Python ProjectSummaryConnection.get_project_sample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_project_sample [as 别名]
    def update(self):
        if not self._check_pargs(["sample_prj"]):
            return
        url = self.pargs.url if self.pargs.url else self.app.config.get("db", "url")
        if not url:
            self.app.log.warn("Please provide a valid url: got {}".format(url))
            return

        s_con = SampleRunMetricsConnection(dbname=self.app.config.get("db", "samples"), **vars(self.app.pargs))
        samples = s_con.get_samples(sample_prj=self.pargs.sample_prj)

        if self.pargs.project_id:
            self.app.log.debug("Going to update 'project_id' to {} for sample runs with 'sample_prj' == {}".format(self.pargs.project_id, self.pargs.sample_prj))
            for s in samples:
                if not s.get("project_id", None) is None:
                    if not query_yes_no("'project_id':{} for sample {}; are you sure you want to overwrite?".format(s["project_id"], s["name"]), force=self.pargs.force):
                        continue
                s["project_id"] = self.pargs.project_id
                s_con.save(s)
        if self.pargs.names:
            self.app.log.debug("Going to update 'project_sample_name' for sample runs with 'sample_prj' == {}".format(self.pargs.sample_prj))
            if os.path.exists(self.pargs.names):
                with open(self.pargs.names) as fh:
                    names_d = json.load(fh)
            else:
                names_d= ast.literal_eval(self.pargs.names)
            samples_sort = sorted(samples, key=lambda s:s["barcode_name"])
            groups = {}
            for k, g in itertools.groupby(samples_sort, key=lambda x:x["barcode_name"]):
                groups[k] = list(g)
            for barcode_name in names_d:
                sample_list = groups.get(barcode_name, None)
                if not sample_list:
                    continue
                for s in sample_list:
                    if not s.get("project_sample_name", None) is None:
                        if not query_yes_no("'project_sample_name':{} for sample {}; are you sure you want to overwrite?".format(s["project_sample_name"], s["name"]), force=self.pargs.force):
                            continue
                    s["project_sample_name"] = names_d[barcode_name]
                    s_con.save(s)
        else:
            self.app.log.info("Trying to use extensive matching...")
            p_con = ProjectSummaryConnection(dbname=self.app.config.get("db", "projects"), **vars(self.app.pargs))
            project_name = self.pargs.sample_prj
            if self.pargs.project_alias:
                project_name = self.pargs.project_alias
            for s in samples:
                project_sample = p_con.get_project_sample(project_name, s["barcode_name"], extensive_matching=True)
                if project_sample:
                    self.app.log.info("using mapping '{} : {}'...".format(s["barcode_name"], project_sample["sample_name"]))
                    s["project_sample_name"] = project_sample["sample_name"]
                    s_con.save(s)

# 需要导入模块: from scilifelab.db.statusdb import ProjectSummaryConnection [as 别名]
# 或者: from scilifelab.db.statusdb.ProjectSummaryConnection import get_project_sample [as 别名]
    def upload_qc(self):
        if not self._check_pargs(["flowcell"]):
            return
        url = self.pargs.url if self.pargs.url else self.app.config.get("db", "url")
        if not url:
            self.app.log.warn("Please provide a valid url: got {}".format(url))
            return
        if not validate_fc_directory_format(self.pargs.flowcell):
            self.app.log.warn(
                "Path '{}' does not conform to bcbio flowcell directory format; aborting".format(self.pargs.flowcell)
            )
            return

        runinfo_csv = os.path.join(os.path.abspath(self.pargs.flowcell), "{}.csv".format(fc_id(self.pargs.flowcell)))
        runinfo_yaml = os.path.join(os.path.abspath(self.pargs.flowcell), "run_info.yaml")
        (fc_date, fc_name) = fc_parts(self.pargs.flowcell)
        if int(fc_date) < 120815:
            self.log.info("Assuming pre-casava based file structure for {}".format(fc_id(self.pargs.flowcell)))
            qc_objects = self._collect_pre_casava_qc()
        else:
            self.log.info("Assuming casava based file structure for {}".format(fc_id(self.pargs.flowcell)))
            qc_objects = self._collect_casava_qc()

        if len(qc_objects) == 0:
            self.log.info("No out-of-date qc objects for {}".format(fc_id(self.pargs.flowcell)))
            return
        else:
            self.log.info("Retrieved {} updated qc objects".format(len(qc_objects)))

        s_con = SampleRunMetricsConnection(dbname=self.app.config.get("db", "samples"), **vars(self.app.pargs))
        fc_con = FlowcellRunMetricsConnection(dbname=self.app.config.get("db", "flowcells"), **vars(self.app.pargs))
        p_con = ProjectSummaryConnection(dbname=self.app.config.get("db", "projects"), **vars(self.app.pargs))
        for obj in qc_objects:
            if self.app.pargs.debug:
                self.log.debug("{}: {}".format(str(obj), obj["_id"]))
            if isinstance(obj, FlowcellRunMetricsDocument):
                dry("Saving object {}".format(repr(obj)), fc_con.save(obj))
            if isinstance(obj, SampleRunMetricsDocument):
                project_sample = p_con.get_project_sample(
                    obj.get("sample_prj", None), obj.get("barcode_name", None), self.pargs.extensive_matching
                )
                if project_sample:
                    obj["project_sample_name"] = project_sample["sample_name"]
                dry("Saving object {}".format(repr(obj)), s_con.save(obj))

# 需要导入模块: from scilifelab.db.statusdb import ProjectSummaryConnection [as 别名]
# 或者: from scilifelab.db.statusdb.ProjectSummaryConnection import get_project_sample [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_project_sample [as 别名]

#.........这里部分代码省略.........
        s_param["sequencing_mode"] = runp.get("RunMode","High Output")
        s_param["sequencing_software"] = "RTA {}".format(runp.get("RTAVersion"))
        if s_param["sequencing_platform"] == "MiSeq":
            s_param["sequencing_software"] = "MCS {}/{}".format(runp.get("MCSVersion"),s_param["sequencing_software"])
        else:
            s_param["sequencing_software"] = "{} {}/{}".format(runp.get("ApplicationName"),runp.get("ApplicationVersion"),s_param["sequencing_software"])
        s_param["is_paired"] = fc_con.is_paired_end(str(fc))
        if s_param["is_paired"] is None:
            LOG.warn("Could not determine run setup for flowcell {}. Will assume paired-end.".format(fc))
            s_param["is_paired"] = True
        s_param.update(software_versions)
        s_param["phix_error_rate"] = fc_con.get_phix_error_rate(str(fc), s["lane"])
        if phix:
            s_param["phix_error_rate"] = _get_phix_error_rate(s["lane"], phix)
        # Get quality score from demultiplex stats, if that fails
        # (which it shouldn't), fall back on fastqc data.
        (avg_quality_score, pct_q30_bases) = fc_con.get_barcode_lane_statistics(project_name, s.get("barcode_name"), fc, s["lane"])
        s_param['avg_quality_score'] = avg_quality_score if avg_quality_score else calc_avg_qv(s)
        if not s_param['avg_quality_score']:
            LOG.warn("Setting average quality failed for sample {}, id {}".format(s.get("name"), s.get("_id")))
        s_param['pct_q30_bases'] = pct_q30_bases
        if not s_param['pct_q30_bases']:
            LOG.warn("Setting % of >= Q30 Bases (PF) failed for sample {}, id {}".format(s.get("name"), s.get("_id")))
        # Compare phix error and qv to cutoffs
        err_stat = "OK"
        qv_stat = "OK"
        if s_param["phix_error_rate"] > cutoffs["phix_err_cutoff"]:
            err_stat = "HIGH"
        elif s_param["phix_error_rate"] == -1:
            err_stat = "N/A"
        if s_param["avg_quality_score"] < cutoffs["qv_cutoff"]:
            qv_stat = "LOW"
        output_data["stdout"].write("{:>18}\t{:>6}\t{:>12}\t{:>12}\t{:>12}\t{:>12}\n".format(s["barcode_name"], s["lane"], s_param["phix_error_rate"], err_stat, s_param["avg_quality_score"], qv_stat))

        # Update/set remaning sample run parameters, falling back on project defaults if *key* is missing
        s_param['ordered_amount'] = s_param.get('ordered_amount',
                                                p_con.get_ordered_amount(project_name,
                                                                         samples=p_con.get_entry(project_name,'samples')))
        s_param['customer_reference'] = s_param.get('customer_reference', project.get('customer_reference'))
        s_param['uppnex_project_id'] = s_param.get('uppnex_project_id', project.get('uppnex_id'))

        # Override database settings if options passed at command line
        if ordered_million_reads:
            s_param["ordered_amount"] = _get_ordered_million_reads(s["barcode_name"], ordered_million_reads)
        if bc_count:
            s_param["rounded_read_count"] = _round_read_count_in_millions(_get_bc_count(s["barcode_name"], bc_count, s))
        else:
            s_param["rounded_read_count"] = _round_read_count_in_millions(s_param["rounded_read_count"])
        if uppnex_id:
            s_param["uppnex_project_id"] = uppnex_id
        if customer_reference:
            s_param["customer_reference"] = customer_reference

        # Get the project sample name corresponding to the sample run
        project_sample = p_con.get_project_sample(project_name, s.get("project_sample_name", None))
        if project_sample:
            LOG.debug("project sample run metrics mapping found: '{}' : '{}'".format(s["name"], project_sample["sample_name"]))
            project_sample_item = project_sample['project_sample']
            # Set project_sample_d: a dictionary mapping from sample run metrics name to sample run metrics database id
            project_sample_d = _set_project_sample_dict(project_sample_item, source)
            if not project_sample_d:
                LOG.warn("No sample_run_metrics information for sample '{}', barcode name '{}', id '{}'\n\tProject summary information {}".format(s["name"], s["barcode_name"], s["_id"], project_sample))
            # Check if sample run metrics name present in project database: if so, verify that database ids are consistent
            if s["name"] not in project_sample_d.keys():
                LOG.warn("no such sample run metrics '{}' in project sample run metrics dictionary".format(s["name"]) )
            else:
                if s["_id"] == project_sample_d[s["name"]]:
                    LOG.debug("project sample run metrics mapping found: '{}' : '{}'".format(s["name"], project_sample_d[s["name"]]))
                else:
                    LOG.warn("inconsistent mapping for '{}': '{}' != '{}' (project summary id)".format(s["name"], s["_id"], project_sample_d[s["name"]]))
            s_param['customer_name'] = project_sample_item.get("customer_name", None)

            # Always normalize submitted id, since module textttable does not support unicode
            if type(s_param['customer_name']) is unicode:
                s_param['customer_name'] = unicodedata.normalize('NFKD', s_param['customer_name']).encode('ascii', 'ignore')
        # No project sample found. Manual upload to database necessary.
        else:
            s_param['customer_name'] = None
            LOG.warn("No project sample name found for sample run name '{}'".format(s["barcode_name"]))
            LOG.info("Please run 'pm qc upload-qc FLOWCELL_ID --extensive-matching' to update project sample names ")
            LOG.info("or 'pm qc update --sample_prj PROJECT_NAME --names BARCODE_TO_SAMPLE_MAP to update project sample names.")
            LOG.info("Please refer to the pm documentation for examples.")
            query_ok(force=kw.get("force", False))

        # Finally assess sequencing success, update parameters and set outputs
        s_param['success'] = sequencing_success(s_param, cutoffs)
        s_param.update({k:"N/A" for k in s_param.keys() if s_param[k] is None or s_param[k] ==  "" or s_param[k] == -1.0})
        if sample_count[s.get("barcode_name")] > 1:
            outfile = "{}_{}_{}_{}.pdf".format(s["barcode_name"], s["date"], s["flowcell"], s["lane"])
        else:
            outfile = "{}_{}_{}.pdf".format(s["barcode_name"], s["date"], s["flowcell"])
        s_param["outfile"] = outfile
        s_param_out.append(s_param)

    # Write final output to reportlab and rst files
    output_data["debug"].write(json.dumps({'s_param': s_param_out, 'sample_runs':{s["name"]:s["barcode_name"] for s in sample_run_list}}))
    notes = [make_note(headers=headers, paragraphs=paragraphs, **sp) for sp in s_param_out]
    rest_notes = make_sample_rest_notes("{}_{}_{}_sample_summary.rst".format(project_name, s.get("date", None), s.get("flowcell", None)), s_param_out)
    concatenate_notes(notes, "{}_{}_{}_sample_summary.pdf".format(project_name, s.get("date", None), s.get("flowcell", None)))
    return output_data

# 需要导入模块: from scilifelab.db.statusdb import ProjectSummaryConnection [as 别名]
# 或者: from scilifelab.db.statusdb.ProjectSummaryConnection import get_project_sample [as 别名]
def project_status_note(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, **kw):
    """Make a project status note. Used keywords:

    :param project_name: project name
    :param user: db user name
    :param password: db password
    :param url: db url
    :param use_ps_map: use project summary mapping
    :param use_bc_map: use project to barcode name mapping
    :param check_consistency: check consistency between mappings
    :param ordered_million_reads: number of ordered reads in millions
    :param uppnex_id: the uppnex id
    :param customer_reference: customer project name
    :param exclude_sample_ids: exclude some sample ids from project note
    :param project_alias: project alias name
    :param sample_aliases: sample alias names
    :param projectdb: project db name
    :param samplesdb: samples db name
    :param flowcelldb: flowcells db name
    :param include_all_samples: include all samples in report
    """
    # parameters
    parameters = {
        "project_name" : project_name,
        "finished" : "Not finished, or cannot yet assess if finished.",
        }
    # 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', 'CustomerID', 'BarcodeSeq', 'MSequenced', 'MOrdered', 'Status']

    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)

    # Set report paragraphs
    paragraphs = project_note_paragraphs()
    headers = project_note_headers()
    # Set local param variable
    param = parameters
    
    # 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))

    # 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))
    param['customer_reference'] = param.get('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 = []
    all_passed = True
    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():
#.........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_project_sample [as 别名]

#.........这里部分代码省略.........

    # 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 = []
    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[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['default'])
        # Get run mode
        s_param["run_mode"] = fc_con.get_run_mode(str(fc))
        s_param.update(software_versions)
        s_param["phix_error_rate"] = fc_con.get_phix_error_rate(str(fc), s["lane"])
        if phix:
            s_param["phix_error_rate"] = _get_phix_error_rate(s["lane"], phix)
        s_param['avg_quality_score'] = calc_avg_qv(s)
        if not s_param['avg_quality_score']:
            LOG.warn("Calculation of average quality failed for sample {}, id {}".format(s.get("name"), s.get("_id")))

        # Compare phix error and qv to cutoffs
        err_stat = "OK"
        qv_stat = "OK"
        if s_param["phix_error_rate"] > cutoffs["phix_err_cutoff"]:
            err_stat = "HIGH"
        elif s_param["phix_error_rate"] == -1:
            err_stat = "N/A"
        if s_param["avg_quality_score"] < cutoffs["qv_cutoff"]:
            qv_stat = "LOW"
        output_data["stdout"].write("{:>18}\t{:>6}\t{:>12}\t{:>12}\t{:>12}\t{:>12}\n".format(s["barcode_name"], s["lane"], s_param["phix_error_rate"], err_stat, s_param["avg_quality_score"], qv_stat))

        # Update/set remaning sample run parameters, falling back on project defaults if *key* is missing
        s_param['ordered_amount'] = s_param.get('ordered_amount', p_con.get_ordered_amount(project_name))
        s_param['customer_reference'] = s_param.get('customer_reference', project.get('customer_reference'))
        s_param['uppnex_project_id'] = s_param.get('uppnex_project_id', project.get('uppnex_id'))

        # Override database settings if options passed at command line
        if ordered_million_reads:
            s_param["ordered_amount"] = _get_ordered_million_reads(s["barcode_name"], ordered_million_reads)
        if bc_count:
            s_param["rounded_read_count"] = _round_read_count_in_millions(_get_bc_count(s["barcode_name"], bc_count, s))
        else:
            s_param["rounded_read_count"] = _round_read_count_in_millions(s_param["rounded_read_count"])
        if uppnex_id:
            s_param["uppnex_project_id"] = uppnex_id
        if customer_reference:
            s_param["customer_reference"] = customer_reference

        # Get the project sample name corresponding to the sample run
        project_sample = p_con.get_project_sample(project_name, s.get("project_sample_name", None))
        if project_sample:
            LOG.debug("project sample run metrics mapping found: '{}' : '{}'".format(s["name"], project_sample["sample_name"]))
            project_sample_item = project_sample['project_sample']
            # Set project_sample_d: a dictionary mapping from sample run metrics name to sample run metrics database id
            project_sample_d = _set_project_sample_dict(project_sample_item)
            if not project_sample_d:
                LOG.warn("No sample_run_metrics information for sample '{}', barcode name '{}', id '{}'\n\tProject summary information {}".format(s["name"], s["barcode_name"], s["_id"], project_sample))
            # Check if sample run metrics name present in project database: if so, verify that database ids are consistent
            if s["name"] not in project_sample_d.keys():
                LOG.warn("no such sample run metrics '{}' in project sample run metrics dictionary".format(s["name"]) )
            else:
                if s["_id"] == project_sample_d[s["name"]]:
                    LOG.debug("project sample run metrics mapping found: '{}' : '{}'".format(s["name"], project_sample_d[s["name"]]))
                else:
                    LOG.warn("inconsistent mapping for '{}': '{}' != '{}' (project summary id)".format(s["name"], s["_id"], project_sample_d[s["name"]]))
            s_param['customer_name'] = project_sample_item.get("customer_name", None)

        # No project sample found. Manual upload to database necessary.
        else:
            s_param['customer_name'] = None
            LOG.warn("No project sample name found for sample run name '{}'".format(s["barcode_name"]))
            LOG.info("Please run 'pm qc upload-qc FLOWCELL_ID --extensive-matching' to update project sample names ")
            LOG.info("or 'pm qc update --sample_prj PROJECT_NAME --names BARCODE_TO_SAMPLE_MAP to update project sample names.")
            LOG.info("Please refer to the pm documentation for examples.")
            query_ok(force=kw.get("force", False))

        # Finally assess sequencing success, update parameters and set outputs
        s_param['success'] = sequencing_success(s_param, cutoffs)
        s_param.update({k:"N/A" for k in s_param.keys() if s_param[k] is None or s_param[k] ==  "" or s_param[k] == -1.0})
        if sample_count[s.get("barcode_name")] > 1:
            outfile = "{}_{}_{}_{}.pdf".format(s["barcode_name"], s["date"], s["flowcell"], s["lane"])
        else:
            outfile = "{}_{}_{}.pdf".format(s["barcode_name"], s["date"], s["flowcell"])
        s_param["outfile"] = outfile
        s_param_out.append(s_param)

    # Write final output to reportlab and rst files
    output_data["debug"].write(json.dumps({'s_param': s_param_out, 'sample_runs':{s["name"]:s["barcode_name"] for s in sample_run_list}}))
    notes = [make_note(headers=headers, paragraphs=paragraphs, **sp) for sp in s_param_out]
    rest_notes = make_sample_rest_notes("{}_{}_{}_sample_summary.rst".format(project_name, s.get("date", None), s.get("flowcell", None)), s_param_out)
    concatenate_notes(notes, "{}_{}_{}_sample_summary.pdf".format(project_name, s.get("date", None), s.get("flowcell", None)))
    return output_data