def __init__(
self,
path,
lastcol=None,
lastrow=None,
colmeta=None,
rowmeta=None,
eps_noise=False,
):
self.tbl = table(path)
self.bak = self.tbl.copy()
# strip / save metadata
if lastrow is not None:
self.tbl.head(lastrow, invert=True)
if lastcol is not None:
self.tbl.head(lastcol, invert=True, transposed=True)
self.row = self.tbl.rowheads[:]
self.col = self.tbl.colheads[:]
if eps_noise:
self.tbl.float()
self.tbl.apply_entries(lambda x: x + c_eps * random.random())
self.dat = self.tbl.table2array()
# colmetas from file / table
if colmeta is None:
self.colmeta = None
self.colmetaname = None
else:
self.colmeta = []
self.colmetaname = []
for x in colmeta:
if os.path.exists(x):
warn("Loading col metadata from file:", x)
temp = col2dict(x, value=1)
self.colmeta.append(
[temp.get(k, c_str_none) for k in self.col])
self.colmetaname.append(path2name(x))
else:
temp = self.bak.rowdict(x)
self.colmeta.append(
[temp.get(k, c_str_none) for k in self.col])
self.colmetaname.append(x)
# rowmetas from file / table
if rowmeta is None:
self.rowmeta = None
self.rowmetaname = None
else:
self.rowmeta = []
self.rowmetaname = []
for x in rowmeta:
if os.path.exists(x):
warn("Loading row metadata from file:", x)
temp = col2dict(x, value=1)
self.rowmeta.append(
[temp.get(k, c_str_none) for k in self.row])
self.rowmetaname.append(path2name(x))
else:
temp = self.bak.coldict(x)
self.rowmeta.append(
[temp.get(k, c_str_none) for k in self.row])
self.rowmetaname.append(x)
def main():
args = get_args()
# load genes (accounting for linkage)
genes = col2dict(
args.genes,
value=(1 if args.linked else None),
headers=args.skip_headers,
)
genes = {g: (g if k is None else k) for g, k in genes.items()}
# load background (accounting for linkage)
background = None
if args.background is not None:
background = col2dict(
args.background,
value=(1 if args.linked else None),
headers=args.skip_headers,
)
background = {
g: (g if k is None else k)
for g, k in background.items()
}
# load gene sets
gene_sets = polymap(
args.gene_sets,
reverse=args.reversed_mapping,
)
# run analysis
results = fisher_enrich(
genes,
gene_sets,
depletions=not args.exclude_depletions,
background=background,
intersect_background=args.intersect_background,
intersect_annotated=args.intersect_annotated,
fdr=args.fdr,
min_expected_overlap=args.min_expected_overlap,
verbose=False,
)
# write results
fh = open(args.outfile, "w") if args.outfile is not None else sys.stdout
writer = csv.writer(fh, dialect="excel-tab")
writer.writerow(c_fisher_fields)
for R in results:
writer.writerow(R.row())
# wrapup
if len(results) == 0:
say("# NO SIGNIFICANT ENRICHMENTS")
fh.close()
return None
def main():
args = get_args()
# derived args
path_faa = args.faa
total_reads = args.reads
pident = args.pident
if pident > 1:
print >> sys.stderr, "interpret", pident, "as percent;",
pident /= 100.0
print >> sys.stderr, "fractional value is", pident
mut_rate = 1 - pident
read_len = args.readlen
frag_len = int(math.ceil(read_len / 3.0))
# load proteins
faa = load_faa(path_faa, frag_len)
# initialize weights to effective protein lengths
weights = {k: (len(v) - frag_len + 1) for k, v in faa.items()}
# augment weights?
if args.weights:
weights2 = col2dict(args.weights, value=1, func=float)
weights = {k: v * weights2.get(k, 0) for k, v in weights.items()}
# make the chooser
wc = WeightedChooser(weights)
# make the reads (weighting by protein length)
read = 0
for prot_name in wc.iter_choice(total_reads):
read += 1
prot_seq = faa[prot_name]
rand_read(prot_seq, prot_name, read, read_len, frag_len, mut_rate)
def metacolors(values, cmap):
found_other = False
found_none = False
unique = set(values)
if c_str_other in unique:
found_other = True
unique -= {c_str_other}
if c_str_none in unique:
found_none = True
unique -= {c_str_none}
if os.path.exists(cmap):
cmap = col2dict(cmap, value=1)
for k in unique:
if k not in cmap:
cmap[k] = c_none_color
cmap = {l: c for l, c in cmap.items() if l in unique}
else:
ncol = mu.ncolors(len(unique), cmap)
cmap = {}
for k, c in zip(sorted(unique), ncol):
cmap[k] = c
if found_other:
cmap[c_str_other] = c_other_color
if found_none:
cmap[c_str_none] = c_none_color
return cmap
def rowlabel(self, df, des, ax_label, scaled=False, path=None):
ax_label = "{} (n={:,})".format(ax_label, len(df.row))
# override row names from the table?
mapping = {}
if path is not None:
mapping = col2dict(path, value=1)
for l in df.row:
if l not in mapping:
mapping[l] = "" if path is not None else l
if len(df.row) > c_max_lab and not scaled:
warn("Too many row labels.")
cx = sum(self.rownames.get_xlim()) / 2.0
cy = sum(self.rownames.get_ylim()) / 2.0
self.rownames.text(cx,
cy,
ax_label,
size=c_font3,
ha="center",
va="center",
rotation=90,
rotation_mode="anchor")
else:
ha = "left"
xi, xf = self.rownames.get_xlim()
if des.wmargin("heatmap") > des.wmargin("rownames"):
ha = "right"
xi, xf = xf, xi
self.rownames.set_ylim(0, len(df.row))
for i, l in enumerate(df.row):
self.rownames.text(
xi,
i + 0.5,
mapping[l],
ha=ha,
va="center",
size=c_font1,
clip_on=False,
)
cx = xf
cy = sum(self.rownames.get_ylim()) / 2.0
self.rownames.text(cx,
cy,
ax_label,
size=c_font3,
ha="center",
va="bottom" if ha == "left" else "top",
rotation=90,
rotation_mode="anchor")
def collabel(self, df, des, ax_label, scaled=False, path=None):
ax_label = "{} (n={:,})".format(ax_label, len(df.col))
# override col names from the table?
mapping = {}
if path is not None:
mapping = col2dict(path, value=1)
for l in df.col:
if l not in mapping:
mapping[l] = "" if path is not None else l
if len(df.col) > c_max_lab and not scaled:
warn("Too many column labels.")
cx = sum(self.colnames.get_xlim()) / 2.0
cy = sum(self.colnames.get_ylim()) / 2.0
self.colnames.text(cx,
cy,
ax_label,
size=c_font3,
ha="center",
va="center")
else:
ha = "left"
yi, yf = self.colnames.get_ylim()
if des.hmargin("heatmap") < des.hmargin("colnames"):
yi, yf = yf, yi
ha = "right"
self.colnames.set_xlim(0, len(df.col))
for i, l in enumerate(df.col):
self.colnames.text(
i + 0.5,
yi,
mapping[l],
rotation=45,
rotation_mode="anchor",
va="center",
ha=ha,
size=c_font1,
clip_on=False,
)
cx = 0
cy = yf
self.colnames.text(
cx,
cy,
ax_label,
size=c_font3,
ha="left",
va="top" if ha == "left" else "bottom",
)
def rowlabel(self, df, ax_label, scaled=False, path=None):
ax_label = "{} (n={:,})".format(ax_label, len(df.row))
# override row names from the table?
mapping = {}
if path is not None:
mapping = col2dict(path, value=1)
for l in df.row:
if l not in mapping:
mapping[l] = "" if path is not None else l
if len(df.row) > c_max_lab and not scaled:
warn("Too many row labels.")
cx = sum(self.rownames.get_xlim()) / 2.0
cy = sum(self.rownames.get_ylim()) / 2.0
self.rownames.text(cx,
cy,
ax_label,
size=c_font3,
ha="center",
va="center",
rotation=90,
rotation_mode="anchor")
else:
self.rownames.set_ylim(0, len(df.row))
for i, l in enumerate(df.row):
self.rownames.text(
0,
i + 0.5,
mapping[l],
va="center",
size=c_font1,
clip_on=True,
)
cx = self.rownames.get_xlim()[1]
cy = sum(self.rownames.get_ylim()) / 2.0
self.rownames.text(cx,
cy,
ax_label,
size=c_font3,
ha="center",
va="bottom",
rotation=90,
rotation_mode="anchor")
def main():
args = get_args()
# load key values
def make_link(row):
key = row[1] if args.linked else row[0]
return Link(key, float(row[-1]))
values = col2dict(
args.values,
func=make_link,
headers=args.skip_headers,
)
# load key sets
gene_sets = polymap(
args.gene_sets,
reverse=args.reversed_mapping,
)
# perform analysis
results = rank_enrich(
values,
gene_sets,
depletions=not args.exclude_depletions,
intersect_annotated=args.intersect_annotated,
fdr=args.fdr,
min_overlap=args.min_overlap,
verbose=True,
)
# write results
fh = open(args.outfile, "w") if args.outfile is not None else sys.stdout
writer = csv.writer(fh, dialect="excel-tab")
writer.writerow(c_rank_fields)
for R in results:
writer.writerow(R.row())
# wrapup
if len(results) == 0:
say("# NO SIGNIFICANT ENRICHMENTS")
fh.close()
return None
def main():
args = get_args()
# load obo / report rel type
obo = Ontology(args.obo)
warn("Summary of relationship types:")
for k in sorted(parentage_types):
warn(k, parentage_types[k])
# attach genes
if args.mapping is not None:
mapping = polymap(args.mapping, reverse=args.flip)
if args.allowed_genes is not None:
allowed = col2dict(args.allowed_genes)
mapping = {k: v for k, v in mapping.items() if k in allowed}
obo.attach_genes(mapping)
warn("# of attached genes:", len(obo.attached_genes))
# informative cut
if args.informative is not None:
threshold = float(args.informative)
if threshold < 1:
warn(
"Intepretting informative cutoff as fraction of annotated genes"
)
threshold *= len(obo.attached_genes)
threshold = int(threshold)
obo.set_informative(threshold)
for term in obo.iter_terms():
if not term.is_informative:
term.is_acceptable = False
# pruning cut
if args.prune is not None:
obo.prune(args.prune)
for term in obo.iter_terms():
if not term.is_pruned:
term.is_acceptable = False
# depth cut
if args.depth is not None:
for term in obo.iter_terms():
if term.depth != args.depth:
term.is_acceptable = False
# grep cut
if args.grep is not None:
for term in obo.iter_terms():
if not re.search(args.grep, term.name):
term.is_acceptable = False
# namespace cut
if args.namespace is not None:
for term in obo.iter_terms():
if term.namespace_short not in args.namespace:
term.is_acceptable = False
# output the new polymap
fh = open(args.outfile, "w") if args.outfile is not None else sys.stdout
for term in obo.iter_terms():
if term.is_acceptable:
outline = [str(term)]
if not args.terms_only:
outline += list(term.get_progeny_genes(
) if not args.ignore_progeny else term.genes)
print >> fh, "\t".join(outline)
fh.close()
# ---------------------------------------------------------------
strInputPath = args.input
strMode = args.mode
strOutputPath = args.output if args.output is not None else ".".join( strInputPath, strMode )
fReadLength = args.read_length
strSampleReadsPath = args.sample_reads
# ---------------------------------------------------------------
# manipulate data
# ---------------------------------------------------------------
if strMode == "rpkm":
if strSampleReadsPath is None:
sys.exit( "to compute rpkm you must include a file mapping sample IDs to #s of reads" )
dictMillions = col2dict( strSampleReadsPath, key=0, value=1, func=lambda x: float( x ) / 1e6 )
tableCladeRPK = table( strInputPath )
tableCladeRPK.grep( "headers", "s__" )
tableCladeRPK.float()
tableCladeRPK.groupby( lambda x: x.split( "|" )[0], median )
if strMode != "rpk":
for bug, sample, value in tableCladeRPK.iter_entries():
if strMode == "coverage":
tableCladeRPK.set( bug, sample, value * fReadLength / 1e3 )
elif strMode == "rpkm":
tableCladeRPK.set( bug, sample, value / dictMillions[sample] if dictMillions[sample] > 0 else 0 )
tableCladeRPK.unfloat()
tableCladeRPK.colsort()
def print2(d):
for key, d2 in d.items():
print key
for key2, val in d2.items():
print " ", key2, "-->", val
print
# ---------------------------------------------------------------
# col2dict tests
# ---------------------------------------------------------------
print "col2dict tests"
os.system("head %s" % (file))
print1(d.col2dict(file))
print1(d.col2dict(file, headers=True))
print1(d.col2dict(file, key=1, headers=True))
print1(d.col2dict(file, key=1, value=2, headers=True))
print1(d.col2dict(file, key=1, func=lambda row: float(row[2]), headers=True))
# ---------------------------------------------------------------
# col2dict2 tests
# ---------------------------------------------------------------
print "col2dict2 tests"
os.system("head %s" % (file))
print2(d.col2dict2(file))
print2(d.col2dict2(file, headers=True, mirror=True))
print2(
d.col2dict2(file,
#! /usr/bin/env python import os, sys, re, glob, argparse from zopy.table2 import table from zopy.dictation import col2dict from zopy.utils import path2name dictMap = col2dict( sys.argv[1], key=0, value=1 ) tableData = table( sys.argv[2] ) tableData.apply_colheads( lambda x: path2name( x ) ) tableData.apply_colheads( lambda x: x.split( "." )[0] ) tableData.apply_colheads( lambda x: dictMap[x] ) tableData.dump( sys.argv[3] )
