Skip to content

Instantly share code, notes, and snippets.

@satra
Created September 27, 2022 00:32
Show Gist options
  • Save satra/f2704caefd7d23038e9aee33d91e15c4 to your computer and use it in GitHub Desktop.
Save satra/f2704caefd7d23038e9aee33d91e15c4 to your computer and use it in GitHub Desktop.
encode biosample schema 26+
{
"title": "Biosample",
"description": "Schema for submitting a biosample.",
"comment": "For cultured samples this object represents unique growths or culture harvests.",
"id": "/profiles/biosample.json",
"$schema": "http://json-schema.org/draft-04/schema#",
"type": "object",
"required": [
"award",
"lab",
"source",
"organism",
"biosample_ontology"
],
"identifyingProperties": [
"uuid",
"accession",
"aliases"
],
"additionalProperties": false,
"mixinProperties": [
{
"$ref": "mixins.json#/genetic_modifications"
},
{
"$ref": "mixins.json#/biosample_ontology"
},
{
"$ref": "mixins.json#/product_id"
},
{
"$ref": "mixins.json#/lot_id"
},
{
"$ref": "mixins.json#/source"
},
{
"$ref": "mixins.json#/references"
},
{
"$ref": "mixins.json#/documents"
},
{
"$ref": "mixins.json#/submitter_comment"
},
{
"$ref": "mixins.json#/notes"
},
{
"$ref": "mixins.json#/submitted"
},
{
"$ref": "mixins.json#/attribution"
},
{
"$ref": "mixins.json#/accessioned_status"
},
{
"$ref": "mixins.json#/schema_version"
},
{
"$ref": "mixins.json#/aliases"
},
{
"$ref": "mixins.json#/url"
},
{
"$ref": "mixins.json#/accession"
},
{
"$ref": "mixins.json#/uuid"
}
],
"dependencies": {
"biosample_ontology": {
"not": {
"properties": {
"biosample_ontology": {
"linkTo": "BiosampleType",
"linkEnum": [
"25d5ad53-15fd-4a44-878a-ece2f7e86509",
"2b3b4181-45b6-4da1-82f8-104e28601d1e"
]
},
"organism": {
"linkTo": "Organism",
"linkEnum": [
"7745b647-ff15-4ff3-9ced-b897d4e2983c"
]
}
}
}
},
"post_synchronization_time_units": {
"comment": "Biosample with a specified post_synchronization_units requires post_synchronization_time specification and specification of the model organism synchronization stage.",
"allOf": [
{
"not": {
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"7745b647-ff15-4ff3-9ced-b897d4e2983c",
"3413218c-3d86-498b-a0a2-9a406638e786"
]
}
}
}
},
{
"oneOf": [
{
"required": [
"fly_synchronization_stage",
"post_synchronization_time"
]
},
{
"required": [
"worm_synchronization_stage",
"post_synchronization_time"
]
}
]
}
]
},
"post_treatment_time": {
"required": [
"post_treatment_time_units",
"treatments"
],
"comment": "Biosample with a specified post_treatment_time requires non-empty treatments list and post_treatment_time_units specification.",
"properties": {
"treatments": {
"minItems": 1
}
}
},
"post_treatment_time_units": {
"required": [
"post_treatment_time",
"treatments"
],
"comment": "Biosample with a specified post_treatment_time_units requires non-empty treatments list post_treatment_time specification.",
"properties": {
"treatments": {
"minItems": 1
}
}
},
"post_differentiation_time": {
"required": [
"post_differentiation_time_units"
],
"comment": "Biosample with a specified post_differentiation_time requires post_differentiation_time_units specification."
},
"post_differentiation_time_units": {
"required": [
"post_differentiation_time"
],
"comment": "Biosample with a specified post_differentiation_time_units requires post_differentiation_time specification."
},
"post_nucleic_acid_delivery_time": {
"required": [
"post_nucleic_acid_delivery_time_units"
],
"comment": "Biosample with a specified post_nucleic_acid_delivery_time requires post_nucleic_acid_delivery_time_units specification."
},
"post_nucleic_acid_delivery_time_units": {
"required": [
"post_nucleic_acid_delivery_time"
],
"comment": "Biosample with a specified post_nucleic_acid_delivery_time_units requires post_nucleic_acid_delivery_time specification."
},
"pooled_from": {
"comment": "Biosample with a specified pooled_from list requires at least two entries in the list.",
"properties": {
"pooled_from": {
"minItems": 2
}
}
},
"starting_amount": {
"required": [
"starting_amount_units"
],
"comment": "Biosamples with a specified starting_amount require starting_amount_units to also be specified."
},
"starting_amount_units": {
"required": [
"starting_amount"
],
"comment": "Biosamples with a specified starting_amount_units require starting_amount to also be specified."
},
"PMI": {
"required": [
"PMI_units"
],
"comment": "Tissue biosamples with a specified PMI require PMI_units to also be specified."
},
"PMI_units": {
"required": [
"PMI"
],
"comment": "Tissue biosamples with a specified PMI_units require PMI to also be specified."
},
"model_organism_age_units": {
"required": [
"model_organism_age"
],
"comment": "Biosample with a specified model_organism_age_units requires model_organism_age specification."
},
"model_organism_age": {
"comment": "Biosample with a specified model_organism_age requires model_organism_age_units specification.",
"required": [
"model_organism_age_units"
]
},
"model_organism_mating_status": {
"comment": "Biosample with a specified model_organism_mating_status requires model_organism_sex specification.",
"required": [
"model_organism_sex"
]
},
"organism": {
"comment": "Human biosamples are not allowed to have model organism properties, and biosample_ontology classification should be different from whole organisms.",
"oneOf": [
{
"not": {
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"7745b647-ff15-4ff3-9ced-b897d4e2983c"
]
}
}
}
},
{
"allOf": [
{
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"7745b647-ff15-4ff3-9ced-b897d4e2983c"
]
}
}
},
{
"not": {
"required": [
"model_organism_mating_status"
]
}
},
{
"not": {
"required": [
"model_organism_sex"
]
}
},
{
"not": {
"required": [
"model_organism_health_status"
]
}
},
{
"not": {
"required": [
"model_organism_age"
]
}
}
]
}
]
},
"post_synchronization_time": {
"comment": "Human and mouse biosamples are not allowed to have post_synchronization_time property. Biosample with a specified post_synchronization_time requires post_synchronization_time_units specification and model organism synchronization stage.",
"allOf": [
{
"not": {
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"7745b647-ff15-4ff3-9ced-b897d4e2983c",
"3413218c-3d86-498b-a0a2-9a406638e786"
]
}
}
}
},
{
"oneOf": [
{
"required": [
"fly_synchronization_stage",
"post_synchronization_time_units"
]
},
{
"required": [
"worm_synchronization_stage",
"post_synchronization_time_units"
]
}
]
}
]
},
"fly_life_stage": {
"comment": "Only fly biosamples are allowed to have fly_life_stage property.",
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"ab546d43-8e2a-4567-8db7-a217e6d6eea0",
"5be68469-94ba-4d60-b361-dde8958399ca",
"74144f1f-f3a6-42b9-abfd-186a1ca93198",
"c3cc08b7-7814-4cae-a363-a16b76883e3f",
"d1072fd2-8374-4f9b-85ce-8bc2c61de122",
"b9ce90a4-b791-40e9-9b4d-ffb1c6a5aa2b",
"0bdd955a-57f0-4e4b-b93d-6dd1df9b766c"
]
}
}
},
"fly_synchronization_stage": {
"comment": "Only fly biosamples are allowed to have fly_synchronization_stage property.",
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"ab546d43-8e2a-4567-8db7-a217e6d6eea0",
"5be68469-94ba-4d60-b361-dde8958399ca",
"74144f1f-f3a6-42b9-abfd-186a1ca93198",
"c3cc08b7-7814-4cae-a363-a16b76883e3f",
"d1072fd2-8374-4f9b-85ce-8bc2c61de122",
"b9ce90a4-b791-40e9-9b4d-ffb1c6a5aa2b",
"0bdd955a-57f0-4e4b-b93d-6dd1df9b766c"
]
}
}
},
"worm_synchronization_stage": {
"comment": "Only roundworm biosamples are allowed to have worm_synchronization_stage property.",
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"2732dfd9-4fe6-4fd2-9d88-61b7c58cbe20",
"e3ec4c1b-a203-4fe7-a013-96c2d45ab242",
"69efae2b-4df5-4957-81da-346f1b93cb98",
"a7e711b9-534c-44a3-a782-2a15af620739",
"451f9e49-685d-40d5-ad89-760b2512262a"
]
}
}
},
"worm_life_stage": {
"comment": "Only roundworm biosamples are allowed to have worm_life_stage property.",
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"2732dfd9-4fe6-4fd2-9d88-61b7c58cbe20",
"e3ec4c1b-a203-4fe7-a013-96c2d45ab242",
"69efae2b-4df5-4957-81da-346f1b93cb98",
"a7e711b9-534c-44a3-a782-2a15af620739",
"451f9e49-685d-40d5-ad89-760b2512262a"
]
}
}
},
"mouse_life_stage": {
"comment": "Only mouse biosamples are allowed to have mouse_life_stage property.",
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"3413218c-3d86-498b-a0a2-9a406638e786"
]
}
}
},
"sample_collection_age": {
"allOf": [
{
"comment": "Only human biosamples can specify the age it was collected.",
"properties": {
"organism": {
"linkTo": "Organism",
"linkEnum": [
"7745b647-ff15-4ff3-9ced-b897d4e2983c"
]
}
}
},
{
"oneOf": [
{
"properties": {
"sample_collection_age": {
"enum": [
"unknown"
]
}
}
},
{
"required": [
"sample_collection_age_units"
],
"properties": {
"sample_collection_age_units": {
"enum": [
"year"
]
},
"sample_collection_age": {
"pattern": "^(([1-8]?\\d)|(90 or above))$"
}
}
},
{
"required": [
"sample_collection_age_units"
],
"properties": {
"sample_collection_age_units": {
"enum": [
"day",
"week",
"month"
]
},
"sample_collection_age": {
"pattern": "^(\\d+(\\.[1-9])?(\\-\\d+(\\.[1-9])?)?)$"
}
}
}
]
}
]
},
"sample_collection_age_units": {
"comment": "Age units is required if age is specified as anything but unknown.",
"required": [
"sample_collection_age"
],
"not": {
"properties": {
"sample_collection_age": {
"enum": [
"unknown"
]
}
}
}
},
"pulse_chase_time": {
"required": [
"pulse_chase_time_units"
],
"comment": "Biosamples with a specified pulse_chase_time require pulse_chase_time_units to also be specified."
},
"pulse_chase_time_units": {
"required": [
"pulse_chase_time"
],
"comment": "Biosamples with a specified pulse_chase_time_units require pulse_chase_time to also be specified."
},
"expressed_genes": {
"comment": "Biosamples with an entry in expressed_genes must have the cell_isolation_method of fluorescence activated cell sorting.",
"required": [
"cell_isolation_method"
],
"properties": {
"cell_isolation_method": {
"items": {
"enum": [
"fluorescence activated cell sorting"
]
}
}
}
}
},
"properties": {
"uuid": {
"title": "UUID",
"description": "The unique identifier associated with every object.",
"comment": "Do not submit. The uuid is set by the server.",
"type": "string",
"format": "uuid",
"serverDefault": "uuid4",
"permission": "import_items",
"requestMethod": "POST",
"readonly": true
},
"accession": {
"title": "Accession",
"description": "A unique identifier to be used to reference the object prefixed with ENC.",
"comment": "Do not submit. The accession is assigned by the server.",
"type": "string",
"format": "accession",
"serverDefault": "accession",
"permission": "import_items",
"accessionType": "BS",
"readonly": true
},
"url": {
"@type": "@id",
"rdfs:subPropertyOf": "rdfs:seeAlso",
"title": "URL",
"description": "An external resource with additional information.",
"type": "string",
"format": "uri"
},
"aliases": {
"title": "Aliases",
"description": "Lab specific identifiers to reference an object.",
"comment": "The purpose of this field is to provide a link into the lab LIMS and to facilitate shared objects.",
"type": "array",
"default": [],
"uniqueItems": true,
"items": {
"uniqueKey": "alias",
"title": "Lab alias",
"description": "A lab specific identifier to reference an object.",
"comment": "Current convention is colon separated lab name and lab identifier. (e.g. john-doe:42).",
"type": "string",
"pattern": "^(?:alexander-hoffmann|alexander-rudensky|alexander-urban|ali-mortazavi|alkes-price|ana-conesa|andrew-fire|angela-brooks|anshul-kundaje|anton-valouev|axel-visel|barbara-wold|bill-noble|bin-yu|bing-ren|bradley-bernstein|brenton-graveley|charles-gersbach|charles-lee|chris-burge|christina-leslie|christopher-vollmers|colin-dewey|david-gifford|david-gilbert|david-hafler|douglas-black|elliott-margulies|emery-bresnick|encode-awg|encode-consortium|encode-processing-pipeline|erez-aiden|erez-lieberman|eric-lecuyer|eric-mendehall|ewan-birney|feng-yue|gene-yeo|george-stamatoyannopoulos|greg-cooper|gregory-crawford|guo-cheng-yuan|haiyan-huang|haiyuan-yu|hongkai-ji|howard-chang|j-michael-cherry|jason-ernst|jason-lieb|jay-shendure|jennifer-harrow|jeremy-luban|job-dekker|joe-ecker|john-lis|john-rinn|john-stamatoyannopoulos|jonathan-pritchard|joseph-costello|kenneth-offit|kevin-struhl|kevin-white|ladeana-hillier|laura-elnitski|len-pennacchio|leonard-lipovich|manolis-kellis|manuel-garber|maria-ciofani|mark-gerstein|mats-ljungman|matteo-pellegrini|michael-bassik|michael-beer|michael-hoffman|michael-schatz|michael-snyder|morgan-giddings|nadav-ahituv|pardis-sabeti|paul-khavari|peggy-farnham|peter-bickel|peter-park|piero-carninci|rafael-irizarry|richard-myers|roadmap-epigenomics|rob-spitale|robert-klein|robert-waterston|roderic-guigo|ross-hardison|ryan-tewhey|scott-tenenbaum|sherman-weissman|souma-raychaudhuri|stephen-smale|sunduz-keles|susan-celniker|thomas-gingeras|thomas-tullius|tim-reddy|timothy-hubbard|ting-wang|tommi-jaakkola|unknown|valerie-reinke|vishwanath-iyer|w-james-kent|wei-wang|will-greenleaf|xiang-dong-fu|xiaole-shirley|xinshu-xiao|yi-xing|yijun-ruan|yin-shen|yoav-gilad|zhiping-weng|brian-oliver|david-macalpine|hugo-bellen|peter-cherbas|terry-orr-weaver|abby-dernburg|anthony-hyman|arshad-desai|david-miller|eric-lai|fabio-piano|frank-slack|gary-karpen|gregory-hannon|james-posakony|john-kim|julie-ahringer|kamran-ahmad|kris-gunsalus|lincoln-stein|michael-brent|michael-maccoss|mitzi-kuroda|nikolaus-rajewsky|norbert-perrimon|philip-green|sarah-elgin|steven-henikoff|steven-russell|susan-strome|vincenzo-pirrotta|MitaniLab|UofC-HGAC|wesley-hung|encode|modern|dnanexus|modencode|gencode|ggr|cgc|bloomington|dssc|gtex|pgp|biochain|promocell|nichd|lonza|allcells|altius|jesse-engreitz):[a-zA-Z\\d_$.+!*,()'-]+(?:\\s[a-zA-Z\\d_$.+!*,()'-]+)*$"
}
},
"schema_version": {
"title": "Schema version",
"description": "The version of the JSON schema that the server uses to validate the object.",
"comment": "Do not submit. The version used to validate the object is set by the server. The default should be set to the current version.",
"type": "string",
"pattern": "^\\d+(\\.\\d+)*$",
"requestMethod": [],
"default": "26"
},
"status": {
"title": "Status",
"type": "string",
"permission": "import_items",
"default": "in progress",
"description": "The status of the metadata object.",
"comment": "Do not submit. This is set by admins along the process of metadata submission.",
"enum": [
"in progress",
"released",
"deleted",
"replaced",
"revoked"
],
"readonly": true
},
"lab": {
"title": "Lab",
"description": "Lab associated with the submission.",
"comment": "Required. See lab.json for list of available identifiers.",
"type": "string",
"linkTo": "Lab",
"linkSubmitsFor": true
},
"award": {
"title": "Award",
"description": "Grant associated with the submission.",
"comment": "Required. See award.json for list of available identifiers.",
"type": "string",
"linkTo": "Award"
},
"date_created": {
"rdfs:subPropertyOf": "dc:created",
"title": "Date created",
"description": "The date the object was created.",
"comment": "Do not submit. The date the object is created is assigned by the server.",
"type": "string",
"anyOf": [
{
"format": "date-time"
},
{
"format": "date"
}
],
"serverDefault": "now",
"permission": "import_items",
"readonly": true
},
"submitted_by": {
"rdfs:subPropertyOf": "dc:creator",
"title": "Submitted by",
"comment": "Do not submit. The user that created the object is assigned by the server.",
"type": "string",
"linkTo": "User",
"serverDefault": "userid",
"permission": "import_items",
"readonly": true
},
"notes": {
"title": "Notes",
"description": "DCC internal notes.",
"comment": "Do not submit. A place for the DCC to keep information that does not have a place in the schema.",
"type": "string",
"pattern": "^(\\S+(\\s|\\S)*\\S+|\\S)$",
"permission": "import_items",
"formInput": "textarea",
"readonly": true
},
"submitter_comment": {
"title": "Submitter comment",
"description": "Additional information specified by the submitter to be displayed as a comment on the portal.",
"type": "string",
"pattern": "^(\\S+(\\s|\\S)*\\S+|\\S)$",
"formInput": "textarea"
},
"documents": {
"title": "Documents",
"description": "Documents that describe the biosample preparation.",
"type": "array",
"default": [],
"uniqueItems": true,
"items": {
"title": "Document",
"description": "A document that provides additional information (not data file).",
"type": "string",
"comment": "See document.json for available identifiers.",
"linkTo": "Document"
}
},
"references": {
"title": "References",
"description": "The publications that provide more information about the object.",
"type": "array",
"default": [],
"uniqueItems": true,
"items": {
"title": "Reference",
"description": "A publication that provide smore information about the object.",
"type": "string",
"linkTo": "Publication"
}
},
"source": {
"title": "Source",
"description": "The originating lab or vendor.",
"comment": "See source.json for available identifiers.",
"type": "string",
"linkTo": "Source"
},
"lot_id": {
"title": "Lot ID",
"description": "The lot identifier provided by the originating lab or vendor.",
"type": "string",
"pattern": "^(\\S+(\\s|\\S)*\\S+|\\S)$"
},
"product_id": {
"title": "Product ID",
"description": "The product identifier provided by the originating lab or vendor.",
"type": "string",
"pattern": "^(\\S+(\\s|\\S)*\\S+|\\S)$"
},
"biosample_ontology": {
"title": "Biosample ontology",
"description": "An embeded property for linking to biosample type which describes the ontology of the biosample.",
"comment": "See biosample_type.json for available identifiers.",
"type": "string",
"linkTo": "BiosampleType"
},
"genetic_modifications": {
"title": "Genetic modifications",
"description": "Genetic modification(s). Any genetic alteration of a biosample or donor.",
"comment": "Constructs, TALENs, and RNAi objects have been migrated to the GeneticModification object.",
"type": "array",
"default": [],
"uniqueItems": true,
"items": {
"title": "Genetic modification",
"description": "Genetic modification(s).",
"comment": "See genetic_modification.json for available identifiers.",
"type": "string",
"linkTo": "GeneticModification"
}
},
"alternate_accessions": {
"title": "Alternate accessions",
"description": "Accessions previously assigned to objects that have been merged with this object.",
"comment": "Do not submit. Only admins are allowed to set or update this value.",
"type": "array",
"default": [],
"permission": "import_items",
"items": {
"title": "Alternate Accession",
"description": "An accession previously assigned to an object that has been merged with this object.",
"comment": "Only accessions of objects that have status equal replaced will work here.",
"type": "string",
"format": "accession",
"pattern": "^(ENCBS\\d{3}[A-Z]{3})$|^(TSTBS\\d{6})$"
},
"readonly": true
},
"description": {
"title": "Description",
"description": "A plain text description of the biosample. Do not include experiment details, genetic modifications or treatments.",
"comment": "Free text description of the biosample, do not mix with biosample summary that is calculated and controlled.",
"type": "string",
"elasticsearch_mapping_index_type": {
"title": "Field mapping index type",
"description": "Defines one of three types of indexing available",
"type": "string",
"default": "analyzed",
"enum": [
"analyzed",
"no",
"not_analyzed"
]
},
"pattern": "^(\\S+(\\s|\\S)*\\S+|\\S)$|^$",
"formInput": "textarea"
},
"treatments": {
"title": "Treatments",
"description": "A list of treatments applied to the biosample.",
"comment": "A list of treatments applied to the biosample, it is required to be non-empty if post_treatment_time or post_treatment_time_units are specified.",
"type": "array",
"default": [],
"uniqueItems": true,
"items": {
"title": "Treatment",
"comment": "See treatment.json for available identifiers.",
"type": "string",
"linkTo": "Treatment"
}
},
"dbxrefs": {
"@type": "@id",
"rdfs:subPropertyOf": "rdfs:seeAlso",
"title": "External resources",
"description": "Biosample identifiers from external resources, such as Biosample database or Cellosaurus.",
"comment": "Do not submit. DCC personnel is responsible for submission of biosample external resource identifiers.",
"permission": "import_items",
"type": "array",
"default": [],
"uniqueItems": true,
"items": {
"title": "External identifier",
"description": "An identifier from external resource.",
"type": "string",
"pattern": "^((UCSC-ENCODE-cv:[\\S\\s\\d\\-\\(\\)\\+]+)|(GTEx:[a-zA-Z0-9\\-_]+)|(GEO:SAMN\\d+)|(Cellosaurus:CVCL_\\w{4}))$"
},
"readonly": true
},
"donor": {
"title": "Donor",
"description": "The donor or strain the biosample was originated from.",
"comment": "For human biosamples, see human_donor.json for available identifiers. For mouse biosamples, see mouse_donor.json for available identifiers. For worm biosamples, see worm_donor.json for available identifiers. For fly biosamples, see fly_donor.json for available identifiers. For manatee biosamples, see manatee_donor.json for available identifiers.",
"type": "string",
"linkTo": "Donor"
},
"organism": {
"title": "Organism",
"description": "The organism the biosample was originated from.",
"comment": "See organism.json for available identifiers.",
"type": "string",
"linkTo": "Organism"
},
"sample_collection_age": {
"title": "Sample collection age",
"description": "The age or age range of the donor when the biosample was collected.",
"comment": "This is designed specifically for cases where more than one biosamples are collected from the same human donor at different ages. Otherwise, you can considering using the age property of human donor.",
"type": "string",
"pattern": "^((\\d+(\\.[1-9])?(\\-\\d+(\\.[1-9])?)?)|(unknown)|([1-8]?\\d)|(90 or above))$"
},
"sample_collection_age_units": {
"title": "Sample collection age units",
"type": "string",
"enum": [
"day",
"week",
"month",
"year"
]
},
"passage_number": {
"title": "Passage number",
"description": "Number of passages including the passages from the source.",
"comment": "In calculating passage number, include passages from the source.",
"type": "integer",
"minimum": 0
},
"depleted_in_term_name": {
"title": "Depleted in term",
"type": "array",
"uniqueItems": true,
"description": "UBERON (Uber Anatomy Ontology) term best matching the tissue(s)/body part(s) that were removed from the biosample.",
"items": {
"type": "string",
"enum": [
"adult maxillary segment",
"antenna",
"arthropod fat body",
"digestive system",
"female gonad",
"female reproductive system",
"head",
"limb",
"male accessory sex gland",
"male reproductive system",
"salivary gland",
"testis"
]
}
},
"model_organism_mating_status": {
"title": "Model organism mating status",
"description": "The mating status of the animal.",
"comment": "The value is not available for human biosamples.",
"type": "string",
"enum": [
"mated",
"mixed",
"sterile",
"virgin"
]
},
"internal_tags": {
"title": "Internal tags",
"description": "Some biosamples are part of particular data collections.",
"comment": "Do not submit. Internal tags are for DCC use only.",
"type": "array",
"default": [],
"permission": "import_items",
"uniqueItems": true,
"items": {
"type": "string",
"enum": [
"Deeply Profiled",
"DREAM",
"ENCORE",
"ENTEx",
"RushAD",
"SESCC",
"YaleImmuneCells"
]
},
"readonly": true
},
"originated_from": {
"title": "Originated from",
"description": "A biosample that the sample was orginated from.",
"comment": "See biosample.json for available identifiers.",
"type": "string",
"linkTo": "Biosample"
},
"pooled_from": {
"title": "Pooled from",
"description": "The biosamples from which aliquots were pooled to form the biosample.",
"comment": "A list of biosamples used to create the biosample, if specified, it requires minimum of two entries.",
"type": "array",
"uniqueItems": true,
"items": {
"description": "A biosample from which an aliquot was taken to form the biosample.",
"comment": "See biosample.json for available identifiers.",
"type": "string",
"linkTo": "Biosample"
}
},
"part_of": {
"title": "Separated from",
"description": "A biosample from which a discrete component was taken. That component is this biosample.",
"comment": "See biosamples.json for available identifiers.",
"type": "string",
"linkTo": "Biosample"
},
"host": {
"title": "Host biosample",
"description": "A biosample that was hosting this biosample.",
"comment": "For example a mouse could be a host of bone marrow biosample in case of transplantation. See biosamples.json for available identifiers.",
"type": "string",
"linkTo": "Biosample"
},
"subcellular_fraction_term_name": {
"title": "Subcellular fraction",
"description": "The GO (Gene Ontology) term name for cellular component that constitutes the biosample.",
"type": "string",
"enum": [
"chromatin",
"cytosol",
"insoluble cytoplasmic fraction",
"membrane",
"mitochondria",
"nuclear matrix",
"nucleolus",
"nucleoplasm",
"nucleus",
"polysome"
]
},
"phase": {
"title": "Cell cycle phase",
"description": "Specification of cell cycle phase of the biosample.",
"comment": "The phase property should be limited to biosamples with biosample_ontology classification that belongs to [primary cell, cell line, in vitro differentiated cells].",
"type": "string",
"enum": [
"G1",
"G1b",
"G2",
"S",
"early S",
"late S",
"S1",
"S2",
"S3",
"S4"
]
},
"culture_harvest_date": {
"title": "Culture harvest date",
"description": "For cultured samples, the date the biosample was taken.",
"comment": "Date should be submitted in as YYYY-MM-DD. The property should be limited to biosamples with biosample_ontology classification that belongs to [primary cell, cell line, in vitro differentiated cells].",
"type": "string",
"format": "date"
},
"culture_start_date": {
"title": "Culture start date",
"description": "For cultured samples, the date the culture was started. For cell lines, the date this particular growth was started, not the date the line was established.",
"comment": "Date should be submitted in as YYYY-MM-DD. The property should be limited to biosamples with biosample_ontology classification that belongs to [primary cell, cell line, in vitro differentiated cells].",
"type": "string",
"format": "date"
},
"date_obtained": {
"title": "Date obtained",
"description": "For tissue samples, the date the biosample was taken.",
"comment": "Date should be submitted in as YYYY-MM-DD.",
"type": "string",
"format": "date"
},
"starting_amount": {
"title": "Starting amount",
"description": "The initial quantity of cells, tissue or animals obtained.",
"type": "number",
"minimum": 0
},
"starting_amount_units": {
"title": "Starting amount units",
"description": "The units used to quantify the amount of cells or tissue obtained.",
"type": "string",
"enum": [
"cells",
"cells/ml",
"g",
"items",
"mg",
"whole animals",
"whole embryos",
"μg",
"ng"
]
},
"PMI": {
"title": "Post-mortem interval",
"description": "The amount of time elapsed since death.",
"comment": "Post-mortem interval for tissues should be reported, if known. Using for biosamples other than tissue is currently not allowed.",
"type": "integer",
"minimum": 1
},
"PMI_units": {
"title": "Post-mortem interval units",
"description": "The unit in which the PMI time was reported.",
"comment": "Post-mortem interval units for tissues should be reported with PMI value, if known. Using for biosamples other than tissue is currently not allowed.",
"type": "string",
"enum": [
"second",
"minute",
"hour",
"day",
"week"
]
},
"preservation_method": {
"title": "Preservation method",
"description": "The method by which the sample was preserved: cryopreservation (slow-freeze) or flash-freezing.",
"comment": "Indicate the sample preservation_method if known and may be/become an experimental variable to track.",
"type": "string",
"enum": [
"cryopreservation",
"flash-freezing"
]
},
"cell_isolation_method": {
"title": "Cell isolation method",
"description": "The method by which the cell(s) in the sample were isolated.",
"comment": "Indicate the method used to isolate cell(s) in the sample. For example Fluidigm C1 cell isolation should specify: microfluidic cell sorting.",
"type": "string",
"enum": [
"micropipetting",
"microfluidic cell sorting",
"dilution",
"laser capture microdissection",
"fluorescence activated cell sorting"
]
},
"model_organism_sex": {
"title": "Model organism sex",
"type": "string",
"description": "The sex of the model organism the biosample comes from.",
"comment": "model_organism_sex is not valid for a human biosample.",
"enum": [
"female",
"male",
"mixed",
"hermaphrodite",
"unknown"
]
},
"mouse_life_stage": {
"title": "Mouse life stage",
"type": "string",
"description": "The life stage of the mouse biosample.",
"comment": "mouse_life_stage is not valid for a human biosample.",
"enum": [
"embryonic",
"postnatal",
"adult",
"unknown"
]
},
"fly_life_stage": {
"title": "Fly life stage",
"type": "string",
"description": "Fly development stage of the animals used to prepare the biosample.",
"comment": "fly_life_stage is valid only for fly biosamples.",
"enum": [
"embryonic",
"larva",
"first instar larva",
"second instar larva",
"third instar larva",
"wandering third instar larva",
"prepupa",
"pupa",
"adult"
]
},
"fly_synchronization_stage": {
"title": "Fly synchronization stage",
"description": "Fly development stage at which flies were synchronized.",
"comment": "Stage at which flies were synchronized. If available use in conjunction with time and time units post-synchronization.",
"type": "string",
"enum": [
"egg laying",
"fertilization",
"first larval molt",
"second larval molt",
"puff stage: PS (1-2), dark blue gut",
"puff stage: PS (3-6), light blue gut",
"puff stage: PS (7-9), clear gut",
"white prepupa",
"eclosion"
]
},
"post_synchronization_time": {
"title": "Post-synchronization time",
"description": "The time that elapsed past the point when animals were synchronized.",
"comment": "Use in conjunction with fly_synchronization_stage or worm_synchronization_stage to specify time elapsed post-synchronization. It requires specification of post_synchronization_time_units as well.",
"type": "string",
"pattern": "^(\\d+(\\.[1-9])?(\\-\\d+(\\.[1-9])?)?)|(unknown)$"
},
"post_synchronization_time_units": {
"title": "Post-synchronization time units",
"description": "The units of time that elapsed past the point when animals were synchronized.",
"comment": "Use in conjunction with fly_synchronization_stage or worm_synchronization_stage and post_synchronization_time to specify time elapsed post-synchronization.",
"type": "string",
"enum": [
"minute",
"hour",
"day",
"week",
"month",
"stage"
]
},
"post_treatment_time": {
"title": "Post-treatment time",
"description": "The time that elapsed past the point when biosamples were treated.",
"comment": "Use in conjunction with treatment and post_treatment_time_units to specify time elapsed post-treatment. post_treatment_time specification requires non-empty treatments list and post_treatment_time_units specification.",
"type": "string",
"pattern": "^(\\d+(\\.[1-9])?(\\-\\d+(\\.[1-9])?)?)|(unknown)$"
},
"post_treatment_time_units": {
"title": "Post-treatment time units",
"description": "The units of time that elapsed past the point when biosamples were treated.",
"comment": "Use in conjunction with post_treatment_time and treatment to specify time elapsed post-treatment. post_treatment_time_units specification requires non-empty treatments list and post_treatment_time specification.",
"type": "string",
"enum": [
"minute",
"hour",
"day",
"week",
"month",
"stage"
]
},
"post_differentiation_time": {
"title": "Post-differentiation time",
"description": "The time that elapsed past the point when biosamples were differentiated.",
"comment": "Use in conjunction with post_differentiation_time_units to specify time elapsed post-differentiation. Use of this property requires post_differentiation_time_units specification.",
"type": "integer"
},
"post_differentiation_time_units": {
"title": "Post-differentiation time units",
"description": "The units of time that elapsed past the point when biosamples were differentiated.",
"comment": "Use in conjunction with post_differentiation_time to specify time elapsed post-differentiation. Use of this property requires post_differentiation_time specification.",
"type": "string",
"enum": [
"minute",
"hour",
"day",
"week",
"month",
"stage"
]
},
"worm_life_stage": {
"title": "Worm life stage",
"type": "string",
"description": "Worm development stage of the animals used to prepare the biosample.",
"comment": "worm_life_stage is valid only for worm biosamples.",
"enum": [
"early embryonic",
"midembryonic",
"late embryonic",
"mixed stage (embryonic)",
"mixed stage (late embryonic and L1 larva)",
"L1 larva",
"L2 larva",
"L2d larva",
"L3 larva",
"L4 larva",
"L4/young adult",
"young adult",
"dauer",
"adult",
"mixed stage"
]
},
"worm_synchronization_stage": {
"title": "Worm synchronization stage",
"description": "Worm development stage at which the animals were synchronized.",
"comment": "Stage at which worms were synchronized. Use in conjunction with time and time units post-synchronization. worm_life_stage is valid only for worm biosamples.",
"type": "string",
"enum": [
"egg laying",
"egg bleaching",
"fertilization",
"4 cell",
"L1 larva starved after bleaching",
"dauer exit"
]
},
"model_organism_age": {
"title": "Age",
"description": " The age or age range of the model donor organism when biological material was sampled.",
"type": "string",
"comment": "model_organism_age is not valid for a human biosample.",
"pattern": "^((\\d+(\\.\\d+)?(\\-\\d+(\\.\\d+)?)?)|(unknown))$"
},
"model_organism_age_units": {
"title": "Age units",
"type": "string",
"description": "Age units of the model organism.",
"comment": "model_organism_age_units are not valid for a human biosample.",
"enum": [
"minute",
"hour",
"day",
"week",
"month",
"year",
"stage"
]
},
"model_organism_health_status": {
"title": "Model organism health status",
"type": "string",
"description": "Health status of the model organism.",
"comment": "model_organism_health_status is not valid for a human biosample."
},
"nih_institutional_certification": {
"type": "string",
"title": "NIH institutional certification",
"description": "Institutional certification given by the NIH for human biosamples.",
"comment": "Required for ENCODE4 human biosamples.",
"pattern": "^NIC[A-Z0-9]+$"
},
"post_nucleic_acid_delivery_time": {
"title": "Post-nucleic acid delivery time",
"description": "The time that elapsed past the point when nucleic acid was introduced into the biosample.",
"comment": "Use in conjunction with post_nucleic_acid_delivery_time_units to specify time elapsed post-nucleic acid delivery. Use of this property requires post_nucleic_acid_delivery_time_units specification.",
"type": "integer"
},
"post_nucleic_acid_delivery_time_units": {
"title": "Post-nucleic acid delivery time units",
"description": "The units of time that elapsed past the point when nucleic acid was introduced into the biosample.",
"comment": "Use in conjunction with post_nucleic_acid_delivery_time to specify time elapsed post-nucleic acid delivery. Use of this property requires post_nucleic_acid_delivery_time specification.",
"type": "string",
"enum": [
"minute",
"hour",
"day",
"week",
"month"
]
},
"disease_term_id": {
"title": "Disease ontology IDs",
"description": "Ontology identifiers describing the disease(s) affecting the biosample.",
"type": "array",
"uniqueItems": true,
"minItems": 1,
"items": {
"title": "Disease ontology ID",
"description": "Ontology identifier describing the disease affecting the biosample.",
"type": "string",
"pattern": "^(DOID:[0-9]{2,7}|HP:[0-9]{7})$"
}
},
"pulse_chase_time": {
"title": "Pulse-chase time",
"description": "The time that elapsed in the chase phase of a pulse-chase experiment.",
"comment": "Use in conjunction with pulse_chase_time_units to specify time elapsed in the chase phase of a pulse-chase experiment. Use of this property requires pulse_chase_time_units specification.",
"type": "integer"
},
"pulse_chase_time_units": {
"title": "Pulse-chase time units",
"description": "The units of time that elapsed in the chase phase of a pulse-chase experiment.",
"comment": "Use in conjunction with pulse_chase_time and treatment to specify time elapsed in the chase phase of a pulse-chase experiment. Use of this property requires pulse_chase_time specification.",
"type": "string",
"enum": [
"minute",
"hour"
]
},
"expressed_genes": {
"title": "Expressed genes",
"description": "Gene expression selected for in the biosample by sorting.",
"comment": "Use in conjunction with fluorescence activated cell sorting in cell_isolation_method to specify the gene cells are sorted on.",
"type": "array",
"uniqueItems": true,
"minItems": 1,
"items": {
"title": "Locus",
"description": "The gene expression that fluorescence activated cell sorting of the biosample is based upon.",
"type": "object",
"additionalProperties": false,
"required": [
"gene"
],
"properties": {
"gene": {
"title": "Gene",
"description": "The gene under investigation.",
"type": "string",
"linkTo": "Gene"
},
"expression_percentile": {
"title": "Gene expression percentile",
"description": "Gene expression read-out expressed as a percentile.",
"type": "integer",
"minimum": 0,
"maximum": 100
},
"expression_range_minimum": {
"title": "Gene expression range minimum",
"description": "Gene expression read-out range minimum percentage value.",
"type": "integer",
"minimum": 0,
"maximum": 100
},
"expression_range_maximum": {
"title": "Gene expression range maximum",
"description": "Gene expression read-out range maximum percentage value.",
"type": "integer",
"minimum": 0,
"maximum": 100
}
},
"dependencies": {
"expression_range_minimum": [
"expression_range_maximum"
],
"expression_range_maximum": [
"expression_range_minimum"
],
"expression_percentile": {
"not": {
"anyOf": [
{
"required": [
"expression_range_minimum"
]
},
{
"required": [
"expression_range_maximum"
]
}
]
}
}
}
}
},
"@id": {
"title": "ID",
"type": "string",
"notSubmittable": true
},
"@type": {
"title": "Type",
"type": "array",
"items": {
"type": "string"
},
"notSubmittable": true
},
"sex": {
"title": "Sex",
"type": "string",
"notSubmittable": true
},
"age": {
"title": "Age",
"type": "string",
"notSubmittable": true
},
"age_units": {
"title": "Age units",
"type": "string",
"notSubmittable": true
},
"disease_term_name": {
"title": "Disease term names",
"description": "Ontology term(s) describing the disease affecting the biosample.",
"comment": "Calculated from disease_term_id",
"type": "array",
"notSubmittable": true,
"uniqueItems": true,
"minItems": 1,
"items": {
"title": "Disease term name",
"description": "Ontology term describing the disease affecting the biosample.",
"type": "string"
}
},
"health_status": {
"title": "Health status",
"type": "string",
"notSubmittable": true
},
"life_stage": {
"title": "Life stage",
"type": "string",
"notSubmittable": true
},
"synchronization": {
"title": "Synchronization",
"type": "string",
"notSubmittable": true
},
"model_organism_donor_modifications": {
"title": "Model organism genetic modifications",
"description": "Genetic modifications made in the model organism of the biosample.",
"type": "array",
"items": {
"title": "Model organism genetic modification",
"description": "Genetic modification made in the model organism of the biosample.",
"comment": "See genetic_modification.json for available identifiers.",
"type": "string",
"linkTo": "GeneticModification"
},
"notSubmittable": true
},
"applied_modifications": {
"title": "Applied modifications",
"description": "All genetic modifications made in either the model organism and/or biosample.",
"type": "array",
"items": {
"title": "Applied modification",
"description": "Genetic modification made in either the model organism and/or biosample.",
"comment": "See genetic_modification.json for available identifiers.",
"type": "string",
"linkTo": "GeneticModification"
},
"notSubmittable": true
},
"characterizations": {
"title": "Characterizations",
"type": "array",
"items": {
"type": [
"string",
"object"
],
"linkFrom": "BiosampleCharacterization.characterizes"
}
},
"parent_of": {
"description": "The biosample(s) that have this biosample in their part_of property.",
"comment": "Do not submit. Values in the list are reverse links of a biosamples that are part_of this biosample.",
"title": "Child biosamples",
"type": "array",
"items": {
"type": [
"string",
"object"
],
"linkFrom": "Biosample.part_of"
},
"notSubmittable": true
},
"age_display": {
"title": "Age display",
"type": "string",
"notSubmittable": true
},
"depleted_in_term_id": {
"title": "Depleted in term ID",
"type": "string",
"notSubmittable": true
},
"subcellular_fraction_term_id": {
"title": "Subcellular fraction term ID",
"type": "string",
"notSubmittable": true
},
"origin_batch": {
"title": "Origin batch",
"description": "Biosample @id representing the origin batch the biosample was obtained from",
"type": "string",
"notSubmittable": true
},
"perturbed": {
"title": "Perturbed",
"description": "A flag to indicate whether the biosample has been perturbed with a treatment or genetic modification.",
"type": "boolean",
"notSubmittable": true
},
"simple_summary": {
"title": "Simple Summary",
"type": "string",
"notSubmittable": true
},
"summary": {
"title": "Summary",
"type": "string",
"notSubmittable": true
}
},
"facet_groups": [
{
"title": "Biosample",
"facet_fields": [
"biosample_ontology.classification",
"biosample_ontology.organ_slims",
"biosample_ontology.cell_slims",
"disease_term_name",
"subcellular_fraction_term_name",
"phase",
"life_stage"
]
},
{
"title": "Donor",
"facet_fields": [
"organism.scientific_name",
"sex"
]
},
{
"title": "Perturbations",
"facet_fields": [
"treatments.treatment_term_name",
"perturbed"
]
},
{
"title": "Provenance",
"facet_fields": [
"lab.title",
"award.project",
"award.rfa",
"source.title",
"nih_institutional_certification"
]
},
{
"title": "Quality",
"facet_fields": [
"status",
"audit.ERROR.category",
"audit.NOT_COMPLIANT.category",
"audit.WARNING.category",
"audit.INTERNAL_ACTION.category"
]
}
],
"facets": {
"organism.scientific_name": {
"title": "Organism"
},
"status": {
"title": "Status"
},
"biosample_ontology.classification": {
"title": "Biosample classification"
},
"biosample_ontology.organ_slims": {
"title": "Organ"
},
"biosample_ontology.cell_slims": {
"title": "Cell"
},
"sex": {
"title": "Sex"
},
"life_stage": {
"title": "Life stage"
},
"disease_term_name": {
"title": "Disease"
},
"subcellular_fraction_term_name": {
"title": "Subcellular fraction"
},
"phase": {
"title": "Cell cycle phase"
},
"treatments.treatment_term_name": {
"title": "Biosample treatment"
},
"source.title": {
"title": "Source"
},
"lab.title": {
"title": "Lab"
},
"award.project": {
"title": "Project"
},
"award.rfa": {
"title": "RFA"
},
"perturbed": {
"title": "Perturbation"
},
"nih_institutional_certification": {
"type": "exists",
"title": "Has NIH institutional certification"
}
},
"columns": {
"accession": {
"title": "Accession"
},
"description": {
"title": "Description"
},
"age": {
"title": "Age"
},
"age_units": {
"title": "Age units"
},
"age_display": {
"title": "Biosample age"
},
"biosample_ontology.term_name": {
"title": "Biosample term name"
},
"biosample_ontology.classification": {
"title": "Biosample classification"
},
"synchronization": {
"title": "Synchronization"
},
"post_synchronization_time": {
"title": "Post-synchronization time"
},
"post_synchronization_time_units": {
"title": "Post-synchronization time units"
},
"organism.scientific_name": {
"title": "Organism"
},
"parent_of": {
"title": "Child biosamples"
},
"applied_modifications.modified_site_by_target_id.name": {
"title": "Modification site"
},
"applied_modifications.modified_site_by_target_id.organism": {
"title": "Modification site target organism"
},
"applied_modifications.introduced_gene.organism": {
"title": "Modification site introduced gene organism"
},
"applied_modifications.purpose": {
"title": "Modification purpose"
},
"applied_modifications.method": {
"title": "Modification method"
},
"applied_modifications.category": {
"title": "Modification category"
},
"source.title": {
"title": "Source"
},
"lab.title": {
"title": "Lab"
},
"life_stage": {
"title": "Life stage"
},
"status": {
"title": "Status"
},
"treatments.treatment_term_name": {
"title": "Biosample treatment"
},
"treatments.treatment_type_details": {
"title": "Biosample treatment type details"
},
"treatments.purpose": {
"title": "Biosample treatment purpose"
},
"culture_harvest_date": {
"title": "Culture harvest date"
},
"date_obtained": {
"title": "Date obtained"
},
"summary": {
"title": "Summary"
}
},
"boost_values": {
"accession": 20,
"@type": 1,
"aliases": 1,
"alternate_accessions": 1,
"biosample_ontology.term_id": 1,
"biosample_ontology.term_name": 5,
"biosample_ontology.organ_slims": 1,
"biosample_ontology.cell_slims": 1,
"biosample_ontology.developmental_slims": 1,
"biosample_ontology.synonyms": 5,
"biosample_ontology.classification": 5,
"dbxrefs": 1,
"subcellular_fraction_term_name": 1,
"phase": 2,
"life_stage": 1,
"synchronization": 1,
"health_status": 1,
"donor.accession": 1,
"donor.alternate_accessions": 1,
"donor.organism.name": 1,
"donor.organism.scientific_name": 1,
"donor.organism.taxon_id": 1,
"award.title": 1,
"award.project": 1,
"award.name": 1,
"submitted_by.email": 1,
"submitted_by.first_name": 1,
"submitted_by.last_name": 1,
"lab.institute_name": 1,
"lab.institute_label": 1,
"lab.title": 1,
"source.title": 1,
"treatments.treatment_type": 1,
"treatments.treatment_term_id": 1,
"treatments.treatment_term_name": 1,
"treatments.dbxrefs": 1,
"treatments.aliases": 1,
"applied_modifications.modified_site_by_target_id.label": 1,
"applied_modifications.modified_site_by_target_id.genes.dbxrefs": 1,
"applied_modifications.modified_site_by_target_id.genes.symbol": 1,
"applied_modifications.modified_site_by_target_id.aliases": 1,
"originated_from.accession": 1,
"originated_from.alternate_accessions": 1,
"originated_from.biosample_ontology.term_id": 1,
"originated_from.biosample_ontology.term_name": 1,
"pooled_from.accession": 1,
"pooled_from.alternate_accessions": 1,
"pooled_from.biosample_ontology.term_id": 1,
"pooled_from.biosample_ontology.term_name": 1,
"characterizations.characterization_method": 1,
"organism.name": 10,
"organism.scientific_name": 1,
"organism.taxon_id": 1,
"references.title": 1,
"award.pi.title": 1,
"notes": 1,
"internal_tags": 2,
"nih_institutional_certification": 1,
"summary": 5,
"description": 3,
"age": 5,
"age_display": 5,
"age_units": 2,
"sex": 2
},
"changelog": "/profiles/changelogs/biosample.md",
"@type": [
"JSONSchema"
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment