def cluster_count_matrix(config_file, lane_id, strain_fmt_string, cond_fmt_string):
config_params = cfp.parse(config_file)
sample_detection_limit, control_detection_limit = get_detection_limits(config_params)
# If the file does not exist, then do not attempt to cluster it!
try:
genes, conditions, matrix = load_dumped_count_matrix(config_params, lane_id)
except IOError:
print "could not find '{}' count matrix".format(lane_id)
return None
thresholded_matrix = matrix
thresholded_matrix[thresholded_matrix < sample_detection_limit] = sample_detection_limit
logged_matrix = np.log2(thresholded_matrix)
# Customize the strain and condition names for interpretable visualization!
custom_genes = customize_strains(genes, config_params, strain_fmt_string)
custom_conditions = customize_conditions(conditions, config_params, cond_fmt_string)
dataset = [custom_genes, custom_conditions, logged_matrix]
record, rows_tree, cols_tree = clus.cluster(dataset)
f = get_clustered_count_matrix_filename(config_params, lane_id)
record.save(f, rows_tree, cols_tree)
def cluster_zscore_matrix(config_file, lane_id, strain_fmt_string, cond_fmt_string):
config_params = cfp.parse(config_file)
# If the file does not exist, then do not attempt to cluster it!
try:
genes, conditions, matrix = load_dumped_zscore_matrix(config_params, lane_id)
except IOError:
print "could not find '{}' zscore matrix".format(lane_id)
return None
# Customize the strain and condition names for interpretable visualization!
strain_table = get_barcode_table(config_params)
sample_table = get_sample_table(config_params)
custom_genes = customize_strains(genes, strain_table, strain_fmt_string)
custom_conditions = customize_conditions(conditions, sample_table, cond_fmt_string)
dataset = [custom_genes, custom_conditions, matrix]
record, rows_tree, cols_tree = clus.cluster(dataset)
f = get_clustered_zscore_matrix_filename(config_params, lane_id)
record.save(f, rows_tree, cols_tree)
# return the filename so the cdt/atr/gtr files can be copied to a directory with all
# of the other clustergrams and eventually tarred/gzipped for distribution!
return f
def cluster_one_stacked_matrix(dataset, matrix_id, strain_table, sample_table, strain_fmt_string, cond_fmt_string, output_folder, new_matrix = None, verbosity = 1):
genes, conditions, matrix = dataset
custom_genes = customize_strains(genes, strain_table, strain_fmt_string, verbosity = verbosity)
custom_conditions = customize_conditions(conditions, sample_table, cond_fmt_string, verbosity = verbosity)
dataset = [custom_genes, custom_conditions, matrix]
f = os.path.join(output_folder, matrix_id)
record, rows_tree, cols_tree = clus.cluster(dataset, file_base = f, new_matrix = new_matrix)
record.save(f, rows_tree, cols_tree)
# return the filename so the cdt/atr/gtr files can be copied to a directory with all
# of the other clustergrams and eventually tarred/gzipped for distribution!
return f
