def create_bucket_from_clusterinfo(cluster_info_filename, param_filename,
clusterinfosummary_filename,
output_filename):
param_object = ming_proteosafe_library.parse_xml_file(
open(param_filename, "r"))
output_file = open(output_filename, "w")
if param_object["CREATE_CLUSTER_BUCKETS"][0] != "1":
output_file.write("No Output")
return
test_network = molecular_network_library.MolecularNetwork()
test_network.load_clustersummary(clusterinfosummary_filename)
line_counts, table_data = ming_fileio_library.parse_table_with_headers(
cluster_info_filename)
mangled_mapping = ming_proteosafe_library.get_mangled_file_mapping(
param_object)
cluster_index_to_file_map = {}
clusters_map = {}
all_files = {}
for i in range(line_counts):
cluster_number = table_data["#ClusterIdx"][i]
if test_network.get_cluster_index(cluster_number) == None:
continue
if not (cluster_number in clusters_map):
clusters_map[cluster_number] = []
cluster_index_to_file_map[cluster_number] = {}
#Adding all file names to mapping
for mangled_name in mangled_mapping.keys():
cluster_index_to_file_map[cluster_number][mangled_name] = 0.0
#print table_data["#Filename"][i].split("/")[1]
mangled_filename_only = os.path.basename(table_data["#Filename"][i])
cluster_index_to_file_map[cluster_number][
mangled_filename_only] += float(table_data["#PrecIntensity"][i])
spectrum_info = {
"filename": table_data["#Filename"][i],
"intensity": table_data["#PrecIntensity"][i]
}
all_files[table_data["#Filename"][i]] = 1
clusters_map[cluster_number].append(spectrum_info)
output_header = "#OTU ID\t"
for header in mangled_mapping.keys():
output_header += os.path.basename(mangled_mapping[header]) + "\t"
output_file.write(output_header + "\n")
for cluster_idx in cluster_index_to_file_map:
line_string = str(cluster_idx) + "\t"
for header in mangled_mapping.keys():
line_string += str(
cluster_index_to_file_map[cluster_idx][header]) + "\t"
#print line_string
output_file.write(line_string + "\n")
def create_ili_output_from_clusterinfo(cluster_info_filename, param_filename, clusterinfosummary_filename, filename_coordinate_mapping, output_filename):
output_file = open(output_filename, "w")
test_network = molecular_network_library.MolecularNetwork()
test_network.load_clustersummary(clusterinfosummary_filename)
line_counts, table_data = ming_fileio_library.parse_table_with_headers(cluster_info_filename)
param_object = ming_proteosafe_library.parse_xml_file(open(param_filename, "r"))
mangled_mapping = ming_proteosafe_library.get_mangled_file_mapping(param_object)
cluster_index_to_file_map = {}
clusters_map = {}
all_files = {}
for i in range(line_counts):
cluster_number = table_data["#ClusterIdx"][i]
if test_network.get_cluster_index(cluster_number) == None:
continue
if not (cluster_number in clusters_map):
clusters_map[cluster_number] = []
cluster_index_to_file_map[cluster_number] = {}
#Adding all file names to mapping
for mangled_name in mangled_mapping.keys():
cluster_index_to_file_map[cluster_number][mangled_name] = 0.0
#print table_data["#Filename"][i].split("/")[1]
mangled_filename_only = os.path.basename(table_data["#Filename"][i])
cluster_index_to_file_map[cluster_number][mangled_filename_only] += float(table_data["#PrecIntensity"][i])
spectrum_info = {"filename":table_data["#Filename"][i], "intensity": table_data["#PrecIntensity"][i]}
all_files[table_data["#Filename"][i]] = 1
clusters_map[cluster_number].append(spectrum_info)
all_headers = ["filename", "X", "Y", "Z", "radius"]
for cluster_idx in cluster_index_to_file_map:
all_headers.append(cluster_idx)
#writing header
output_file.write(",".join(all_headers) + "\n")
for sample_name in mangled_mapping:
if sample_name.find("spec") == -1:
continue
real_filename = mangled_mapping[sample_name]
if not os.path.basename(real_filename) in filename_coordinate_mapping:
continue
line_output = [real_filename]
coordinate_object = filename_coordinate_mapping[os.path.basename(real_filename)]
line_output.append(coordinate_object["x"])
line_output.append(coordinate_object["y"])
line_output.append(coordinate_object["z"])
line_output.append(coordinate_object["radius"])
print(line_output, coordinate_object)
for cluster_idx in cluster_index_to_file_map:
line_output.append(str(cluster_index_to_file_map[cluster_idx][sample_name]))
output_file.write(",".join(line_output) + "\n")
output_file.close()
def get_molecular_network_obj(job_obj):
try:
print(job_obj)
path_to_clusterinfosummary = ming_proteosafe_library.get_proteosafe_result_file_path(
job_obj["task"], "continuous",
"clusterinfosummarygroup_attributes_withIDs")[0]
path_to_pairs = ming_proteosafe_library.get_proteosafe_result_file_path(
job_obj["task"], "continuous", "networkedges_selfloop")[0]
molecular_network = molecular_network_library.MolecularNetwork()
molecular_network.load_network(path_to_clusterinfosummary,
path_to_pairs)
return molecular_network
except KeyboardInterrupt:
raise
except:
#raise
return None