def find_matches_in_dataset(dataset_id, input_spectrum_collection):
dataset_match_list = []
path_to_clustered_mgf = os.path.join(PATH_TO_DATASET_UPLOADS, dataset_id,
"clustered",
dataset_id + "_specs_ms.mgf")
relative_user_path_to_clustered = os.path.join(
dataset_id, "clustered", dataset_id + "_specs_ms.mgf")
if not ming_fileio_library.is_path_present(path_to_clustered_mgf):
return dataset_match_list
#Lets compare these two files
# input_spectra_filename and symlink_destination
dataset_clustered_spectra = ming_spectrum_library.SpectrumCollection(
path_to_clustered_mgf)
dataset_clustered_spectra.load_from_file()
for myspectrum in input_spectrum_collection.spectrum_list:
match_list = dataset_clustered_spectra.search_spectrum(
myspectrum, 1.0, 1.0, 6, 0.7, 1)
for match in match_list:
match.filename = relative_user_path_to_clustered
dataset_match_list += match_list
print "Dataset matches: " + str(len(dataset_match_list))
return dataset_match_list
def get_proteosafe_result_file_path(task_id, username, source_folder_name):
proteosafe_data_path = "/data/ccms-data/tasks/"
source_folder_path = os.path.join(proteosafe_data_path, username, task_id, source_folder_name)
if not ming_fileio_library.is_path_present(source_folder_path):
return []
source_files = ming_fileio_library.list_files_in_dir(source_folder_path)
return source_files
def get_proteosafe_result_file_path(task_id, username, source_folder_name):
proteosafe_data_path = "/data/ccms-data/tasks/"
source_folder_path = os.path.join(proteosafe_data_path, username, task_id, source_folder_name)
if not ming_fileio_library.is_path_present(source_folder_path):
return []
source_files = ming_fileio_library.list_files_in_dir(source_folder_path)
return source_files
def get_proteosafe_backend_result_file_path(task_id, source_folder_name, site):
proteosafe_data_path = "/data/"
if site == "proteomics2":
proteosafe_data_path += "beta-proteomics2"
source_folder_path = os.path.join(proteosafe_data_path, "tasks", task_id, source_folder_name)
if not ming_fileio_library.is_path_present(source_folder_path):
return []
source_files = ming_fileio_library.list_files_in_dir(source_folder_path)
return source_files
def get_proteosafe_backend_result_file_path(task_id, source_folder_name, site):
proteosafe_data_path = "/data/"
if site == "proteomics2":
proteosafe_data_path += "beta-proteomics2"
source_folder_path = os.path.join(proteosafe_data_path, "tasks", task_id, source_folder_name)
if not ming_fileio_library.is_path_present(source_folder_path):
return []
source_files = ming_fileio_library.list_files_in_dir(source_folder_path)
return source_files
def find_matches_in_file(input_spectrum_collection,
dataset_filepath,
relative_dataset_filepath,
match_parameters,
top_k=1):
dataset_match_list = []
if not ming_fileio_library.is_path_present(dataset_filepath):
print("Cant find", dataset_filepath)
return dataset_match_list
dataset_query_spectra = ming_spectrum_library.SpectrumCollection(
dataset_filepath)
try:
dataset_query_spectra.load_from_file()
except:
return dataset_match_list
for repo_spectrum in dataset_query_spectra.spectrum_list:
if match_parameters["FILTER_WINDOW"]:
repo_spectrum.window_filter_peaks(50, 6)
if match_parameters["FILTER_PRECURSOR"]:
repo_spectrum.filter_precursor_peaks()
for myspectrum in input_spectrum_collection.spectrum_list:
if match_parameters["FILTER_WINDOW"]:
myspectrum.window_filter_peaks(50, 6)
if match_parameters["FILTER_PRECURSOR"]:
myspectrum.filter_precursor_peaks()
try:
match_list = dataset_query_spectra.search_spectrum(
myspectrum,
match_parameters["PM_TOLERANCE"],
match_parameters["FRAGMENT_TOLERANCE"],
match_parameters["MIN_MATCHED_PEAKS"],
match_parameters["MIN_COSINE"],
analog_search=match_parameters["ANALOG_SEARCH"],
top_k=top_k)
for match in match_list:
match["filename"] = relative_dataset_filepath
dataset_match_list += match_list
except:
print("Error in Matching")
print("Dataset matches: " + str(len(dataset_match_list)))
return dataset_match_list
def find_matches_in_dataset(dataset_id, input_spectrum_collection):
dataset_match_list = []
path_to_clustered_mgf = os.path.join(PATH_TO_DATASET_UPLOADS, dataset_id, "clustered", dataset_id + "_specs_ms.mgf")
relative_user_path_to_clustered = os.path.join(dataset_id, "clustered", dataset_id + "_specs_ms.mgf")
if not ming_fileio_library.is_path_present(path_to_clustered_mgf):
return dataset_match_list
#Lets compare these two files
# input_spectra_filename and symlink_destination
dataset_clustered_spectra = ming_spectrum_library.SpectrumCollection(path_to_clustered_mgf)
dataset_clustered_spectra.load_from_file()
for myspectrum in input_spectrum_collection.spectrum_list:
match_list = dataset_clustered_spectra.search_spectrum(myspectrum, 1.0, 1.0, 6, 0.7, 1)
for match in match_list:
match.filename = relative_user_path_to_clustered
dataset_match_list += match_list
print "Dataset matches: " + str(len(dataset_match_list))
return dataset_match_list
