class ReadGroup(db.Model, Base):
"""
ReadGroup entity.
:param kf_id: Unique id given by the Kid's First DCC
:param external_id: Name given to sequencing experiment by contributor
:param paired_end: The direction of the read
:param flow_cell: The identifier for the group's flow cell
:param lane_number: The group's lane
:param quality_scale: The quality score encoding of the fastq file
"""
__tablename__ = 'read_group'
__prefix__ = 'RG'
external_id = db.Column(db.Text(),
nullable=True,
doc='Name given to read group by the contributor')
flow_cell = db.Column(db.Text(),
doc='The identifier of the group\'s flow cell')
lane_number = db.Column(db.Float(), doc='The group\'s lane')
quality_scale = db.Column(db.Text(),
doc='The scale used to encode quality scores')
genomic_files = association_proxy(
'read_group_genomic_files',
'genomic_file',
creator=lambda gf: ReadGroupGenomicFile(genomic_file=gf))
read_group_genomic_files = db.relationship('ReadGroupGenomicFile',
backref='read_group',
cascade='all, delete-orphan')
class SequencingExperiment(db.Model, Base):
"""
SequencingExperiment entity.
:param kf_id: Unique id given by the Kid's First DCC
:param external_id: Name given to sequencing experiment by contributor
:param experiment_date : Date of the sequencing experiment conducted
:param experiment_strategy: Text term that represents the library strategy
:param library_name: Text term that represents the name of the library
:param library_strand: Text term that represents the library stranded-ness
:param is_paired_end: Boolean term specifies whether reads have paired end
:param platform: Name of the platform used to obtain data
:param instrument_model: Text term that represents the model of instrument
:param max_insert_size: Maximum size of the fragmented DNA
:param mean_insert_size: Mean size of the fragmented DNA
:param mean_depth: (Coverage)Describes the amount of sequence data that
is available per position in the sequenced genome territory
:param total_reads: Total reads of the sequencing experiment
:param mean_read_length: Mean lenth of the reads
"""
__tablename__ = 'sequencing_experiment'
__prefix__ = 'SE'
external_id = db.Column(db.Text(), nullable=False,
doc='Name given to sequencing experiment by'
' contributor')
experiment_date = db.Column(db.DateTime(),
doc='Date of the sequencing experiment'
' conducted')
experiment_strategy = db.Column(db.Text(), nullable=False,
doc='Text term that represents the'
' Library strategy')
library_name = db.Column(db.Text(),
doc='Text term that represents the name of the'
' library')
library_strand = db.Column(db.Text(),
doc='Text term that represents the'
' library stranded-ness')
is_paired_end = db.Column(db.Boolean(), nullable=False,
doc='Boolean term specifies whether reads have'
' paired end')
platform = db.Column(db.Text(), nullable=False,
doc='Name of the platform used to obtain data')
instrument_model = db.Column(db.Text(),
doc='Text term that represents the model of'
' instrument')
max_insert_size = db.Column(db.Integer(),
doc='Maximum size of the fragmented DNA')
mean_insert_size = db.Column(db.Float(),
doc='Mean size of the fragmented DNA')
mean_depth = db.Column(db.Float(),
doc='Mean depth or coverage describes the amount of'
' sequence data that is available per position in'
' the sequenced genome territory')
total_reads = db.Column(db.Integer(),
doc='Total reads of the sequencing experiment')
mean_read_length = db.Column(db.Float(),
doc='Mean lenth of the reads')
genomic_files = db.relationship(GenomicFile,
backref=db.backref(
'sequencing_experiment',
lazy=True))
sequencing_center_id = db.Column(KfId(),
db.ForeignKey('sequencing_center.kf_id'),
nullable=False,
doc='The kf_id of the sequencing center')
class Biospecimen(db.Model, Base):
"""
Biospecimen entity.
:param kf_id: Unique id given by the Kid's First DCC
:param external_sample_id: Name given to sample by contributor
:param external_aliquot_id: Name given to aliquot by contributor
:param composition : The cellular composition of the biospecimen.
:param source_text_tissue_type: description of the kind of tissue collected
with respect to disease status or proximity to tumor tissue
:param source_text_anatomical_site : The name of the primary disease site
of the submitted tumor biospecimen
:param age_at_event_days: Age at the time biospecimen was
acquired, expressed in number of days since birth
:param source_text_tumor_descriptor: The kind of disease present in the
tumor specimen as related to a specific timepoint
:param shipment_origin : The origin of the shipment
:param analyte_type: Text term that represents the kind of molecular
specimen analyte
:param concentration_mg_per_ml: The concentration of an analyte or aliquot
extracted from the biospecimen or biospecimen portion, measured in
milligrams per milliliter
:param volume_ul: The volume in microliters (ul) of the aliquots derived
from the analyte(s) shipped for sequencing and characterization
:param shipment_date: The date item was shipped in YYYY-MM-DD format
:param uberon_id_anatomical_site: The ID of the term from Uber-anatomy
ontology which represents harmonized anatomical ontologies
:param ncit_id_tissue_type: The ID term from the National Cancer Institute
Thesaurus which represents a harmonized tissue_type
:param ncit_id_anatomical_site: The ID term from the National Cancer
Institute Thesaurus which represents a harmonized anatomical_site
:param spatial_descriptor: Ontology term that harmonizes the spatial
concepts from Biological Spatial Ontology
:param consent_type: Short name of consent
:param dbgap_consent_code: Consent classification code from dbgap
"""
__tablename__ = 'biospecimen'
__prefix__ = 'BS'
external_sample_id = db.Column(db.Text(),
doc='Name given to sample by contributor')
external_aliquot_id = db.Column(db.Text(),
doc='Name given to aliquot by contributor')
source_text_tissue_type = db.Column(db.Text(),
doc='Description of the kind of '
'biospecimen collected')
composition = db.Column(db.Text(),
doc='The cellular composition of the biospecimen')
source_text_anatomical_site = db.Column(db.Text(),
doc='The anatomical location of '
'collection')
age_at_event_days = db.Column(db.Integer(),
doc='Age at the time of event occurred in '
'number of days since birth.')
source_text_tumor_descriptor = db.Column(db.Text(),
doc='Disease present in the '
'biospecimen')
shipment_origin = db.Column(db.Text(),
doc='The original site of the aliquot')
analyte_type = db.Column(db.Text(),
nullable=False,
doc='The molecular description of the aliquot')
concentration_mg_per_ml = db.Column(db.Float(),
doc='The concentration of the aliquot')
volume_ul = db.Column(db.Float(), doc='The volume of the aliquot')
shipment_date = db.Column(db.DateTime(),
doc='The date the aliquot was shipped')
uberon_id_anatomical_site = db.Column(db.Text(),
doc='The ID of the term from '
'Uber-anatomy ontology which '
'represents harmonized anatomical'
' ontologies')
ncit_id_tissue_type = db.Column(db.Text(),
doc='The ID term from the National Cancer'
'Institute Thesaurus which represents a '
'harmonized tissue_type')
ncit_id_anatomical_site = db.Column(db.Text(),
doc='The ID term from the National'
'Cancer Institute Thesaurus which '
'represents a harmonized'
' anatomical_site')
spatial_descriptor = db.Column(db.Text(),
doc='Ontology term that harmonizes the'
'spatial concepts from Biological Spatial'
' Ontology')
method_of_sample_procurement = db.Column(db.Text(),
doc='The method used to procure '
'the sample used to extract '
'analyte(s)')
participant_id = db.Column(KfId(),
db.ForeignKey('participant.kf_id'),
nullable=False,
doc='The kf_id of the biospecimen\'s donor')
sequencing_center_id = db.Column(KfId(),
db.ForeignKey('sequencing_center.kf_id'),
nullable=False,
doc='The kf_id of the sequencing center')
consent_type = db.Column(db.Text(), doc='Short name of consent')
dbgap_consent_code = db.Column(
db.Text(), doc='Consent classification code from dbgap')
genomic_files = association_proxy(
'biospecimen_genomic_files',
'genomic_file',
creator=lambda genomic_file: BiospecimenGenomicFile(genomic_file=
genomic_file))
diagnoses = association_proxy(
'biospecimen_diagnoses',
'diagnosis',
creator=lambda dg: BiospecimenDiagnosis(diagnosis=dg))
biospecimen_genomic_files = db.relationship(BiospecimenGenomicFile,
backref='biospecimen',
cascade='all, delete-orphan')