def parse_individuals(samples):
"""Parse the individual information
Reformat sample information to proper individuals
Args:
samples(list(dict))
Returns:
individuals(list(dict))
"""
individuals = []
if len(samples) == 0:
raise PedigreeError("No samples could be found")
ind_ids = set()
for sample_info in samples:
parsed_ind = parse_individual(sample_info)
individuals.append(parsed_ind)
ind_ids.add(parsed_ind['individual_id'])
# Check if relations are correct
for parsed_ind in individuals:
father = parsed_ind['father']
if (father and father != '0'):
if father not in ind_ids:
raise PedigreeError('father %s does not exist in family' %
father)
mother = parsed_ind['mother']
if (mother and mother != '0'):
if mother not in ind_ids:
raise PedigreeError('mother %s does not exist in family' %
mother)
return individuals
def parse_individual(sample):
"""Parse individual information
Args:
sample (dict)
Returns:
{
'individual_id': str,
'father': str,
'mother': str,
'display_name': str,
'sex': str,
'phenotype': str,
'bam_file': str,
'analysis_type': str,
'capture_kits': list(str),
}
"""
ind_info = {}
if 'sample_id' not in sample:
raise PedigreeError("One sample is missing 'sample_id'")
sample_id = sample['sample_id']
# Check the sex
if 'sex' not in sample:
raise PedigreeError("Sample %s is missing 'sex'" % sample_id)
sex = sample['sex']
if sex not in REV_SEX_MAP:
logger.warning("'sex' is only allowed to have values from {}".format(
', '.join(list(REV_SEX_MAP.keys()))))
raise PedigreeError("Individual %s has wrong formated sex" % sample_id)
# Check the phenotype
if 'phenotype' not in sample:
raise PedigreeError("Sample %s is missing 'phenotype'" % sample_id)
phenotype = sample['phenotype']
if phenotype not in REV_PHENOTYPE_MAP:
logger.warning(
"'phenotype' is only allowed to have values from {}".format(
', '.join(list(REV_PHENOTYPE_MAP.keys()))))
raise PedigreeError("Individual %s has wrong formated phenotype" %
sample_id)
ind_info['individual_id'] = sample_id
ind_info['display_name'] = sample.get('sample_name', sample['sample_id'])
ind_info['sex'] = sex
ind_info['phenotype'] = phenotype
ind_info['father'] = sample.get('father')
ind_info['mother'] = sample.get('mother')
ind_info['bam_file'] = sample.get('bam_path')
ind_info['analysis_type'] = sample.get('analysis_type')
ind_info['capture_kits'] = ([sample.get('capture_kit')]
if 'capture_kit' in sample else [])
return ind_info
def parse_ped(ped_stream, family_type="ped"):
"""Parse out minimal family information from a PED file.
Args:
ped_stream(iterable(str))
family_type(str): Format of the pedigree information
Returns:
family_id(str), samples(list[dict])
"""
pedigree = FamilyParser(ped_stream, family_type=family_type)
if len(pedigree.families) != 1:
raise PedigreeError("Only one case per ped file is allowed")
family_id = list(pedigree.families.keys())[0]
family = pedigree.families[family_id]
samples = [
{
"sample_id": ind_id,
"father": individual.father,
"mother": individual.mother,
# Convert sex to human readable
"sex": SEX_MAP[individual.sex],
"phenotype": PHENOTYPE_MAP[int(individual.phenotype)],
} for ind_id, individual in family.individuals.items()
]
return family_id, samples
def family_relations_consistent(cls, individuals):
"""Check family relationships. If configured parent exist. If
individual(s) are configured"""
individual_dicts = [i.dict() for i in individuals]
if len(individual_dicts) == 0:
raise PedigreeError("No samples could be found")
all_ids = [i["individual_id"] for i in individual_dicts]
# Check if relations are correct
for parsed_ind in individual_dicts:
father = parsed_ind.get("father")
if father and father != "0":
if father not in all_ids:
raise PedigreeError("father %s does not exist in family" %
father)
mother = parsed_ind.get("mother")
if mother and mother != "0":
if mother not in all_ids:
raise PedigreeError("mother %s does not exist in family" %
mother)
return individuals
def parse_ped(ped_stream, family_type='ped'):
"""Parse out minimal family information from a PED file."""
pedigree = FamilyParser(ped_stream, family_type=family_type)
if len(pedigree.families) != 1:
raise PedigreeError("Only one case per ped file is allowed")
family_id = list(pedigree.families.keys())[0]
family = pedigree.families[family_id]
samples = [{
'sample_id': ind_id,
'father': individual.father,
'mother': individual.mother,
'sex': SEX_MAP[individual.sex],
'phenotype': PHENOTYPE_MAP[int(individual.phenotype)],
} for ind_id, individual in family.individuals.items()]
return family_id, samples
def build_individual(ind):
"""Build a Individual object
Args:
ind (dict): A dictionary with individual information
Returns:
ind_obj (dict): A Individual object
dict(
individual_id = str, # required
display_name = str,
sex = str,
phenotype = int,
father = str, # Individual id of father
mother = str, # Individual id of mother
capture_kits = list, # List of names of capture kits
bam_file = str, # Path to bam file
analysis_type = str, # choices=ANALYSIS_TYPES
)
"""
try:
ind_obj = dict(individual_id=ind['individual_id'])
log.info("Building Individual with id:{0}".format(
ind['individual_id']))
except KeyError as err:
raise PedigreeError("Individual is missing individual_id")
ind_obj['display_name'] = ind.get('display_name', ind_obj['individual_id'])
sex = ind.get('sex', 'unknown')
# Convert sex to .ped
try:
ind_obj['sex'] = str(REV_SEX_MAP[sex])
except KeyError as err:
raise (PedigreeError("Unknown sex: %s" % sex))
phenotype = ind.get('phenotype', 'unknown')
# Make the phenotype integers
try:
ped_phenotype = REV_PHENOTYPE_MAP[phenotype]
if ped_phenotype == -9:
ped_phenotype = 0
ind_obj['phenotype'] = ped_phenotype
except KeyError as err:
raise (PedigreeError("Unknown phenotype: %s" % phenotype))
ind_obj['father'] = ind.get('father')
ind_obj['mother'] = ind.get('mother')
ind_obj['capture_kits'] = ind.get('capture_kits', [])
ind_obj['bam_file'] = ind.get('bam_file')
ind_obj['confirmed_sex'] = ind.get('confirmed_sex')
ind_obj['confirmed_parent'] = ind.get('confirmed_parent')
ind_obj['predicted_ancestry'] = ind.get('predicted_ancestry')
# Check if the analysis type is ok
# Can be anyone of ('wgs', 'wes', 'mixed', 'unknown')
analysis_type = ind.get('analysis_type', 'unknown')
if not analysis_type in ANALYSIS_TYPES:
raise PedigreeError("Analysis type %s not allowed", analysis_type)
ind_obj['analysis_type'] = analysis_type
return ind_obj
def build_individual(ind):
"""Build a Individual object
Args:
ind (dict): A dictionary with individual information
Returns:
ind_obj (dict): A Individual object
Raises:
PedigreeError: if sex is unknown,
if phenotype is unknown,
if analysis_type is unknwon,
or missing individual_id
dict(
individual_id = str, # required
display_name = str,
sex = str,
phenotype = int,
father = str, # Individual id of father
mother = str, # Individual id of mother
capture_kits = list, # List of names of capture kits
bam_file = str, # Path to bam file,
rhocall_wig = str, # Path to a rhocall wig file showing heterozygosity levels
rhocall_bed = str, # Path to a rhocall bed file marking LOH regions
tiddit_coverage_wig = str, # Path to a TIDDIT coverage wig - overview coverage
upd_regions_bed = str, # Path to a UPD regions bed marking UPD calls
upd_sites_bed = str, # Path to a UPD sites bed, showing UPD info for vars
vcf2cytosure = str, # Path to CGH file
analysis_type = str, # choices=ANALYSIS_TYPES
)
"""
try:
ind_obj = dict(individual_id=ind['individual_id'])
log.info("Building Individual with id:{0}".format(
ind['individual_id']))
except KeyError as err:
raise PedigreeError("Individual is missing individual_id")
# Use individual_id if display_name does not exist
ind_obj['display_name'] = ind.get('display_name', ind_obj['individual_id'])
sex = ind.get('sex', 'unknown')
# Convert sex to .ped
try:
# Check if sex is coded as an integer
int(sex)
ind_obj['sex'] = str(sex)
except ValueError as err:
try:
# Sex are numbers in the database
ind_obj['sex'] = REV_SEX_MAP[sex]
except KeyError as err:
raise (PedigreeError("Unknown sex: %s" % sex))
phenotype = ind.get('phenotype', 'unknown')
# Make the phenotype integers
try:
ped_phenotype = REV_PHENOTYPE_MAP[phenotype]
if ped_phenotype == -9:
ped_phenotype = 0
ind_obj['phenotype'] = ped_phenotype
except KeyError as err:
raise (PedigreeError("Unknown phenotype: %s" % phenotype))
# Fix absolute path for individual bam files (takes care of incomplete path for demo files)
ind_files = [
'bam_file', 'mt_bam', 'vcf2cytosure', 'rhocall_bed', 'rhocall_wig',
'tiddit_coverage_wig', 'upd_regions_bed', 'upd_sites_bed'
]
for ind_file in ind_files:
file_path = ind.get(ind_file)
if file_path and os.path.exists(file_path):
ind_obj[ind_file] = os.path.abspath(file_path)
else:
ind_obj[ind_file] = None
ind_obj['father'] = ind.get('father')
ind_obj['mother'] = ind.get('mother')
ind_obj['capture_kits'] = ind.get('capture_kits', [])
ind_obj['confirmed_sex'] = ind.get('confirmed_sex')
ind_obj['confirmed_parent'] = ind.get('confirmed_parent')
ind_obj['predicted_ancestry'] = ind.get('predicted_ancestry')
# Check if the analysis type is ok
# Can be anyone of ('wgs', 'wes', 'mixed', 'unknown')
analysis_type = ind.get('analysis_type', 'unknown')
if not analysis_type in ANALYSIS_TYPES:
raise PedigreeError("Analysis type %s not allowed", analysis_type)
ind_obj['analysis_type'] = analysis_type
if 'tmb' in ind:
ind_obj['tmb'] = ind['tmb']
if 'msi' in ind:
ind_obj['msi'] = ind['msi']
if 'tumor_purity' in ind:
ind_obj['tumor_purity'] = ind['tumor_purity']
if 'tumor_type' in ind:
ind_obj['tumor_type'] = ind['tumor_type']
ind_obj['tissue_type'] = ind.get('tissue_type', 'unknown')
return ind_obj
def parse_individual(sample):
"""Parse individual information
Args:
sample (dict)
Returns:
{
'individual_id': str,
'father': str,
'mother': str,
'display_name': str,
'sex': str,
'phenotype': str,
'bam_file': str,
'mt_bam': str,
'analysis_type': str,
'vcf2cytosure': str,
'capture_kits': list(str),
'upd_sites_bed': str,
'upd_regions_bed': str,
'rhocall_bed': str,
'rhocall_wig': str,
'tiddit_coverage_wig': str,
'predicted_ancestry' = str,
'is_sma': boolean,
'is_sma_carrier': boolean,
'smn1_cn' = int,
'smn2_cn' = int,
'smn2delta78_cn' = int,
'smn_27134_cn' = int,
'tumor_type': str,
'tmb': str,
'msi': str,
'tumor_purity': float,
'tissue_type': str,
}
"""
ind_info = {}
if "sample_id" not in sample:
raise PedigreeError("One sample is missing 'sample_id'")
sample_id = sample["sample_id"]
# Check the sex
if "sex" not in sample:
raise PedigreeError("Sample %s is missing 'sex'" % sample_id)
sex = sample["sex"]
if sex not in REV_SEX_MAP:
LOG.warning("'sex' is only allowed to have values from {}".format(
", ".join(list(REV_SEX_MAP.keys()))))
raise PedigreeError("Individual %s has wrong formated sex" % sample_id)
# Check the phenotype
if "phenotype" not in sample:
raise PedigreeError("Sample %s is missing 'phenotype'" % sample_id)
phenotype = sample["phenotype"]
if phenotype not in REV_PHENOTYPE_MAP:
LOG.warning(
"'phenotype' is only allowed to have values from {}".format(
", ".join(list(REV_PHENOTYPE_MAP.keys()))))
raise PedigreeError("Individual %s has wrong formated phenotype" %
sample_id)
ind_info["individual_id"] = sample_id
ind_info["display_name"] = sample.get("sample_name", sample["sample_id"])
ind_info["sex"] = sex
ind_info["phenotype"] = phenotype
ind_info["father"] = sample.get("father")
ind_info["mother"] = sample.get("mother")
ind_info["confirmed_parent"] = sample.get("confirmed_parent")
ind_info["confirmed_sex"] = sample.get("confirmed_sex")
ind_info["predicted_ancestry"] = sample.get("predicted_ancestry")
# IGV files these can be bam or cram format
bam_path_options = ["bam_path", "bam_file", "alignment_path"]
for option in bam_path_options:
if sample.get(option) and not sample.get(option).strip() == "":
ind_info["bam_file"] = sample[option]
break
ind_info["rhocall_bed"] = sample.get("rhocall_bed",
sample.get("rhocall_bed"))
ind_info["rhocall_wig"] = sample.get("rhocall_wig",
sample.get("rhocall_wig"))
ind_info["tiddit_coverage_wig"] = sample.get(
"tiddit_coverage_wig", sample.get("tiddit_coverage_wig"))
ind_info["upd_regions_bed"] = sample.get("upd_regions_bed",
sample.get("upd_regions_bed"))
ind_info["upd_sites_bed"] = sample.get("upd_sites_bed",
sample.get("upd_sites_bed"))
ind_info["mt_bam"] = sample.get("mt_bam")
ind_info["analysis_type"] = sample.get("analysis_type")
# Path to downloadable vcf2cytosure file
ind_info["vcf2cytosure"] = sample.get("vcf2cytosure")
# load sma file if it is not done at this point!
ind_info["is_sma"] = sample.get("is_sma", None)
ind_info["is_sma_carrier"] = sample.get("is_sma_carrier", None)
ind_info["smn1_cn"] = sample.get("smn1_cn", None)
ind_info["smn2_cn"] = sample.get("smn2_cn", None)
ind_info["smn2delta78_cn"] = sample.get("smn2delta78_cn", None)
ind_info["smn_27134_cn"] = sample.get("smn_27134_cn", None)
ind_info["capture_kits"] = ([sample.get("capture_kit")]
if "capture_kit" in sample else [])
# Cancer specific values
ind_info["tumor_type"] = sample.get("tumor_type")
# tumor_mutational_burden
ind_info["tmb"] = sample.get("tmb")
ind_info["msi"] = sample.get("msi")
ind_info["tumor_purity"] = sample.get("tumor_purity")
# might be a string-formatted fraction, example: 30/90
if isinstance(ind_info["tumor_purity"], str):
ind_info["tumor_purity"] = float(Fraction(ind_info["tumor_purity"]))
ind_info["tissue_type"] = sample.get("tissue_type")
# Remove key-value pairs from ind_info where key==None and return
return removeNoneValues(ind_info)
def build_individual(ind):
"""Build a Individual object
Args:
ind (dict): A dictionary with individual information
Returns:
ind_obj (dict): A Individual object
Raises:
PedigreeError: if sex is unknown,
if phenotype is unknown,
if analysis_type is unknwon,
or missing individual_id
dict(
individual_id = str, # required
display_name = str,
sex = str,
phenotype = int,
father = str, # Individual id of father
mother = str, # Individual id of mother
capture_kits = list, # List of names of capture kits
bam_file = str, # Path to bam file,
rhocall_wig = str, # Path to a rhocall wig file showing heterozygosity levels
rhocall_bed = str, # Path to a rhocall bed file marking LOH regions
tiddit_coverage_wig = str, # Path to a TIDDIT coverage wig - overview coverage
upd_regions_bed = str, # Path to a UPD regions bed marking UPD calls
upd_sites_bed = str, # Path to a UPD sites bed, showing UPD info for vars
vcf2cytosure = str, # Path to CGH file
is_sma = boolean,
is_sma_carrier = boolean,
smn1_cn = int,
smn2_cn = int,
smn2delta78_cn = int,
smn_27134_cn = int,
predicted_ancestry = str,
analysis_type = str, # choices=ANALYSIS_TYPES
)
"""
try:
ind_obj = dict(individual_id=ind["individual_id"])
log.info("Building Individual with id:{0}".format(ind["individual_id"]))
except KeyError as err:
raise PedigreeError("Individual is missing individual_id")
# Use individual_id if display_name does not exist
ind_obj["display_name"] = ind.get("display_name", ind_obj["individual_id"])
sex = ind.get("sex", "unknown")
# Convert sex to .ped
try:
# Check if sex is coded as an integer
int(sex)
ind_obj["sex"] = str(sex)
except ValueError as err:
try:
# Sex are numbers in the database
ind_obj["sex"] = REV_SEX_MAP[sex]
except KeyError as err:
raise (PedigreeError("Unknown sex: %s" % sex))
phenotype = ind.get("phenotype", "unknown")
# Make the phenotype integers
try:
ped_phenotype = REV_PHENOTYPE_MAP[phenotype]
if ped_phenotype == -9:
ped_phenotype = 0
ind_obj["phenotype"] = ped_phenotype
except KeyError as err:
raise (PedigreeError("Unknown phenotype: %s" % phenotype))
# Fix absolute path for individual bam files (takes care of incomplete path for demo files)
ind_files = [
"bam_file",
"mt_bam",
"vcf2cytosure",
"rhocall_bed",
"rhocall_wig",
"tiddit_coverage_wig",
"upd_regions_bed",
"upd_sites_bed",
]
for ind_file in ind_files:
file_path = ind.get(ind_file)
if file_path and os.path.exists(file_path):
ind_obj[ind_file] = os.path.abspath(file_path)
else:
ind_obj[ind_file] = None
ind_obj["father"] = ind.get("father")
ind_obj["mother"] = ind.get("mother")
ind_obj["capture_kits"] = ind.get("capture_kits", [])
ind_obj["confirmed_sex"] = ind.get("confirmed_sex")
ind_obj["confirmed_parent"] = ind.get("confirmed_parent")
ind_obj["predicted_ancestry"] = ind.get("predicted_ancestry")
# Check if the analysis type is ok
# Can be anyone of ('wgs', 'wes', 'mixed', 'unknown')
analysis_type = ind.get("analysis_type", "unknown")
if not analysis_type in ANALYSIS_TYPES:
raise PedigreeError("Analysis type %s not allowed", analysis_type)
ind_obj["analysis_type"] = analysis_type
if "tmb" in ind:
ind_obj["tmb"] = ind["tmb"]
if "msi" in ind:
ind_obj["msi"] = ind["msi"]
if "tumor_purity" in ind:
ind_obj["tumor_purity"] = ind["tumor_purity"]
if "tumor_type" in ind:
ind_obj["tumor_type"] = ind["tumor_type"]
ind_obj["tissue_type"] = ind.get("tissue_type", "unknown")
# SMA
ind_obj["is_sma"] = ind.get("is_sma", None)
ind_obj["is_sma_carrier"] = ind.get("is_sma_carrier", None)
ind_obj["smn1_cn"] = ind.get("smn1_cn", None)
ind_obj["smn2_cn"] = ind.get("smn2_cn", None)
ind_obj["smn2delta78_cn"] = ind.get("smn2delta78_cn", None)
ind_obj["smn_27134_cn"] = ind.get("smn_27134_cn", None)
return ind_obj
def parse_individual(sample):
"""Parse individual information
Args:
sample (dict)
Returns:
{
'individual_id': str,
'father': str,
'mother': str,
'display_name': str,
'sex': str,
'phenotype': str,
'bam_file': str,
'mt_bam': str,
'analysis_type': str,
'vcf2cytosure': str,
'capture_kits': list(str),
'tumor_type': str,
'tmb': str,
'msi': str,
'tumor_purity': str,
'tissue_type': str,
}
"""
ind_info = {}
if 'sample_id' not in sample:
raise PedigreeError("One sample is missing 'sample_id'")
sample_id = sample['sample_id']
# Check the sex
if 'sex' not in sample:
raise PedigreeError("Sample %s is missing 'sex'" % sample_id)
sex = sample['sex']
if sex not in REV_SEX_MAP:
log.warning("'sex' is only allowed to have values from {}".format(
', '.join(list(REV_SEX_MAP.keys()))))
raise PedigreeError("Individual %s has wrong formated sex" % sample_id)
# Check the phenotype
if 'phenotype' not in sample:
raise PedigreeError("Sample %s is missing 'phenotype'" % sample_id)
phenotype = sample['phenotype']
if phenotype not in REV_PHENOTYPE_MAP:
log.warning(
"'phenotype' is only allowed to have values from {}".format(
', '.join(list(REV_PHENOTYPE_MAP.keys()))))
raise PedigreeError("Individual %s has wrong formated phenotype" %
sample_id)
ind_info['individual_id'] = sample_id
ind_info['display_name'] = sample.get('sample_name', sample['sample_id'])
ind_info['sex'] = sex
ind_info['phenotype'] = phenotype
ind_info['father'] = sample.get('father')
ind_info['mother'] = sample.get('mother')
ind_info['confirmed_parent'] = sample.get('confirmed_parent')
ind_info['confirmed_sex'] = sample.get('confirmed_sex')
ind_info['predicted_ancestry'] = sample.get('predicted_ancestry')
ind_info['bam_file'] = sample.get('bam_path')
ind_info['mt_bam'] = sample.get('mt_bam')
ind_info['analysis_type'] = sample.get('analysis_type')
# Path to downloadable vcf2cytosure file
ind_info['vcf2cytosure'] = sample.get('vcf2cytosure')
ind_info['capture_kits'] = ([sample.get('capture_kit')]
if 'capture_kit' in sample else [])
# Cancer specific values
ind_info['tumor_type'] = sample.get('tumor_type')
# tumor_mutational_burden
ind_info['tmb'] = sample.get('tmb')
ind_info['msi'] = sample.get('msi')
ind_info['tumor_purity'] = sample.get('tumor_purity')
ind_info['tissue_type'] = sample.get('tissue_type')
# Remove key-value pairs from ind_info where key==None and return
return removeNoneValues(ind_info)
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,
analysis_dates = list, # list of datetimes
# 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 = float,
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
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
)
"""
try:
log.info("build case with id: {0}".format(case_data['case_id']))
case_obj = {'_id': case_data['case_id']}
case_obj['case_id'] = case_data['case_id']
except KeyError as err:
raise PedigreeError("Case has to have a case id")
case_obj['display_name'] = case_data.get('display_name', case_obj['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
case_obj['analysis_dates'] = [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'] = float(case_data['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['vcf_files'] = case_data.get('vcf_files', {})
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['is_migrated'] = False
return case_obj
