{
    "data_id": "44963",
    "name": "physiochemical_protein",
    "exact_name": "physiochemical_protein",
    "version": 7,
    "version_label": null,
    "description": "**Data Description**\n\nThis is a data set of Physicochemical Properties of Protein Tertiary Structure. The data set is taken from CASP 5-9. There are 45730 decoys and size varying from 0 to 21 armstrong.\n\nThe goal of the dataset is to predict the size of the residue for a tertiary protein structure (a 3d protein structure). Once linked in the protein chain, an individual amino acid is called a residue. The target feature is root mean square error of the residue.\n\n**Attribute Description**\n\n1. *RMSD* - size of the residue\n2. *F1* - total surface area\n3. *F2* - non polar exposed area\n4. *F3* - fractional area of exposed non polar residue\n5. *F4* - fractional area of exposed non polar part of residue\n6. *F5* - molecular mass weighted exposed area\n7. *F6* - average deviation from standard exposed area of residue\n8. *F7* - Euclidian distance\n9. *F8* - secondary structure penalty\n10. *F9* - Spacial Distribution constraints (N,K Value)",
    "format": "arff",
    "uploader": "Sebastian Fischer",
    "uploader_id": 30127,
    "visibility": "public",
    "creator": null,
    "contributor": null,
    "date": "2022-12-22 16:11:56",
    "update_comment": null,
    "last_update": "2022-12-22 16:11:56",
    "licence": "CC BY 4.0",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22111827\/file22f167620a212.arff",
    "kaggle_url": null,
    "default_target_attribute": "RMSD",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "physiochemical_protein",
            "This is a data set of Physicochemical Properties of Protein Tertiary Structure. The data set is taken from CASP 5-9. There are 45730 decoys and size varying from 0 to 21 armstrong. The goal of the dataset is to predict the size of the residue for a tertiary protein structure (a 3d protein structure). Once linked in the protein chain, an individual amino acid is called a residue. The target feature is root mean square error of the residue. 1. *RMSD* - size of the residue 2. *F1* - total surface a "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 45730,
        "NumberOfFeatures": 10,
        "NumberOfClasses": 0,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 10,
        "NumberOfSymbolicFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "PercentageOfMissingValues": 0,
        "AutoCorrelation": -5.824410658444305,
        "PercentageOfNumericFeatures": 100,
        "Dimensionality": 0.00021867483052700635,
        "PercentageOfSymbolicFeatures": 0,
        "MajorityClassPercentage": null,
        "MajorityClassSize": null,
        "MinorityClassPercentage": null,
        "MinorityClassSize": null,
        "NumberOfBinaryFeatures": 0
    },
    "tags": [],
    "features": [
        {
            "name": "RMSD",
            "index": "0",
            "type": "numeric",
            "distinct": "15903",
            "missing": "0",
            "target": "1",
            "min": "0",
            "max": "21",
            "mean": "8",
            "stdev": "6"
        },
        {
            "name": "F1",
            "index": "1",
            "type": "numeric",
            "distinct": "39916",
            "missing": "0",
            "min": "2392",
            "max": "40035",
            "mean": "9872",
            "stdev": "4058"
        },
        {
            "name": "F2",
            "index": "2",
            "type": "numeric",
            "distinct": "39863",
            "missing": "0",
            "min": "404",
            "max": "15312",
            "mean": "3017",
            "stdev": "1464"
        },
        {
            "name": "F3",
            "index": "3",
            "type": "numeric",
            "distinct": "20089",
            "missing": "0",
            "min": "0",
            "max": "1",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "F4",
            "index": "4",
            "type": "numeric",
            "distinct": "40374",
            "missing": "0",
            "min": "10",
            "max": "369",
            "mean": "103",
            "stdev": "55"
        },
        {
            "name": "F5",
            "index": "5",
            "type": "numeric",
            "distinct": "41868",
            "missing": "0",
            "min": "319490",
            "max": "5472011",
            "mean": "1368299",
            "stdev": "564037"
        },
        {
            "name": "F6",
            "index": "6",
            "type": "numeric",
            "distinct": "39155",
            "missing": "0",
            "min": "32",
            "max": "598",
            "mean": "146",
            "stdev": "70"
        },
        {
            "name": "F7",
            "index": "7",
            "type": "numeric",
            "distinct": "39450",
            "missing": "0",
            "min": "0",
            "max": "105948",
            "mean": "3990",
            "stdev": "1994"
        },
        {
            "name": "F8",
            "index": "8",
            "type": "numeric",
            "distinct": "341",
            "missing": "0",
            "min": "0",
            "max": "350",
            "mean": "70",
            "stdev": "56"
        },
        {
            "name": "F9",
            "index": "9",
            "type": "numeric",
            "distinct": "37299",
            "missing": "0",
            "min": "15",
            "max": "55",
            "mean": "35",
            "stdev": "6"
        }
    ],
    "nr_of_issues": 0,
    "nr_of_downvotes": 0,
    "nr_of_likes": 0,
    "nr_of_downloads": 0,
    "total_downloads": 0,
    "reach": 0,
    "reuse": 0,
    "impact_of_reuse": 0,
    "reach_of_reuse": 0,
    "impact": 0
}