Related Experiment Video
Updated: Jul 29, 2025

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
Augmenting bioactivity by docking-generated multiple ligand poses to enhance machine learning and pharmacophore
Amenah M Al-Imam1, Safa Daoud2, Ma'mon M Hatmal3
1Department of Pharmaceutical Sciences, Faculty of Pharmacy, University of Jordan, Amman, 11492, Jordan.
Abstract:
Dual specificity protein kinase threonine/Tyrosine kinase (TTK) is one of the mitotic kinases. High levels of TTK are detected in several types of cancer. Hence, TTK inhibition is considered a promising therapeutic anti-cancer strategy. In this work, we used multiple docked poses of TTK inhibitors to augment training data for machine learning QSAR modeling. Ligand-Receptor Contacts Fingerprints and docking scoring values were used as descriptor variables. Escalating docking-scoring consensus levels were scanned against orthogonal machine learners, and the best learners (Random Forests and XGBoost) were coupled with genetic algorithm and Shapley additive explanations (SHAP) to determine critical descriptors for predicting anti-TTK bioactivity and for pharmacophore generation. Three successful pharmacophores were deduced and subsequently used for in silico screening against the NCI database. A total of 14 hits were evaluated in vitro for their anti-TTK bioactivities. One hit of novel chemotype showed reasonable dose-response curve with experimental IC50 of 1.0 μM. The presented work indicates the validity of data augmentation using multiple docked poses for building successful machine learning models and pharmacophore hypotheses.
Insights
This study developed a machine learning model to identify dual specificity protein kinase threonine/Tyrosine kinase (TTK) inhibitors for cancer therapy. Data augmentation with docked poses improved model accuracy, leading to a novel TTK inhibitor candidate.
Area of Science:
- Medicinal Chemistry
- Computational Biology
- Drug Discovery
Background:
- Dual specificity protein kinase threonine/Tyrosine kinase (TTK) is a mitotic kinase.
- Elevated TTK levels are observed in various cancers, making it a therapeutic target.
- TTK inhibition represents a promising anti-cancer strategy.
Purpose of the Study:
- To augment training data for Quantitative Structure-Activity Relationship (QSAR) modeling using multiple docked poses of TTK inhibitors.
- To identify critical descriptors for predicting anti-TTK bioactivity and generate pharmacophore models.
- To discover novel TTK inhibitors through in silico screening and in vitro validation.
Main Methods:
- Utilized Ligand-Receptor Contacts Fingerprints and docking scores as descriptor variables.
- Employed machine learning algorithms (Random Forests, XGBoost) coupled with genetic algorithms and SHAP.
- Generated and screened pharmacophore hypotheses against the NCI database.
- Performed in vitro evaluation of identified hits for anti-TTK bioactivity.
Main Results:
- Successfully augmented QSAR modeling data using multiple docked poses.
- Identified key descriptors influencing anti-TTK bioactivity.
- Deduced three pharmacophore models leading to the identification of 14 potential hits.
- One novel chemotype inhibitor demonstrated significant anti-TTK activity with an IC50 of 1.0 μM.
Conclusions:
- Data augmentation with multiple docked poses is a valid approach for building effective machine learning models.
- The developed pharmacophore models are effective for identifying potential TTK inhibitors.
- This study successfully identified a novel TTK inhibitor candidate with therapeutic potential.
More Related Videos
08:49Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
Published on: June 20, 2025
08:31Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
Related Concept Videos
Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Drug Discovery: Overview
Ligand Binding and Linkage
The Equilibrium Binding Constant and Binding Strength
Protein-protein Interfaces
Cooperative Allosteric Transitions