def parse_case(config, ped=None):
"""Parse case information from config or PED files.
Args:
config (dict): case config with detailed information
ped (stream): PED file stream with sample information
Returns:
dict: parsed case data
"""
if 'owner' not in config:
raise ConfigError("A case has to have a owner")
owner = config['owner']
if ped:
with open(ped, 'r') as f:
family_id, samples = parse_ped(f)
config['family'] = family_id
config['samples'] = samples
if 'family' not in config:
raise ConfigError("A case has to have a 'family'")
family_id = config['family']
individuals = parse_individuals(config['samples'])
if 'vcf_snv' not in config:
raise ConfigError("A case has to have a snv vcf")
case_data = {
'owner': owner,
'collaborators': [owner],
# Q: can we switch to a dash? we use this across other apps
'case_id': "{}-{}".format(owner, family_id),
'display_name': family_id,
'genome_build': config.get('human_genome_build'),
'rank_model_version': config.get('rank_model_version'),
'rank_score_threshold': config.get('rank_score_threshold', 5),
'analysis_date': config['analysis_date'],
'individuals': individuals,
'vcf_files': {
'vcf_snv': config.get('vcf_snv'),
'vcf_sv': config.get('vcf_sv'),
'vcf_snv_research': config.get('vcf_snv_research'),
'vcf_sv_research': config.get('vcf_sv_research'),
},
'default_panels': config.get('default_gene_panels'),
'gene_panels': config.get('gene_panels'),
'assignee': config.get('assignee'),
}
# add the pedigree figure, this is a xml file which is dumped in the db
if 'madeline' in config:
mad_path = Path(config['madeline'])
if not mad_path.exists():
raise ValueError("madeline path not found: {}".format(mad_path))
with mad_path.open('r') as in_handle:
case_data['madeline_info'] = in_handle.read()
return case_data
def parse_case(config):
"""Parse case information from config or PED files.
Args:
config (dict): case config with detailed information
Returns:
dict: parsed case data
"""
if 'owner' not in config:
raise ConfigError("A case has to have a owner")
if 'family' not in config:
raise ConfigError("A case has to have a 'family'")
individuals = parse_individuals(config['samples'])
case_data = {
'owner': config['owner'],
'collaborators': [config['owner']],
'case_id': config['family'],
'display_name': config.get('family_name', config['family']),
'genome_build': config.get('human_genome_build'),
'rank_model_version': config.get('rank_model_version'),
'rank_score_threshold': config.get('rank_score_threshold', 0),
'sv_rank_model_version': config.get('sv_rank_model_version'),
'analysis_date': config['analysis_date'],
'individuals': individuals,
'vcf_files': {
'vcf_snv': config.get('vcf_snv'),
'vcf_sv': config.get('vcf_sv'),
'vcf_str': config.get('vcf_str'),
'vcf_cancer': config.get('vcf_cancer'),
'vcf_snv_research': config.get('vcf_snv_research'),
'vcf_sv_research': config.get('vcf_sv_research'),
'vcf_cancer_research': config.get('vcf_cancer_research'),
},
'default_panels': config.get('default_gene_panels', []),
'gene_panels': config.get('gene_panels', []),
'assignee': config.get('assignee'),
'peddy_ped': config.get('peddy_ped'),
'peddy_sex': config.get('peddy_sex'),
'peddy_check': config.get('peddy_check'),
'delivery_report': config.get('delivery_report'),
'multiqc': config.get('multiqc'),
'track': config.get('track', 'rare'),
}
# add the pedigree figure, this is a xml file which is dumped in the db
if 'madeline' in config:
mad_path = Path(config['madeline'])
if not mad_path.exists():
raise ValueError("madeline path not found: {}".format(mad_path))
with mad_path.open('r') as in_handle:
case_data['madeline_info'] = in_handle.read()
if (case_data['vcf_files']['vcf_cancer']
or case_data['vcf_files']['vcf_cancer_research']):
case_data['track'] = 'cancer'
return case_data
def build_case(case_data, adapter):
"""Build a case object that is to be inserted to the database
Args:
case_data (dict): A dictionary with the relevant case information
adapter (scout.adapter.MongoAdapter)
Returns:
case_obj (dict): A case object
dict(
case_id = str, # required=True, unique
display_name = str, # If not display name use case_id
owner = str, # required
# These are the names of all the collaborators that are allowed to view the
# case, including the owner
collaborators = list, # List of institute_ids
assignee = str, # _id of a user
individuals = list, # list of dictionaries with individuals
created_at = datetime,
updated_at = datetime,
suspects = list, # List of variants referred by there _id
causatives = list, # List of variants referred by there _id
synopsis = str, # The synopsis is a text blob
status = str, # default='inactive', choices=STATUS
is_research = bool, # default=False
research_requested = bool, # default=False
rerun_requested = bool, # default=False
analysis_date = datetime,
analyses = list, # list of dict
# default_panels specifies which panels that should be shown when
# the case is opened
panels = list, # list of dictionaries with panel information
dynamic_gene_list = list, # List of genes
genome_build = str, # This should be 37 or 38
genome_version = float, # What version of the build
rank_model_version = str,
rank_score_threshold = int, # default=8
phenotype_terms = list, # List of dictionaries with phenotype information
phenotype_groups = list, # List of dictionaries with phenotype information
madeline_info = str, # madeline info is a full xml file
multiqc = str, # path to dir with multiqc information
vcf_files = dict, # A dictionary with vcf files
diagnosis_phenotypes = list, # List of references to diseases
diagnosis_genes = list, # List of references to genes
has_svvariants = bool, # default=False
is_migrated = bool # default=False
)
"""
log.info("build case with id: {0}".format(case_data['case_id']))
case_obj = {
'_id': case_data['case_id'],
'display_name': case_data.get('display_name', case_data['case_id']),
}
# Check if institute exists in database
try:
institute_id = case_data['owner']
except KeyError as err:
raise ConfigError("Case has to have a institute")
institute_obj = adapter.institute(institute_id)
if not institute_obj:
raise IntegrityError("Institute %s not found in database" %
institute_id)
case_obj['owner'] = case_data['owner']
# Owner allways has to be part of collaborators
collaborators = set(case_data.get('collaborators', []))
collaborators.add(case_data['owner'])
case_obj['collaborators'] = list(collaborators)
if case_data.get('assignee'):
case_obj['assignees'] = [case_data['assignee']]
# Individuals
ind_objs = []
try:
for individual in case_data.get('individuals', []):
ind_objs.append(build_individual(individual))
except Exception as error:
## TODO add some action here
raise error
# sort the samples to put the affected individual first
sorted_inds = sorted(ind_objs, key=lambda ind: -ind['phenotype'])
case_obj['individuals'] = sorted_inds
now = datetime.now()
case_obj['created_at'] = now
case_obj['updated_at'] = now
if case_data.get('suspects'):
case_obj['suspects'] = case_data['suspects']
if case_data.get('causatives'):
case_obj['causatives'] = case_data['causatives']
case_obj['synopsis'] = case_data.get('synopsis', '')
case_obj['status'] = 'inactive'
case_obj['is_research'] = False
case_obj['research_requested'] = False
case_obj['rerun_requested'] = False
analysis_date = case_data.get('analysis_date')
if analysis_date:
case_obj['analysis_date'] = analysis_date
# We store some metadata and references about gene panels in 'panels'
case_panels = case_data.get('gene_panels', [])
default_panels = case_data.get('default_panels', [])
panels = []
for panel_name in case_panels:
panel_obj = adapter.gene_panel(panel_name)
if not panel_obj:
raise IntegrityError("Panel %s does not exist in database" %
panel_name)
panel = {
'panel_id': panel_obj['_id'],
'panel_name': panel_obj['panel_name'],
'display_name': panel_obj['display_name'],
'version': panel_obj['version'],
'updated_at': panel_obj['date'],
'nr_genes': len(panel_obj['genes'])
}
if panel_name in default_panels:
panel['is_default'] = True
else:
panel['is_default'] = False
panels.append(panel)
case_obj['panels'] = panels
case_obj['dynamic_gene_list'] = []
# Meta data
genome_build = case_data.get('genome_build', '37')
if not genome_build in ['37', '38']:
pass
##TODO raise exception if invalid genome build was used
case_obj['genome_build'] = genome_build
case_obj['genome_version'] = case_data.get('genome_version')
if case_data.get('rank_model_version'):
case_obj['rank_model_version'] = str(case_data['rank_model_version'])
if case_data.get('sv_rank_model_version'):
case_obj['sv_rank_model_version'] = str(
case_data['sv_rank_model_version'])
if case_data.get('rank_score_threshold'):
case_obj['rank_score_threshold'] = float(
case_data['rank_score_threshold'])
# phenotype information
phenotypes = []
for phenotype in case_data.get('phenotype_terms', []):
phenotype_obj = build_phenotype(phenotype, adapter)
if phenotype_obj:
phenotypes.append(phenotype_obj)
if phenotypes:
case_obj['phenotype_terms'] = phenotypes
# phenotype groups
phenotype_groups = []
for phenotype in case_data.get('phenotype_groups', []):
phenotype_obj = build_phenotype(phenotype, adapter)
if phenotype_obj:
phenotype_groups.append(phenotype_obj)
if phenotype_groups:
case_obj['phenotype_groups'] = phenotype_groups
# Files
case_obj['madeline_info'] = case_data.get('madeline_info')
case_obj['chromograph_image_files'] = case_data.get(
'chromograph_image_files')
case_obj['chromograph_prefixes'] = case_data.get('chromograph_prefixes')
if 'multiqc' in case_data:
case_obj['multiqc'] = case_data.get('multiqc')
case_obj['vcf_files'] = case_data.get('vcf_files', {})
case_obj['delivery_report'] = case_data.get('delivery_report')
case_obj['has_svvariants'] = False
if (case_obj['vcf_files'].get('vcf_sv')
or case_obj['vcf_files'].get('vcf_sv_research')):
case_obj['has_svvariants'] = True
case_obj['has_strvariants'] = False
if (case_obj['vcf_files'].get('vcf_str')):
case_obj['has_strvariants'] = True
case_obj['is_migrated'] = False
# What experiment is used, alternatives are rare (rare disease) or cancer
case_obj['track'] = case_data.get('track', 'rare')
return case_obj
def mandatory_check_family(cls, value):
"""`family` is mandatory in a case configuration. If not
provided in config file an exception is raised"""
if value is None:
raise ConfigError("A case has to have a 'family'")
return value
def build_case(case_data, adapter):
"""Build a case object that is to be inserted to the database
Args:
case_data (dict): A dictionary with the relevant case information
adapter (scout.adapter.MongoAdapter)
Returns:
case_obj (dict): A case object
dict(
case_id = str, # required=True, unique
display_name = str, # If not display name use case_id
owner = str, # required
# These are the names of all the collaborators that are allowed to view the
# case, including the owner
collaborators = list, # List of institute_ids
assignee = str, # _id of a user
individuals = list, # list of dictionaries with individuals
created_at = datetime,
updated_at = datetime,
suspects = list, # List of variants referred by there _id
causatives = list, # List of variants referred by there _id
synopsis = str, # The synopsis is a text blob
status = str, # default='inactive', choices=STATUS
is_research = bool, # default=False
research_requested = bool, # default=False
rerun_requested = bool, # default=False
cohorts = list, # list of strings
analysis_date = datetime,
analyses = list, # list of dict
# default_panels specifies which panels that should be shown when
# the case is opened
panels = list, # list of dictionaries with panel information
dynamic_gene_list = list, # List of genes
genome_build = str, # This should be 37 or 38
rank_model_version = str,
rank_score_threshold = int, # default=8
phenotype_terms = list, # List of dictionaries with phenotype information
phenotype_groups = list, # List of dictionaries with phenotype information
madeline_info = str, # madeline info is a full xml file
multiqc = str, # path to dir with multiqc information
cnv_report = str, # path to file with cnv report
coverage_qc_report = str, # path to file with coverage and qc report
gene_fusion_report = str, # path to the gene fusions report
gene_fusion_report_research = str, # path to the research gene fusions report
vcf_files = dict, # A dictionary with vcf files
diagnosis_phenotypes = list, # List of references to diseases
diagnosis_genes = list, # List of references to genes
has_svvariants = bool, # default=False
is_migrated = bool # default=False
)
"""
LOG.info("build case with id: {0}".format(case_data["case_id"]))
case_obj = {
"_id": case_data["case_id"],
"display_name": case_data.get("display_name", case_data["case_id"]),
}
# Check if institute exists in database
try:
institute_id = case_data["owner"]
except KeyError as err:
raise ConfigError("Case has to have a institute")
institute_obj = adapter.institute(institute_id)
if not institute_obj:
raise IntegrityError("Institute %s not found in database" %
institute_id)
case_obj["owner"] = case_data["owner"]
# Owner allways has to be part of collaborators
collaborators = set(case_data.get("collaborators", []))
collaborators.add(case_data["owner"])
case_obj["collaborators"] = list(collaborators)
if case_data.get("assignee"):
case_obj["assignees"] = [case_data["assignee"]]
case_obj["smn_tsv"] = case_data.get("smn_tsv")
# Individuals
ind_objs = []
try:
for individual in case_data.get("individuals", []):
ind_objs.append(build_individual(individual))
except Exception as error:
## TODO add some action here
raise error
# sort the samples to put the affected individual first
sorted_inds = sorted(ind_objs, key=lambda ind: -ind["phenotype"])
case_obj["individuals"] = sorted_inds
now = datetime.now()
case_obj["created_at"] = now
case_obj["updated_at"] = now
if case_data.get("suspects"):
case_obj["suspects"] = case_data["suspects"]
if case_data.get("causatives"):
case_obj["causatives"] = case_data["causatives"]
case_obj["synopsis"] = case_data.get("synopsis", "")
case_obj["status"] = "inactive"
case_obj["is_research"] = False
case_obj["research_requested"] = False
case_obj["rerun_requested"] = False
case_obj["lims_id"] = case_data.get("lims_id", "")
analysis_date = case_data.get("analysis_date")
if analysis_date:
case_obj["analysis_date"] = analysis_date
# We store some metadata and references about gene panels in 'panels'
case_panels = case_data.get("gene_panels", [])
default_panels = case_data.get("default_panels", [])
panels = []
for panel_name in case_panels:
panel_obj = adapter.gene_panel(panel_name)
if not panel_obj:
LOG.warning(
"Panel %s does not exist in database and will not be saved in case document."
% panel_name)
continue
panel = {
"panel_id": panel_obj["_id"],
"panel_name": panel_obj["panel_name"],
"display_name": panel_obj["display_name"],
"version": panel_obj["version"],
"updated_at": panel_obj["date"],
"nr_genes": len(panel_obj["genes"]),
}
if panel_name in default_panels:
panel["is_default"] = True
else:
panel["is_default"] = False
panels.append(panel)
case_obj["panels"] = panels
case_obj["dynamic_gene_list"] = []
# Meta data
genome_build = case_data.get("genome_build", "37")
if not genome_build in ["37", "38"]:
pass
##TODO raise exception if invalid genome build was used
case_obj["genome_build"] = genome_build
if case_data.get("rank_model_version"):
case_obj["rank_model_version"] = str(case_data["rank_model_version"])
if case_data.get("sv_rank_model_version"):
case_obj["sv_rank_model_version"] = str(
case_data["sv_rank_model_version"])
if case_data.get("rank_score_threshold"):
case_obj["rank_score_threshold"] = float(
case_data["rank_score_threshold"])
# Cohort information
if case_data.get("cohorts"):
case_obj["cohorts"] = case_data["cohorts"]
# Check if all case cohorts are registered under the institute
institute_cohorts = set(institute_obj.get("cohorts", []))
all_cohorts = institute_cohorts.union(set(case_obj["cohorts"]))
if len(all_cohorts) > len(institute_cohorts):
# if not, update institute with new cohorts
LOG.warning("Updating institute object with new cohort terms")
adapter.institute_collection.find_one_and_update(
{"_id": institute_obj["_id"]},
{"$set": {
"cohorts": list(all_cohorts)
}})
# phenotype information
if case_data.get("phenotype_terms"):
phenotypes = []
for phenotype in case_data["phenotype_terms"]:
phenotype_obj = adapter.hpo_term(phenotype)
if phenotype_obj is None:
LOG.warning(
f"Could not find term with ID '{phenotype}' in HPO collection, skipping phenotype term."
)
continue
phenotypes.append({
"phenotype_id": phenotype,
"feature": phenotype_obj.get("description")
})
if phenotypes:
case_obj["phenotype_terms"] = phenotypes
# phenotype groups
if case_data.get("phenotype_groups"):
phenotype_groups = []
for phenotype in case_data["phenotype_groups"]:
phenotype_obj = build_phenotype(phenotype, adapter)
if phenotype_obj:
phenotype_groups.append(phenotype_obj)
if phenotype_groups:
case_obj["phenotype_groups"] = phenotype_groups
# Files
case_obj["madeline_info"] = case_data.get("madeline_info")
case_obj["custom_images"] = case_data.get("custom_images")
for custom_report in CUSTOM_CASE_REPORTS:
if custom_report in case_data:
case_obj[custom_report] = case_data.get(custom_report)
case_obj["vcf_files"] = case_data.get("vcf_files", {})
case_obj["delivery_report"] = case_data.get("delivery_report")
case_obj["has_svvariants"] = False
if case_obj["vcf_files"].get("vcf_sv") or case_obj["vcf_files"].get(
"vcf_sv_research"):
case_obj["has_svvariants"] = True
case_obj["has_strvariants"] = False
if case_obj["vcf_files"].get("vcf_str"):
case_obj["has_strvariants"] = True
case_obj["is_migrated"] = False
# What experiment is used, alternatives are rare (rare disease) or cancer
case_obj["track"] = case_data.get("track", "rare")
case_obj["group"] = case_data.get("group", [])
return case_obj
def build_case(case_data, adapter):
"""Build a case object that is to be inserted to the database
Args:
case_data (dict): A dictionary with the relevant case information
adapter (scout.adapter.MongoAdapter)
Returns:
case_obj (dict): A case object
dict(
case_id = str, # required=True, unique
display_name = str, # If not display name use case_id
owner = str, # required
# These are the names of all the collaborators that are allowed to view the
# case, including the owner
collaborators = list, # List of institute_ids
assignee = str, # _id of a user
individuals = list, # list of dictionaries with individuals
created_at = datetime,
updated_at = datetime,
suspects = list, # List of variants referred by there _id
causatives = list, # List of variants referred by there _id
synopsis = str, # The synopsis is a text blob
status = str, # default='inactive', choices=STATUS
is_research = bool, # default=False
research_requested = bool, # default=False
rerun_requested = bool, # default=False
analysis_date = datetime,
analyses = list, # list of dict
# default_panels specifies which panels that should be shown when
# the case is opened
panels = list, # list of dictionaries with panel information
dynamic_gene_list = list, # List of genes
genome_build = str, # This should be 37 or 38
genome_version = float, # What version of the build
rank_model_version = str,
rank_score_threshold = int, # default=8
phenotype_terms = list, # List of dictionaries with phenotype information
phenotype_groups = list, # List of dictionaries with phenotype information
madeline_info = str, # madeline info is a full xml file
multiqc = str, # path to dir with multiqc information
vcf_files = dict, # A dictionary with vcf files
diagnosis_phenotypes = list, # List of references to diseases
diagnosis_genes = list, # List of references to genes
has_svvariants = bool, # default=False
is_migrated = bool # default=False
)
"""
log.info("build case with id: {0}".format(case_data["case_id"]))
case_obj = {
"_id": case_data["case_id"],
"display_name": case_data.get("display_name", case_data["case_id"]),
}
# Check if institute exists in database
try:
institute_id = case_data["owner"]
except KeyError as err:
raise ConfigError("Case has to have a institute")
institute_obj = adapter.institute(institute_id)
if not institute_obj:
raise IntegrityError("Institute %s not found in database" %
institute_id)
case_obj["owner"] = case_data["owner"]
# Owner allways has to be part of collaborators
collaborators = set(case_data.get("collaborators", []))
collaborators.add(case_data["owner"])
case_obj["collaborators"] = list(collaborators)
if case_data.get("assignee"):
case_obj["assignees"] = [case_data["assignee"]]
case_obj["smn_tsv"] = case_data.get("smn_tsv")
# Individuals
ind_objs = []
try:
for individual in case_data.get("individuals", []):
ind_objs.append(build_individual(individual))
except Exception as error:
## TODO add some action here
raise error
# sort the samples to put the affected individual first
sorted_inds = sorted(ind_objs, key=lambda ind: -ind["phenotype"])
case_obj["individuals"] = sorted_inds
now = datetime.now()
case_obj["created_at"] = now
case_obj["updated_at"] = now
if case_data.get("suspects"):
case_obj["suspects"] = case_data["suspects"]
if case_data.get("causatives"):
case_obj["causatives"] = case_data["causatives"]
case_obj["synopsis"] = case_data.get("synopsis", "")
case_obj["status"] = "inactive"
case_obj["is_research"] = False
case_obj["research_requested"] = False
case_obj["rerun_requested"] = False
analysis_date = case_data.get("analysis_date")
if analysis_date:
case_obj["analysis_date"] = analysis_date
# We store some metadata and references about gene panels in 'panels'
case_panels = case_data.get("gene_panels", [])
default_panels = case_data.get("default_panels", [])
panels = []
for panel_name in case_panels:
panel_obj = adapter.gene_panel(panel_name)
if not panel_obj:
raise IntegrityError("Panel %s does not exist in database" %
panel_name)
panel = {
"panel_id": panel_obj["_id"],
"panel_name": panel_obj["panel_name"],
"display_name": panel_obj["display_name"],
"version": panel_obj["version"],
"updated_at": panel_obj["date"],
"nr_genes": len(panel_obj["genes"]),
}
if panel_name in default_panels:
panel["is_default"] = True
else:
panel["is_default"] = False
panels.append(panel)
case_obj["panels"] = panels
case_obj["dynamic_gene_list"] = []
# Meta data
genome_build = case_data.get("genome_build", "37")
if not genome_build in ["37", "38"]:
pass
##TODO raise exception if invalid genome build was used
case_obj["genome_build"] = genome_build
case_obj["genome_version"] = case_data.get("genome_version")
if case_data.get("rank_model_version"):
case_obj["rank_model_version"] = str(case_data["rank_model_version"])
if case_data.get("sv_rank_model_version"):
case_obj["sv_rank_model_version"] = str(
case_data["sv_rank_model_version"])
if case_data.get("rank_score_threshold"):
case_obj["rank_score_threshold"] = float(
case_data["rank_score_threshold"])
# phenotype information
phenotypes = []
for phenotype in case_data.get("phenotype_terms", []):
phenotype_obj = build_phenotype(phenotype, adapter)
if phenotype_obj:
phenotypes.append(phenotype_obj)
if phenotypes:
case_obj["phenotype_terms"] = phenotypes
# phenotype groups
phenotype_groups = []
for phenotype in case_data.get("phenotype_groups", []):
phenotype_obj = build_phenotype(phenotype, adapter)
if phenotype_obj:
phenotype_groups.append(phenotype_obj)
if phenotype_groups:
case_obj["phenotype_groups"] = phenotype_groups
# Files
case_obj["madeline_info"] = case_data.get("madeline_info")
case_obj["chromograph_image_files"] = case_data.get(
"chromograph_image_files")
case_obj["chromograph_prefixes"] = case_data.get("chromograph_prefixes")
if "multiqc" in case_data:
case_obj["multiqc"] = case_data.get("multiqc")
case_obj["vcf_files"] = case_data.get("vcf_files", {})
case_obj["delivery_report"] = case_data.get("delivery_report")
case_obj["has_svvariants"] = False
if case_obj["vcf_files"].get("vcf_sv") or case_obj["vcf_files"].get(
"vcf_sv_research"):
case_obj["has_svvariants"] = True
case_obj["has_strvariants"] = False
if case_obj["vcf_files"].get("vcf_str"):
case_obj["has_strvariants"] = True
case_obj["is_migrated"] = False
# What experiment is used, alternatives are rare (rare disease) or cancer
case_obj["track"] = case_data.get("track", "rare")
return case_obj
def parse_case(config):
"""Parse case information from config or PED files.
Args:
config (dict): case config with detailed information
Returns:
dict: parsed case data
"""
if "owner" not in config:
raise ConfigError("A case has to have a owner")
if "family" not in config:
raise ConfigError("A case has to have a 'family'")
individuals = parse_individuals(config["samples"])
case_data = {
"owner": config["owner"],
"collaborators": [config["owner"]],
"case_id": config["family"],
"display_name": config.get("family_name", config["family"]),
"genome_build": config.get("human_genome_build"),
"rank_model_version": str(config.get("rank_model_version", "")),
"rank_score_threshold": config.get("rank_score_threshold", 0),
"sv_rank_model_version": str(config.get("sv_rank_model_version", "")),
"analysis_date": config.get("analysis_date"),
"individuals": individuals,
"vcf_files": {
"vcf_snv": config.get("vcf_snv"),
"vcf_sv": config.get("vcf_sv"),
"vcf_str": config.get("vcf_str"),
"vcf_cancer": config.get("vcf_cancer"),
"vcf_cancer_sv": config.get("vcf_cancer_sv"),
"vcf_snv_research": config.get("vcf_snv_research"),
"vcf_sv_research": config.get("vcf_sv_research"),
"vcf_cancer_research": config.get("vcf_cancer_research"),
"vcf_cancer_sv_research": config.get("vcf_cancer_sv_research"),
},
"smn_tsv": config.get("smn_tsv"),
"default_panels": config.get("default_gene_panels", []),
"gene_panels": config.get("gene_panels", []),
"assignee": config.get("assignee"),
"peddy_ped": config.get("peddy_ped"),
"peddy_sex": config.get("peddy_sex"),
"peddy_check": config.get("peddy_check"),
"delivery_report": config.get("delivery_report"),
"multiqc": config.get("multiqc"),
"track": config.get("track", "rare"),
"chromograph_image_files": config.get("chromograph_image_files"),
"chromograph_prefixes": config.get("chromograph_prefixes"),
}
# add SMN info
LOG.debug("Checking for SMN TSV..")
if case_data["smn_tsv"]:
LOG.info("Adding SMN info from {}.".format(case_data["smn_tsv"]))
add_smn_info_case(case_data)
# add the pedigree figure, this is a xml file which is dumped in the db
if "madeline" in config:
mad_path = Path(config["madeline"])
if not mad_path.exists():
raise ValueError("madeline path not found: {}".format(mad_path))
with mad_path.open("r") as in_handle:
case_data["madeline_info"] = in_handle.read()
if (case_data["vcf_files"]["vcf_cancer"]
or case_data["vcf_files"]["vcf_cancer_research"]
or case_data["vcf_files"]["vcf_cancer_sv"]
or case_data["vcf_files"]["vcf_cancer_sv_research"]):
case_data["track"] = "cancer"
case_data["analysis_date"] = get_correct_date(
case_data.get("analysis_date"))
return case_data