BlueSTARR-K562

released
{
    "@context": "/terms/",
    "@id": "/model-sets/IGVFDS0103FMQG/",
    "@type": [
        "ModelSet",
        "FileSet",
        "Item"
    ],
    "accession": "IGVFDS0103FMQG",
    "aliases": [
        "bill-majoros:bluestarr-k562-model-v0.1.1"
    ],
    "audit": {
        "INTERNAL_ACTION": [
            {
                "category": "missing publication",
                "detail": "In vitro system [IGVFSM7883WOIS](/in-vitro-systems/IGVFSM7883WOIS/) has no `publications`. Released and archived samples are expected to be associated with a publication.",
                "level": 30,
                "level_name": "INTERNAL_ACTION",
                "name": "audit_sample_missing_publication",
                "path": "/in-vitro-systems/IGVFSM7883WOIS/"
            },
            {
                "category": "missing publication",
                "detail": "Model set [IGVFDS0103FMQG](/model-sets/IGVFDS0103FMQG/) has no `publications`. Released and archived file sets are expected to be associated with a publication.",
                "level": 30,
                "level_name": "INTERNAL_ACTION",
                "name": "audit_file_set_missing_publication",
                "path": "/model-sets/IGVFDS0103FMQG/"
            }
        ]
    },
    "award": {
        "@id": "/awards/HG011967/",
        "component": "predictive modeling",
        "contact_pi": {
            "@id": "/users/42adfdcc-7ff1-4c2a-b9af-d424c71c6e5a/",
            "title": "Andrew Allen"
        },
        "title": "Design, prediction, and prioritization of systematic perturbations of the human genome"
    },
    "control_for": [],
    "creation_timestamp": "2025-01-31T19:27:00.571583+00:00",
    "description": "BlueSTARR v0.1.1 is the updated version that was trained on a full-set dataset containing sequences from all chromosomes, unlike the original model (v0.1.0), which excluded chromosomes 1 and 2 for testing and validation. It uses DNA and RNA counts normalized by library size, employs unbiased down-sampling for training, and optimizes predictions using Mean Squared Error (MSE) as the loss function",
    "documents": [
        "/documents/616c46f5-7f2e-4d31-af0a-d91f8084bcc4/"
    ],
    "externally_hosted": false,
    "file_set_type": "neural network",
    "files": [
        {
            "@id": "/model-files/IGVFFI7316UCOH/",
            "accession": "IGVFFI7316UCOH",
            "aliases": [
                "bill-majoros:bluestarr-k562-v1.1.0-model-file-hdf5"
            ],
            "content_type": "edge weights",
            "creation_timestamp": "2025-03-07T20:49:35.697031+00:00",
            "file_format": "hdf5",
            "file_size": 63138304,
            "href": "/model-files/IGVFFI7316UCOH/@@download/IGVFFI7316UCOH.h5",
            "s3_uri": "s3://igvf-files/2025/03/07/9094bc0b-86b2-48db-af9c-4e230fef6665/IGVFFI7316UCOH.h5",
            "status": "released",
            "submitted_file_name": "/data/reddylab/Alex/IGVF/data_submissions/processed_data/predictive_modeling/K562.h5",
            "upload_status": "validated"
        },
        {
            "@id": "/model-files/IGVFFI1704UATO/",
            "accession": "IGVFFI1704UATO",
            "aliases": [
                "bill-majoros:bluestarr-k562-v1.1.0-model-file-json"
            ],
            "content_type": "graph structure",
            "creation_timestamp": "2025-03-07T20:49:34.073590+00:00",
            "file_format": "json",
            "file_size": 13365,
            "href": "/model-files/IGVFFI1704UATO/@@download/IGVFFI1704UATO.json",
            "s3_uri": "s3://igvf-files/2025/03/07/3091f6a2-7a8a-4e4e-84db-0be65c9c4fea/IGVFFI1704UATO.json",
            "status": "released",
            "submitted_file_name": "/data/reddylab/Alex/IGVF/data_submissions/processed_data/predictive_modeling/K562.json",
            "upload_status": "validated"
        }
    ],
    "input_for": [
        "/prediction-sets/IGVFDS2340WJRV/"
    ],
    "lab": {
        "@id": "/labs/bill-majoros/",
        "title": "Bill Majoros, Duke"
    },
    "model_name": "BlueSTARR-K562",
    "model_version": "v0.1.1",
    "notes": "This model set previously specified 6ca6a480-0057-4462-84b8-e7c21ec29e9f, but this property has been removed and replaced by software_versions calculated through analysis_step_version on the model file.",
    "prediction_objects": [
        "regulatory elements"
    ],
    "release_timestamp": "2025-03-17T21:40:58.132826+00:00",
    "samples": [
        {
            "@id": "/in-vitro-systems/IGVFSM7883WOIS/",
            "@type": [
                "InVitroSystem",
                "Biosample",
                "Sample",
                "Item"
            ],
            "accession": "IGVFSM7883WOIS",
            "aliases": [
                "andrew-allen:bluestarr-k562-in-vitro-system"
            ],
            "classifications": [
                "cell line"
            ],
            "institutional_certificates": [],
            "sample_terms": [
                {
                    "@id": "/sample-terms/EFO_0002067/",
                    "@type": [
                        "SampleTerm",
                        "OntologyTerm",
                        "Item"
                    ],
                    "aliases": [
                        "igvf:K562"
                    ],
                    "status": "released",
                    "summary": "K562",
                    "term_name": "K562"
                }
            ],
            "status": "released",
            "summary": "virtual Homo sapiens (female) K562 cell line",
            "taxa": "Homo sapiens"
        }
    ],
    "schema_version": "5",
    "software_versions": [
        {
            "@id": "/software-versions/bluestarr-v0.1.1/",
            "download_id": "95b5033342fbbd7a5ffb532038946481ffafb6db",
            "status": "released",
            "summary": "BlueSTARR v0.1.1"
        }
    ],
    "status": "released",
    "submitted_by": {
        "@id": "/users/a53b8173-d4ac-4f0b-b578-23156ca1f934/",
        "title": "Brendan Kearney"
    },
    "submitted_files_timestamp": "2025-03-07T20:49:34.073590+00:00",
    "summary": "BlueSTARR-K562 v0.1.1 neural network predicting regulatory elements",
    "uuid": "23c86e3d-f14f-4068-a0c1-8e6291911a01"
}