Benchmarking ML in ADMET predictions: the practical impact of feature representations in ligand-based models
Abstract This study, focusing on predicting Absorption, Distribution, Metabolism, Excretion, and Toxicology (ADMET) properties, addresses the key challenges of ML models trained using ligand-based representations. We propose a structured approach to data feature selection, taking a step beyond the c...
Saved in:
| Main Authors: | Gintautas Kamuntavičius, Tanya Paquet, Orestis Bastas, Dainius Šalkauskas, Alvaro Prat, Hisham Abdel Aty, Aurimas Pabrinkis, Povilas Norvaišas, Roy Tal |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | Journal of Cheminformatics |
| Online Access: | https://doi.org/10.1186/s13321-025-01041-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Machine learning in big data: A performance benchmarking study of Flink-ML and Spark MLlib
by: Messaoud MEZATI, et al.
Published: (2025-06-01) -
Unveiling Palmitoyl Thymidine Derivatives as Antimicrobial/Antiviral Inhibitors: Synthesis, Molecular Docking, Dynamic Simulations, ADMET, and Assessment of Protein–Ligand Interactions
by: Sarkar M. A. Kawsar, et al.
Published: (2025-05-01) -
Novel phosphoramide ligand shows promise as a cytotoxic agent against breast cancer: Molecular docking, ADMET studies and quantum studies
by: Sadegh Nikakhtar, et al.
Published: (2025-07-01) -
AutoML based workflow for design of experiments (DOE) selection and benchmarking data acquisition strategies with simulation models
by: Xukuan Xu, et al.
Published: (2024-12-01) -
In vitro technology and ADMET research in traditional Chinese medicine
by: Jinhao Xue, et al.
Published: (2025-07-01)