Hybrid consensus and k-nearest neighbours (kNN) strategies to classify dual BRD4/PLK1 inhibitors
H Rezaie1, M Asadollahi-Baboli1, S K Hassaninejad-Darzi1
1Department of Chemistry, Faculty of Science, Babol Noshirvani University of Technology, Babol, Iran.
Abstract:
A novel decision-making procedure is proposed here for the first time to identify active/inactive and selective/non-selective dual inhibitors using consensus approaches and pools of k-nearest neighbours (kNN) classifications instead of individual models. Dual BRD4/PLK1 inhibition with adequate selectivity is a potential therapeutic strategy for targeting tumour cells in high-risk patients. We report the unique way to identify both active and selective dual BRD4/PLK1 inhibitors using consensus and kNN strategies together with two sources of receptor-based and ligand-based information which are the ranked binding energies of residues and important molecular features, respectively. The results of consensus approaches were compared with the results of individual kNN models. The chemical space similarity was measured using three different distance functions to increase the reliability. All activity and selectivity classification models were validated using cross-validation and y-randomization tests. The outcomes show that consensus approaches can increase the reliability and accuracy of active/inactive or selective/non-selective detections up to 90%. Consensus approaches also reached more balanced values of sensitivity and specificity compared to the individual kNN models because of the compensation in the integration of diverse sources of information.
Insights
A new consensus approach using k-nearest neighbors (kNN) classifications improves the identification of dual BRD4/PLK1 inhibitors. This method enhances accuracy and reliability in detecting active and selective compounds for cancer therapy.
Area of Science:
- Medicinal Chemistry
- Computational Drug Discovery
- Pharmacology
Background:
- Dual inhibition of BRD4 (Bromodomain-containing protein 4) and PLK1 (Polo-like kinase 1) presents a promising therapeutic strategy for high-risk cancer patients.
- Identifying selective dual inhibitors is crucial for maximizing efficacy while minimizing off-target effects.
Purpose of the Study:
- To develop and validate a novel decision-making procedure for identifying active/inactive and selective/non-selective dual BRD4/PLK1 inhibitors.
- To evaluate the performance of consensus approaches compared to individual k-nearest neighbors (kNN) models.
Main Methods:
- Utilized consensus approaches combining multiple kNN classifications.
- Integrated receptor-based (ranked binding energies of residues) and ligand-based (molecular features) information.
- Employed three different distance functions for chemical space similarity measurement.
- Validated classification models using cross-validation and y-randomization tests.
Main Results:
- Consensus approaches demonstrated an improvement in the reliability and accuracy of active/inactive and selective/non-selective detections, reaching up to 90%.
- Consensus methods achieved more balanced sensitivity and specificity compared to individual kNN models.
- The integration of diverse information sources compensated for individual model limitations.
Conclusions:
- Consensus strategies offer a more robust and reliable method for identifying dual BRD4/PLK1 inhibitors.
- This approach enhances the accuracy of drug discovery pipelines for targeted cancer therapies.
- The developed procedure provides a valuable tool for medicinal chemists and computational drug designers.
