def parsed_panel(request, panel_info): """docstring for parsed_panels""" panel = parse_gene_panel(path=panel_info['file'], institute=panel_info['institute'], panel_id=panel_info['panel_name'], panel_type=panel_info['type'], date=panel_info['date'], version=panel_info['version'], display_name=panel_info['full_name']) return panel
def parsed_panel(request, panel_info): """docstring for parsed_panels""" panel = parse_gene_panel( path=panel_info["file"], institute=panel_info["institute"], panel_id=panel_info["panel_name"], panel_type=panel_info["type"], date=panel_info["date"], version=panel_info["version"], display_name=panel_info["full_name"], ) return panel
def test_get_full_list_panel(panel_info): panel_1_file = panel_info['file'] nr_genes = 0 with open(panel_1_file, 'r') as f: for line in f: if not line.startswith('#'): nr_genes += 1 panel = parse_gene_panel(panel_info) assert panel['panel_name'] == panel_info['panel_name'] assert len(panel['genes']) == nr_genes assert panel['date'] == panel_info['date'] assert panel['institute'] == panel_info['institute']
def load_panel(adapter, panel_info): """Load a gene panel into the databse Args: adapter(MongoAdapter) panel_info(dict) """ panel_data = parse_gene_panel(panel_info) panel_obj = build_panel(panel_data, adapter) # Check if the panel exists in database panel = adapter.gene_panel(panel_obj['panel_name'], panel_obj['version']) if not panel: adapter.add_gene_panel(panel_obj) else: logger.info("Panel {} version {} already exists".format(panel_obj['panel_name'], panel_obj['version']))
def load_panel(self, path, institute, panel_id, date, panel_type='clinical', version=1.0, display_name=None): """Load a gene panel based on the info sent The panel info is first parsed, then a panel object is built and integrity checks are made. The panel object is then loaded into the database. Args: path(str): Path to panel file institute(str): Name of institute that owns the panel panel_id(str): Panel id date(datetime.datetime): Date of creation version(float) full_name(str): Option to have a long name panel_info(dict): { 'file': <path to panel file>(str), 'institute': <institute>(str), 'type': <panel type>(str), 'date': date, 'version': version, 'panel_name': panel_id, 'full_name': name, } """ panel_data = parse_gene_panel( path=path, institute=institute, panel_type=panel_type, date=date, version=version, panel_id=panel_id, display_name=display_name, ) panel_obj = build_panel(panel_data, self) self.add_gene_panel(panel_obj)
def test_get_full_list_panel(panel_info): panel_1_file = panel_info['file'] nr_genes = 0 with open(panel_1_file, 'r') as f: for line in f: if not line.startswith('#'): nr_genes += 1 panel = parse_gene_panel(path=panel_info['file'], institute=panel_info['institute'], panel_id=panel_info['panel_name'], panel_type=panel_info['type'], date=panel_info['date'], version=panel_info['version'], display_name=panel_info['full_name']) assert panel['panel_id'] == panel_info['panel_name'] assert len(panel['genes']) == nr_genes assert panel['date'] == panel_info['date'] assert panel['institute'] == panel_info['institute']
def test_get_full_list_panel(panel_info): panel_1_file = panel_info["file"] nr_genes = 0 with open(panel_1_file, "r") as f: for line in f: if not line.startswith("#"): nr_genes += 1 panel = parse_gene_panel( path=panel_info["file"], institute=panel_info["institute"], panel_id=panel_info["panel_name"], panel_type=panel_info["type"], date=panel_info["date"], version=panel_info["version"], display_name=panel_info["full_name"], ) assert panel["panel_id"] == panel_info["panel_name"] assert len(panel["genes"]) == nr_genes assert panel["date"] == panel_info["date"] assert panel["institute"] == panel_info["institute"]
def test_get_full_list_panel(panel_info): panel_1_file = panel_info['file'] nr_genes = 0 with open(panel_1_file, 'r') as f: for line in f: if not line.startswith('#'): nr_genes += 1 panel = parse_gene_panel( path=panel_info['file'], institute=panel_info['institute'], panel_id=panel_info['panel_name'], panel_type=panel_info['type'], date=panel_info['date'], version=panel_info['version'], display_name=panel_info['full_name'] ) assert panel['panel_id'] == panel_info['panel_name'] assert len(panel['genes']) == nr_genes assert panel['date'] == panel_info['date'] assert panel['institute'] == panel_info['institute']
def setup_scout( adapter, institute_id="cust000", user_name="Clark Kent", user_mail="*****@*****.**", api_key=None, demo=False, resource_files=None, ): """Function to setup a working scout instance. WARNING: If the instance is populated all collections will be deleted Build insert a institute and an admin user. There are multiple sources of information that is used by scout and that needs to exist for scout to work proper. Genes: Scout uses HGNC as the source for gene identifiers en ensembl as source for coordinates. Additional information of disease connections for genes if fetched from OMIM. Link between hpo terms and genes is fetched from HPO For more details check the documentation. """ LOG.info("Check if there was a database, delete if existing") existing_database = False for collection_name in adapter.db.list_collection_names(): if collection_name.startswith("system"): continue LOG.info("Deleting collection %s", collection_name) adapter.db.drop_collection(collection_name) existing_database = True if existing_database: LOG.info("Database deleted") institute_obj = build_institute( internal_id=institute_id, display_name=institute_id, sanger_recipients=[user_mail], ) adapter.add_institute(institute_obj) user_obj = dict( _id=user_mail, email=user_mail, name=user_name, roles=["admin"], institutes=[institute_id], ) adapter.add_user(user_obj) resource_files = resource_files or {} if demo: resource_files = demo_files mim2gene_lines = None genemap_lines = None mim2gene_path = resource_files.get("mim2gene_path") genemap_path = resource_files.get("genemap_path") if genemap_path and mim2gene_path: mim2gene_lines = [line for line in get_file_handle(mim2gene_path)] genemap_lines = [line for line in get_file_handle(genemap_path)] if (genemap_lines is None) and api_key: try: mim_files = fetch_mim_files(api_key, mim2genes=True, genemap2=True) except Exception as err: LOG.warning(err) raise err mim2gene_lines = mim_files["mim2genes"] genemap_lines = mim_files["genemap2"] if resource_files.get("hpogenes_path"): hpo_gene_lines = [ line for line in get_file_handle(resource_files.get("hpogenes_path")) ] else: hpo_gene_lines = fetch_genes_to_hpo_to_disease() if resource_files.get("hgnc_path"): hgnc_lines = [ line for line in get_file_handle(resource_files.get("hgnc_path")) ] else: hgnc_lines = fetch_hgnc() if resource_files.get("exac_path"): exac_lines = [ line for line in get_file_handle(resource_files.get("exac_path")) ] else: exac_lines = fetch_exac_constraint() # Load cytobands into cytoband collection for genome_build, cytobands_path in cytoband_files.items(): load_cytobands(cytobands_path, genome_build, adapter) builds = ["37", "38"] for build in builds: genes_path = "genes{}_path".format(build) if resource_files.get(genes_path): ensembl_genes = get_file_handle(resource_files[genes_path]) else: ensembl_genes = fetch_ensembl_genes(build=build) hgnc_genes = load_hgnc_genes( adapter=adapter, ensembl_lines=ensembl_genes, hgnc_lines=hgnc_lines, exac_lines=exac_lines, mim2gene_lines=mim2gene_lines, genemap_lines=genemap_lines, hpo_lines=hpo_gene_lines, build=build, ) # Create a map from ensembl ids to gene objects ensembl_genes = {} for gene_obj in hgnc_genes: ensembl_id = gene_obj["ensembl_id"] ensembl_genes[ensembl_id] = gene_obj tx_path = "transcripts{}_path".format(build) if resource_files.get(tx_path): ensembl_transcripts = get_file_handle(resource_files[tx_path]) else: ensembl_transcripts = fetch_ensembl_transcripts(build=build) # Load the transcripts for a certain build transcripts = load_transcripts(adapter, ensembl_transcripts, build, ensembl_genes) hpo_terms_handle = None if resource_files.get("hpoterms_path"): hpo_terms_handle = get_file_handle(resource_files["hpoterms_path"]) hpo_to_genes_handle = None if resource_files.get("hpo_to_genes_path"): hpo_to_genes_handle = get_file_handle( resource_files["hpo_to_genes_path"]) hpo_disease_handle = None if resource_files.get("hpo_disease_path"): hpo_disease_handle = get_file_handle( resource_files["hpo_disease_path"]) load_hpo( adapter=adapter, disease_lines=genemap_lines, hpo_lines=hpo_terms_handle, hpo_gene_lines=hpo_to_genes_handle, ) # If demo we load a gene panel and some case information if demo: parsed_panel = parse_gene_panel( path=panel_path, institute="cust000", panel_id="panel1", version=1.0, display_name="Test panel", ) adapter.load_panel(parsed_panel) case_handle = get_file_handle(load_path) case_data = yaml.load(case_handle, Loader=yaml.FullLoader) config_data = parse_case_data(config=case_data) adapter.load_case(config_data) LOG.info("Creating indexes") adapter.load_indexes() LOG.info("Scout instance setup successful")
def setup_scout(adapter, institute_id='cust000', user_name='Clark Kent', user_mail='*****@*****.**', api_key=None, demo=False): """docstring for setup_scout""" ########################## Delete previous information ########################## LOG.info("Deleting previous database") for collection_name in adapter.db.collection_names(): if not collection_name.startswith('system'): LOG.info("Deleting collection %s", collection_name) adapter.db.drop_collection(collection_name) LOG.info("Database deleted") ########################## Add a institute ########################## ##################################################################### # Build a institute with id institute_name institute_obj = build_institute(internal_id=institute_id, display_name=institute_id, sanger_recipients=[user_mail]) # Add the institute to database adapter.add_institute(institute_obj) ########################## Add a User ############################### ##################################################################### # Build a user obj user_obj = dict(_id=user_mail, email=user_mail, name=user_name, roles=['admin'], institutes=[institute_id]) adapter.add_user(user_obj) ### Get the mim information ### if not demo: # Fetch the mim files try: mim_files = fetch_mim_files(api_key, mim2genes=True, morbidmap=True, genemap2=True) except Exception as err: LOG.warning(err) context.abort() mim2gene_lines = mim_files['mim2genes'] genemap_lines = mim_files['genemap2'] # Fetch the genes to hpo information hpo_gene_lines = fetch_hpo_genes() # Fetch the latest version of the hgnc information hgnc_lines = fetch_hgnc() # Fetch the latest exac pli score information exac_lines = fetch_exac_constraint() else: mim2gene_lines = [ line for line in get_file_handle(mim2gene_reduced_path) ] genemap_lines = [ line for line in get_file_handle(genemap2_reduced_path) ] # Fetch the genes to hpo information hpo_gene_lines = [ line for line in get_file_handle(hpogenes_reduced_path) ] # Fetch the reduced hgnc information hgnc_lines = [line for line in get_file_handle(hgnc_reduced_path)] # Fetch the latest exac pli score information exac_lines = [line for line in get_file_handle(exac_reduced_path)] builds = ['37', '38'] ################## Load Genes and transcripts ####################### ##################################################################### for build in builds: # Fetch the ensembl information if not demo: ensembl_genes = fetch_ensembl_genes(build=build) else: ensembl_genes = get_file_handle(genes37_reduced_path) # load the genes hgnc_genes = load_hgnc_genes( adapter=adapter, ensembl_lines=ensembl_genes, hgnc_lines=hgnc_lines, exac_lines=exac_lines, mim2gene_lines=mim2gene_lines, genemap_lines=genemap_lines, hpo_lines=hpo_gene_lines, build=build, ) # Create a map from ensembl ids to gene objects ensembl_genes = {} for gene_obj in hgnc_genes: ensembl_id = gene_obj['ensembl_id'] ensembl_genes[ensembl_id] = gene_obj # Fetch the transcripts from ensembl if not demo: ensembl_transcripts = fetch_ensembl_transcripts(build=build) else: ensembl_transcripts = get_file_handle(transcripts37_reduced_path) # Load the transcripts for a certain build transcripts = load_transcripts(adapter, ensembl_transcripts, build, ensembl_genes) hpo_terms_handle = None hpo_to_genes_handle = None hpo_disease_handle = None if demo: hpo_terms_handle = get_file_handle(hpoterms_reduced_path) hpo_to_genes_handle = get_file_handle(hpo_to_genes_reduced_path) hpo_disease_handle = get_file_handle( hpo_phenotype_to_terms_reduced_path) load_hpo(adapter=adapter, hpo_lines=hpo_terms_handle, hpo_gene_lines=hpo_to_genes_handle, disease_lines=genemap_lines, hpo_disease_lines=hpo_disease_handle) # If demo we load a gene panel and some case information if demo: parsed_panel = parse_gene_panel(path=panel_path, institute='cust000', panel_id='panel1', version=1.0, display_name='Test panel') adapter.load_panel(parsed_panel) case_handle = get_file_handle(load_path) case_data = yaml.load(case_handle) adapter.load_case(case_data) LOG.info("Creating indexes") adapter.load_indexes() LOG.info("Scout instance setup successful")
def load_panel( panel_path, adapter, date=None, display_name=None, version=None, panel_type=None, panel_id=None, institute=None, ): """Load a manually curated gene panel into scout Args: panel_path(str): path to gene panel file adapter(scout.adapter.MongoAdapter) date(str): date of gene panel on format 2017-12-24 display_name(str) version(float) panel_type(str) panel_id(str) institute(str) """ panel_lines = get_file_handle(panel_path) try: # This will parse panel metadata if includeed in panel file panel_info = get_panel_info( panel_lines=panel_lines, panel_id=panel_id, institute=institute, version=version, date=date, display_name=display_name, ) except Exception as err: raise err version = None if panel_info.get("version"): version = float(panel_info["version"]) panel_id = panel_info["panel_id"] display_name = panel_info["display_name"] or panel_id institute = panel_info["institute"] date = panel_info["date"] if not institute: raise SyntaxError("A Panel has to belong to a institute") # Check if institute exists in database if not adapter.institute(institute): raise SyntaxError("Institute {0} does not exist in database".format(institute)) if not panel_id: raise SyntaxError("A Panel has to have a panel id") if version: existing_panel = adapter.gene_panel(panel_id, version) else: ## Assuming version 1.0 existing_panel = adapter.gene_panel(panel_id) version = 1.0 LOG.info("Set version to %s", version) if existing_panel: LOG.info("found existing panel") if version == existing_panel["version"]: LOG.warning("Panel with same version exists in database") LOG.info("Reload with updated version") raise SyntaxError() display_name = display_name or existing_panel["display_name"] institute = institute or existing_panel["institute"] parsed_panel = parse_gene_panel( path=panel_path, institute=institute, panel_type=panel_type, date=date, version=version, panel_id=panel_id, display_name=display_name, ) try: adapter.load_panel(parsed_panel=parsed_panel) except Exception as err: raise err
def demo(context): """Setup a scout demo instance. This instance will be populated with a case a gene panel and some variants. """ log.info("Running scout setup demo") institute_name = context.obj['institute_name'] user_name = context.obj['user_name'] user_mail = context.obj['user_mail'] adapter = context.obj['adapter'] log.info("Setting up database %s", context.obj['mongodb']) log.info("Deleting previous database") for collection_name in adapter.db.collection_names(): log.info("Deleting collection %s", collection_name) adapter.db.drop_collection(collection_name) log.info("Database deleted") # Build a institute with id institute_name institute_obj = build_institute( internal_id=institute_name, display_name=institute_name, sanger_recipients=[user_mail] ) # Add the institute to database adapter.add_institute(institute_obj) # Build a user obj user_obj = dict( _id=user_mail, email=user_mail, name=user_name, roles=['admin'], institutes=[institute_name] ) adapter.add_user(user_obj) # Load the genes and transcripts hgnc_handle = context.obj['hgnc'] transcripts37_handle = context.obj['transcripts37'] # transcripts38_handle = context.obj['transcripts38'] exac_handle = context.obj['exac'] hpo_genes_handle = context.obj['hpogenes'] mim2gene_handle = context.obj['mim2gene'] genemap_handle = context.obj['genemap2'] genes37 = link_genes( ensembl_lines=transcripts37_handle, hgnc_lines=hgnc_handle, exac_lines=exac_handle, mim2gene_lines=mim2gene_handle, genemap_lines=genemap_handle, hpo_lines=hpo_genes_handle, ) load_hgnc_genes(adapter, genes37, build='37') hpo_terms_handle = context.obj['hpo_terms'] disease_handle = context.obj['disease_terms'] hpo_disease_handle = context.obj['hpodiseases'] load_hpo( adapter=adapter, hpo_lines=hpo_terms_handle, disease_lines=disease_handle, hpo_disease_lines=hpo_disease_handle ) panel_info = { 'date': datetime.datetime.now(), 'file': panel_path, 'type': 'clinical', 'institute': 'cust000', 'version': '1.0', 'panel_name': 'panel1', 'full_name': 'Test panel' } parsed_panel = parse_gene_panel(panel_info) panel_obj = build_panel(parsed_panel, adapter) load_panel( adapter=adapter, panel_info=panel_info ) case_handle = get_file_handle(load_path) case_data = yaml.load(case_handle) case_data['vcf_snv'] = clinical_snv_path case_data['vcf_sv'] = clinical_sv_path case_data['vcf_snv_research'] = research_snv_path case_data['vcf_sv_research'] = research_sv_path case_data['madeline'] = madeline_path load_scout(adapter, case_data) log.info("Creating indexes") adapter.hgnc_collection.create_index([('build', pymongo.ASCENDING), ('chromosome', pymongo.ASCENDING)]) log.info("hgnc gene index created") log.info("Scout demo instance setup successful")
def setup_scout(adapter, institute_id='cust000', user_name='Clark Kent', user_mail='*****@*****.**', api_key=None, demo=False): """docstring for setup_scout""" ########################## Delete previous information ########################## LOG.info("Deleting previous database") for collection_name in adapter.db.collection_names(): if not collection_name.startswith('system'): LOG.info("Deleting collection %s", collection_name) adapter.db.drop_collection(collection_name) LOG.info("Database deleted") ########################## Add a institute ########################## ##################################################################### # Build a institute with id institute_name institute_obj = build_institute( internal_id=institute_id, display_name=institute_id, sanger_recipients=[user_mail] ) # Add the institute to database adapter.add_institute(institute_obj) ########################## Add a User ############################### ##################################################################### # Build a user obj user_obj = dict( _id=user_mail, email=user_mail, name=user_name, roles=['admin'], institutes=[institute_id] ) adapter.add_user(user_obj) ### Get the mim information ### if not demo: # Fetch the mim files try: mim_files = fetch_mim_files(api_key, mim2genes=True, morbidmap=True, genemap2=True) except Exception as err: LOG.warning(err) raise err mim2gene_lines = mim_files['mim2genes'] genemap_lines = mim_files['genemap2'] # Fetch the genes to hpo information hpo_gene_lines = fetch_hpo_genes() # Fetch the latest version of the hgnc information hgnc_lines = fetch_hgnc() # Fetch the latest exac pli score information exac_lines = fetch_exac_constraint() else: mim2gene_lines = [line for line in get_file_handle(mim2gene_reduced_path)] genemap_lines = [line for line in get_file_handle(genemap2_reduced_path)] # Fetch the genes to hpo information hpo_gene_lines = [line for line in get_file_handle(hpogenes_reduced_path)] # Fetch the reduced hgnc information hgnc_lines = [line for line in get_file_handle(hgnc_reduced_path)] # Fetch the latest exac pli score information exac_lines = [line for line in get_file_handle(exac_reduced_path)] builds = ['37', '38'] ################## Load Genes and transcripts ####################### ##################################################################### for build in builds: # Fetch the ensembl information if not demo: ensembl_genes = fetch_ensembl_genes(build=build) else: ensembl_genes = get_file_handle(genes37_reduced_path) # load the genes hgnc_genes = load_hgnc_genes( adapter=adapter, ensembl_lines=ensembl_genes, hgnc_lines=hgnc_lines, exac_lines=exac_lines, mim2gene_lines=mim2gene_lines, genemap_lines=genemap_lines, hpo_lines=hpo_gene_lines, build=build, ) # Create a map from ensembl ids to gene objects ensembl_genes = {} for gene_obj in hgnc_genes: ensembl_id = gene_obj['ensembl_id'] ensembl_genes[ensembl_id] = gene_obj # Fetch the transcripts from ensembl if not demo: ensembl_transcripts = fetch_ensembl_transcripts(build=build) else: ensembl_transcripts = get_file_handle(transcripts37_reduced_path) # Load the transcripts for a certain build transcripts = load_transcripts(adapter, ensembl_transcripts, build, ensembl_genes) hpo_terms_handle = None hpo_to_genes_handle = None hpo_disease_handle = None if demo: hpo_terms_handle = get_file_handle(hpoterms_reduced_path) hpo_to_genes_handle = get_file_handle(hpo_to_genes_reduced_path) hpo_disease_handle = get_file_handle(hpo_phenotype_to_terms_reduced_path) load_hpo( adapter=adapter, hpo_lines=hpo_terms_handle, hpo_gene_lines=hpo_to_genes_handle, disease_lines=genemap_lines, hpo_disease_lines=hpo_disease_handle ) # If demo we load a gene panel and some case information if demo: parsed_panel = parse_gene_panel( path=panel_path, institute='cust000', panel_id='panel1', version=1.0, display_name='Test panel' ) adapter.load_panel(parsed_panel) case_handle = get_file_handle(load_path) case_data = yaml.load(case_handle, Loader=yaml.FullLoader) adapter.load_case(case_data) LOG.info("Creating indexes") adapter.load_indexes() LOG.info("Scout instance setup successful")
def parsed_panel(request, panel_info): """docstring for parsed_panels""" panel = parse_gene_panel(panel_info) return panel