def search_by_keywords_and_filters(self, keyword, query_filter, page_size, page, date_gap, sort_direction, sort_fields):
"""
search PRIDE API projects by keyword and filters
:param keyword: keyword to search projects
:param query_filter: Parameters to filter the search results
:param page_size: Number of results to fetch in a page
:param page: Identifies which page of results to fetch
:param date_gap: A date range field with possible values of +1MONTH, +1YEAR
:param sort_direction: Sorting direction: ASC or DESC
:param sort_fields: Field(s) for sorting the results on
:return: PRIDE projects in json format
"""
request_url = self.api_base_url + "search/projects?keyword=" + keyword + "&"
if query_filter:
request_url = request_url + "filter=" + query_filter + "&"
request_url = request_url + "pageSize=" + str(page_size) + "&page=" + str(page) + "&"
if date_gap != "":
request_url = request_url + "dateGap=" + str(date_gap) + "&"
request_url = request_url + "sortDirection=" + sort_direction + "&sortFields=" + sort_fields
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def protein_evidences(self, project_accession, assay_accession,
reported_accession, page_size, page, sort_direction,
sort_conditions):
"""
search protein_evidences from PRIDE API
:param project_accession: PRIDE accession
:param assay_accession: PRIDE assay accession
:param reported_accession: PRIDE reported accession
:param page_size: Number of results to fetch in a page
:param page: Identifies which page of results to fetch
:param sort_direction: Sorting direction: ASC or DESC
:param sort_conditions: Field(s) for sorting the results on
:return: return protein evidences in json format
"""
request_url = self.api_base_url + "proteinevidences?"
if project_accession:
request_url = request_url + "projectAccession=" + project_accession + "&"
if assay_accession:
request_url = request_url + "assayAccession=" + assay_accession + "&"
if reported_accession:
request_url = request_url + "reportedAccession=" + reported_accession + "&"
request_url = request_url + "pageSize=" + str(
page_size
) + "&page=" + str(
page
) + "&sortDirection=" + sort_direction + "&sortConditions=" + sort_conditions
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def update_msrun_metadata(self, filename, token):
"""
Updates the metadata extracted from the raw file into MongoDB database
:param filename: metadata json file
:param token: pride authentication token to access the api update method
:return: response
"""
# get project file accession from the prefix of the file name (e.g: PXF00000145820)
accession = filename.split('-', 1)[0]
url = self.base_url + "msruns/" + accession + "/updateMetadata"
headers = {
'Content-type': 'application/json',
'Accept': 'application/json',
'Authorization': 'Bearer ' + token
}
with open(filename) as json_file:
data = json.load(json_file)
logging.debug(json.dumps(data))
response = Util.update_api_call(url, headers, json.dumps(data))
return response
def get_all_paged_files(self, query_filter, page_size, page,
sort_direction, sort_conditions):
"""
Get all filtered pride submission files
:param query_filter: Parameters to filter the search results
:param page_size: Number of results to fetch in a page
:param page: Identifies which page of results to fetch
:param sort_direction: Sorting direction: ASC or DESC
:param sort_conditions: Field(s) for sorting the results on
:return: paged file list on JSON format
"""
"""
"""
request_url = self.api_base_url + "files?"
if query_filter:
request_url = request_url + "filter=" + query_filter + "&"
request_url = request_url + "pageSize=" + str(
page_size
) + "&page=" + str(
page
) + "&sortDirection=" + sort_direction + "&sortConditions=" + sort_conditions
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def get_reanalysis_projects_by_accession(self, accession):
"""
search PRIDE projects by reanalysis accession
:return: project list on JSON format
"""
request_url = self.api_base_url + "projects/reanalysis/" + accession
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def get_all_raw_file_list(self, project_accession):
"""
Get all the file list from PRIDE api in JSON format
:return: file list on JSON format
"""
request_url = self.api_base_url + "files/byProject?accession=" + project_accession + ",fileCategory.value==RAW"
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def get_projects(self, page_size, page, sort_direction, sort_conditions):
"""
get projects from PRIDE API in JSON format
:param page_size: Number of results to fetch in a page
:param page: Identifies which page of results to fetch
:param sort_direction: Sorting direction: ASC or DESC
:param sort_conditions: Field(s) for sorting the results on
:return: paged peptide_evidences in json format
"""
request_url = self.api_base_url + "projects?" + "pageSize=" + str(page_size) + "&page=" + str(page) + "&sortDirection=" + sort_direction + "&sortConditions=" + sort_conditions
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def get_similar_projects_by_accession(self, accession):
"""
Search similar projects by accession
:param accession: PRIDE accession
:return: similar PRIDE projects
"""
"""
search PRIDE project's files by accession
:return: file list on JSON format
"""
request_url = self.api_base_url + "projects/" + accession + "/files"
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def get_file_from_api(self, accession, file_name):
"""
Fetches file from API
:param accession: PRIDE accession
:param file_name: file name
:return: file in json format
"""
request_url = self.api_base_url + "files/byProject?accession=" + accession + ",fileName==" + file_name
headers = {"Accept": "application/JSON"}
try:
response = Util.get_api_call(request_url, headers)
return response.json()
except Exception as e:
raise Exception("File not found" + str(e))
def spectra_evidences(self, usi, project_accession, assay_accession,
peptide_sequence, modified_sequence, result_type,
page_size, page, sort_direction, sort_conditions):
"""
Search spectra evidences from PRIDE API
:param usi: USI
:param project_accession: PRIDE project accession
:param assay_accession: PRIDE assay accession
:param peptide_sequence: PRIDE peptide sequence
:param modified_sequence: modified sequence
:param result_type: result type
:param page_size: Number of results to fetch in a page
:param page: Identifies which page of results to fetch
:param sort_direction: Sorting direction: ASC or DESC
:param sort_conditions: Field(s) for sorting the results on
:return: spectra_evidences in JSON format
"""
request_url = self.api_base_url + "spectra?"
if usi:
usiArray = usi.split("\\n")
for usiElement in usiArray:
request_url = request_url + "usi=" + usiElement + "&"
if project_accession:
request_url = request_url + "projectAccession=" + project_accession + "&"
if assay_accession:
request_url = request_url + "assayAccession=" + assay_accession + "&"
if peptide_sequence:
request_url = request_url + "peptideSequence=" + peptide_sequence + "&"
if modified_sequence:
request_url = request_url + "modifiedSequence=" + modified_sequence + "&"
if result_type:
request_url = request_url + "resultType=" + result_type + "&"
request_url = request_url + "pageSize=" + str(
page_size
) + "&page=" + str(
page
) + "&sortDirection=" + sort_direction + "&sortConditions=" + sort_conditions
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def get_files_by_accession(self, accession, query_filter, page_size, page, sort_direction, sort_conditions):
"""
search PRIDE project's files by accession
:param accession: PRIDE project accession
:param query_filter: Parameters to filter the search results
:param page_size: Number of results to fetch in a page
:param page: Identifies which page of results to fetch
:param sort_direction: Sorting direction: ASC or DESC
:param sort_conditions: Field(s) for sorting the results on
:return: PRIDE project files
"""
request_url = self.api_base_url + "projects/" + accession + "/files?"
if query_filter:
request_url = request_url + "filter=" + query_filter + "&"
request_url = request_url + "pageSize=" + str(page_size) + "&page=" + str(page) + "&sortDirection=" + sort_direction + "&sortConditions=" + sort_conditions
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
return response.json()
def plot_monthly_submissions(output_filename):
"""
Plot monthly submission as a bar chart and save into a file
:param output_filename: html output file
:return:
"""
# get monthly submission data from API
request_url = base_url + "stats/submissions-monthly"
headers = {"Accept": "application/JSON"}
response = Util.get_api_call(request_url, headers)
response_body = response.json()
# sort data by past to present
data = [
go.Bar(x=[d[0] for d in response_body][::-1],
y=[d[1] for d in response_body][::-1])
]
# plot the data in a bar chart
plotly.offline.plot(data, filename=output_filename, auto_open=True)