def remap_expn_sample_names(expn):
"""
Super-specific method to remap the sample names.
"""
names = expn.getConditionNames()
new_names = []
for n in names:
if n in sample_description:
new_names.append(sample_description[n])
else:
new_names.append('?%s' % n)
expn.setConditionNames(new_names)
if __name__ == "__main__":
# This should later be changed to mm10v79:
expn = glload("../te_counts/genes_cpm_expression.glb") # Using the published one for now
print(expn.getConditionNames())
print("Testing coherence")
print("\nSample names:")
# Test that all desc names are actually in the expn and vice versa:
expn_names = expn.getConditionNames()
desc_names = list(sample_description.keys())
ss1 = set(expn_names) - set(desc_names)
ss2 = set(desc_names) - set(expn_names)
if ss1:
print(">>>Missing in sample_description:\n", '\n'.join(sorted(list(ss1))))
print()
if ss2:
print(">>>Missing in exp:\n", '\n'.join(sorted(list(ss2))))
'white matter glia': 'White-matter glia',
'X2clc': '2C-like cells (MERVL+ Zscan+)',
'X2clc D1 rp3': '2C-like cells (MERVL+)',
'X2C embryo': '2C Embryo',
'X4C embryo': '4C Embryo',
'X8C embryo': '8C Embryo',
'XEN': 'XEN cells',
'zona limitans intrathalamica': 'Zona limitans intrathalamica',
}
if __name__ == '__main__':
from glbase3 import glload
from .gene_layer_name import gene_layer_name
# Check all sample names are actually used:
expn = glload("../../te_counts/genes_cpm_expression.glb")
cond_names = expn.getConditionNames()
print('\nFound in "sample_description" but not in expn:')
for c in sorted(sample_description.keys()):
if c not in cond_names:
print('! %s' % (c, ))
print('\nFound in "expn" but not in sample_description:')
for c in cond_names:
if c not in list(sample_description.keys()):
print("'%s': ," % (c, ))
print()
print('Spell check')
# For spell check:
def bind_genome(self, genelist_glb_filename):
self.genome = glbase3.glload(genelist_glb_filename)
print('Loaded %s' % genelist_glb_filename)