{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/accurate-admet-prediction-with-xgboost","title":"Accurate ADMET Prediction with XGBoost","arxiv_id":"2204.07532","date":"2022-04-15","proceeding":null,"authors":["Hao Tian","Rajas Ketkar","Peng Tao"],"abstract":"The absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties are important in drug discovery as they define efficacy and safety. In this work, we applied an ensemble of features, including fingerprints and descriptors, and a tree-based machine learning model, extreme gradient boosting, for accurate ADMET prediction. Our model performs well in the Therapeutics Data Commons ADMET benchmark group. For 22 tasks, our model is ranked first in 18 tasks and top 3 in 21 tasks. The trained machine learning models are integrated in ADMETboost, a web server that is publicly available at https://ai-druglab.smu.edu/admet.","url_abs":"https://arxiv.org/abs/2204.07532v3","url_pdf":"https://arxiv.org/pdf/2204.07532v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"accurate-admet-prediction-with-xgboost","repo_url":"https://github.com/smu-tao-group/ADMET_XGBoost","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"tdc-admet-benchmarking-group","task_name":"TDC ADMET Benchmarking Group"},{"task_slug":"therapeutics-data-commons","task_name":"Therapeutics Data Commons"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"XGBoost","rank_in_archive_order":4,"of":29,"metrics":{"ROC-AUC":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/tdc-admet-benchmarking-group-on-tdcommons","task":"TDC ADMET Benchmarking Group","dataset":"tdcommons","model":"XGBoost","rank_in_archive_order":2,"of":12,"metrics":{"TDC.AMES":"0.859","TDC.BBB_Martins":"0.905","TDC.Bioavailability_Ma":"0.7","TDC.CYP2C9_Inhibition_Veith":"0.877","TDC.CYP2C9_Substrate_CarbonMangels":"0.680","TDC.CYP2D6_Inhibition_Veith":"0.794","TDC.CYP2D6_Substrate_CarbonMangels":"0.387","TDC.CYP3A4_Inhibition_Veith":"0.721","TDC.CYP3A4_Substrate_CarbonMangels":"0.648","TDC.Caco2_Wang":"0.288","TDC.Clearance_Hepatocyte_AZ":"0.587","TDC.Clearance_Microsome_AZ":"0.420","TDC.DILI":"0.933","TDC.HIA_Hou":"0.987","TDC.Half_Life_Obach":"0.396","TDC.LD50_Zhu":"0.602","TDC.Lipophilicity_AstraZeneca":"0.533","TDC.PPBR_AZ":"8.251","TDC.Pgp_Broccatelli":"0.911","TDC.Solubility_AqSolDB":"0.727","TDC.VDss_Lombardo":"0.612","TDC.hERG":"0.806"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.07532","atlas_url":"https://app.syntology.ai/?focus=2204.07532","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}