Python metadata_template.PrepTemplate类代码示例

    def test_dataframe_from_template(self):
        template = PrepTemplate(1)
        obs = template.to_dataframe()

        # 27 samples
        self.assertEqual(len(obs), 27)
        self.assertTrue(set(obs.index), {
            u'SKB1.640202', u'SKB2.640194', u'SKB3.640195', u'SKB4.640189',
            u'SKB5.640181', u'SKB6.640176', u'SKB7.640196', u'SKB8.640193',
            u'SKB9.640200', u'SKD1.640179', u'SKD2.640178', u'SKD3.640198',
            u'SKD4.640185', u'SKD5.640186', u'SKD6.640190', u'SKD7.640191',
            u'SKD8.640184', u'SKD9.640182', u'SKM1.640183', u'SKM2.640199',
            u'SKM3.640197', u'SKM4.640180', u'SKM5.640177', u'SKM6.640187',
            u'SKM7.640188', u'SKM8.640201', u'SKM9.640192'})

        self.assertTrue(set(obs.columns), {
            u'tot_org_carb', u'common_name', u'has_extracted_data',
            u'required_sample_info_status', u'water_content_soil',
            u'env_feature', u'assigned_from_geo', u'altitude', u'env_biome',
            u'texture', u'has_physical_specimen', u'description_duplicate',
            u'physical_location', u'latitude', u'ph', u'host_taxid',
            u'elevation', u'description', u'collection_timestamp',
            u'taxon_id', u'samp_salinity', u'host_subject_id', u'sample_type',
            u'season_environment', u'temp', u'country', u'longitude',
            u'tot_nitro', u'depth', u'anonymized_name', u'target_subfragment',
            u'sample_center', u'samp_size', u'run_date', u'experiment_center',
            u'pcr_primers', u'center_name', u'barcodesequence', u'run_center',
            u'run_prefix', u'library_construction_protocol', u'emp_status',
            u'linkerprimersequence', u'experiment_design_description',
            u'target_gene', u'center_project_name', u'illumina_technology',
            u'sequencing_meth', u'platform', u'experiment_title',
            u'study_center'})

    def add_raw_data(self, study, user, callback):
        """Adds an existing raw data to the study

        Parameters
        ----------
        study : Study
            The current study object
        user : User
            The current user object
        callback : function
            The callback function to call with the results once the processing
            is done
        """
        msg = "Raw data successfully added"
        msg_level = "success"

        # Get the arguments to add the raw data
        pt_id = self.get_argument('prep_template_id')
        raw_data_id = self.get_argument('raw_data_id')

        prep_template = PrepTemplate(pt_id)
        raw_data = RawData(raw_data_id)

        try:
            prep_template.raw_data = raw_data
        except QiitaDBError as e:
            msg = html_error_message % ("adding the raw data",
                                        str(raw_data_id), str(e))
            msg = convert_text_html(msg)

        callback((msg, msg_level, 'prep_template_tab', pt_id, None))

    def setUp(self):
        fd, self.seqs_fp = mkstemp(suffix='_seqs.fastq')
        close(fd)
        fd, self.barcodes_fp = mkstemp(suffix='_barcodes.fastq')
        close(fd)
        self.filetype = 2
        self.filepaths = [(self.seqs_fp, 1), (self.barcodes_fp, 2)]
        _, self.db_test_raw_dir = get_mountpoint('raw_data')[0]

        with open(self.seqs_fp, "w") as f:
            f.write("\n")
        with open(self.barcodes_fp, "w") as f:
            f.write("\n")
        self._clean_up_files = []

        # Create some new PrepTemplates
        metadata_dict = {
            'SKB8.640193': {'center_name': 'ANL',
                            'primer': 'GTGCCAGCMGCCGCGGTAA',
                            'barcode': 'GTCCGCAAGTTA',
                            'run_prefix': "s_G1_L001_sequences",
                            'platform': 'ILLUMINA',
                            'library_construction_protocol': 'AAAA',
                            'experiment_design_description': 'BBBB'}}
        metadata = pd.DataFrame.from_dict(metadata_dict, orient='index')
        self.pt1 = PrepTemplate.create(metadata, Study(1), "16S")
        self.pt2 = PrepTemplate.create(metadata, Study(1), "18S")
        self.prep_templates = [self.pt1, self.pt2]

    def delete_prep_template(self, study, user, callback):
        """Delete the selected prep template

        Parameters
        ----------
        study : Study
            The current study object
        user : User
            The current user object
        callback : function
            The callback function to call with the results once the processing
            is done
        """
        prep_template_id = int(self.get_argument('prep_template_id'))
        prep_id = PrepTemplate(prep_template_id).raw_data

        try:
            PrepTemplate.delete(prep_template_id)
            msg = ("Prep template %d has been deleted" % prep_template_id)
            msg_level = "success"
            prep_id = None
        except Exception as e:
            msg = ("Couldn't remove prep template: %s" % str(e))
            msg_level = "danger"

        callback((msg, msg_level, 'prep_template_tab', prep_id, None))

    def test_get_qiime_minimal_mapping_single_reverse_primer(self):
        conn_handler = SQLConnectionHandler()
        conn_handler
        sql = """INSERT INTO qiita.prep_columns
                        (prep_template_id, column_name, column_type)
                    VALUES (1, 'reverselinkerprimer', 'varchar');
                 ALTER TABLE qiita.prep_1
                    ADD COLUMN reverselinkerprimer varchar;
                 DELETE FROM qiita.prep_columns
                 WHERE prep_template_id = 1 AND column_name = 'run_prefix';
                 ALTER TABLE qiita.prep_1 DROP COLUMN run_prefix;
                 UPDATE qiita.prep_1 SET reverselinkerprimer = %s
                 """
        conn_handler.execute(sql, ('GTGCCAGCM',))
        prep_template = PrepTemplate(1)
        prep_template.generate_files()
        out_dir = mkdtemp()

        obs_fps = _get_qiime_minimal_mapping(prep_template, out_dir)
        exp_fps = [join(out_dir, 'prep_1_MMF.txt')]

        # Check that the returned list is as expected
        self.assertEqual(obs_fps, exp_fps)
        # Check that the file exists
        self.assertTrue(exists(exp_fps[0]))
        # Check the contents of the file
        with open(exp_fps[0], "U") as f:
            self.assertEqual(f.read(), EXP_PREP_RLP)

    def update_prep_template(self, study, user, callback):
        """Update a prep template from the POST method

        Parameters
        ----------
        study : Study
            The current study object
        user : User
            The current user object
        callback : function
            The callback function to call with the results once the processing
            is done

        Raises
        ------
        HTTPError
            If the prep template file does not exists
        """
        # If we are on this function, the arguments "prep_template_id",
        # "update_prep_template_file" must defined. If not, let tornado
        # raise its error
        pt_id = int(self.get_argument('prep_template_id'))
        prep_template = self.get_argument('update_prep_template_file')

        # Define here the message and message level in case of success
        msg = "The prep template '%s' has been updated" % prep_template
        msg_level = "success"
        # Get the uploads folder
        _, base_fp = get_mountpoint("uploads")[0]
        # Get the path of the prep template in the uploads folder
        fp = join(base_fp, str(study.id), prep_template)

        if not exists(fp):
            # The file does not exist, fail nicely
            # Using 400 because we want the user to get the error in the GUI
            raise HTTPError(400, "This file doesn't exist: %s" % fp)
        try:
            with warnings.catch_warnings(record=True) as warns:
                pt = PrepTemplate(pt_id)
                pt.update(load_template_to_dataframe(fp))
                remove(fp)

                # join all the warning messages into one. Note that this info
                # will be ignored if an exception is raised
                if warns:
                    msg = '; '.join([str(w.message) for w in warns])
                    msg_level = 'warning'

        except (TypeError, QiitaDBColumnError, QiitaDBExecutionError,
                QiitaDBDuplicateError, IOError, ValueError, KeyError,
                CParserError, QiitaDBDuplicateHeaderError, QiitaDBError) as e:
            # Some error occurred while processing the sample template
            # Show the error to the user so they can fix the template
            msg = html_error_message % ('updating the prep template:',
                                        basename(fp), str(e))
            msg = convert_text_html(msg)
            msg_level = "danger"

        callback((msg, msg_level, 'prep_template_tab', pt_id, None))

def submit_VAMPS(preprocessed_data_id):
    """Submit preprocessed data to VAMPS

    Parameters
    ----------
    preprocessed_data_id : int
        The preprocesssed data id
    """
    preprocessed_data = PreprocessedData(preprocessed_data_id)
    study = Study(preprocessed_data.study)
    sample_template = SampleTemplate(study.sample_template)
    prep_template = PrepTemplate(preprocessed_data.prep_template)

    status = preprocessed_data.submitted_to_vamps_status()
    if status in ('submitting', 'success'):
        raise ValueError("Cannot resubmit! Current status is: %s" % status)

        preprocessed_data.update_vamps_status('submitting')

    # Generating a tgz
    targz_folder = mkdtemp(prefix=qiita_config.working_dir)
    targz_fp = join(targz_folder, '%d_%d_%d.tgz' % (study.id,
                                                    prep_template.id,
                                                    preprocessed_data.id))
    targz = taropen(targz_fp, mode='w:gz')

    # adding sample/prep
    samp_fp = join(targz_folder, 'sample_metadata.txt')
    sample_template.to_file(samp_fp)
    targz.add(samp_fp, arcname='sample_metadata.txt')
    prep_fp = join(targz_folder, 'prep_metadata.txt')
    prep_template.to_file(prep_fp)
    targz.add(prep_fp, arcname='prep_metadata.txt')

    # adding preprocessed data
    for _, fp, fp_type in preprocessed_data.get_filepaths():
        if fp_type == 'preprocessed_fasta':
            targz.add(fp, arcname='preprocessed_fasta.fna')

    targz.close()

    # submitting
    cmd = ("curl -F user=%s -F pass='%s' -F [email protected]%s -F "
           "press=UploadFile %s" % (qiita_config.vamps_user,
                                    qiita_config.vamps_pass,
                                    targz_fp,
                                    qiita_config.vamps_url))
    obs, _, _ = system_call(cmd)

    exp = ("<html>\n<head>\n<title>Process Uploaded File</title>\n</head>\n"
           "<body>\n</body>\n</html>")

    if obs != exp:
        preprocessed_data.update_vamps_status('failure')
        return False
    else:
        preprocessed_data.update_vamps_status('success')
        return True

    def test_get_sample_names_by_run_prefix(self):
        metadata_dict = {
            'SKB8.640193': {'run_prefix': "s1", 'primer': 'A',
                            'barcode': 'A', 'center_name': 'ANL',
                            'platform': 'ILLUMINA',
                            'instrument_model': 'Illumina MiSeq',
                            'library_construction_protocol': 'A',
                            'experiment_design_description': 'A'},
            'SKD8.640184': {'run_prefix': "s2", 'primer': 'A',
                            'barcode': 'A', 'center_name': 'ANL',
                            'platform': 'ILLUMINA',
                            'instrument_model': 'Illumina MiSeq',
                            'library_construction_protocol': 'A',
                            'experiment_design_description': 'A'},
            'SKB7.640196': {'run_prefix': "s3", 'primer': 'A',
                            'barcode': 'A', 'center_name': 'ANL',
                            'platform': 'ILLUMINA',
                            'instrument_model': 'Illumina MiSeq',
                            'library_construction_protocol': 'A',
                            'experiment_design_description': 'A'}}
        md_template = pd.DataFrame.from_dict(metadata_dict, orient='index')
        prep_template = PrepTemplate.create(md_template, Study(1), '16S')
        for _, fp in prep_template.get_filepaths():
            self.files_to_remove.append(fp)

        obs = _get_sample_names_by_run_prefix(prep_template)

        exp = {'s3': '1.SKB7.640196', 's2': '1.SKD8.640184',
               's1': '1.SKB8.640193'}
        self.assertEqual(obs, exp)

        # This should raise an error
        metadata_dict = {
            'SKB8.640193': {'run_prefix': "s1", 'primer': 'A',
                            'barcode': 'A', 'center_name': 'ANL',
                            'platform': 'ILLUMINA',
                            'instrument_model': 'Illumina MiSeq',
                            'library_construction_protocol': 'A',
                            'experiment_design_description': 'A'},
            'SKD8.640184': {'run_prefix': "s1", 'primer': 'A',
                            'barcode': 'A', 'center_name': 'ANL',
                            'platform': 'ILLUMINA',
                            'instrument_model': 'Illumina MiSeq',
                            'library_construction_protocol': 'A',
                            'experiment_design_description': 'A'},
            'SKB7.640196': {'run_prefix': "s3", 'primer': 'A',
                            'barcode': 'A', 'center_name': 'ANL',
                            'platform': 'ILLUMINA',
                            'instrument_model': 'Illumina MiSeq',
                            'library_construction_protocol': 'A',
                            'experiment_design_description': 'A'}}
        md_template = pd.DataFrame.from_dict(metadata_dict, orient='index')
        prep_template = PrepTemplate.create(md_template, Study(1), '16S')
        for _, fp in prep_template.get_filepaths():
            self.files_to_remove.append(fp)

        with self.assertRaises(ValueError):
            _get_sample_names_by_run_prefix(prep_template)

    def remove_add_prep_template(self, fp_rpt, raw_data_id, study,
                                 data_type_id, investigation_type, callback):
        """add prep templates
        """
        PrepTemplate.create(load_template_to_dataframe(fp_rpt),
                            RawData(raw_data_id), study, int(data_type_id),
                            investigation_type=investigation_type)
        remove(fp_rpt)

        callback()

    def remove_add_study_template(self, raw_data, study_id, fp_rsp):
        """Replace prep templates, raw data, and sample template with a new one
        """
        for rd in raw_data():
            rd = RawData(rd)
            for pt in rd.prep_templates:
                if PrepTemplate.exists(pt):
                    PrepTemplate.delete(pt)
        if SampleTemplate.exists(study_id):
            SampleTemplate.delete(study_id)

        SampleTemplate.create(load_template_to_dataframe(fp_rsp),
                              Study(study_id))
        remove(fp_rsp)

    def update_investigation_type(self, study, user, callback):
        """Updates the investigation type of a prep template

        Parameters
        ----------
        study : Study
            The current study object
        user : User
            The current user object
        callback : function
            The callback function to call with the results once the processing
            is done
        """
        msg = "investigation type successfully updated"
        msg_level = "success"

        ppd_id = int(self.get_argument('ppd_id'))

        prep_id = self.get_argument('prep_id')
        edit_investigation_type = self.get_argument('edit-investigation-type',
                                                    None)
        edit_user_defined_investigation_type = self.get_argument(
            'edit-user-defined-investigation-type', None)
        edit_new_investigation_type = self.get_argument(
            'edit-new-investigation-type', None)

        pt = PrepTemplate(prep_id)

        investigation_type = self._process_investigation_type(
            edit_investigation_type, edit_user_defined_investigation_type,
            edit_new_investigation_type)

        try:
            pt.investigation_type = investigation_type
        except QiitaDBColumnError as e:
            msg = html_error_message % (", invalid investigation type: ",
                                        investigation_type, str(e))
            msg = convert_text_html(msg)
            msg_level = "danger"

        if ppd_id == 0:
            top_tab = "prep_template_tab"
            sub_tab = prep_id
            prep_tab = None
        else:
            top_tab = "preprocessed_data_tab"
            sub_tab = ppd_id
            prep_tab = None

        callback((msg, msg_level, top_tab, sub_tab, prep_tab))

def preprocessor(study_id, prep_template_id, param_id, param_constructor):
    """Dispatch for preprocessor work"""
    study = Study(study_id)
    prep_template = PrepTemplate(prep_template_id)
    params = param_constructor(param_id)

    sp = StudyPreprocessor()
    try:
        preprocess_out = sp(study, prep_template, params)
    except Exception as e:
        error_msg = ''.join(format_exception_only(e, exc_info()))
        prep_template.preprocessing_status = "failed: %s" % error_msg
        preprocess_out = None

    return preprocess_out

 def remove_add_prep_template(self, fp_rpt, study, data_type_id, investigation_type):
     """add prep templates"""
     pt_id = PrepTemplate.create(
         load_template_to_dataframe(fp_rpt), study, _to_int(data_type_id), investigation_type=investigation_type
     ).id
     remove(fp_rpt)
     return pt_id

    def test_create(self):
        """Creates a new PrepTemplate"""
        pt = PrepTemplate.create(self.metadata, self.new_raw_data)
        # The returned object has the correct id
        self.assertEqual(pt.id, 3)

        # The relevant rows to common_prep_info have been added.
        obs = self.conn_handler.execute_fetchall(
            "SELECT * FROM qiita.common_prep_info WHERE raw_data_id=3")
        # raw_data_id, sample_id, center_name, center_project_name,
        # ebi_submission_accession, ebi_study_accession, emp_status_id,
        # data_type_id
        exp = [[3, 'SKB8.640193', 'ANL', 'Test Project', None, None, 1, 2],
               [3, 'SKD8.640184', 'ANL', 'Test Project', None, None, 1, 2],
               [3, 'SKB7.640196', 'ANL', 'Test Project', None, None, 1, 2]]
        self.assertEqual(sorted(obs), sorted(exp))

        # The relevant rows have been added to the raw_data_prep_columns
        obs = self.conn_handler.execute_fetchall(
            "SELECT * FROM qiita.raw_data_prep_columns WHERE raw_data_id=3")
        # raw_data_id, column_name, column_type
        exp = [[3, "str_column", "varchar"]]
        self.assertEqual(obs, exp)

        # The new table exists
        self.assertTrue(exists_table("prep_3", self.conn_handler))

        # The new table hosts the correct values
        obs = self.conn_handler.execute_fetchall(
            "SELECT * FROM qiita.prep_3")
        # sample_id, str_column
        exp = [['SKB8.640193', "Value for sample 1"],
               ['SKD8.640184', "Value for sample 2"],
               ['SKB7.640196', "Value for sample 3"]]
        self.assertEqual(sorted(obs), sorted(exp))

    def test_get_preprocess_fastq_cmd_per_sample_FASTQ_failure(self):
        metadata_dict = {
            'SKB8.640193': {'run_prefix': "sample1_failure", 'primer': 'A',
                            'barcode': 'A', 'center_name': 'ANL',
                            'platform': 'ILLUMINA',
                            'library_construction_protocol': 'A',
                            'experiment_design_description': 'A'}}
        md_template = pd.DataFrame.from_dict(metadata_dict, orient='index')
        prep_template = PrepTemplate.create(md_template, Study(1), '16S')

        # This part should fail
        fp1 = self.path_builder('sample1_failure.fastq')
        with open(fp1, 'w') as f:
            f.write('\n')
        self.files_to_remove.append(fp1)
        fp2 = self.path_builder('sample1_failure.barcodes.fastq.gz')
        with open(fp2, 'w') as f:
            f.write('\n')
        self.files_to_remove.append(fp2)
        forward_filepath_id = convert_to_id('raw_forward_seqs',
                                            'filepath_type')
        barcode_filepath_id = convert_to_id('raw_barcodes', 'filepath_type')

        fps = [(fp1, forward_filepath_id), (fp2, barcode_filepath_id)]

        filetype_id = get_filetypes()['per_sample_FASTQ']
        raw_data = RawData.create(filetype_id, [prep_template], fps)
        params = [p for p in list(PreprocessedIlluminaParams.iter())
                  if p.name == 'per sample FASTQ defaults'][0]

        with self.assertRaises(ValueError):
            _get_preprocess_fastq_cmd(raw_data, prep_template, params)