{
    "bcoid": "GLY_000625",
    "title": "Human Protein Biomarkers (Biomarker Database)",
    "description": "This is a Human Protein Biomarkers dataset. It contains human [taxonomy:9606] protein biomarker information, ...",
    "filename_list": "human_protein_biomarkers.csv",
    "filename": "human_protein_biomarkers.csv",
    "filetype": "csv",
    "categories": {
        "species": [
            "Homo sapiens"
        ],
        "molecule": [
            "Protein"
        ],
        "tag": [
            "Cancer Biomarker (BiomarkerDB)"
        ],
        "file_type": [
            "csv"
        ],
        "status": [
            "Reviewed"
        ],
        "scope": [
            "internal"
        ]
    },
    "minitable": {
        "content": [
            [
                "P05231-1...",
                "AN6278..."
            ],
            [
                "P05231-1...",
                "AN6278..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "biomarker_ca..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "biomarker_canonical_id"
                },
                {
                    "type": "string",
                    "label": "biomarker_id"
                },
                {
                    "type": "string",
                    "label": "biomarker"
                },
                {
                    "type": "string",
                    "label": "assessed_biomarker_entity"
                },
                {
                    "type": "string",
                    "label": "assessed_biomarker_entity_id"
                },
                {
                    "type": "string",
                    "label": "assessed_entity_type"
                },
                {
                    "type": "string",
                    "label": "exposure_agent"
                },
                {
                    "type": "string",
                    "label": "exposure_agent_id"
                },
                {
                    "type": "string",
                    "label": "best_biomarker_role"
                },
                {
                    "type": "string",
                    "label": "loinc_code"
                },
                {
                    "type": "string",
                    "label": "evidence"
                },
                {
                    "type": "string",
                    "label": "condition"
                },
                {
                    "type": "string",
                    "label": "component_level_tags"
                },
                {
                    "type": "string",
                    "label": "top_level_tags"
                },
                {
                    "type": "string",
                    "label": "evidence_type"
                },
                {
                    "type": "string",
                    "label": "component_synonyms"
                },
                {
                    "type": "string",
                    "label": "uberon_id"
                },
                {
                    "type": "string",
                    "label": "anatomical_entity"
                },
                {
                    "type": "string",
                    "label": "do_id"
                },
                {
                    "type": "string",
                    "label": "do_name"
                },
                {
                    "type": "string",
                    "label": "do_desc"
                },
                {
                    "type": "string",
                    "label": "do_syn"
                },
                {
                    "type": "string",
                    "label": "xref_key"
                },
                {
                    "type": "string",
                    "label": "xref_id"
                },
                {
                    "type": "string",
                    "label": "src_xref_key"
                },
                {
                    "type": "string",
                    "label": "src_xref_id"
                }
            ],
            [
                "P05231-1",
                "AN6278",
                "AN6278-1",
                "increased IL6 level",
                "Interleukin-6",
                "UPKB:P05231",
                "protein",
                "",
                "",
                "prognostic",
                "26881-3",
                "Univariate analysis of all patients demonstrated that an extent of disease (EOD) on bone scanning > or = 1, IL-6 > or = 7 pg/ml, PS > or = 1, PSA > 100 ng/ml, and ALP > 620 IU/liter were associated with a significantly lower survival rate than their respective counterparts. In multivariate analysis, however, the only two significant prognostic factors were EOD and IL-6. These results indicate that the serum IL-6 level is a significant prognostic factor for prostate cancer as well as EOD.",
                "prostate cancer",
                "assessed_biomarker_entity; biomarker; specimen",
                "best_biomarker_role; condition",
                "both_levels",
                "Interferon beta-2|IFN-beta-2||CTL differentiation factor|CDF|B-cell stimulatory factor 2|BSF-2|Hybridoma growth factor",
                "0000178",
                "blood",
                "10283",
                "prostate cancer",
                "A male reproductive organ cancer that is located_in the prostate.",
                "NGP - new growth of prostate|hereditary prostate cancer|malignant tumor of the prostate|prostate cancer, familial|prostate neoplasm|prostatic cancer|prostatic neoplasm|tumor of the prostate",
                "protein_xref_pubmed",
                "10914713",
                "protein_xref_biomarkerkb",
                "AN6278-1"
            ],
            [
                "P05231-1",
                "AN6278",
                "AN6278-5",
                "increased IL6 level",
                "Interleukin-6",
                "UPKB:P05231",
                "protein",
                "",
                "",
                "prognostic",
                "26881-3",
                "IL-6 plays multifaceted roles in regulation of vascular leakage, complement activation, and coagulation pathways, which ultimately causes poor outcomes for acute respiratory distress syndrome, multiple organ dysfunction syndrome, and SARS.",
                "COVID-19",
                "assessed_biomarker_entity; biomarker; specimen",
                "best_biomarker_role; condition",
                "both_levels",
                "Interferon beta-2|IFN-beta-2||CTL differentiation factor|CDF|B-cell stimulatory factor 2|BSF-2|Hybridoma growth factor",
                "0000178",
                "blood",
                "0080600",
                "COVID-19",
                "A Coronavirus infectious disease that is characterized by fever, cough and shortness of breath and that has_material_basis_in Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), a subtype of Betacoronavirus pandemicum.",
                "2019 Novel Coronavirus (2019-nCoV)|2019-nCoV infection|Wuhan coronavirus infection|Wuhan seafood market pneumonia virus infection|COVID19|SARS-CoV-2 infection",
                "protein_xref_pubmed",
                "32479790",
                "protein_xref_biomarkerkb",
                "AN6278-5"
            ]
        ]
    },
    "readme": "Name\n   - Human Protein Biomarkers (Biomarker Database)\n\nVersion\n   - v-2.9.1\n\nCreated on\n  - 2022-03-29T11:06:26.279356\n\nModified on\n   - 2024-05-17T11:24:07.032Z\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Biomarker DB [], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@gwu.edu], Kate Warner [k.warner1@gwu.edu]\n\nAuthors\n   - \n\nChecksum\n   - \n\nUsability Domain\n   - This is a Human Protein Biomarkers dataset. It contains human [taxonomy:9606] protein biomarker information, including cross-mapped UniProtKB or Protein Ontology accessions, assessed biomarker entity, biomarker status, biomarker type, specimen type, LOINC code, disease name, and source evidence from the cancer biomarker portal (https://data.oncomx.org/cancerbiomarkers). This dataset can be used to obtain biomarker information for 19 cancer types and COVID-19. If you use this dataset, please provide proper attribution to OncoMX and GlyGen. Cite: PMID:32142370, PMID:34015823, and PMID:31616925. The dataset was earlier called as human_protein_cancer_biomarkers.csv\n\nDescription Domain\n   Keywords\n   - biomarker\n   - cancer\n\n   Pipeline Steps\n   - Step-1: The script maps the UniProtKB accession from the source file to UniProtKB canonical accession. The script extracts the other fields as is from the source input file.\n\nExecution Domain\n   Scripts   - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py\n\n\n   Software Prerequisites\n      Name: Python\n      Version: 2.7.5\n      URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n   Input Subdomain\n      Name: human_protein_altnames.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_protein_altnames.csv\n      Name: human_protein_submittednames.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_protein_submittednames.csv\n      Name: protein_disease_names.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/protein_disease_names.csv\n      Name: sample_mapping.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.9.1/misc/sample_mapping.csv\n      Name: oncomx.tsv\n      URI: https:/data.glygen.org/ln2downloads/biomarkerdb/2025_05_27/oncomx.tsv\n   Output Subdomain\n      Name: human_protein_biomarkers.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_protein_biomarkers.csv\n      Name: human_protein_biomarkers.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_protein_biomarkers.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"218\"\n      Name: \"biomarker_canonical_id\"\n     Description: \"\"\n      Unique Values: \"246\"\n      Name: \"biomarker_id\"\n     Description: \"\"\n      Unique Values: \"317\"\n      Name: \"biomarker\"\n     Description: \"\"\n      Unique Values: \"248\"\n      Name: \"assessed_biomarker_entity\"\n     Description: \"\"\n      Unique Values: \"218\"\n      Name: \"assessed_biomarker_entity_id\"\n     Description: \"\"\n      Unique Values: \"218\"\n      Name: \"assessed_entity_type\"\n     Description: \"\"\n      Unique Values: \"3\"\n      Name: \"exposure_agent\"\n     Description: \"\"\n      Unique Values: \"1\"\n      Name: \"exposure_agent_id\"\n     Description: \"\"\n      Unique Values: \"1\"\n      Name: \"best_biomarker_role\"\n     Description: \"\"\n      Unique Values: \"6\"\n      Name: \"loinc_code\"\n     Description: \"\"\n      Unique Values: \"54\"\n      Name: \"evidence\"\n     Description: \"NCBI PubMed Id (PMID) or DOI (Digital Object Identifier) as evidence for the entry/annotation\"\n      Unique Values: \"355\"\n      Name: \"condition\"\n     Description: \"\"\n      Unique Values: \"20\"\n      Name: \"component_level_tags\"\n     Description: \"\"\n      Unique Values: \"3\"\n      Name: \"top_level_tags\"\n     Description: \"\"\n      Unique Values: \"2\"\n      Name: \"evidence_type\"\n     Description: \"\"\n      Unique Values: \"3\"\n      Name: \"component_synonyms\"\n     Description: \"\"\n      Unique Values: \"198\"\n      Name: \"uberon_id\"\n     Description: \"\"\n      Unique Values: \"19\"\n      Name: \"anatomical_entity\"\n     Description: \"\"\n      Unique Values: \"19\"\n      Name: \"do_id\"\n     Description: \"Disease Ontology identifier\"\n      Unique Values: \"20\"\n      Name: \"do_name\"\n     Description: \"Disease Ontology term or name for the disease assigned to the Disease Ontology identifier\"\n      Unique Values: \"20\"\n      Name: \"do_desc\"\n     Description: \"\"\n      Unique Values: \"20\"\n      Name: \"do_syn\"\n     Description: \"\"\n      Unique Values: \"19\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"1\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"290\"\n      Name: \"src_xref_key\"\n     Description: \"Source Xref  key\"\n      Unique Values: \"1\"\n      Name: \"src_xref_id\"\n     Description: \"Source X-ref ID\"\n      Unique Values: \"317\"",
    "downloadurl": "/ln2data/releases/data/v-2.9.1/reviewed/human_protein_biomarkers.csv"
}