コード例 #1
0
 def setUpClass(cls):
     token = os.environ.get('KB_AUTH_TOKEN', None)
     # WARNING: don't call any logging methods on the context object,
     # it'll result in a NoneType error
     cls.ctx = MethodContext(None)
     cls.ctx['token'] = token
     cls.ctx.update({
         'token':
         token,
         'provenance': [{
             'service': 'GenomeFileUtil',
             'method': 'please_never_use_it_in_production',
             'method_params': []
         }],
         'authenticated':
         1
     })
     config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
     cls.cfg = {}
     config = ConfigParser()
     config.read(config_file)
     for nameval in config.items('GenomeFileUtil'):
         cls.cfg[nameval[0]] = nameval[1]
     cls.wsURL = cls.cfg['workspace-url']
     cls.wsClient = workspaceService(cls.wsURL, token=token)
     cls.serviceImpl = GenomeFileUtil(cls.cfg)
コード例 #2
0
 def setUpClass(cls):
     token = os.environ.get('KB_AUTH_TOKEN', None)
     # WARNING: don't call any logging methods on the context object,
     # it'll result in a NoneType error
     cls.ctx = MethodContext(None)
     cls.ctx.update({'token': token,
                     'provenance': [
                         {'service': 'GenomeFileUtil',
                          'method': 'please_never_use_it_in_production',
                          'method_params': []
                          }],
                     'authenticated': 1})
     config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
     cls.cfg = {}
     config = ConfigParser()
     config.read(config_file)
     for nameval in config.items('GenomeFileUtil'):
         cls.cfg[nameval[0]] = nameval[1]
     cls.wsURL = cls.cfg['workspace-url']
     cls.wsClient = workspaceService(cls.wsURL, token=token)
     cls.serviceImpl = GenomeFileUtil(cls.cfg)
     suffix = int(time.time() * 1000)
     cls.wsName = "test_GenomeFileUtil_" + str(suffix)
     ret = cls.wsClient.create_workspace({'workspace': cls.wsName})
     cls.genome_ref = 'KBaseExampleData/Escherichia_coli_K-12_MG1655'
コード例 #3
0
    def setUpClass(cls):
        token = environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({
            'token':
            token,
            'provenance': [{
                'service': 'GenomeFileUtil',
                'method': 'please_never_use_it_in_production',
                'method_params': []
            }],
            'authenticated':
            1
        })
        config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.ws = workspaceService(cls.wsURL, token=token)
        cls.gaa = GenomeAnnotationAPI(os.environ['SDK_CALLBACK_URL'])
        cls.serviceImpl = GenomeFileUtil(cls.cfg)

        # create one WS for all tests
        suffix = int(time.time() * 1000)
        wsName = "test_GenomeAnnotationAPI_" + str(suffix)
        ret = cls.ws.create_workspace({'workspace': wsName})
        cls.wsName = wsName
コード例 #4
0
    def setUpClass(cls):
        print('setting up class')
        token = environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({
            'token':
            token,
            'provenance': [{
                'service': 'GenomeFileUtil',
                'method': 'please_never_use_it_in_production',
                'method_params': []
            }],
            'authenticated':
            1
        })
        config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']

        cls.ws = workspaceService(cls.wsURL, token=token)
        cls.impl = GenomeFileUtil(cls.cfg)

        cls.MINIMAL_TEST_FILE = os.path.join(cls.cfg['scratch'],
                                             'minimal.gbff')
        shutil.copy('data/minimal.gbff', cls.MINIMAL_TEST_FILE)
コード例 #5
0
 def setUpClass(cls):
     cls.token = environ.get('KB_AUTH_TOKEN', None)
     config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
     cls.cfg = {}
     config = ConfigParser()
     config.read(config_file)  # type: ignore
     for nameval in config.items('GenomeFileUtil'):
         cls.cfg[nameval[0]] = nameval[1]
     authServiceUrl = cls.cfg.get(
         'auth-service-url',
         "https://kbase.us/services/authorization/Sessions/Login")
     auth_client = _KBaseAuth(authServiceUrl)
     cls.user_id = auth_client.get_user(cls.token)
     cls.ctx = MethodContext(None)
     cls.ctx.update({
         'token':
         cls.token,
         'user_id':
         cls.user_id,
         'provenance': [{
             'service': 'GenomeFileUtil',
             'method': 'please_never_use_it_in_production',
             'method_params': []
         }],
         'authenticated':
         1
     })
     cls.wsURL = cls.cfg['workspace-url']
     cls.wsClient = workspaceService(cls.wsURL, token=cls.token)
     cls.serviceImpl = GenomeFileUtil(cls.cfg)
     cls.dfu = DataFileUtil(os.environ['SDK_CALLBACK_URL'], token=cls.token)
     cls.scratch = cls.cfg['scratch']
     cls.shockURL = cls.cfg['shock-url']
     cls.gfu_cfg = SDKConfig(cls.cfg)
     cls.prepare_data()
コード例 #6
0
    def setUpClass(cls):
        token = os.environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({'token': token,
                        'provenance': [
                            {'service': 'GenomeFileUtil',
                             'method': 'please_never_use_it_in_production',
                             'method_params': []
                             }],
                        'authenticated': 1})
        config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.wsClient = workspaceService(cls.wsURL, token=token)
        cls.serviceImpl = GenomeFileUtil(cls.cfg)
        gff_path = "data/fasta_gff/RefSeq/Bacterial_Data/NC_021490.gff.gz"
        fasta_path = "data/fasta_gff/RefSeq/Bacterial_Data/NC_021490.fasta.gz"
        ws_obj_name = 'fungal_model'
        suffix = int(time.time() * 1000)
        cls.wsName = "test_GenomeFileUtil_" + str(suffix)
        ret = cls.wsClient.create_workspace({'workspace': cls.wsName})

        print('Uploading GFF file')
        result = cls.serviceImpl.fasta_gff_to_genome(
            cls.ctx,
            {
                'workspace_name': cls.wsName,
                'genome_name': 'MyGenome',
                'fasta_file': {'path': fasta_path},
                'gff_file': {'path': gff_path},
                'source': 'GFF',
                'type': 'Reference'
            })[0]
        data_file_cli = DataFileUtil(os.environ['SDK_CALLBACK_URL'])
        cls.genome_orig = data_file_cli.get_objects(
            {'object_refs': [result['genome_ref']]})['data'][0]['data']

        print('testing GFF download by building the file')
        down_result = cls.serviceImpl.genome_to_gff(
            cls.ctx, {'genome_ref': result['genome_ref']})[0]

        print('Reuploading GFF file')
        new_result = cls.serviceImpl.fasta_gff_to_genome(
            cls.ctx,
            {
                'workspace_name': cls.wsName,
                'genome_name': 'MyGenome',
                'fasta_file': {'path': fasta_path},
                'gff_file': {'path': down_result['file_path']},
                'source': 'GFF',
                'type': 'Reference'
            })[0]
        cls.genome_new = data_file_cli.get_objects({'object_refs': [new_result['genome_ref']]})['data'][0]['data']
コード例 #7
0
    def setUpClass(cls):
        token = os.environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({'token': token,
                        'provenance': [
                            {'service': 'GenomeFileUtil',
                             'method': 'please_never_use_it_in_production',
                             'method_params': []
                             }],
                        'authenticated': 1})
        config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.wsClient = workspaceService(cls.wsURL, token=token)
        cls.serviceImpl = GenomeFileUtil(cls.cfg)
        # gbk_path = "data/Cyanidioschyzon/Cyanidioschyzon_merolae.ASM9120v1.30.gbff"
        gbk_path = "data/Cyanidioschyzon/Cyanidioschyzon_merolae_one_locus.gbff"
        ws_obj_name = 'Cyanidioschyzon_merolae_duplicate_test_orig'
        suffix = int(time.time() * 1000)
        cls.wsName = "test_GenomeFileUtil_" + str(suffix)
        cls.wsClient.create_workspace({'workspace': cls.wsName})
        result = cls.serviceImpl.genbank_to_genome(cls.ctx, {
            'file': {'path': gbk_path},
            'workspace_name': cls.wsName,
            'genome_name': ws_obj_name,
            'generate_ids_if_needed': 1,
            'taxon_id': '511145',
            'source': "Ensembl user"
        })[0]

        data_file_cli = DataFileUtil(
            os.environ['SDK_CALLBACK_URL'],
            token=cls.ctx['token'],
            service_ver='dev'
        )
        cls.genome_orig = data_file_cli.get_objects({'object_refs': [result['genome_ref']]})['data'][0]['data']
        print('testing Genbank download by building the file')
        cls.serviceImpl.export_genome_as_genbank(cls.ctx, {
            'input_ref': result['genome_ref']})
        new_gbk_path = "/kb/module/work/tmp/Cyanidioschyzon_merolae_duplicate_test_orig/KBase_derived_Cyanidioschyzon_merolae_duplicate_test_orig.gbff"
        new_ws_obj_name = 'Cyanidioschyzon_merolae_duplicate_test_new'
        new_result = cls.serviceImpl.genbank_to_genome(cls.ctx, {
            'file': {'path': new_gbk_path},
            'workspace_name': cls.wsName,
            'genome_name': new_ws_obj_name,
            'generate_ids_if_needed': 1,
            'taxon_id': '511145',
            'source': "Ensembl user"
        })[0]
        cls.genome_new = data_file_cli.get_objects({'object_refs': [new_result['genome_ref']]})['data'][0]['data']
コード例 #8
0
 def setUpClass(cls):
     token = os.environ.get('KB_AUTH_TOKEN', None)
     # WARNING: don't call any logging methods on the context object,
     # it'll result in a NoneType error
     cls.ctx = MethodContext(None)
     cls.ctx.update({
         'token':
         token,
         'provenance': [{
             'service': 'GenomeFileUtil',
             'method': 'please_never_use_it_in_production',
             'method_params': []
         }],
         'authenticated':
         1
     })
     config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
     cls.cfg = {}
     config = ConfigParser()
     config.read(config_file)
     for nameval in config.items('GenomeFileUtil'):
         cls.cfg[nameval[0]] = nameval[1]
     cls.wsURL = cls.cfg['workspace-url']
     cls.wsClient = workspaceService(cls.wsURL, token=token)
     cls.serviceImpl = GenomeFileUtil(cls.cfg)
     gbk_path = "data/Arabidopsis_gbff/A_thaliana_Ensembl_TAIR10_38_chr4_minus_xref.gbff"
     ws_obj_name = 'Yeast_chromosome1'
     suffix = int(time.time() * 1000)
     cls.wsName = "test_GenomeFileUtil_" + str(suffix)
     ret = cls.wsClient.create_workspace({'workspace': cls.wsName})
     result = cls.serviceImpl.genbank_to_genome(
         cls.ctx, {
             'file': {
                 'path': gbk_path
             },
             'workspace_name': cls.wsName,
             'genome_name': ws_obj_name,
             'generate_ids_if_needed': 1,
             'source': "Ensembl"
         })[0]
     #        print("HERE IS THE RESULT:")
     data_file_cli = DataFileUtil(os.environ['SDK_CALLBACK_URL'],
                                  token=cls.ctx['token'],
                                  service_ver='dev')
     cls.genome = data_file_cli.get_objects(
         {'object_refs': [result['genome_ref']]})['data'][0]['data']
     json.dump(
         cls.genome,
         open(cls.cfg['scratch'] + "/relationship_test_genome.json", 'w'))
     cls.gene_ids = set((x['id'] for x in cls.genome['features']))
     cls.nc_feat_ids = set(
         (x['id'] for x in cls.genome['non_coding_features']))
     cls.mrna_ids = set((x['id'] for x in cls.genome['mrnas']))
     cls.cds_ids = set((x['id'] for x in cls.genome['cdss']))
コード例 #9
0
 def setUpClass(cls):
     token = os.environ.get('KB_AUTH_TOKEN', None)
     # WARNING: don't call any logging methods on the context object,
     # it'll result in a NoneType error
     cls.ctx = MethodContext(None)
     cls.ctx.update({
         'token':
         token,
         'provenance': [{
             'service': 'GenomeFileUtil',
             'method': 'please_never_use_it_in_production',
             'method_params': []
         }],
         'authenticated':
         1
     })
     config_file = os.environ['KB_DEPLOYMENT_CONFIG']
     cls.cfg = {}
     config = ConfigParser()
     config.read(config_file)
     for nameval in config.items('GenomeFileUtil'):
         cls.cfg[nameval[0]] = nameval[1]
     cls.wsURL = cls.cfg['workspace-url']
     cls.wsClient = workspaceService(cls.wsURL, token=token)
     cls.serviceImpl = GenomeFileUtil(cls.cfg)
     gff_path = "data/e_coli/NC_000913.3.gff3"
     fna_path = "data/e_coli/NC_000913.3.fasta"
     # fna_path = "data/e_coli/GCF_000005845.2_ASM584v2.fasta"
     ws_obj_name = 'ecoli_contigs'
     suffix = int(time.time() * 1000)
     cls.wsName = "test_GenomeFileUtil_" + str(suffix)
     cls.wsClient.create_workspace({'workspace': cls.wsName})
     result = cls.serviceImpl.fasta_gff_to_genome(
         cls.ctx, {
             'gff_file': {
                 'path': gff_path
             },
             'fasta_file': {
                 'path': fna_path
             },
             'taxon_id': 511145,
             'workspace_name': cls.wsName,
             'genome_name': ws_obj_name,
             'generate_missing_genes': 1,
             'generate_ids_if_needed': 1
         })[0]
     data_file_cli = DataFileUtil(os.environ['SDK_CALLBACK_URL'],
                                  token=cls.ctx['token'],
                                  service_ver='dev')
     dfu_result = data_file_cli.get_objects(
         {'object_refs': [result['genome_ref']]})
     cls.genome = dfu_result['data'][0]['data']
コード例 #10
0
    def setUpClass(cls):
        token = environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({'token': token,
                        'provenance': [
                            {'service': 'GenomeFileUtil',
                             'method': 'please_never_use_it_in_production',
                             'method_params': []
                             }],
                        'authenticated': 1})
        config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.ws = workspaceService(cls.wsURL, token=token)
        cls.serviceImpl = GenomeFileUtil(cls.cfg)
        gi_config = SDKConfig(cls.cfg)
        cls.genome_interface = GenomeInterface(gi_config)
        # create one WS for all tests
        suffix = int(time.time() * 1000)
        wsName = "test_GenomeAnnotationAPI_" + str(suffix)
        cls.ws.create_workspace({'workspace': wsName})
        cls.wsName = wsName

        # save new genome
        assembly_file_path = os.path.join(cls.cfg['scratch'],
                                          'Rhodo_SPAdes_assembly.fa')
        shutil.copy('data/Rhodo_SPAdes_assembly.fa', assembly_file_path)
        au = AssemblyUtil(os.environ['SDK_CALLBACK_URL'])
        cls.assembly_ref = au.save_assembly_from_fasta({
            'workspace_name': cls.wsName,
            'assembly_name': 'ecoli.assembly',
            'file': {'path': assembly_file_path}
        })

        rhodobacter_contigs = json.load(open('data/rhodobacter_contigs.json'))
        save_info = {
            'workspace': cls.wsName,
            'objects': [{
                'type': 'KBaseGenomes.ContigSet',
                'data': rhodobacter_contigs,
                'name': 'rhodobacter_contigs'
            }]
        }
        cls.contigset_ref = cls.ws.save_objects(save_info)
コード例 #11
0
 def setUpClass(cls):
     token = os.environ.get('KB_AUTH_TOKEN', None)
     # WARNING: don't call any logging methods on the context object,
     # it'll result in a NoneType error
     cls.ctx = MethodContext(None)
     cls.ctx.update({
         'token':
         token,
         'provenance': [{
             'service': 'GenomeFileUtil',
             'method': 'please_never_use_it_in_production',
             'method_params': []
         }],
         'authenticated':
         1
     })
     config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
     cls.cfg = {}
     config = ConfigParser()
     config.read(config_file)
     for nameval in config.items('GenomeFileUtil'):
         cls.cfg[nameval[0]] = nameval[1]
     cls.wsURL = cls.cfg['workspace-url']
     cls.wsClient = workspaceService(cls.wsURL, token=token)
     cls.serviceImpl = GenomeFileUtil(cls.cfg)
     gbk_path = "data/e_coli/GCF_000005845.2_ASM584v2_genomic.gbff"
     ws_obj_name = 'ecoli_genome'
     suffix = int(time.time() * 1000)
     cls.wsName = "test_GenomeFileUtil_" + str(suffix)
     ret = cls.wsClient.create_workspace({'workspace': cls.wsName})
     result = cls.serviceImpl.genbank_to_genome(
         cls.ctx, {
             'file': {
                 'path': gbk_path
             },
             'workspace_name': cls.wsName,
             'genome_name': ws_obj_name,
             'generate_ids_if_needed': 1,
             'source': "RefSeq Reference"
         })[0]
     #        print("HERE IS THE RESULT:")
     data_file_cli = DataFileUtil(os.environ['SDK_CALLBACK_URL'],
                                  token=cls.ctx['token'],
                                  service_ver='dev')
     genome = data_file_cli.get_objects(
         {'object_refs': [result['genome_ref']]})['data'][0]['data']
     cls.assembly_ref = genome["assembly_ref"]
コード例 #12
0
 def setUpClass(cls):
     token = os.environ.get('KB_AUTH_TOKEN', None)
     # WARNING: don't call any logging methods on the context object,
     # it'll result in a NoneType error
     cls.ctx = MethodContext(None)
     cls.ctx.update({'token': token,
                     'provenance': [
                         {'service': 'GenomeFileUtil',
                          'method': 'please_never_use_it_in_production',
                          'method_params': []
                          }],
                     'authenticated': 1})
     config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
     cls.cfg = {}
     config = ConfigParser()
     config.read(config_file)
     for nameval in config.items('GenomeFileUtil'):
         cls.cfg[nameval[0]] = nameval[1]
     cls.wsURL = cls.cfg['workspace-url']
     cls.wsClient = workspaceService(cls.wsURL, token=token)
     cls.serviceImpl = GenomeFileUtil(cls.cfg)
     gbk_path = "data/Arabidopsis_gbff/Arab_Chloro_Modified.gbff"
     ws_obj_name = 'ArabidopsisChloro'
     suffix = int(time.time() * 1000)
     cls.wsName = "test_GenomeFileUtil_" + str(suffix)
     ret = cls.wsClient.create_workspace({'workspace': cls.wsName})
     result = cls.serviceImpl.genbank_to_genome(
         cls.ctx,
         {
           'file': {
               'path': gbk_path},
           'workspace_name': cls.wsName,
           'genome_name': ws_obj_name,
           'generate_ids_if_needed': 1,
           'source': "RefSeq Latest"
         })[0]
     data_file_cli = DataFileUtil(os.environ['SDK_CALLBACK_URL'],
                             token=cls.ctx['token'],
                             service_ver='dev')
     cls.genome = data_file_cli.get_objects({'object_refs': [result['genome_ref']]})['data'][0]['data']
     json.dump(cls.genome, open(cls.cfg['scratch']+"/test_genome.json", 'w'))
コード例 #13
0
    def setUpClass(cls):
        token = environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({'token': token,
                        'provenance': [
                            {'service': 'GenomeFileUtil',
                             'method': 'please_never_use_it_in_production',
                             'method_params': []
                             }],
                        'authenticated': 1})
        config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.wsClient = workspaceService(cls.wsURL, token=token)
        cls.serviceImpl = GenomeFileUtil(cls.cfg)

        cls.TEST_ECOLI_FILE_FTP = 'ftp://ftp.ncbi.nlm.nih.gov/genomes/refseq/bacteria/Escherichia_coli/reference/GCF_000005845.2_ASM584v2/GCF_000005845.2_ASM584v2_genomic.gbff.gz'
コード例 #14
0
    def setUpClass(cls):
        token = os.environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({'token': token,
                        'provenance': [
                            {'service': 'GenomeFileUtil',
                             'method': 'please_never_use_it_in_production',
                             'method_params': []
                             }],
                        'authenticated': 1})
        config_file = os.environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.wsClient = workspaceService(cls.wsURL, token=token)
        cls.serviceImpl = GenomeFileUtil(cls.cfg)
        # get metagenome data.
        cls.gff_path = "data/metagenomes/ebi/59111.assembled.gff"
        cls.fasta_path = "data/metagenomes/ebi/59111.assembled.fna"
        if not os.path.isfile(cls.fasta_path) or not os.path.isfile(cls.gff_path):
            raise InputError(f'Files {cls.gff_path} and/or {cls.fasta_path} not in test directory ')

        suffix = int(time.time() * 1000)
        cls.wsName = "test_GenomeFileUtil_" + str(suffix)
        cls.wsClient.create_workspace({'workspace': cls.wsName})

        print('Uploading GFF file')
        result = cls.serviceImpl.fasta_gff_to_metagenome(cls.ctx, {
            'workspace_name': cls.wsName,
            'genome_name': 'MyGenome',
            'fasta_file': {'path': cls.fasta_path},
            'gff_file': {'path': cls.gff_path},
            'source': 'GFF',
            'taxon_id': '3702',
            'type': 'Reference',
            'genome_type': 'Metagenome',
            'is_metagenome': True,
            'generate_missing_genes': True
        })[0]
        data_file_cli = DataFileUtil(os.environ['SDK_CALLBACK_URL'])
        cls.metagenome_ref = result['metagenome_ref']
        cls.genome_orig = data_file_cli.get_objects(
            {'object_refs': [result['metagenome_ref']]})['data'][0]['data']

        print('testing GFF download by building the file')
        down_result = cls.serviceImpl.metagenome_to_gff(
            cls.ctx, {'metagenome_ref': result['metagenome_ref']})[0]

        print('Reuploading GFF file')
        new_result = cls.serviceImpl.fasta_gff_to_metagenome(cls.ctx, {
            'workspace_name': cls.wsName,
            'genome_name': 'MyGenome',
            'fasta_file': {'path': cls.fasta_path},
            'gff_file': {'path': down_result['file_path']},
            'source': 'GFF',
            'type': 'Reference',
            'genome_type': 'Metagenome',
            'is_metagenome': True,
            'generate_missing_genes': True,
            'taxon_id': '3702',
        })[0]
        cls.genome_new = data_file_cli.get_objects({'object_refs': [new_result['metagenome_ref']]})['data'][0]['data']
コード例 #15
0
    def setUpClass(cls):
        token = environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({
            'token':
            token,
            'provenance': [{
                'service': 'GenomeFileUtil',
                'method': 'please_never_use_it_in_production',
                'method_params': []
            }],
            'authenticated':
            1
        })
        config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.ws = workspaceService(cls.wsURL, token=token)
        cls.serviceImpl = GenomeFileUtil(cls.cfg)

        # create one WS for all tests
        suffix = int(time.time() * 1000)
        wsName = "test_GenomeAnnotationAPI_" + str(suffix)
        ret = cls.ws.create_workspace({'workspace': wsName})
        cls.wsName = wsName

        # preload with reference data
        with open('data/rhodobacter.json', 'r') as file:
            data_str = file.read()
        data = json.loads(data_str)
        # save to ws
        save_info = {
            'workspace':
            wsName,
            'objects': [{
                'type': 'KBaseGenomes.Genome',
                'data': data,
                'name': 'rhodobacter'
            }]
        }
        result = cls.ws.save_objects(save_info)
        info = result[0]
        cls.rhodobacter_ref = str(info[6]) + '/' + str(info[0]) + '/' + str(
            info[4])
        print('created rhodobacter test genome: ' + cls.rhodobacter_ref)

        # save a GFF file to shock, preload a genome pointing to it
        dfu = DataFileUtil(os.environ['SDK_CALLBACK_URL'])
        shutil.copy('data/rhodobacter.gtf', cls.cfg['scratch'])
        shock_file = dfu.file_to_shock({
            'file_path':
            os.path.join(cls.cfg['scratch'], 'rhodobacter.gtf'),
            'make_handle':
            1
        })
        data['gff_handle_ref'] = shock_file['handle']['hid']

        # save to ws
        save_info['objects'][0]['name'] = 'rhodobacter_with_gff'
        result = cls.ws.save_objects(save_info)
        info = result[0]
        cls.rhodobacter_ref_with_gff = str(info[6]) + '/' + str(
            info[0]) + '/' + str(info[4])
        print('created rhodobacter test genome with handle: ' +
              cls.rhodobacter_ref_with_gff)
コード例 #16
0
    def setUpClass(cls):
        cls.token = environ.get('KB_AUTH_TOKEN', None)
        config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        # Getting username from Auth profile for token
        authServiceUrl = cls.cfg['auth-service-url']
        auth_client = _KBaseAuth(authServiceUrl)
        cls.user_id = auth_client.get_user(cls.token)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({'token': cls.token,
                        'user_id': cls.user_id,
                        'provenance': [
                            {'service': 'kb_ke_util',
                             'method': 'please_never_use_it_in_production',
                             'method_params': []
                             }],
                        'authenticated': 1})
        cls.shockURL = cls.cfg['shock-url']
        cls.wsURL = cls.cfg['workspace-url']
        cls.wsClient = workspaceService(cls.wsURL)
        cls.serviceImpl = GenomeFileUtil(cls.cfg)
        cls.scratch = cls.cfg['scratch']
        cls.callback_url = os.environ['SDK_CALLBACK_URL']

        cls.dfu = DataFileUtil(cls.callback_url)
        cls.cfg['KB_AUTH_TOKEN'] = cls.token

        # build genome interface instance
        gi_config = SDKConfig(cls.cfg)
        cls.genome_interface = GenomeInterface(gi_config)

        # second user
        test_cfg_file = '/kb/module/work/test.cfg'
        test_cfg_text = "[test]\n"
        with open(test_cfg_file, "r") as f:
            test_cfg_text += f.read()

        config = ConfigParser()
        config.readfp(io.StringIO(test_cfg_text))

        test_cfg_dict = dict(config.items("test"))
        if ('test_token2' not in test_cfg_dict):
            raise ValueError("Configuration in <module>/test_local/test.cfg file should " +
                             "include second user credentials ('test_token2')")
        token2 = test_cfg_dict['test_token2']
        user2 = auth_client.get_user(token2)
        cls.ctx2 = MethodContext(None)
        cls.ctx2.update({'token': token2,
                         'user_id': user2,
                         'provenance': [
                            {'service': 'NarrativeService',
                             'method': 'please_never_use_it_in_production',
                             'method_params': []
                             }],
                         'authenticated': 1})

        suffix = int(time.time() * 1000)
        cls.wsName = "test_SaveGenomeTest_" + str(suffix)
        cls.wsClient.create_workspace({'workspace': cls.wsName})

        cls.nodes_to_delete = []
        cls.prepare_data()
コード例 #17
0
    def setUpClass(cls):
        token = environ.get('KB_AUTH_TOKEN', None)
        # WARNING: don't call any logging methods on the context object,
        # it'll result in a NoneType error
        cls.ctx = MethodContext(None)
        cls.ctx.update({
            'token':
            token,
            'provenance': [{
                'service': 'GenomeFileUtil',
                'method': 'please_never_use_it_in_production',
                'method_params': []
            }],
            'authenticated':
            1
        })
        config_file = environ.get('KB_DEPLOYMENT_CONFIG', None)
        cls.cfg = {}
        config = ConfigParser()
        config.read(config_file)
        for nameval in config.items('GenomeFileUtil'):
            cls.cfg[nameval[0]] = nameval[1]
        cls.wsURL = cls.cfg['workspace-url']
        cls.ws = workspaceService(cls.wsURL, token=token)
        cls.gaa = GenomeAnnotationAPI(os.environ['SDK_CALLBACK_URL'])
        cls.serviceImpl = GenomeFileUtil(cls.cfg)

        # create one WS for all tests
        suffix = int(time.time() * 1000)
        wsName = "test_GenomeAnnotationAPI_" + str(suffix)
        ret = cls.ws.create_workspace({'workspace': wsName})
        cls.wsName = wsName

        cls.ara_ref = cls.serviceImpl.genbank_to_genome(
            cls.ctx, {
                'file': {
                    'path':
                    'data/Arabidopsis_gbff/A_thaliana_Ensembl_TAIR10_38_chr4_minus_xref.gbff'
                },
                'workspace_name': cls.wsName,
                'genome_name': "arab",
                'source': 'Ensembl',
            })[0]['genome_ref']

        # preload with reference data
        data = json.load(open('data/rhodobacter.json'))
        # save to ws
        save_info = {'workspace': wsName, 'data': data, 'name': 'rhodobacter'}
        info = cls.gaa.save_one_genome_v1(save_info)['info']
        cls.rhodobacter_ref = str(info[6]) + '/' + str(info[0]) + '/' + str(
            info[4])
        print(('created rhodobacter test genome: ' + cls.rhodobacter_ref))

        # save new genome
        assembly_file_path = os.path.join(cls.cfg['scratch'],
                                          'e_coli_assembly.fasta')
        shutil.copy('data/e_coli/e_coli_assembly.fasta', assembly_file_path)
        au = AssemblyUtil(os.environ['SDK_CALLBACK_URL'])
        assembly_ref = au.save_assembly_from_fasta({
            'workspace_name': cls.wsName,
            'assembly_name': 'ecoli.assembly',
            'file': {
                'path': assembly_file_path
            }
        })
        data = json.load(open('data/e_coli/new_ecoli_genome.json'))
        data['assembly_ref'] = assembly_ref
        # save to ws
        save_info = {
            'workspace':
            wsName,
            'objects': [{
                'type': 'KBaseGenomes.Genome',
                'data': data,
                'name': 'new_ecoli'
            }]
        }
        result = cls.ws.save_objects(save_info)
        info = result[0]
        cls.ecoli_ref = str(info[6]) + '/' + str(info[0]) + '/' + str(info[4])
        print(('created ecoli test genome: ' + cls.rhodobacter_ref))

        # save a GFF file to shock, preload a genome pointing to it
        dfu = DataFileUtil(os.environ['SDK_CALLBACK_URL'])
        shutil.copy('data/rhodobacter.gtf', cls.cfg['scratch'])
        shock_file = dfu.file_to_shock({
            'file_path':
            os.path.join(cls.cfg['scratch'], 'rhodobacter.gtf'),
            'make_handle':
            1
        })
        data['gff_handle_ref'] = shock_file['handle']['hid']

        # save to ws
        save_info['objects'][0]['name'] = 'rhodobacter_with_gff'
        result = cls.ws.save_objects(save_info)
        info = result[0]
        cls.rhodobacter_ref_with_gff = str(info[6]) + '/' + str(
            info[0]) + '/' + str(info[4])
        print(('created rhodobacter test genome with handle: ' +
               cls.rhodobacter_ref_with_gff))