def to_biom( clusters_file, count_file, output_biom, size_separator ):
"""
@summary : Write a biom file from swarm results.
@param clusters_file : [str] path to the '.clstr' file.
@param count_file : [str] path to the count file. It contains the count of
sequences by sample of each preclusters.
Line format : "Precluster_id nb_in_sampleA nb_in_sampleB"
@param output_biom : [str] path to the output file.
@param size_separator : [str] the pre-cluster abundance separator.
"""
biom = Biom( generated_by='swarm', matrix_type="sparse" )
# Preclusters count by sample
preclusters_count = dict()
count_fh = open( count_file )
samples = count_fh.readline().strip().split()[1:]
for line in count_fh:
precluster_id, count_str = line.strip().split(None, 1)
preclusters_count[precluster_id] = count_str # For large dataset store count into a string consumes minus RAM than a sparse count
count_fh.close()
# Add samples
for sample_name in samples:
biom.add_sample( sample_name )
# Process count
cluster_idx = 1
clusters_fh = open( clusters_file )
for line in clusters_fh:
seed_id = line.strip().split()[0]
if "FROGS_combined" in seed_id:
cluster_name = "Cluster_" + str(cluster_idx) + "_FROGS_combined"
comment = "WARNING"
else:
cluster_name = "Cluster_" + str(cluster_idx)
comment = "na"
cluster_count = {key:0 for key in samples}
line_fields = line.strip().split()
# Retrieve count by sample
for seq_id in line_fields:
real_seq_id = seq_id.rsplit(size_separator, 1)[0]
sample_counts = preclusters_count[real_seq_id].split()
for sample_idx, sample_name in enumerate(samples):
cluster_count[sample_name] += int(sample_counts[sample_idx])
preclusters_count[real_seq_id] = None
# Add cluster on biom
biom.add_observation( cluster_name, {'comment': comment, 'seed_id':line_fields[0].rsplit(size_separator, 1)[0]} )
observation_idx = biom.find_idx("observation", cluster_name)
for sample_idx, sample_name in enumerate(samples):
if cluster_count[sample_name] > 0:
biom.data.change( observation_idx, sample_idx, cluster_count[sample_name] )
# Next cluster
cluster_idx += 1
# Write
BiomIO.write( output_biom, biom )
def to_biom( clusters_file, count_file, output_biom, size_separator ):
"""
@summary : Write a biom file from swarm results.
@param clusters_file : [str] path to the '.clstr' file.
@param count_file : [str] path to the count file. It contains the count of
sequences by sample of each preclusters.
Line format : "Precluster_id nb_in_sampleA nb_in_sampleB"
@param output_biom : [str] path to the output file.
@param size_separator : [str] the pre-cluster abundance separator.
"""
biom = Biom( generated_by='swarm', matrix_type="sparse" )
# Preclusters count by sample
preclusters_count = dict()
count_fh = open( count_file )
samples = count_fh.readline().strip().split()[1:]
for line in count_fh:
precluster_id, count_str = line.strip().split(None, 1)
preclusters_count[precluster_id] = count_str # For large dataset store count into a string consumes minus RAM than a sparse count
count_fh.close()
# Add samples
for sample_name in samples:
biom.add_sample( sample_name )
# Process count
cluster_idx = 1
clusters_fh = open( clusters_file )
for line in clusters_fh:
cluster_name = "Cluster_" + str(cluster_idx)
cluster_count = {key:0 for key in samples}
line_fields = line.strip().split()
# Retrieve count by sample
for seq_id in line_fields:
real_seq_id = seq_id.rsplit(size_separator, 1)[0]
sample_counts = preclusters_count[real_seq_id].split()
for sample_idx, sample_name in enumerate(samples):
cluster_count[sample_name] += int(sample_counts[sample_idx])
preclusters_count[real_seq_id] = None
# Add cluster on biom
biom.add_observation( cluster_name, {'seed_id':line_fields[0].rsplit(size_separator, 1)[0]} )
observation_idx = biom.find_idx("observation", cluster_name)
for sample_idx, sample_name in enumerate(samples):
if cluster_count[sample_name] > 0:
biom.data.change( observation_idx, sample_idx, cluster_count[sample_name] )
# Next cluster
cluster_idx += 1
# Write
BiomIO.write( output_biom, biom )
