def load_elution(fname, getname=True):
# expected file structure:
# first col: gene id
# second col: treat differently if 2nd col header is 'Total' or
# 'Description'
# remaining cols: elution profile data
lines = [l for l in ut.load_tab_file(fname)]
# final row: total count in msblender output; don't skip in cuihong's data
skip_final_row = (lines[-1][0][0] == '#')
rows = lines[1:-1] if skip_final_row else lines[1:]
fractions = [f for f in lines[0][1:]]
if fractions[0].lower() in ['total', 'totalcount', 'description']:
start_data_col = 2
fractions.remove(fractions[0])
else:
start_data_col = 1
mat = np.matrix([row[start_data_col:] for row in rows],dtype='float32')
prots = [row[0] for row in rows]
elut = Struct(mat=mat, prots=prots, fractions=fractions, filename=fname,
filename_original=fname)
if start_data_col == 2:
col2name_vals = [row[1] for row in rows]
elut.column2vals = col2name_vals
if getname: elut.name = os.path.basename(fname).split('.')[0]
return elut
def load_go_ont(fname, filter_namespace='cellular_component'):
dterms = {}
term = None
for r in file(fname,'r'):
if r.strip()=='[Term]':
if hasattr(term,'set_is_a'):
if not filter_namespace or filter_namespace==term.namespace:
dterms[term.acc] = (term.name, term.set_is_a)
term = Struct()
elif r.strip() and term:
att = r.split(': ')[0]
val = ': '.join(r.split(': ')[1:]).strip()
if att=='id':
term.acc = val
elif att=='name':
term.name = val
elif att=='namespace':
term.namespace = val
elif att=='is_a':
val = val.split(' ! ')[0]
if hasattr(term,'set_is_a'):
term.set_is_a.add(val)
else:
term.set_is_a = set([val])
return dterms
def load_elution(fname, getname=True):
# expected file structure:
# first col: gene id
# second col: treat differently if 2nd col header is 'Total' or
# 'Description'
# remaining cols: elution profile data
lines = [l for l in ut.load_tab_file(fname)]
# final row: total count in msblender output; don't skip in cuihong's data
skip_final_row = lines[-1][0][0] == "#"
rows = lines[1:-1] if skip_final_row else lines[1:]
fractions = [f for f in lines[0][1:]]
if fractions[0].lower() in ["total", "totalcount", "description"]:
start_data_col = 2
fractions.remove(fractions[0])
else:
start_data_col = 1
mat = np.matrix([row[start_data_col:] for row in rows], dtype="float32")
prots = [row[0] for row in rows]
elut = Struct(mat=mat, prots=prots, fractions=fractions, filename=fname, filename_original=fname)
if start_data_col == 2:
col2name_vals = [row[1] for row in rows]
elut.column2vals = col2name_vals
if getname:
elut.name = os.path.basename(fname).split(".")[0]
return elut
def downsample_elution(elution, downsample, seed=0):
"""
Return a new elution with every downsample-th fraction.
"""
down_elut = Struct()
down_elut.__dict__ = elution.__dict__.copy()
down_elut.mat = elution.mat[:,seed::2]
down_elut.fractions = elution.fractions[::2]
down_elut.name = elution.name + '_down%i' % downsample
return(down_elut)
def downsample_elution(elution, downsample, seed=0):
"""
Return a new elution with every downsample-th fraction.
"""
down_elut = Struct()
down_elut.__dict__ = elution.__dict__.copy()
down_elut.mat = elution.mat[:, seed::2]
down_elut.fractions = elution.fractions[::2]
down_elut.name = elution.name + "_down%i" % downsample
return down_elut
