def grab_results_from_task(task_id, user, output_peptide_directory,
output_psm_directory, params_obj,
folder_for_results):
return_dict = {}
return_dict["number_psms"] = 0
return_dict["number_peptides"] = 0
return_dict["task_id"] = task_id
#Copying the psm files
path_to_psm_files_list = ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, folder_for_results)
if len(path_to_psm_files_list) == 1:
output_psm_path = os.path.join(output_psm_directory, task_id + ".psms")
path_to_param_file = ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "params")[0]
#These are original results that are from MSGF+ that includes the fragmentation method
print(
task_id, user,
ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "mergedResult"))
path_to_merged_results = ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "mergedResult")[0]
print(path_to_psm_files_list[0] + " to " + output_psm_path)
#name_demangle_filenames(path_to_psm_files_list[0], output_psm_path, path_to_param_file, "filename", "filename")
name_demangle_filenames_and_instrument_collision(
path_to_psm_files_list[0], output_psm_path, path_to_param_file,
path_to_merged_results, "filename", "filename")
#Now lets generate the peptide list from the psm list
psm_set = ming_psm_library.PSMset("task results")
psm_set.load_PSM_tsvfile(output_psm_path, True)
print("PSM Count", len(psm_set.psms))
psm_set.psms = filter_psms_with_params(params_obj, psm_set.psms)
#Setting the task of each psm
for psm in psm_set.psms:
psm.extra_metadata["proteosafe_task"] = task_id
print("PSM Count Filtered", len(psm_set.psms))
psm_set.filter_to_fdr_by_length(0.05)
output_pickle = open(output_psm_path, 'wb')
pickle.dump(psm_set, output_pickle, pickle.HIGHEST_PROTOCOL)
output_pickle.close()
output_peptide_path = output_psm_path = os.path.join(
output_peptide_directory, task_id + ".peptides")
peptide_variant_set = save_psms_as_peptides(psm_set,
output_peptide_path, 0.05)
return_dict["number_psms"] = len(psm_set.psms)
return_dict["number_peptides"] = len(peptide_variant_set.peptide_list)
return return_dict
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
def grab_single_result(task_id, output_peptide_directory,
output_psm_directory):
return_dict = {}
return_dict["number_psms"] = 0
return_dict["number_peptides"] = 0
return_dict["task_id"] = task_id
task_info = ming_proteosafe_library.get_task_information(
"proteomics2.ucsd.edu", task_id)
user = task_info["user"]
if task_info["status"] == "FAILED":
return return_dict
#lets check whether whether this has the peptide output, if not we can create it
path_to_secondpass_peptides_files_list = ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "updated_eval_psms_with_kl_with_ambiguity")
if len(path_to_secondpass_peptides_files_list) == 0:
return_dict = grab_results_from_MSGFDB(task_id, user,
output_peptide_directory,
output_psm_directory)
return return_dict
if len(path_to_secondpass_peptides_files_list) == 1:
return_dict = grab_results_from_multipass(task_id, user,
output_peptide_directory,
output_psm_directory)
return return_dict
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
def grab_results_from_multipass(task_id, user, output_peptide_directory,
output_psm_directory):
return_dict = {}
return_dict["number_psms"] = 0
return_dict["number_peptides"] = 0
return_dict["task_id"] = task_id
#Copying the psm files
path_to_psm_files_list = ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "updated_eval_psms_with_kl_with_ambiguity")
if len(path_to_psm_files_list) == 1:
output_psm_path = os.path.join(output_psm_directory, task_id + ".psms")
path_to_param_file = ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "params")[0]
#path_to_merged_results = ming_proteosafe_library.get_proteosafe_backend_result_file_path(task_id, "mergedResult", "proteomics2")[0]
print(
ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "mergedResult"))
path_to_merged_results = ming_proteosafe_library.get_proteosafe_result_file_path(
task_id, user, "mergedResult")[0]
print(path_to_psm_files_list[0] + " to " + output_psm_path)
#name_demangle_filenames(path_to_psm_files_list[0], output_psm_path, path_to_param_file, "filename", "filename")
name_demangle_filenames_and_instrument_collision(
path_to_psm_files_list[0], output_psm_path, path_to_param_file,
path_to_merged_results, "filename", "filename")
#Now lets generate the peptide list from the psm list
psm_set = ming_psm_library.PSMset("task results")
psm_set.load_PSM_tsvfile(output_psm_path)
output_peptide_path = output_psm_path = os.path.join(
output_peptide_directory, task_id + ".peptides")
peptide_variant_set = library_creation.create_library_unique_peptides_filtered(
[psm_set], 0.01)
peptide_variant_set.write_output(open(output_peptide_path, "w"))
return_dict["number_psms"] = len(psm_set.psms)
return_dict["number_peptides"] = len(peptide_variant_set.peptide_list)
return return_dict