def add_corrupt_tree_order(corrupt_tree, metrics, output):
"""
adds corrupt tree order to metrics
"""
with open(corrupt_tree) as newickfile:
newickdata = newickfile.readline()
assert newickfile.readline() == ''
tree = Tree(newickdata, format=1)
leaves = [node.name for node in tree.traverse("levelorder")]
leaves = [val[len('cell_'):] for val in leaves if val.startswith("cell_")]
ordering = {val: i for i, val in enumerate(leaves)}
metrics = csvutils.read_csv_and_yaml(metrics)
cells = metrics.cell_id
for cellid in cells:
order = ordering.get(cellid, float('nan'))
metrics.loc[metrics["cell_id"] == cellid, "order_corrupt_tree"] = order
col_dtype = dtypes()['metrics']['order_corrupt_tree']
metrics['order_corrupt_tree'] = metrics['order_corrupt_tree'].astype(
col_dtype)
csvutils.write_dataframe_to_csv_and_yaml(metrics,
output,
dtypes()['metrics'],
write_header=True)
def add_contamination_status(infile,
outfile,
config,
reference='grch37',
threshold=0.05):
data = csvutils.read_csv_and_yaml(infile)
data = data.set_index('cell_id', drop=False)
organisms = [genome['name'] for genome in config['genomes']]
if reference not in organisms:
raise Exception("Could not find the fastq screen counts")
alts = [col for col in organisms if not col == reference]
data['is_contaminated'] = False
for altcol in alts:
perc_alt = _get_col_data(data, altcol) / data['total_reads']
data.loc[perc_alt > threshold, 'is_contaminated'] = True
col_type = dtypes()['metrics']['is_contaminated']
data['is_contaminated'] = data['is_contaminated'].astype(col_type)
csvutils.write_dataframe_to_csv_and_yaml(data, outfile,
dtypes()['metrics'])
def cell_cycle_classifier(hmmcopy_reads, hmmcopy_metrics, alignment_metrics,
output, tempdir, genome_labels):
helpers.makedirs(tempdir)
temp_output = os.path.join(tempdir, 'cell_cycle_output.csv')
cmd = [
'cell_cycle_classifier', 'train-classify', hmmcopy_reads,
hmmcopy_metrics, alignment_metrics, temp_output
]
pypeliner.commandline.execute(*cmd)
cell_cycle_df = pd.read_csv(temp_output)
cols_cell_cycle = cell_cycle_df.columns.values
hmm_metrics_df = csvutils.read_csv_and_yaml(hmmcopy_metrics)
hmm_metrics_df = hmm_metrics_df.merge(cell_cycle_df,
on=['cell_id'],
how='outer')
out_dtypes = dtypes(genome_labels)
for colname in cols_cell_cycle:
hmm_metrics_df[colname] = hmm_metrics_df[colname].astype(
out_dtypes[colname])
csvutils.write_dataframe_to_csv_and_yaml(hmm_metrics_df, output,
out_dtypes)
def generate_qc_report(tempdir, reference_gc, fastqscreen_training_data,
metrics_df, gc_metrics_df, qc_report,
metrics_df_annotated):
helpers.makedirs(tempdir)
fastqscreen_classify.classify_fastqscreen(fastqscreen_training_data,
metrics_df, metrics_df_annotated,
dtypes()['metrics'])
generate_qc.generate_html_report(tempdir, qc_report, reference_gc,
metrics_df, gc_metrics_df)
def annotate_metrics(metrics, output, sample_info, cells):
"""
adds sample information to metrics in place
"""
metrics = csvutils.read_csv_and_yaml(metrics)
for cellid in cells:
cellinfo = sample_info[cellid]
for colname, value in cellinfo.items():
metrics.loc[metrics["cell_id"] == cellid, colname] = value
csvutils.write_dataframe_to_csv_and_yaml(metrics, output,
dtypes()['metrics'])
def add_quality(hmmcopy_metrics, alignment_metrics, output, training_data,
tempdir, genome_labels):
helpers.makedirs(tempdir)
intermediate_output = os.path.join(tempdir, 'metrics_with_quality.csv')
model = classify.train_classifier(training_data)
feature_names = model.feature_names_
data = classify.load_data(hmmcopy_metrics, alignment_metrics,
feature_names)
predictions = classify.classify(model, data)
classify.write_to_output(hmmcopy_metrics, intermediate_output, predictions)
csvutils.rewrite_csv_file(intermediate_output,
output,
dtypes=dtypes(genome_labels))
def add_contamination_status(infile,
outfile,
genome_labels,
reference='grch37',
threshold=0.05):
data = csvutils.read_csv_and_yaml(infile)
data = data.set_index('cell_id', drop=False)
if reference not in genome_labels:
raise Exception("Could not find the fastq screen counts")
alts = [col for col in genome_labels if not col == reference]
data['is_contaminated'] = False
for altcol in alts:
perc_alt = _get_col_data(data, altcol) / data['total_reads']
data.loc[perc_alt > threshold, 'is_contaminated'] = True
data['is_contaminated'] = data['is_contaminated'].astype('bool')
csvutils.write_dataframe_to_csv_and_yaml(data, outfile,
dtypes(genome_labels))