.png){kind=icon}
Return
Efficient decoy selection to improve virtual screening using machine learning models
.png){kind=icon}
OA
AI
DOI：10.1186/s13321-025-01107-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Machine learning models using protein-ligand interaction fingerprints show promise as target-specific scoring functions in drug discovery, but their performance critically depends on the underlying decoy selection strategies. Recognizing this critical role in model performance, various decoy selection strategies were analyzed to enhance machine learning models based on the Protein per Atom Score Contributions Derived Interaction Fingerprint (PADIF). We explored three distinct workflows for decoy selection: (1) random selection from extensive databases like ZINC15, (2) leveraging recurrent non-binders from high-throughput screening (HTS) assays stored as dark chemical matter, and (3) data augmentation by utilizing diverse conformations from docking results. Active molecules from ChEMBL, combined with these decoy approaches, were used to train and test different machine learning models based on PADIF. The final validation was done by confirming experimentally determined inactive compounds from the LIT-PCBA dataset. Our findings reveal that models trained with random selections from ZINC15 and compounds from dark chemical matter closely mimic the performance of those trained with actual non-binders, presenting viable alternatives for creating accurate models in the absence of specific inactivity data. Furthermore, all models showed an enhanced ability to explore new chemical spaces for their specific target and enhanced the top active compound selection over classical scoring functions, thereby boosting the screening power in molecular docking. These findings demonstrate that appropriate decoy selection strategies can maintain model accuracy while expanding applicability to targets even when lacking extensive experimental data. This study enhances the available options for decoys to create new bioactive machine learning classification models from public datasets. Through a molecular docking protocol and PADIF representation, we identify the benefits of using this methodology to improve binder selection in molecular docking
Journal
IF:
5.7
Papers:
1.5K
Citations:
1.1W
Organization
Cited Papers
Docking-based generative approaches in the search for new drug candidates.png)
DRUG DISCOVERY TODAY
OAAI
DRUG DISCOVERY TODAYIF7.5
OAAIShareSaveShareSaveDark chemical matter as a promising starting point for drug lead discoveryNATURE CHEMICAL BIOLOGY
NATURE CHEMICAL BIOLOGYIF13.7
PREAI
ShareSaveAdding Stochastic Negative Examples into Machine Learning Improves Molecular Bioactivity PredictionOAAI
OAAIShareSaveShareSave
View more