def get_dataset(tissue, membrane_only=True):
counts = parse_counts(tissue)
if membrane_only:
go = parse_go_plasma_membrane()
genes_membrane = go[go.isin(counts.index)]
counts = counts.loc[genes_membrane]
ds = Dataset(
samplesheet=SampleSheet(cell_types),
counts_table=CountsTable(counts),
)
return ds
def test_initialize():
from singlet.samplesheet import SampleSheet
ss = SampleSheet.from_sheetname('example_sheet_tsv')
def test_initialize_fromdataset():
from singlet.samplesheet import SampleSheet
ct = SampleSheet.from_datasetname('example_dataset')
def get_dataset(tissue,
membrane_only=True,
regenerate=False,
go_contains=None,
go_exclude=None):
# Some tissues like brain were split for sorting, we merge them here
dss = []
for tissue_facs in tissues_prediction[tissue]:
cell_types, plates = parse_annotations(tissue_facs)
counts = parse_counts(tissue_facs, regenerate=regenerate)
if membrane_only:
go = parse_go_plasma_membrane().index
genes_membrane = go[go.isin(counts.index)]
counts = counts.loc[genes_membrane]
if (go_contains is not None) and (go_exclude is not None):
raise ValueError('Use either go_contains or go_exclude')
if go_contains is not None:
go = parse_go_plasma_membrane()
genes = go.index[go['GONames'].str.contains(go_contains)]
genes = np.intersect1d(genes, counts.index)
counts = counts.loc[genes]
elif go_exclude is not None:
go = parse_go_plasma_membrane()
genes = go.index[~go['GONames'].str.contains(go_exclude)]
genes = np.intersect1d(genes, counts.index)
counts = counts.loc[genes]
dss.append({'samplesheet': cell_types, 'counts': counts})
if len(dss) == 1:
ds = Dataset(
samplesheet=SampleSheet(cell_types),
counts_table=counts,
)
return ds
else:
# Merging is kind of messy because some genes are absent from either
# subtissue (grrr); I put zeroes for now, Michelle is working on the
# better solution (we have those numbers somewhere)
genes = set()
for ds in dss:
genes |= set(ds['counts'].index.values)
genes = pd.Index(sorted(genes), name=ds['counts'].index.name)
for ds in dss:
genes_missing = genes[~genes.isin(ds['counts'].index)]
for gene in genes_missing:
# The stuff is normalized, pseudocounted, and logged
ds['counts'].loc[gene] = -1.0
ds['counts'] = ds['counts'].loc[genes]
ngenes = len(genes)
ncells = sum(ds['samplesheet'].shape[0] for ds in dss)
samplesheet_all = pd.concat([ds['samplesheet'] for ds in dss], axis=0)
counts_all = pd.DataFrame(np.zeros((ngenes, ncells), float),
index=genes,
columns=samplesheet_all.index)
for ds in dss:
counts_all.loc[:,
ds['counts'].columns.values] = ds['counts'].values
counts_all = CountsTable(counts_all)
if ds['counts']._normalized:
counts_all._normalized = ds['counts']._normalized
ds = Dataset(
samplesheet=SampleSheet(samplesheet_all),
counts_table=counts_all,
)
return ds
#!/usr/bin/env python
# vim: fdm=indent
'''
author: Fabio Zanini
date: 15/08/17
content: Test SampleSheet class.
'''
# Script
if __name__ == '__main__':
# NOTE: an env variable for the config file needs to be set when
# calling this script
print('Instantiating SampleSheet')
from singlet.samplesheet import SampleSheet
ss = SampleSheet.from_sheetname('example_sheet_tsv')
print('Done!')