dataset_descriptions.json

{
    "ADMET_Caco2_Wang": {
        "task_type": "regression",
        "description": "predict drug permeability, measured in cm/s, using the Caco-2 cell line as an in vitro model to simulate human intestinal tissue permeability",
        "num_molecules": 906
    },
    "ADMET_Bioavailability_Ma": {
        "task_type": "classification",
        "description": "predict oral bioavailability with binary labels, indicating the rate and extent a drug becomes available at its site of action",
        "num_molecules": 640
    },
    "ADMET_Lipophilicity_AstraZeneca": {
        "task_type": "regression",
        "description": "predict lipophilicity with continuous labels, measured as a log-ratio, indicating a drug's ability to dissolve in lipid environments",
        "num_molecules": 4200
    },
    "ADMET_Solubility_AqSolDB": {
        "task_type": "regression",
        "description": "predict aqueous solubility with continuous labels, measured in log mol/L, indicating a drug's ability to dissolve in water",
        "num_molecules": 9982
    },
    "ADMET_HIA_Hou": {
        "task_type": "classification",
        "description": "predict human intestinal absorption (HIA) with binary labels, indicating a drug's ability to be absorbed into the bloodstream",
        "num_molecules": 578
    },
    "ADMET_Pgp_Broccatelli": {
        "task_type": "classification",
        "description": "predict P-glycoprotein (Pgp) inhibition with binary labels, indicating a drug's potential to alter bioavailability and overcome multidrug resistance",
        "num_molecules": 1212
    },
    "ADMET_BBB_Martins": {
        "task_type": "classification",
        "description": "predict blood-brain barrier permeability with binary labels, indicating a drug's ability to penetrate the barrier to reach the brain",
        "num_molecules": 1915
    },
    "ADMET_PPBR_AZ": {
        "task_type": "regression",
        "description": "predict plasma protein binding rate with continuous labels, indicating the percentage of a drug bound to plasma proteins in the blood",
        "num_molecules": 1797
    },
    "ADMET_VDss_Lombardo": {
        "task_type": "regression",
        "description": "predict the volume of distribution at steady state (VDss), indicating drug concentration in tissues versus blood",
        "num_molecules": 1130
    },
    "ADMET_CYP2C9_Veith": {
        "task_type": "classification",
        "description": "predict CYP2C9 inhibition with binary labels, indicating the drug's ability to inhibit the CYP2C9 enzyme involved in metabolism",
        "num_molecules": 12092
    },
    "ADMET_CYP2D6_Veith": {
        "task_type": "classification",
        "description": "predict CYP2D6 inhibition with binary labels, indicating the drug's potential to inhibit the CYP2D6 enzyme involved in metabolism",
        "num_molecules": 13130
    },
    "ADMET_CYP3A4_Veith": {
        "task_type": "classification",
        "description": "predict CPY3A4 inhibition with binary labels, indicating the drug's ability to inhibit the CPY3A4 enzyme involved in metabolism",
        "num_molecules": 12328
    },
    "ADMET_CYP2C9_Substrate_CarbonMangels": {
        "task_type": "classification",
        "description": "predict whether a drug is a substrate of the CYP2C9 enzyme with binary labels, indicating its potential to be metabolized",
        "num_molecules": 666
    },
    "ADMET_CYP2D6_Substrate_CarbonMangels": {
        "task_type": "classification",
        "description": "predict whether a drug is a substrate of the CYP2D6 enzyme with binary labels, indicating its potential to be metabolized",
        "num_molecules": 664
    },
    "ADMET_CYP3A4_Substrate_CarbonMangels": {
        "task_type": "classification",
        "description": "predict whether a drug is a substrate of the CYP3A4 enzyme with binary labels, indicating its potential to be metabolized",
        "num_molecules": 667
    },
    "ADMET_Half_Life_Obach": {
        "task_type": "regression",
        "description": "predict the half-life duration of a drug, measured in hours, indicating the time for its concentration to reduce by half",
        "num_molecules": 667
    },
    "ADMET_Clearance_Hepatocyte_AZ": {
        "task_type": "regression",
        "description": "predict drug clearance, measured in \u03bcL/min/10^6 cells, from hepatocyte experiments, indicating the rate at which the drug is removed from body",
        "num_molecules": 1020
    },
    "ADMET_Clearance_Microsome_AZ": {
        "task_type": "regression",
        "description": "predict drug clearance, measured in mL/min/g, from microsome experiments, indicating the rate at which the drug is removed from body",
        "num_molecules": 1102
    },
    "ADMET_LD50_Zhu": {
        "task_type": "regression",
        "description": "predict the acute toxicity of a drug, measured as the dose leading to lethal effects in log(kg/mol)",
        "num_molecules": 7385
    },
    "ADMET_hERG": {
        "task_type": "classification",
        "description": "predict whether a drug blocks the hERG channel, which is crucial for heart rhythm, potentially leading to adverse effects",
        "num_molecules": 648
    },
    "ADMET_AMES": {
        "task_type": "classification",
        "description": "predict whether a drug is mutagenic with binary labels, indicating its ability to induce genetic alterations",
        "num_molecules": 7255
    },
    "ADMET_DILI": {
        "task_type": "classification",
        "description": "predict whether a drug can cause liver injury with binary labels, indicating its potential for hepatotoxicity",
        "num_molecules": 475
    }
}