Data file

Schema for submitting metadata for a data file.

{
    "title": "Data file",
    "description": "Schema for submitting metadata for a data file.",
    "id": "/profiles/file.json",
    "$schema": "http://json-schema.org/draft-04/schema#",
    "type": "object",
    "anyOf": [
        {
            "required": [
                "dataset",
                "file_format",
                "output_type",
                "award",
                "lab",
                "md5sum"
            ]
        },
        {
            "required": [
                "dataset",
                "file_format",
                "output_type",
                "award",
                "lab",
                "no_file_available"
            ]
        }
    ],
    "identifyingProperties": [
        "uuid",
        "accession",
        "aliases"
    ],
    "additionalProperties": false,
    "mixinProperties": [
        {
            "$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#/accession"
        },
        {
            "$ref": "mixins.json#/uuid"
        }
    ],
    "facets": {
        "status": {
            "title": "File status"
        },
        "output_category": {
            "title": "Content category"
        },
        "output_type": {
            "title": "Content type"
        },
        "file_format": {
            "title": "File format"
        },
        "file_format_type": {
            "title": "Specific file format type"
        },
        "award.project": {
            "title": "Project"
        },
        "assembly": {
            "title": "Mapping assembly"
        },
        "lab.title": {
            "title": "Lab"
        }
    },
    "dependencies": {
        "no_file_available": {
            "comment": "md5sum is required for all files unless the file is not available from the portal. file_size is required for files present on portal and have one of the statuses: in progress, revoked, archived or released.",
            "oneOf": [
                {
                    "properties": {
                        "no_file_available": {
                            "enum": [
                                true
                            ]
                        }
                    }
                },
                {
                    "allOf": [
                        {
                            "required": [
                                "md5sum"
                            ],
                            "properties": {
                                "no_file_available": {
                                    "enum": [
                                        false
                                    ]
                                }
                            }
                        },
                        {
                            "oneOf": [
                                {
                                    "not": {
                                        "required": [
                                            "status"
                                        ]
                                    },
                                    "properties": {
                                        "no_file_available": {
                                            "enum": [
                                                false
                                            ]
                                        }
                                    }
                                },
                                {
                                    "required": [
                                        "file_size",
                                        "status"
                                    ],
                                    "properties": {
                                        "status": {
                                            "enum": [
                                                "in progress",
                                                "revoked",
                                                "archived",
                                                "released"
                                            ]
                                        },
                                        "no_file_available": {
                                            "enum": [
                                                false
                                            ]
                                        }
                                    }
                                },
                                {
                                    "required": [
                                        "status"
                                    ],
                                    "properties": {
                                        "status": {
                                            "enum": [
                                                "uploading",
                                                "upload failed",
                                                "deleted",
                                                "replaced",
                                                "content error"
                                            ]
                                        },
                                        "no_file_available": {
                                            "enum": [
                                                false
                                            ]
                                        }
                                    }
                                }
                            ]
                        }
                    ]
                }
            ]
        },
        "paired_with": {
            "comment": "Only paired-ended files should have paired_with value.",
            "required": [
                "run_type"
            ],
            "properties": {
                "run_type": {
                    "enum": [
                        "paired-ended"
                    ]
                }
            }
        },
        "run_type": {
            "comment": "Only paired-ended files should have paired_end values.",
            "oneOf": [
                {
                    "properties": {
                        "run_type": {
                            "enum": [
                                "single-ended"
                            ]
                        }
                    }
                },
                {
                    "required": [
                        "paired_end"
                    ],
                    "properties": {
                        "run_type": {
                            "enum": [
                                "paired-ended"
                            ]
                        },
                        "paired_end": {
                            "enum": [
                                "1",
                                "2",
                                "1,2"
                            ]
                        }
                    }
                }
            ]
        },
        "external_accession": {
            "comment": "A file with an external accession should not get an ENCODE accession.",
            "not": {
                "required": [
                    "accession"
                ]
            }
        },
        "revoke_detail": {
            "comment": "Only revoked files can have revoke_detail specified.",
            "properties": {
                "status": {
                    "enum": [
                        "revoked"
                    ]
                }
            }
        },
        "mapped_run_type": {
            "comment": "Only bam files can have mapped_run_type specified.",
            "properties": {
                "file_format": {
                    "enum": [
                        "bam"
                    ]
                }
            }
        },
        "mapped_read_length": {
            "comment": "Only bam files can have mapped_read_length specified.",
            "properties": {
                "file_format": {
                    "enum": [
                        "bam"
                    ]
                }
            }
        },
        "paired_end": {
            "comment": "Files with paired-end value 2 require a paired_with value and files with paired_end specified require run_type to be specified as paired-ended",
            "oneOf": [
                {
                    "required": [
                        "paired_with",
                        "run_type"
                    ],
                    "properties": {
                        "paired_end": {
                            "enum": [
                                "2"
                            ]
                        },
                        "run_type": {
                            "enum": [
                                "paired-ended"
                            ]
                        }
                    }
                },
                {
                    "required": [
                        "run_type"
                    ],
                    "properties": {
                        "paired_end": {
                            "enum": [
                                "1"
                            ]
                        },
                        "run_type": {
                            "enum": [
                                "paired-ended"
                            ]
                        }
                    }
                },
                {
                    "required": [
                        "run_type"
                    ],
                    "properties": {
                        "file_format": {
                            "enum": [
                                "sra"
                            ]
                        },
                        "paired_end": {
                            "enum": [
                                "1,2"
                            ]
                        },
                        "run_type": {
                            "enum": [
                                "paired-ended"
                            ]
                        }
                    }
                }
            ]
        },
        "output_type": {
            "comment": "Files with output_type reads and file format fastq, fatsa, csfasta, csqual and sra require read_length to be specified.",
            "oneOf": [
                {
                    "required": [
                        "read_length"
                    ],
                    "properties": {
                        "file_format": {
                            "enum": [
                                "fastq",
                                "fasta",
                                "csfasta",
                                "csqual",
                                "sra"
                            ]
                        },
                        "output_type": {
                            "enum": [
                                "reads"
                            ]
                        }
                    }
                },
                {
                    "not": {
                        "properties": {
                            "output_type": {
                                "enum": [
                                    "reads"
                                ]
                            }
                        }
                    }
                }
            ]
        },
        "file_format": {
            "comment": "Fastq and sra files require run_type and replicate but should not have assembly. Raw data files require platform to be specified. Processed files require assembly to be specified.",
            "oneOf": [
                {
                    "allOf": [
                        {
                            "required": [
                                "replicate",
                                "run_type"
                            ],
                            "properties": {
                                "file_format": {
                                    "enum": [
                                        "fastq",
                                        "sra"
                                    ]
                                }
                            }
                        },
                        {
                            "not": {
                                "required": [
                                    "assembly"
                                ],
                                "properties": {
                                    "file_format": {
                                        "enum": [
                                            "fastq",
                                            "sra"
                                        ]
                                    }
                                }
                            }
                        },
                        {
                            "required": [
                                "platform"
                            ],
                            "properties": {
                                "file_format": {
                                    "enum": [
                                        "sra",
                                        "fastq",
                                        "csfasta",
                                        "csqual",
                                        "rcc",
                                        "idat",
                                        "CEL"
                                    ]
                                }
                            }
                        }
                    ]
                },
                {
                    "required": [
                        "file_format_type",
                        "assembly"
                    ],
                    "properties": {
                        "file_format": {
                            "enum": [
                                "gff",
                                "bed",
                                "bigBed"
                            ]
                        }
                    }
                },
                {
                    "required": [
                        "assembly"
                    ],
                    "properties": {
                        "file_format": {
                            "enum": [
                                "bam",
                                "sam",
                                "gtf",
                                "bigWig"
                            ]
                        }
                    }
                },
                {
                    "not": {
                        "properties": {
                            "file_format": {
                                "enum": [
                                    "fastq",
                                    "gff",
                                    "gtf",
                                    "bed",
                                    "bigBed",
                                    "bam",
                                    "sam",
                                    "sra",
                                    "bigWig"
                                ]
                            }
                        }
                    }
                }
            ]
        },
        "content_error_detail": {
            "comment": "Specification of status of content error is required if content_error_detail is specified",
            "required": [
                "status"
            ],
            "properties": {
                "status": {
                    "enum": [
                        "content error"
                    ]
                }
            }
        },
        "status": {
            "comment": "file_size is required in files with statuses in progress, revoked, archived and released unless the file is not available from the portal. content_error_details can be specified in files with status deleted and is required in files with the status content error.",
            "allOf": [
                {
                    "oneOf": [
                        {
                            "anyOf": [
                                {
                                    "required": [
                                        "no_file_available"
                                    ],
                                    "properties": {
                                        "status": {
                                            "enum": [
                                                "in progress",
                                                "revoked",
                                                "archived",
                                                "released"
                                            ]
                                        },
                                        "no_file_available": {
                                            "enum": [
                                                true
                                            ]
                                        }
                                    }
                                },
                                {
                                    "required": [
                                        "file_size"
                                    ],
                                    "properties": {
                                        "status": {
                                            "enum": [
                                                "in progress",
                                                "revoked",
                                                "archived",
                                                "released"
                                            ]
                                        }
                                    }
                                }
                            ]
                        },
                        {
                            "properties": {
                                "status": {
                                    "enum": [
                                        "uploading",
                                        "upload failed",
                                        "deleted",
                                        "replaced",
                                        "content error"
                                    ]
                                }
                            }
                        }
                    ]
                },
                {
                    "oneOf": [
                        {
                            "required": [
                                "content_error_detail"
                            ],
                            "properties": {
                                "status": {
                                    "enum": [
                                        "content error"
                                    ]
                                }
                            }
                        },
                        {
                            "not": {
                                "oneOf": [
                                    {
                                        "required": [
                                            "content_error_detail"
                                        ],
                                        "properties": {
                                            "status": {
                                                "enum": [
                                                    "uploading",
                                                    "uploaded",
                                                    "upload failed",
                                                    "format check failed",
                                                    "in progress",
                                                    "replaced",
                                                    "revoked",
                                                    "archived",
                                                    "released"
                                                ]
                                            }
                                        }
                                    },
                                    {
                                        "properties": {
                                            "status": {
                                                "enum": [
                                                    "content error"
                                                ]
                                            }
                                        }
                                    }
                                ]
                            }
                        }
                    ]
                }
            ]
        }
    },
    "properties": {
        "uuid": {
            "comment": "Do not submit. The uuid is set by the server.",
            "type": "string",
            "format": "uuid",
            "readonly": true,
            "requestMethod": "POST",
            "serverDefault": "uuid4",
            "description": "The unique identifier associated with every object.",
            "permission": "import_items",
            "title": "UUID"
        },
        "accession": {
            "comment": "Do not submit. The accession is assigned by the server.",
            "type": "string",
            "format": "accession",
            "accessionType": "FF",
            "readonly": true,
            "serverDefault": "accession",
            "description": "A unique identifier to be used to reference the object prefixed with ENC.",
            "permission": "import_items",
            "title": "Accession"
        },
        "aliases": {
            "comment": "The purpose of this field is to provide a link into the lab LIMS and to facilitate shared objects.",
            "type": "array",
            "uniqueItems": true,
            "default": [],
            "description": "Lab specific identifiers to reference an object.",
            "items": {
                "uniqueKey": "alias",
                "comment": "Current convention is colon separated lab name and lab identifier. (e.g. john-doe:42).",
                "type": "string",
                "description": "A lab specific identifier to reference an object.",
                "pattern": "^(?:alexander-hoffmann|alexander-rudensky|alexander-urban|ali-mortazavi|alkes-price|andrew-fire|anshul-kundaje|anton-valouev|barbara-wold|bill-noble|bin-yu|bing-ren|bradley-bernstein|brenton-graveley|chris-burge|christina-leslie|colin-dewey|david-gifford|david-gilbert|douglas-black|elliott-margulies|emery-bresnick|encode-awg|encode-consortium|encode-processing-pipeline|erez-lieberman|eric-lecuyer|eric-mendehall|ewan-birney|feng-yue|gene-yeo|george-stamatoyannopoulos|greg-cooper|gregory-crawford|guo-cheng-yuan|haiyan-huang|howard-chang|j-michael-cherry|jason-ernst|jason-lieb|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|mark-gerstein|mats-ljungman|matteo-pellegrini|michael-beer|michael-hoffman|michael-snyder|morgan-giddings|nadav-ahituv|paul-khavari|peggy-farnham|peter-bickel|peter-park|piero-carninci|rafael-irizarry|richard-myers|roadmap-epigenomics|robert-klein|robert-waterston|roderic-guigo|ross-hardison|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|kyoto|gtex|pgp|biochain|promocell|nichd):[a-zA-Z\\d_$.+!*,()'-]+(?:\\s[a-zA-Z\\d_$.+!*,()'-]+)*$",
                "title": "Lab alias"
            },
            "title": "Lab aliases"
        },
        "schema_version": {
            "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",
            "requestMethod": [],
            "default": "11",
            "description": "The version of the JSON schema that the server uses to validate the object.",
            "pattern": "^\\d+(\\.\\d+)*$",
            "title": "Schema Version"
        },
        "status": {
            "comment": "Do not submit.  This is set by admins along the process of file submission.",
            "enum": [
                "uploading",
                "content error",
                "upload failed",
                "in progress",
                "deleted",
                "released",
                "replaced",
                "revoked",
                "archived"
            ],
            "readonly": true,
            "type": "string",
            "default": "uploading",
            "description": "The status of the file object.",
            "permission": "import_items",
            "title": "Status"
        },
        "lab": {
            "comment": "Required. See lab.json for list of available identifiers.",
            "type": "string",
            "linkSubmitsFor": true,
            "description": "Lab associated with the submission.",
            "linkTo": "Lab",
            "title": "Lab"
        },
        "award": {
            "description": "Grant associated with the submission.",
            "title": "Grant",
            "comment": "Required. See award.json for list of available identifiers.",
            "linkTo": "Award",
            "type": "string"
        },
        "date_created": {
            "comment": "Do not submit. The date the object is created is assigned by the server.",
            "type": "string",
            "anyOf": [
                {
                    "format": "date-time"
                },
                {
                    "format": "date"
                }
            ],
            "format": "date-time",
            "rdfs:subPropertyOf": "dc:created",
            "readonly": true,
            "serverDefault": "now",
            "decription": "The date the object was created.",
            "description": "The date the object was created.",
            "permission": "import_items",
            "title": "Date created"
        },
        "submitted_by": {
            "comment": "Do not submit. The user that created the object is assigned by the server.",
            "readonly": true,
            "type": "string",
            "serverDefault": "userid",
            "permission": "import_items",
            "rdfs:subPropertyOf": "dc:creator",
            "linkTo": "User",
            "title": "Submitted by"
        },
        "notes": {
            "comment": "Do not submit. A place for the DCC to keep information that does not have a place in the schema.",
            "permission": "import_items",
            "readonly": true,
            "type": "string",
            "description": "DCC internal notes.",
            "pattern": "^(\\S+(\\s|\\S)*\\S+|\\S)$",
            "title": "Notes"
        },
        "alternate_accessions": {
            "comment": "Do not submit. Only admins are allowed to set or update this value.",
            "permission": "import_items",
            "readonly": true,
            "type": "array",
            "default": [],
            "description": "Accessions previously assigned to objects that have been merged with this object.",
            "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": "^(ENCFF\\d{3}[A-Z]{3})$|^(TSTFF\\d{6})$"
            },
            "title": "Alternate accessions"
        },
        "external_accession": {
            "uniqueKey": "accession",
            "comment": "Do not submit. Only admins are allowed to set or update this value.",
            "readonly": true,
            "type": "string",
            "description": "For files that were not accessioned at our site but have an accession elsewhere.",
            "permission": "import_items",
            "title": "External accession"
        },
        "read_count": {
            "comment": "Do not submit. This value is calculated and posted by checkfiles script upon submission.",
            "readonly": true,
            "type": "integer",
            "description": "Number of reads in fastq file.",
            "permission": "import_items",
            "title": "Read count"
        },
        "file_format": {
            "oneOf": [
                {
                    "comment": "This field is required.",
                    "enum": [
                        "bam",
                        "bed",
                        "bigBed",
                        "bigWig",
                        "fasta",
                        "fastq",
                        "gff",
                        "gtf",
                        "hdf5",
                        "hic",
                        "idat",
                        "rcc",
                        "CEL",
                        "tsv",
                        "csv",
                        "sam",
                        "tar",
                        "tagAlign",
                        "vcf",
                        "wig",
                        "bedpe",
                        "PWM",
                        "chain"
                    ]
                },
                {
                    "comment": "Historical file formats, not valid for new submissions.",
                    "permission": "import_items",
                    "enum": [
                        "btr",
                        "2bit",
                        "csfasta",
                        "sra",
                        "csqual"
                    ]
                }
            ],
            "type": "string",
            "title": "File format"
        },
        "file_format_type": {
            "description": "Files of type bed and gff require further specification",
            "oneOf": [
                {
                    "enum": [
                        "bed3",
                        "bed3+",
                        "bed5",
                        "bed6",
                        "bed6+",
                        "bed9",
                        "bed9+",
                        "bed12",
                        "bedGraph",
                        "bedLogR",
                        "bedMethyl",
                        "broadPeak",
                        "enhancerAssay",
                        "gappedPeak",
                        "gff2",
                        "gff3",
                        "narrowPeak",
                        "candidate enhancer predictions",
                        "enhancer predictions",
                        "tss_peak",
                        "idr_peak"
                    ]
                },
                {
                    "comment": "Historical file formats, not valid for new submissions.",
                    "permission": "import_items",
                    "enum": [
                        "unknown",
                        "bedRnaElements",
                        "peptideMapping",
                        "modPepMap",
                        "pepMap",
                        "shortFrags",
                        "bedExonScore",
                        "openChromCombinedPeaks",
                        "mango"
                    ]
                }
            ],
            "type": "string",
            "title": "Specific file format type"
        },
        "file_format_specifications": {
            "description": "Text or .as files the further explain the file format",
            "items": {
                "comment": "See document.json for a list of available identifiers.",
                "type": "string",
                "linkTo": "Document"
            },
            "type": "array",
            "uniqueItems": true,
            "title": "File format specifications documents"
        },
        "restricted": {
            "comment": "Do not submit. This value can only be set by admins.",
            "readonly": true,
            "type": "boolean",
            "description": "A flag to indicate whether this file is subject to restricted access",
            "permission": "import_items",
            "title": "Restricted file"
        },
        "no_file_available": {
            "comment": "Do not submit. This value can only be set by admins.",
            "readonly": true,
            "type": "boolean",
            "default": false,
            "description": "A flag to indicate whether this file is available to download. It may also not exist if it is the result of an unproductive analysis.",
            "permission": "import_items",
            "title": "No file available"
        },
        "submitted_file_name": {
            "description": "The local file name used at time of submission.",
            "comment": "Although this is not required. It is highly recommended.",
            "type": "string",
            "title": "Original file name"
        },
        "md5sum": {
            "comment": "Required for files with no_file_available = false . Warning: This value can vary for files of same content gzipped at different times",
            "type": "string",
            "maxLength": 32,
            "description": "The md5sum of the file being transferred.",
            "pattern": "[a-f\\d]{32}|[A-F\\d]{32}",
            "format": "hex",
            "title": "MD5sum"
        },
        "content_md5sum": {
            "comment": "Do not submit. This is only relavant for gzipped files. This value is calculated and posted by checkfiles script upon submission.",
            "type": "string",
            "pattern": "[a-f\\d]{32}|[A-F\\d]{32}",
            "format": "hex",
            "readonly": true,
            "maxLength": 32,
            "description": "The MD5sum of the uncompressed file.",
            "permission": "import_items",
            "title": "Content MD5sum"
        },
        "fastq_signature": {
            "comment": "Do not submit. This value is calculated and posted by checkfiles script upon submission.",
            "permission": "import_items",
            "type": "array",
            "uniqueItems": true,
            "default": [],
            "readonly": true,
            "description": "Fastq file flowcell based unique signature to reference a file.",
            "items": {
                "title": "Flowcell based fastq siganture part",
                "description": "Fastq file flowcell based unique signature to reference a file.",
                "comment": "Current convention is based on the Illumina unique sequence identifier, colon separated flowcell, lane, read_end(1/2) and barcode.",
                "type": "string",
                "pattern": "^[a-zA-Z0-9_-]+:[0-9]+:[12]:.*:.*$"
            },
            "title": "Fastq file flowcell based signature"
        },
        "file_size": {
            "description": "File size specified in bytes.",
            "comment": "Required.",
            "type": "integer",
            "title": "File size"
        },
        "platform": {
            "description": "The measurement device used to collect data.",
            "linkTo": "Platform",
            "comment": "This field is required for csfasta, csqual, rcc, idat and CEL file formats. See platform.json for identifer format.",
            "type": "string",
            "title": "Platform"
        },
        "read_length": {
            "description": "For high-throughput sequencing, the number of contiguous nucleotides determined by sequencing.",
            "comment": "This field is required for fastq, fasta, csfasta, csqual and sra file formats containing sequencing reads.",
            "type": "integer",
            "title": "Read length"
        },
        "run_type": {
            "description": "Indicates if file is part of a single or paired end sequencing run",
            "enum": [
                "single-ended",
                "paired-ended"
            ],
            "comment": "This field is required for sra and fastq files.",
            "type": "string",
            "title": "Run type for sequencing files"
        },
        "paired_end": {
            "description": "Which read of the pair the file represents (in case of paired end sequencing run)",
            "enum": [
                "1",
                "2",
                "1,2"
            ],
            "comment": "This field is required if run_type is paired-ended.",
            "type": "string",
            "title": "Paired End Identifier"
        },
        "paired_with": {
            "description": "The paired end fastq that corresponds with this file.",
            "linkTo": "File",
            "comment": "This is required for files with paired_end 2 and is calculated for files with paired_end 1.",
            "type": "string",
            "title": "File pairing"
        },
        "mapped_read_length": {
            "comment": "This is used when the original sequenced read length needed to be adjusted to match a replicate, or to match experiments and controls.",
            "readonly": true,
            "type": "integer",
            "description": "The length of the reads actually mapped, if the original read length was clipped.",
            "permission": "import_items",
            "title": "Mapped read length"
        },
        "mapped_run_type": {
            "comment": "When the control and experiment run types do not match, one may be changed in order to meet pipeline requirements.",
            "enum": [
                "single-ended",
                "paired-ended"
            ],
            "readonly": true,
            "type": "string",
            "description": "The mapped run type of the alignment file which may differ from the fastqs it is derived from.",
            "permission": "import_items",
            "title": "Mapped run type for bam files"
        },
        "flowcell_details": {
            "items": {
                "title": "Flowcell details",
                "type": "object",
                "additionalProperties": false,
                "properties": {
                    "machine": {
                        "title": "Machine Name",
                        "description": "The lab specific name of the machine used.",
                        "type": "string"
                    },
                    "flowcell": {
                        "title": "Flowcell ID",
                        "type": "string"
                    },
                    "lane": {
                        "title": "Lane",
                        "type": "string"
                    },
                    "barcode": {
                        "title": "Barcode",
                        "type": "string"
                    },
                    "barcode_in_read": {
                        "title": "Barcode in read",
                        "description": "The read the barcode is located on.",
                        "type": "string",
                        "enum": [
                            "1",
                            "2"
                        ]
                    },
                    "barcode_position": {
                        "title": "Barcode position",
                        "description": "The 1-based start position of the barcode in 5->3 orientation.",
                        "type": "integer"
                    },
                    "chunk": {
                        "title": "Chunk",
                        "description": "The file chunk label as assigned by Illumina software when splitting up a fastq into specified chunk sizes.",
                        "comment": "This label is used to re-assemble the chunks into the original file in the correct order.",
                        "type": "string"
                    }
                }
            },
            "description": "For high-throughput sequencing, the flowcells used for the sequencing of the replicate.",
            "default": [],
            "type": "array",
            "title": "Flowcells"
        },
        "output_type": {
            "description": "A description of the file's purpose or contents.",
            "oneOf": [
                {
                    "enum": [
                        "idat green channel",
                        "idat red channel",
                        "reads",
                        "intensity values",
                        "reporter code counts",
                        "alignments",
                        "unfiltered alignments",
                        "transcriptome alignments",
                        "maternal haplotype mapping",
                        "paternal haplotype mapping",
                        "phased mapping",
                        "minus strand signal of all reads",
                        "plus strand signal of all reads",
                        "signal of all reads",
                        "normalized signal of all reads",
                        "raw minus strand signal",
                        "raw plus strand signal",
                        "raw signal",
                        "raw normalized signal",
                        "read-depth normalized signal",
                        "control normalized signal",
                        "minus strand signal of unique reads",
                        "plus strand signal of unique reads",
                        "signal of unique reads",
                        "signal p-value",
                        "fold change over control",
                        "exon quantifications",
                        "gene quantifications",
                        "microRNA quantifications",
                        "transcript quantifications",
                        "library fraction",
                        "methylation state at CpG",
                        "methylation state at CHG",
                        "methylation state at CHH",
                        "enrichment",
                        "replication timing profile",
                        "relative replication signal",
                        "maternal variant calls",
                        "paternal variant calls",
                        "phased variant calls",
                        "variant calls",
                        "filtered SNPs",
                        "filtered indels",
                        "motif model",
                        "hotspots",
                        "long range chromatin interactions",
                        "chromatin interactions",
                        "topologically associated domains",
                        "nested topologically associated domains",
                        "genome compartments",
                        "open chromatin regions",
                        "filtered peaks",
                        "filtered regions",
                        "DHS peaks",
                        "peaks",
                        "replicated peaks",
                        "RNA-binding protein associated mRNAs",
                        "splice junctions",
                        "transcription start sites",
                        "predicted enhancers",
                        "candidate enhancers",
                        "candidate promoters",
                        "candidate regulatory elements",
                        "representative dnase hypersensitivity sites",
                        "genome reference",
                        "transcriptome reference",
                        "transcriptome index",
                        "rRNA reference",
                        "TSS reference",
                        "reference variants",
                        "genome index",
                        "female genome reference",
                        "female genome index",
                        "male genome reference",
                        "male genome index",
                        "spike-in sequence",
                        "optimal idr thresholded peaks",
                        "conservative idr thresholded peaks",
                        "pseudoreplicated idr thresholded peaks",
                        "stable peaks",
                        "enhancer validation",
                        "semi-automated genome annotation",
                        "blacklisted regions",
                        "mitochondria blacklisted regions"
                    ]
                },
                {
                    "comment": "Historical output types, not valid for new submissions.",
                    "permission": "import_items",
                    "enum": [
                        "rejected reads",
                        "raw data",
                        "tRNA reference",
                        "miRNA reference",
                        "snRNA reference",
                        "spike-in alignments",
                        "signal",
                        "minus strand signal",
                        "plus strand signal",
                        "summed densities signal",
                        "percentage normalized signal",
                        "base overlap signal",
                        "wavelet-smoothed signal",
                        "filtered modified peptide quantification",
                        "unfiltered modified peptide quantification",
                        "filtered peptide quantification",
                        "unfiltered peptide quantification",
                        "clusters",
                        "contigs",
                        "copy number variation",
                        "transcribed fragments",
                        "filtered transcribed fragments",
                        "valleys",
                        "sequence uniqueness",
                        "primer sequence",
                        "reference",
                        "predicted transcription start sites",
                        "minus strand transcription start sites",
                        "plus strand transcription start sites",
                        "distal peaks",
                        "proximal peaks",
                        "validation",
                        "HMM predicted chromatin state",
                        "predicted forebrain enhancers",
                        "predicted heart enhancers",
                        "predicted whole brain enhancers",
                        "sequence alignability"
                    ]
                }
            ],
            "type": "string",
            "title": "Output type"
        },
        "derived_from": {
            "description": "The files participating as inputs into software to produce this output file.",
            "items": {
                "comment": "See file.json for a list of available identifiers.",
                "type": "string",
                "linkTo": "File"
            },
            "type": "array",
            "uniqueItems": true,
            "title": "Derived from"
        },
        "controlled_by": {
            "comment": "This is used by the pipeline to find ChIP-seq controls.",
            "type": "array",
            "uniqueItems": true,
            "description": "The files which should be used as a control for this file. ",
            "items": {
                "comment": "See file.json for a list of available identifiers.",
                "type": "string",
                "linkTo": "File"
            },
            "title": "Controlled by"
        },
        "supersedes": {
            "comment": "The files in this list should be obsolete and the superseeding file object should be used instead.",
            "type": "array",
            "uniqueItems": true,
            "description": "The files that this file supersedes.",
            "items": {
                "comment": "The files in this list should be archived or revoked.",
                "type": "string",
                "linkTo": "File"
            },
            "title": "Supersedes"
        },
        "dataset": {
            "description": "The experiment or dataset the file belongs to.",
            "linkTo": "Dataset",
            "comment": "Required. See dataset.json for available identifiers.",
            "type": "string",
            "title": "Dataset"
        },
        "replicate": {
            "description": "The experimental replicate designation for the file.",
            "linkTo": "Replicate",
            "comment": "This field is required for sra and fastq files. See replicate.json for available identifiers.",
            "type": "string",
            "title": "Replicate"
        },
        "assembly": {
            "description": "Genome assembly that files were mapped to.",
            "enum": [
                "mm9",
                "mm10",
                "mm10-minimal",
                "hg19",
                "GRCh38",
                "GRCh38-minimal",
                "ce10",
                "ce11",
                "dm3",
                "dm6",
                "J02459.1"
            ],
            "comment": "Required property for bam, sam, gtf, gff, bed and bigBed file format files. This property should not be submitted with sra or fastq files.",
            "type": "string",
            "title": "Mapping assembly"
        },
        "genome_annotation": {
            "description": "Genome annotation that file was generated with.",
            "enum": [
                "None",
                "M2",
                "M3",
                "M4",
                "M7",
                "V3c",
                "V7",
                "V10",
                "V19",
                "V22",
                "V24",
                "ENSEMBL V65",
                "miRBase V21",
                "WS235",
                "WS245"
            ],
            "comment": "Applies to files created using annotations.",
            "type": "string",
            "title": "Genome annotation"
        },
        "dbxrefs": {
            "comment": "Do not submit.  This is for admins to make virtual file objects for files at external resources.",
            "items": {
                "title": "External identifier",
                "description": "Identifier from an external resource that may have 1-to-1 or 1-to-many relationships with ENCODE objects.",
                "type": "string",
                "pattern": "^(SRA:(SRR|SRX)\\d+)$"
            },
            "type": "array",
            "uniqueItems": true,
            "default": [],
            "description": "Identifiers from external resources that may have 1-to-1 or 1-to-many relationships with ENCODE objects.",
            "@type": "@id",
            "rdfs:subPropertyOf": "rdfs:seeAlso",
            "title": "External identifiers"
        },
        "step_run": {
            "description": "The run instance of the step used to generate the file.",
            "linkTo": "AnalysisStepRun",
            "comment": "This may be linked to an individual instance at DNANexus or it may be virtual and have many files linked to it.",
            "type": "string",
            "title": "Analysis step run"
        },
        "content_error_detail": {
            "comment": "Do not submit.  This is posted by the checkfiles script. It is required when status is 'content error'",
            "readonly": true,
            "type": "string",
            "description": "Explanation of why the file failed the automated content checks.",
            "permission": "import_items",
            "title": "Content error detail"
        },
        "revoke_detail": {
            "comment": "Do not submit. The field would be posted by DCC.",
            "readonly": true,
            "type": "string",
            "description": "Explanation of why the file was revoked.",
            "permission": "import_items",
            "title": "Revoke error detail"
        },
        "analysis_step_version": {
            "calculatedProperty": true,
            "comment": "Do not submit.  This field is calculated from step_run.",
            "type": "string",
            "description": "The step version of the pipeline from which this file is an output.",
            "linkTo": "AnalysisStepVersion",
            "title": "Analysis Step Version"
        },
        "superseded_by": {
            "description": "The file(s) that supersede this file (i.e. are more preferable to use).",
            "items": {
                "linkFrom": "File.supersedes",
                "type": [
                    "string",
                    "object"
                ]
            },
            "comment": "Do not submit. Values in the list are reverse links of a file that supersedes.",
            "type": "array",
            "title": "Superseded by"
        },
        "biological_replicates": {
            "calculatedProperty": true,
            "comment": "Do not submit.  This field is calculated through the derived_from relationship back to the raw data.",
            "type": "array",
            "description": "The biological replicate numbers associated with this file.",
            "items": {
                "description": "The identifying number of each relevant biological replicate",
                "type": "integer",
                "title": "Biological replicate number"
            },
            "title": "Biological replicates"
        },
        "href": {
            "calculatedProperty": true,
            "description": "The download path for S3 to obtain the actual file.",
            "title": "Download URL",
            "comment": "Do not submit. This is issued by the server.",
            "type": "string"
        },
        "@id": {
            "calculatedProperty": true,
            "type": "string",
            "title": "ID"
        },
        "technical_replicates": {
            "calculatedProperty": true,
            "comment": "Do not submit.  This field is calculated through the derived_from relationship back to the raw data.",
            "type": "array",
            "description": "The technical replicate numbers associated with this file.",
            "items": {
                "description": "The identifying number of each relevant technical replicate",
                "type": "string",
                "title": "Technical replicate number"
            },
            "title": "Technical replicates"
        },
        "title": {
            "calculatedProperty": true,
            "description": "The title of the file either the accession or the external_accession.",
            "title": "Title",
            "comment": "Do not submit. This is a calculated property",
            "type": "string"
        },
        "read_length_units": {
            "calculatedProperty": true,
            "comment": "Do not submit. This is a fixed value.",
            "type": "string",
            "description": "The units for read length.",
            "enum": [
                "nt"
            ],
            "title": "Read length units"
        },
        "file_type": {
            "calculatedProperty": true,
            "description": "The concatenation of file_format and file_format_type",
            "title": "File type",
            "comment": "Do not submit. This field is calculated from file_format and file_format_type.",
            "type": "string"
        },
        "quality_metrics": {
            "description": "The list of QC metric objects associated with this file.",
            "items": {
                "linkFrom": "QualityMetric.quality_metric_of",
                "type": [
                    "string",
                    "object"
                ]
            },
            "comment": "Do not submit. Values in the list are reverse links of a quality metric with this file in quality_metric_of field.",
            "type": "array",
            "title": "QC Metric"
        },
        "output_category": {
            "calculatedProperty": true,
            "comment": "Do not submit.  This field is calculated from output_type_output_category.",
            "type": "string",
            "description": "The overall catagory of the file content.",
            "enum": [
                "raw data",
                "alignment",
                "signal",
                "annotation",
                "quantification",
                "reference"
            ],
            "title": "Output category"
        },
        "upload_credentials": {
            "calculatedProperty": true,
            "description": "The upload credentials for S3 to submit the file content.",
            "title": "Upload Credentials",
            "comment": "Do not submit. This is issued by the server.",
            "type": "object"
        },
        "@type": {
            "calculatedProperty": true,
            "items": {
                "type": "string"
            },
            "type": "array",
            "title": "Type"
        }
    },
    "columns": {
        "title": {
            "title": "Title"
        },
        "accession": {
            "title": "Accession"
        },
        "dataset": {
            "title": "Dataset"
        },
        "assembly": {
            "title": "Mapping assembly"
        },
        "technical_replicates": {
            "title": "Technical replicates"
        },
        "biological_replicates": {
            "title": "Biological replicates"
        },
        "file_format": {
            "title": "File Format"
        },
        "file_type": {
            "title": "File type"
        },
        "file_format_type": {
            "title": "Specific file format type"
        },
        "file_size": {
            "title": "File size"
        },
        "href": {
            "title": "Download URL"
        },
        "derived_from": {
            "title": "Derived from"
        },
        "genome_annotation": {
            "title": "Genome annotation"
        },
        "replicate.library.accession": {
            "title": "Library"
        },
        "paired_end": {
            "title": "Paired End Identifier"
        },
        "paired_with": {
            "title": "File pairing"
        },
        "run_type": {
            "title": "Run type for sequencing files"
        },
        "read_length": {
            "title": "Read length"
        },
        "mapped_read_length": {
            "title": "Mapped read length"
        },
        "read_length_units": {
            "title": "Read length units"
        },
        "output_category": {
            "title": "Data category"
        },
        "output_type": {
            "title": "Data type"
        },
        "quality_metrics": {
            "title": "QC Metric"
        },
        "lab": {
            "title": "Lab"
        },
        "award.project": {
            "title": "BioProject"
        },
        "step_run": {
            "title": "Analysis step run"
        },
        "date_created": {
            "title": "Date added"
        },
        "analysis_step_version": {
            "title": "Analysis Step Version"
        },
        "restricted": {
            "title": "Restricted file"
        },
        "status": {
            "title": "File status"
        }
    },
    "output_type_output_category": {
        "idat green channel": "raw data",
        "idat red channel": "raw data",
        "intensity values": "raw data",
        "reads": "raw data",
        "rejected reads": "raw data",
        "raw data": "raw data",
        "reporter code counts": "raw data",
        "alignments": "alignment",
        "unfiltered alignments": "alignment",
        "transcriptome alignments": "alignment",
        "spike-in alignments": "alignment",
        "maternal haplotype mapping": "alignment",
        "paternal haplotype mapping": "alignment",
        "phased mapping": "alignment",
        "minus strand signal of all reads": "signal",
        "plus strand signal of all reads": "signal",
        "signal of all reads": "signal",
        "normalized signal of all reads": "signal",
        "raw minus strand signal": "signal",
        "raw plus strand signal": "signal",
        "raw signal": "signal",
        "raw normalized signal": "signal",
        "read-depth normalized signal": "signal",
        "control normalized signal": "signal",
        "minus strand signal of unique reads": "signal",
        "plus strand signal of unique reads": "signal",
        "signal of unique reads": "signal",
        "signal p-value": "signal",
        "fold change over control": "signal",
        "minus strand signal": "signal",
        "plus strand signal": "signal",
        "signal": "signal",
        "base overlap signal": "signal",
        "percentage normalized signal": "signal",
        "summed densities signal": "signal",
        "wavelet-smoothed signal": "signal",
        "relative replication signal": "signal",
        "enrichment": "quantification",
        "library fraction": "quantification",
        "exon quantifications": "quantification",
        "gene quantifications": "quantification",
        "microRNA quantifications": "quantification",
        "transcript quantifications": "quantification",
        "methylation state at CpG": "quantification",
        "methylation state at CHG": "quantification",
        "methylation state at CHH": "quantification",
        "filtered modified peptide quantification": "quantification",
        "unfiltered modified peptide quantification": "quantification",
        "filtered peptide quantification": "quantification",
        "unfiltered peptide quantification": "quantification",
        "replication timing profile": "quantification",
        "motif model": "quantification",
        "hotspots": "annotation",
        "long range chromatin interactions": "annotation",
        "chromatin interactions": "annotation",
        "topologically associated domains": "annotation",
        "nested topologically associated domains": "annotation",
        "genome compartments": "annotation",
        "open chromatin regions": "annotation",
        "filtered peaks": "annotation",
        "filtered regions": "annotation",
        "DHS peaks": "annotation",
        "peaks": "annotation",
        "replicated peaks": "annotation",
        "RNA-binding protein associated mRNAs": "annotation",
        "splice junctions": "annotation",
        "copy number variation": "annotation",
        "clusters": "annotation",
        "contigs": "annotation",
        "transcribed fragments": "annotation",
        "filtered transcribed fragments": "annotation",
        "valleys": "annotation",
        "blacklisted regions": "annotation",
        "mitochondria blacklisted regions": "annotation",
        "distal peaks": "annotation",
        "proximal peaks": "annotation",
        "optimal idr thresholded peaks": "annotation",
        "conservative idr thresholded peaks": "annotation",
        "pseudoreplicated idr thresholded peaks": "annotation",
        "stable peaks": "annotation",
        "predicted forebrain enhancers": "annotation",
        "predicted heart enhancers": "annotation",
        "predicted whole brain enhancers": "annotation",
        "predicted enhancers": "annotation",
        "candidate enhancers": "annotation",
        "candidate promoters": "annotation",
        "predicted transcription start sites": "annotation",
        "transcription start sites": "annotation",
        "candidate regulatory elements": "annotation",
        "representative dnase hypersensitivity sites": "annotation",
        "variant calls": "annotation",
        "maternal variant calls": "annotation",
        "paternal variant calls": "annotation",
        "phased variant calls": "annotation",
        "filtered SNPs": "annotation",
        "filtered indels": "annotation",
        "transcriptome reference": "reference",
        "transcriptome index": "reference",
        "genome index": "reference",
        "tRNA reference": "reference",
        "miRNA reference": "reference",
        "snRNA reference": "reference",
        "rRNA reference": "reference",
        "TSS reference": "reference",
        "reference variants": "reference",
        "genome reference": "reference",
        "female genome reference": "reference",
        "female genome index": "reference",
        "male genome reference": "reference",
        "male genome index": "reference",
        "primer sequence": "reference",
        "spike-in sequence": "reference",
        "reference": "reference",
        "sequence alignability": "reference",
        "sequence uniqueness": "reference",
        "enhancer validation": "validation",
        "validation": "validation",
        "HMM predicted chromatin state": "annotation",
        "semi-automated genome annotation": "annotation"
    },
    "file_format_file_extension": {
        "2bit": ".2bit",
        "CEL": ".cel.gz",
        "bam": ".bam",
        "bed": ".bed.gz",
        "bedpe": ".bedpe.gz",
        "chain": ".chain",
        "bigBed": ".bigBed",
        "bigWig": ".bigWig",
        "btr": ".btr",
        "csfasta": ".csfasta.gz",
        "csqual": ".csqual.gz",
        "fasta": ".fasta.gz",
        "fastq": ".fastq.gz",
        "gff": ".gff.gz",
        "gtf": ".gtf.gz",
        "hic": ".hic",
        "hdf5": ".h5",
        "idat": ".idat",
        "PWM": ".pwm",
        "rcc": ".rcc",
        "sra": ".sra",
        "tagAlign": ".tagAlign.gz",
        "tar": ".tar.gz",
        "tsv": ".tsv",
        "csv": ".csv",
        "vcf": ".vcf.gz",
        "wig": ".wig.gz",
        "sam": ".sam.gz"
    },
    "changelog": "/profiles/changelogs/file.md",
    "@type": [
        "JSONSchema"
    ]
}