import matplotlib.pyplot as plt
import seaborn as sns
os.environ['SINGLET_CONFIG_FILENAME'] = 'singlet.yml'
sys.path.append('/home/fabio/university/postdoc/singlet')
from singlet.dataset import Dataset
# Script
if __name__ == '__main__':
ds = Dataset(
counts_table='dengue',
samplesheet='virus',
featuresheet='humanGC38',
)
ds.query_samples_by_counts('total >= 50000', inplace=True)
ds.samplesheet.rename(columns={'time [h]': 'time'}, inplace=True)
cov = ds.samplesheet['coverage'] = ds.counts.sum(axis=0)
ds.counts.normalize('counts_per_million', inplace=True)
n = ds.samplesheet['numberDengueReads'].astype(int)
ds.samplesheet['virus_reads_per_million'] = 1e6 * n / (cov + n)
ds.counts.log(inplace=True)
# Only select cells without virus
ds.query_samples_by_metadata('virus_reads_per_million < 0.1', inplace=True)
# Check table with number of cells
table = (ds.samplesheet.groupby(
['time', 'MOI']).count().iloc[:,
# NOTE: an env variable for the config file needs to be set when
# calling this script
from singlet.dataset import Dataset
ds = Dataset(
samplesheet='example_sheet_tsv',
counts_table='example_table_tsv')
print('Query samples by metadata')
ds_tmp = ds.query_samples_by_metadata(
'experiment == "test_pipeline"',
inplace=False)
assert(tuple(ds_tmp.samplenames) == ('test_pipeline',))
print('Done!')
print('Query sample by counts in one gene')
ds_tmp = ds.query_samples_by_counts('KRIT1 > 100', inplace=False)
assert(tuple(ds_tmp.samplenames) == ('third_sample',))
print('Done!')
print('Query sample by total counts')
ds_tmp = ds.query_samples_by_counts('total < 3000000', inplace=False)
assert(tuple(ds_tmp.samplenames) == ('second_sample',))
print('Done!')
print('Query sample by mapped counts')
ds_tmp = ds.query_samples_by_counts('mapped < 1000000', inplace=False)
assert(tuple(ds_tmp.samplenames) == ('second_sample',))
print('Done!')
print('Query features by counts')
ds_tmp = ds.query_features_by_counts(
