def main():
"""Compute sample hierarchical clustering."""
args = parse_args()
expressions = get_expressions(fnames=args.sample_files,
gene_set=args.genes)
expressions = transform(expressions,
log2=args.log2,
normalization=args.normalization)
zero_genes = get_zero_genes(expressions)
zero_samples = get_zero_samples(expressions)
linkage, dendrogram = get_clustering(expressions,
distance_metric=get_distance_metric(
args.distance),
linkage_method=args.linkage,
ordering_method=args.ordering,
n_keep=args.n_keep,
n_trials=args.n_trials)
result = {
'linkage':
linkage.tolist(),
'sample_ids':
{i: {
'id': sampleid
}
for i, sampleid in enumerate(args.sampleids)},
'order':
dendrogram['leaves'],
'zero_gene_symbols':
zero_genes,
'missing_gene_symbols':
list(set(args.genes).difference(set(expressions.index))),
'zero_sample_ids': [args.sampleids[sample] for sample in zero_samples]
}
output_json(result, args.output)
def main():
"""Compute sample hierarchical clustering."""
args = parse_args()
if len(args.sample_files) != len(args.sample_ids):
msg = "The number of sample files does not match the number of sample IDs."
set_error(msg)
if len(args.sample_files) != len(args.sample_names):
msg = "The number of sample files does not match the number of sample names."
set_error(msg)
if len(args.sample_files) < 2:
msg = (
"Select at least two samples to compute hierarchical clustering of samples."
)
set_error(msg)
if len(args.gene_labels) == 1 and args.distance_metric != "euclidean":
msg = (
"Select at least two genes to compute hierarchical clustering of samples with "
"correlation distance metric or use Euclidean distance metric.")
set_error(msg)
expressions, excluded = get_expressions(fnames=args.sample_files,
gene_set=args.gene_labels)
if len(expressions.index) == 0:
if not args.gene_labels:
msg = "The selected samples do not have any common genes."
else:
msg = "None of the selected genes are present in all samples."
set_error(msg)
if len(expressions.index) == 1 and args.distance_metric != "euclidean":
if not args.gene_labels:
msg = (
"The selected samples contain only one common gene ({}). At least two common "
"genes are required to compute hierarchical clustering of samples with "
"correlation distance metric. Select a different set of samples or use Euclidean "
"distance metric.".format(
get_gene_names(list(expressions.index), args.source,
args.species)[0]))
else:
msg = (
"Only one of the selected genes ({}) is present in all samples but at least two "
"such genes are required to compute hierarchical clustering of samples with "
"correlation distance metric. Select more genes or use Euclidean distance "
"metric.".format(
get_gene_names(list(expressions.index), args.source,
args.species)[0]))
set_error(msg)
expressions = transform(expressions, log2=args.log2, z_score=args.z_score)
if args.remove_const:
expressions, matches = remove_const_samples(expressions)
if len(expressions.columns) == 0:
msg = (
"All of the selected samples have constant expression across genes. Hierarchical "
"clustering of samples cannot be computed.")
set_error(msg)
if len(expressions.columns) == 1:
sample_name = [
id for i, id in enumerate(args.sample_names) if matches[i]
][0]
msg = (
"Only one of the selected samples ({}) has a non-constant expression across "
"genes. However, hierarchical clustering of samples cannot be computed with "
"just one sample.".format(sample_name))
set_error(msg)
removed = [
name for i, name in enumerate(args.sample_names) if not matches[i]
]
suffix = "" if len(removed) <= 3 else ", ..."
if removed:
msg = (
"{} of the selected samples ({}) have constant expression across genes. "
"Those samples are excluded from the computation of hierarchical clustering of "
"samples with correlation distance "
"metric.".format(len(removed),
", ".join(removed[:3]) + suffix))
send_message(warning(msg))
else:
matches = [True] * len(args.sample_files)
suffix = "" if len(excluded) <= 3 else ", ..."
if excluded:
excluded_names = get_gene_names(excluded[:3], args.source,
args.species)
if len(excluded) == 1:
if not args.gene_labels:
msg = (
"Gene {} is present in some but not all of the selected samples. This "
"gene is excluded from the computation of hierarchical clustering of "
"samples.".format(", ".join(excluded_names)))
else:
msg = (
"{} of the selected genes ({}) is missing in at least one of the selected "
"samples. This gene is excluded from the computation of hierarchical "
"clustering of samples.".format(len(excluded),
", ".join(excluded_names)))
send_message(warning(msg))
if len(excluded) > 1:
if not args.gene_labels:
msg = (
"{} genes ({}) are present in some but not all of the selected samples. Those "
"genes are excluded from the computation of hierarchical clustering of "
"samples.".format(len(excluded), ", ".join(excluded_names)))
else:
msg = (
"{} of the selected genes ({}) are missing in at least one of the selected "
"samples. Those genes are excluded from the computation of hierarchical "
"clustering of samples.".format(len(excluded),
", ".join(excluded_names)))
send_message(warning(msg))
linkage, dendrogram = get_clustering(
expressions,
distance_metric=get_distance_metric(args.distance_metric),
linkage_method=args.linkage_method,
order=args.order,
)
sample_ids = [
sample_id for i, sample_id in enumerate(args.sample_ids) if matches[i]
]
result = {
"sample_ids":
{i: {
"id": sample_id
}
for i, sample_id in enumerate(sample_ids)},
"linkage": linkage.tolist(),
"order": dendrogram["leaves"],
}
output_json(result, args.output)
def main():
"""Compute gene hierarchical clustering."""
args = parse_args()
if len(args.sample_files) != len(args.sample_names):
msg = 'The number of sample files does not match the number of sample names.'
set_error(msg)
if len(args.gene_labels) == 1:
msg = 'Select at least two genes to compute hierarchical clustering of genes.'
set_error(msg)
if len(args.sample_files) == 1 and args.distance_metric != 'euclidean':
msg = (
'Select at least two samples to compute hierarchical clustering of genes with '
'correlation distance metric or use Euclidean distance metric.')
set_error(msg)
expressions, excluded = get_expressions(fnames=args.sample_files,
gene_set=args.gene_labels)
if len(expressions.index) == 0:
if not args.gene_labels:
msg = 'The selected samples do not have any common genes.'
else:
msg = 'None of the selected genes are present in all samples.'
set_error(msg)
if len(expressions.index) == 1 and args.distance_metric != 'euclidean':
if not args.gene_labels:
msg = (
'The selected samples contain only one common gene ({}). At least two common '
'genes are required to compute hierarchical clustering of genes with '
'correlation distance metric. Select a different set of samples or use Euclidean '
'distance metric.'.format(
get_gene_names(list(expressions.index), args.source,
args.species)[0]))
else:
msg = (
'Only one of the selected genes ({}) is present in all samples but at least two '
'such genes are required to compute hierarchical clustering of genes with '
'correlation distance metric. Select more genes or use Euclidean distance '
'metric.'.format(
get_gene_names(list(expressions.index), args.source,
args.species)[0]))
set_error(msg)
expressions = transform(expressions, log2=args.log2, z_score=args.z_score)
if args.remove_const:
expressions, matches = remove_const_genes(expressions)
if len(expressions.index) == 0:
msg = (
'All of the selected genes have constant expression across samples. '
'Hierarchical clustering of genes cannot be computed.')
set_error(msg)
if len(expressions.index) == 1:
gene_names = get_gene_names(list(expressions.index), args.source,
args.species)
msg = (
'Only one of the selected genes ({}) has a non-constant expression across '
'samples. However, hierarchical clustering of genes cannot be computed with '
'just one gene.'.format(gene_names[0]))
set_error(msg)
removed = [
name for i, name in enumerate(expressions.index) if not matches[i]
]
suffix = '' if len(removed) <= 3 else ', ...'
if removed:
removed_names = get_gene_names(removed[:3], args.source,
args.species)
msg = (
'{} of the selected genes ({}) have constant expression across samples. '
'Those genes are excluded from the computation of hierarchical clustering of '
'genes with correlation distance '
'metric.'.format(len(removed),
', '.join(removed_names) + suffix))
print(warning(msg))
else:
matches = [True] * len(expressions.index)
suffix = '' if len(excluded) <= 3 else ', ...'
if excluded:
excluded_names = get_gene_names(excluded[:3], args.source,
args.species)
if len(excluded) == 1:
if not args.gene_labels:
msg = (
'Gene {} is present in some but not all of the selected samples. This '
'gene is excluded from the computation of hierarchical clustering of '
'genes.'.format(len(excluded), ', '.join(excluded_names)))
else:
msg = (
'{} of the selected genes ({}) is missing in at least one of the selected '
'samples. This gene is excluded from the computation of hierarchical '
'clustering of genes.'.format(len(excluded),
', '.join(excluded_names)))
print(warning(msg))
if len(excluded) > 1:
if not args.gene_labels:
msg = (
'{} genes ({}) are present in some but not all of the selected samples. Those '
'genes are excluded from the computation of hierarchical clustering of '
'genes.'.format(len(excluded), ', '.join(excluded_names)))
else:
msg = (
'{} of the selected genes ({}) are missing in at least one of the selected '
'samples. Those genes are excluded from the computation of hierarchical '
'clustering of genes.'.format(len(excluded),
', '.join(excluded_names)))
print(warning(msg))
linkage, dendrogram = get_clustering(expressions,
distance_metric=get_distance_metric(
args.distance_metric),
linkage_method=args.linkage_method,
order=args.order)
result = {
'gene_symbols':
{i: {
'gene': gene
}
for i, gene in enumerate(expressions.index)},
'linkage': linkage.tolist(),
'order': dendrogram['leaves'],
}
output_json(result, args.output)
def main():
"""Compute sample hierarchical clustering."""
args = parse_args()
if len(args.sample_files) != len(args.sample_ids):
msg = 'The number of sample files does not match the number of sample IDs.'
set_error(msg)
if len(args.sample_files) != len(args.sample_names):
msg = 'The number of sample files does not match the number of sample names.'
set_error(msg)
if len(args.sample_files) < 2:
msg = 'Select at least two samples to compute hierarchical clustering of samples.'
set_error(msg)
if len(args.gene_labels) == 1 and args.distance_metric != 'euclidean':
msg = ('Select at least two genes to compute hierarchical clustering of samples with '
'correlation distance metric or use Euclidean distance metric.')
set_error(msg)
expressions, excluded = get_expressions(fnames=args.sample_files, gene_set=args.gene_labels)
if len(expressions.index) == 0:
if not args.gene_labels:
msg = 'The selected samples do not have any common genes.'
else:
msg = 'None of the selected genes are present in all samples.'
set_error(msg)
if len(expressions.index) == 1 and args.distance_metric != 'euclidean':
if not args.gene_labels:
msg = ('The selected samples contain only one common gene ({}). At least two common '
'genes are required to compute hierarchical clustering of samples with '
'correlation distance metric. Select a different set of samples or use Euclidean '
'distance metric.'.format(get_gene_names(list(expressions.index), args.source, args.species)[0]))
else:
msg = ('Only one of the selected genes ({}) is present in all samples but at least two '
'such genes are required to compute hierarchical clustering of samples with '
'correlation distance metric. Select more genes or use Euclidean distance '
'metric.'.format(get_gene_names(list(expressions.index), args.source, args.species)[0]))
set_error(msg)
expressions = transform(expressions, log2=args.log2, z_score=args.z_score)
if args.remove_const:
expressions, matches = remove_const_samples(expressions)
if len(expressions.columns) == 0:
msg = ('All of the selected samples have constant expression across genes. Hierarchical '
'clustering of samples cannot be computed.')
set_error(msg)
if len(expressions.columns) == 1:
sample_name = [id for i, id in enumerate(args.sample_names) if matches[i]][0]
msg = ('Only one of the selected samples ({}) has a non-constant expression across '
'genes. However, hierarchical clustering of samples cannot be computed with '
'just one sample.'.format(sample_name))
set_error(msg)
removed = [name for i, name in enumerate(args.sample_names) if not matches[i]]
suffix = '' if len(removed) <= 3 else ', ...'
if removed:
msg = ('{} of the selected samples ({}) have constant expression across genes. '
'Those samples are excluded from the computation of hierarchical clustering of '
'samples with correlation distance '
'metric.'.format(len(removed), ', '.join(removed[:3]) + suffix))
print(warning(msg))
else:
matches = [True] * len(args.sample_files)
suffix = '' if len(excluded) <= 3 else ', ...'
if excluded:
excluded_names = get_gene_names(excluded[:3], args.source, args.species)
if len(excluded) == 1:
if not args.gene_labels:
msg = ('Gene {} is present in some but not all of the selected samples. This '
'gene is excluded from the computation of hierarchical clustering of '
'samples.'.format(len(excluded), ', '.join(excluded_names)))
else:
msg = ('{} of the selected genes ({}) is missing in at least one of the selected '
'samples. This gene is excluded from the computation of hierarchical '
'clustering of samples.'.format(len(excluded), ', '.join(excluded_names)))
print(warning(msg))
if len(excluded) > 1:
if not args.gene_labels:
msg = ('{} genes ({}) are present in some but not all of the selected samples. Those '
'genes are excluded from the computation of hierarchical clustering of '
'samples.'.format(len(excluded), ', '.join(excluded_names)))
else:
msg = ('{} of the selected genes ({}) are missing in at least one of the selected '
'samples. Those genes are excluded from the computation of hierarchical '
'clustering of samples.'.format(len(excluded), ', '.join(excluded_names)))
print(warning(msg))
linkage, dendrogram = get_clustering(
expressions,
distance_metric=get_distance_metric(args.distance_metric),
linkage_method=args.linkage_method,
order=args.order
)
sample_ids = [sample_id for i, sample_id in enumerate(args.sample_ids) if matches[i]]
result = {
'sample_ids': {i: {'id': sample_id} for i, sample_id in enumerate(sample_ids)},
'linkage': linkage.tolist(),
'order': dendrogram['leaves'],
}
output_json(result, args.output)