Python ProjectSummaryConnection.get_info_source方法代码示例

# 需要导入模块: from scilifelab.db.statusdb import ProjectSummaryConnection [as 别名]
# 或者: from scilifelab.db.statusdb.ProjectSummaryConnection import get_info_source [as 别名]
def _project_status_note_table(project_name=None, username=None, password=None, url=None,
                               use_ps_map=True, use_bc_map=False, check_consistency=False,
                               ordered_million_reads=None, uppnex_id=None, customer_reference=None,
                               exclude_sample_ids={}, project_alias=None, sample_aliases={},
                               projectdb="projects", samplesdb="samples", flowcelldb="flowcells",
                               include_all_samples=False, param={}, **kw):

    # mapping project_summary to parameter keys
    ps_to_parameter = {"scilife_name":"scilife_name", "customer_name":"customer_name", "project_name":"project_name"}
    # mapping project sample to table
    table_keys = ['ScilifeID', 'SubmittedID', 'BarcodeSeq', 'MSequenced', 'MOrdered']

    output_data = {'stdout':StringIO(), 'stderr':StringIO(), 'debug':StringIO()}
    # Connect and run
    s_con = SampleRunMetricsConnection(dbname=samplesdb, username=username, password=password, url=url)
    fc_con = FlowcellRunMetricsConnection(dbname=flowcelldb, username=username, password=password, url=url)
    p_con = ProjectSummaryConnection(dbname=projectdb, username=username, password=password, url=url)

    #Get the information source for this project
    source = p_con.get_info_source(project_name)

    # Get project summary from project database
    sample_aliases = _literal_eval_option(sample_aliases, default={})
    prj_summary = p_con.get_entry(project_name)
    if not prj_summary:
        LOG.warn("No such project '{}'".format(project_name))
        return
    LOG.debug("Working on project '{}'.".format(project_name))

    # Determine if project is finished by getting all samples sequenced date
    try:
        all_samples_sequenced = prj_summary['project_summary']['all_samples_sequenced']
    except (TypeError,KeyError):
        all_samples_sequenced = False

    # Get sample run list and loop samples to make mapping sample -> {sampleruns}
    sample_run_list = _set_sample_run_list(project_name, flowcell=None, project_alias=project_alias, s_con=s_con)
    samples = {}
    for s in sample_run_list:
        prj_sample = p_con.get_project_sample(project_name, s.get("project_sample_name", None))
        if prj_sample:
            sample_name = prj_sample['project_sample'].get("scilife_name", None)
            s_d = {s["name"] : {'sample':sample_name, 'id':s["_id"]}}
            samples.update(s_d)
        else:
            if s["barcode_name"] in sample_aliases:
                s_d = {sample_aliases[s["barcode_name"]] : {'sample':sample_aliases[s["barcode_name"]], 'id':s["_id"]}}
                samples.update(s_d)
            else:
                s_d = {s["name"]:{'sample':s["name"], 'id':s["_id"], 'barcode_name':s["barcode_name"]}}
                LOG.warn("No mapping found for sample run:\n  '{}'".format(s_d))

    # Convert to mapping from desired sample name to list of aliases
    # Less important for the moment; one solution is to update the
    # Google docs summary table to use the P names
    sample_dict = prj_summary['samples']
    param.update({key:prj_summary.get(ps_to_parameter[key], None) for key in ps_to_parameter.keys()})
    param["ordered_amount"] = param.get("ordered_amount", p_con.get_ordered_amount(project_name, samples=sample_dict))

    if not param.get('customer_reference') :
        try:
            param['customer_reference'] = prj_summary['details']['customer_project_reference']
        except (TypeError,KeyError):
            param['customer_reference'] = prj_summary.get('customer_reference')
    param['uppnex_project_id'] = param.get('uppnex_project_id', prj_summary.get('uppnex_id'))

    # Override database values if options passed at command line
    if uppnex_id:
        param["uppnex_project_id"] = uppnex_id
    if customer_reference:
        param["customer_reference"] = customer_reference

    # Process options
    ordered_million_reads = _literal_eval_option(ordered_million_reads)
    exclude_sample_ids = _literal_eval_option(exclude_sample_ids, default={})

    ## Start collecting the data
    sample_table = []
    samples_excluded = []
    last_library_preps = p_con.get_latest_library_prep(project_name)
    last_library_preps_srm = [x for l in last_library_preps.values() for x in l]
    LOG.debug("Looping through sample map that maps project sample names to sample run metrics ids")
    for k,v in samples.items():
        LOG.debug("project sample '{}' maps to '{}'".format(k, v))
        if not include_all_samples:
            if v['sample'] not in last_library_preps.keys():
                LOG.info("No library prep information for sample {}; keeping in report".format(v['sample']))
            else:
                if k not in last_library_preps_srm:
                    LOG.info("Sample run {} ('{}') is not latest library prep ({}) for project sample {}: excluding from report".format(k, v["id"], ",".join(list(set(last_library_preps[v['sample']].values()))), v['sample']))
                    continue
        else:
            pass

        if re.search("Unexpected", k):
            continue
        barcode_seq = s_con.get_entry(k, "sequence")
        # Exclude sample id?
        if _exclude_sample_id(exclude_sample_ids, v['sample'], barcode_seq):
            samples_excluded.append(v['sample'])
#.........这里部分代码省略.........

# 需要导入模块: from scilifelab.db.statusdb import ProjectSummaryConnection [as 别名]
# 或者: from scilifelab.db.statusdb.ProjectSummaryConnection import get_info_source [as 别名]
def sample_status_note(project_name=None, flowcell=None, username=None, password=None, url=None,
                       ordered_million_reads=None, uppnex_id=None, customer_reference=None, bc_count=None,
                       project_alias=[], projectdb="projects", samplesdb="samples", flowcelldb="flowcells",
                       phix=None, is_paired=True, **kw):
    """Make a sample status note. Used keywords:

    :param project_name: project name
    :param flowcell: flowcell id
    :param username: db username
    :param password: db password
    :param url: db url
    :param ordered_million_reads: number of ordered reads in millions
    :param uppnex_id: the uppnex id
    :param customer_reference: customer project name
    :param project_alias: project alias name
    :param phix: phix error rate
    :param is_paired: True if run is paired-end, False for single-end
    """
    # Cutoffs
    cutoffs = {
        "phix_err_cutoff" : 2.0,
        "qv_cutoff" : 30,
        }

    instrument = _parse_instrument_config(os.path.expanduser(kw.get("instrument_config","")))
    instrument_dict = {i['instrument_id']: i for i in instrument}

    # parameters
    parameters = {
        "project_name" : None,
        "start_date" : None,
        "FC_id" : None,
        "scilifelab_name" : None,
        "rounded_read_count" : None,
        "phix_error_rate" : None,
        "avg_quality_score" : None,
        "pct_q30_bases" : None,
        "success" : None,
        "run_mode":None,
        "is_paired":True
        }
    # key mapping from sample_run_metrics to parameter keys
    srm_to_parameter = {"project_name":"sample_prj", "FC_id":"flowcell",
                        "scilifelab_name":"barcode_name", "start_date":"date",
                        "rounded_read_count":"bc_count", "lane": "lane"}

    LOG.debug("got parameters {}".format(parameters))
    output_data = {'stdout':StringIO(), 'stderr':StringIO(), 'debug':StringIO()}
    if not _assert_flowcell_format(flowcell):
        LOG.warn("Wrong flowcell format {}; skipping. Please use the flowcell id (format \"[A-Z0-9\-]+\")".format(flowcell) )
        return output_data
    output_data = _update_sample_output_data(output_data, cutoffs)

    # Connect and run
    s_con = SampleRunMetricsConnection(dbname=samplesdb, username=username, password=password, url=url)
    fc_con = FlowcellRunMetricsConnection(dbname=flowcelldb, username=username, password=password, url=url)
    p_con = ProjectSummaryConnection(dbname=projectdb, username=username, password=password, url=url)

    # Set up paragraphs
    paragraphs = sample_note_paragraphs()
    headers = sample_note_headers()

    # Get project
    project = p_con.get_entry(project_name)
    source = p_con.get_info_source(project_name)
    if not project:
        LOG.warn("No such project '{}'".format(project_name))
        return output_data

    # Set samples list
    sample_run_list = _set_sample_run_list(project_name, flowcell, project_alias, s_con)
    if len(sample_run_list) == 0:
        LOG.warn("No samples for project '{}', flowcell '{}'. Maybe there are no sample run metrics in statusdb?".format(project_name, flowcell))
        return output_data

    # Set options
    ordered_million_reads = _literal_eval_option(ordered_million_reads)
    bc_count = _literal_eval_option(bc_count)
    phix = _literal_eval_option(phix)

    # Count number of times a sample has been run on a flowcell; if several, make lane-specific reports
    sample_count = Counter([x.get("barcode_name") for x in sample_run_list])

    # Loop samples and collect information
    s_param_out = []
    fcdoc = None
    for s in sample_run_list:
        s_param = {}
        LOG.debug("working on sample '{}', sample run metrics name '{}', id '{}'".format(s.get("barcode_name", None), s.get("name", None), s.get("_id", None)))
        s_param.update(parameters)
        s_param.update({key:s[srm_to_parameter[key]] for key in srm_to_parameter.keys()})
        fc = "{}_{}".format(s.get("date"), s.get("flowcell"))
        # Get instrument
        try:
            s_param.update(instrument_dict[fc_con.get_instrument(str(fc))])
        except:
            LOG.warn("Failed to set instrument and software versions for flowcell {} in report due to missing RunInfo -> Instrument field in statusdb. Either rerun 'pm qc update-qc' or search-and-replace 'NN' in the sample report.".format(fc))
            s_param.update(instrument_dict['default'])
        # Get run mode
        if not fcdoc or fcdoc.get("name") != fc:
#.........这里部分代码省略.........