
"""Print grouped and sorted GO IDs."""
# deprecated
# Set print format string
if prtfmt is None:
prtfmt = "{{hdr1usr01:2}} {FMT}\n".format(
FMT=self.grprobj.gosubdag.prt_attr['fmt'])
# 1-D: data to print is a flat list of namedtuples
if 'flat' in desc2nts:
prt_txt(prt, desc2nts['flat'], prtfmt=prtfmt)
# 2-D: data to print is a list of [(section, nts), ...
else:
WrSectionsTxt.prt_sections(prt, desc2nts['sections'], prtfmt)
def prt_txt(self, prt, goea_results, prtfmt=None, **kws):
"""Print GOEA results in text format."""
objprt = PrtFmt()
if prtfmt is None:
flds = ['GO', 'NS', 'p_uncorrected', 'ratio_in_study', 'ratio_in_pop', 'depth', 'name', 'study_items']
prtfmt = objprt.get_prtfmt_str(flds)
#### prtfmt = " ".join([objprt.default_fld2fmt[f] for f in flds])
#### prtfmt = ("{GO} {NS} {p_uncorrected:5.2e} {ratio_in_study:>6} {ratio_in_pop:>9} "
#### "{depth:02} {name:40} {study_items}\n")
prtfmt = objprt.adjust_prtfmt(prtfmt)
prt_flds = RPT.get_fmtflds(prtfmt)
data_nts = MgrNtGOEAs(goea_results).get_goea_nts_prt(prt_flds, **kws)
RPT.prt_txt(prt, data_nts, prtfmt, prt_flds, **kws)
return data_nts
def wr_txt(self, fout_txt):
"""Write counts of GO terms at all levels and depths."""
from goatools.wr_tbl import prt_txt
data = self.get_data()
with open(fout_txt, 'w') as prt:
prtfmt = "{Depth_Level:>7} " \
"{BP_D:6,} {MF_D:6,} {CC_D:>6,} " \
"{BP_L:>6,} {MF_L:>6,} {CC_L:>6,}\n"
prt.write("{TITLE}\n\n".format(TITLE=self.title))
prt.write(" |<---- Depth ---->| |<---- Level ---->|\n")
prt.write("Dep/Lev BP MF CC BP MF CC\n")
prt.write("------- ----- ----- ----- ----- ----- -----\n")
prt_txt(prt, data, prtfmt=prtfmt, title=self.title)
sys.stdout.write(" {N:>5,} items WROTE: {TXT}\n".format(
N=len(data), TXT=fout_txt))
def wr_txt(self, fout_txt):
"""Write counts of GO terms at all levels and depths."""
from goatools.wr_tbl import prt_txt
data = self.get_data()
with open(fout_txt, 'w') as prt:
prtfmt = "{Depth_Level:>7} " \
"{BP_D:6,} {MF_D:6,} {CC_D:>6,} " \
"{BP_L:>6,} {MF_L:>6,} {CC_L:>6,}\n"
prt.write("{TITLE}\n\n".format(TITLE=self.title))
prt.write(" |<---- Depth ---->| |<---- Level ---->|\n")
prt.write("Dep/Lev BP MF CC BP MF CC\n")
prt.write("------- ----- ----- ----- ----- ----- -----\n")
prt_txt(prt, data, prtfmt=prtfmt, title=self.title)
sys.stdout.write(" {N:>5,} items WROTE: {TXT}\n".format(
N=len(data), TXT=fout_txt))
def prt_txt_desc2nts(self, prt, desc2nts, prtfmt):
"""Print grouped and sorted GO IDs."""
# 1-D: data to print is a flat list of namedtuples
if 'flat' in desc2nts:
nts = desc2nts.get('flat')
# sys.stdout.write("FLAT NTS: {FLDS}\n".format(FLDS=" ".join(next(iter(nts))._fields)))
prt_txt(prt, nts, prtfmt)
# 2-D: data to print is a list of [(section, nts), ...
else:
for section, nts in desc2nts['sections']:
prt.write("\nSECTION: {SEC}\n".format(SEC=section))
prt_txt(prt, nts, prtfmt)
grprobj = self.sortobj.grprobj
dat = SummarySec2dHdrGos().summarize_sec2hdrnts(desc2nts['sections'])
ugos_y = dat['G'].intersection(grprobj.usrgos)
ugos_n = dat['U'].intersection(grprobj.usrgos)
return {'GO_DESC':'usr', 'SECs':len(dat['S']), 'GOs':len(ugos_y),
'UNGRP':len(ugos_n), 'undesc':'ungrpd'}
def wr_txt(self, fout_txt="gos_depth01.txt", title=None):
"""write text table of depth-01 GO terms and their letter representation."""
data_nts = self.get_d1nts()
with open(fout_txt, 'w') as prt:
if title is not None:
prt.write("{TITLE}\n\n".format(TITLE=title))
prt.write(
" D1 : Letter representing the depth-01 GO term\n")
prt.write(" dcnt: Total number of all descendants\n")
prt.write(" dep: Depth; The maximum length path to ")
prt.write("leaf-level (childless) GO descendant(s)\n\n")
prt.write("D1 NS dcnt dep GO ID Description\n")
prt.write(
"- -- ------ --- ---------- ------------------------------\n"
)
prt_txt(prt, data_nts)
sys.stdout.write(" {N:>5} items WROTE: {TXT}\n".format(
N=len(data_nts), TXT=fout_txt))
def prt_genes(fout_genes, geneids, taxid, log):
"""Print 'cell cycle' geneids, with or without Symbol and description information."""
fin_symbols = "genes_NCBI_{TAXID}_All.py".format(TAXID=taxid)
# If gene Symbol information is available, print geneid and Symbol
if os.path.isfile(fin_symbols):
import importlib
module_name = "".join(["goatools.test_data.", fin_symbols[:-3]])
module = importlib.import_module(module_name)
GeneID2nt = module.GeneID2nt
fmtstr = "{GeneID:>9} {Symbol:<16} {description}\n"
nts = [GeneID2nt[geneid] for geneid in sorted(geneids) if geneid in GeneID2nt]
with open(fout_genes, 'w') as prt:
prt_txt(prt, nts, fmtstr)
if log is not None:
log.write(" WROTE {N:>5} genes: {FOUT}\n".format(FOUT=fout_genes, N=len(nts)))
# Just print geneids
else:
with open(fout_genes, 'w') as prt:
for geneid in geneids:
prt.write("{geneid}\n".format(geneid=geneid))
if log is not None:
log.write(" WROTE {N:>5} genes: {FOUT}\n".format(FOUT=fout_genes, N=len(geneids)))
def prt_genes(fout_genes, geneids, taxid, log):
"""Print 'cell cycle' geneids, with or without Symbol and description information."""
fin_symbols = "genes_NCBI_{TAXID}_All.py".format(TAXID=taxid)
# If gene Symbol information is available, print geneid and Symbol
if os.path.isfile(fin_symbols):
import importlib
module_name = "".join(["goatools.test_data.", fin_symbols[:-3]])
module = importlib.import_module(module_name)
geneid2nt = module.GENEID2NT
fmtstr = "{GeneID:>9} {Symbol:<16} {description}\n"
nts = [geneid2nt[geneid] for geneid in sorted(geneids) if geneid in geneid2nt]
with open(fout_genes, 'w') as prt:
prt_txt(prt, nts, fmtstr)
if log is not None:
log.write(" WROTE {N:>5} genes: {FOUT}\n".format(FOUT=fout_genes, N=len(nts)))
# Just print geneids
else:
with open(fout_genes, 'w') as prt:
for geneid in geneids:
prt.write("{geneid}\n".format(geneid=geneid))
if log is not None:
log.write(" WROTE {N:>5} genes: {FOUT}\n".format(
FOUT=fout_genes, N=len(geneids)))
def prt_txt_desc2nts(self, prt, desc2nts, prtfmt):
"""Print grouped and sorted GO IDs."""
# 1-D: data to print is a flat list of namedtuples
if 'flat' in desc2nts:
nts = desc2nts.get('flat')
# sys.stdout.write("FLAT NTS: {FLDS}\n".format(FLDS=" ".join(next(iter(nts))._fields)))
prt_txt(prt, nts, prtfmt)
# 2-D: data to print is a list of [(section, nts), ...
else:
for section, nts in desc2nts['sections']:
prt.write("\nSECTION: {SEC}\n".format(SEC=section))
prt_txt(prt, nts, prtfmt)
grprobj = self.sortobj.grprobj
dat = SummarySec2dHdrGos().summarize_sec2hdrnts(
desc2nts['sections'])
ugos_y = dat['G'].intersection(grprobj.usrgos)
ugos_n = dat['U'].intersection(grprobj.usrgos)
return {
'GO_DESC': 'usr',
'SECs': len(dat['S']),
'GOs': len(ugos_y),
'UNGRP': len(ugos_n),
'undesc': 'ungrpd'
}
def prt_txt(self, prt, results_nt, prtfmt, **kws):
"""Print GOEA results in text format."""
prtfmt = self.adjust_prtfmt(prtfmt)
prt_flds = RPT.get_fmtflds(prtfmt)
data_nts = self._get_nts(results_nt, prt_flds, True, **kws)
RPT.prt_txt(prt, data_nts, prtfmt, prt_flds, **kws)
def prt_txt(self, prt, results_nt, prtfmt, **kws):
"""Print GOEA results in text format."""
prtfmt = self.adjust_prtfmt(prtfmt)
prt_flds = RPT.get_fmtflds(prtfmt)
data_nts = self._get_nts(results_nt, prt_flds, True, **kws)
RPT.prt_txt(prt, data_nts, prtfmt, prt_flds, **kws)
def prt_mdtbl(self, nts, prt_flds=None, prt=sys.stdout):
"""Write specified namedtuples into an Excel spreadsheet."""
if prt_flds is None:
prt_flds = self.prt_flds
prtfmt = "|{DATA}|\n".format(DATA="|".join(self.fld2prtfmt[f] for f in prt_flds))
prt_txt(prt, nts, prtfmt=prtfmt)
