def transform(self, data):
# check if data is melted:
if len(data.columns) != 1:
raise ValueError(
'transformer requires dataframe with '
'a single column, got %s' % data.columns)
column = data.columns[0]
# iterate over lowest levels to build a dictionary of
# sets
genesets = {}
nlevels = Utils.getDataFrameLevels(data)
for key, group in data.groupby(level=list(range(nlevels))):
if "background" in key and not self.background:
continue
genesets[key] = set(group[column])
values = []
if len(genesets) == 2:
a = set(genesets[list(genesets.keys())[0]])
b = set(genesets[list(genesets.keys())[1]])
values.append(("10", len(a - b)))
values.append(("01", len(b - a)))
values.append(("11", len(a & b)))
values.append(
("labels", list(map(path2str, list(genesets.keys())))))
elif len(genesets) == 3:
a = set(genesets[list(genesets.keys())[0]])
b = set(genesets[list(genesets.keys())[1]])
c = set(genesets[list(genesets.keys())[2]])
values.append(("100", len(a - b - c)))
values.append(("010", len(b - a - c)))
values.append(("001", len(c - a - b)))
values.append(("110", len((a & b) - c)))
values.append(("101", len((a & c) - b)))
values.append(("011", len((b & c) - a)))
values.append(("111", len((a & b) & c)))
values.append(
("labels", list(map(path2str, list(genesets.keys())))))
else:
raise ValueError(
"Can currently only cope with 2 or 3 way intersections")
return DataTree.listAsDataFrame(values)
def transform(self, data):
# check if data is melted:
if len(data.columns) != 1:
raise ValueError(
'transformer requires dataframe with'
'a single column, got %s' % data.columns)
column = data.columns[0]
# iterate over lowest levels to build a dictionary of
# sets
genesets = {}
nlevels = Utils.getDataFrameLevels(data)
for key, group in data.groupby(level=range(nlevels)):
genesets[path2str(key)] = set(group[column])
keys = genesets.keys()
background = None
foreground = []
for key in keys:
if "background" in key:
background = genesets[key]
else:
foreground.append(key)
if len(keys) < 3 or background is None:
raise ValueError(
"Expected at least 3 lists, with one called background, "
"instead got %i lists called %s" %
(len(keys), ", ".join(keys)))
missing = {
y: [str(x) for x in genesets[y]
if x not in background] for y in foreground}
if any([len(missing[x]) > 0 for x in missing]):
missing_items = "\n\t".join(
["%s:\t%s" % (x, ",".join(missing[x])) for x in missing])
raise ValueError(
"Found items in lists not in background. "
"Missing items:\n\t %s" % missing_items)
M = len(set(background))
if len(keys) == 2:
n = len(set(genesets[keys[1]]))
N = len(set(genesets[keys[0]]))
x = len(set(genesets[keys[0]]) & set(genesets[keys[1]]))
p = scipy.stats.hypergeom.sf(x, M, n, N)
fc = ((x + 0.0) / N) / ((n + 0.0) / M)
values = [("Enrichment", fc),
("P-value", p)]
else:
enrichments = []
pvals = []
As = []
Bs = []
for a, b in itertools.combinations(keys, 2):
N = len(set(genesets[a]))
n = len(set(genesets[b]))
x = len(set(genesets[a]) & set(genesets[b]))
p = scipy.stats.hypergeom.sf(x, M, n, N)
fc = ((x + 0.0) / N) / ((n + 0.0) / M)
As.append(a)
Bs.append(b)
pvals.append(p)
enrichments.append(fc)
values = [("ListA", As),
("ListB", Bs),
("Enrichment", enrichments),
("P-value", pvals)]
return DataTree.listAsDataFrame(values, values_are_rows=True)
