Related Experiment Video
Updated: Jun 11, 2025
Continuous Fluorescence-Based Endonuclease-Coupled DNA Methylation Assay to Screen for DNA Methyltransferase Inhibitors
Published on: August 5, 2022
Cheminformatic Identification of Tyrosyl-DNA Phosphodiesterase 1 (Tdp1) Inhibitors: A Comparative Study of
Conan Hong-Lun Lai1,2, Alex Pak Ki Kwok2, Kwong-Cheong Wong2
1Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong 999077, China.
Background:
Tyrosyl-DNA phosphodiesterase 1 (Tdp1) repairs damages in DNA induced by abortive topoisomerase 1 activity; however, maintenance of genetic integrity may sustain cellular division of neoplastic cells. It follows that Tdp1-targeting chemical inhibitors could synergize well with existing chemotherapy drugs to deny cancer growth; therefore, identification of Tdp1 inhibitors may advance precision medicine in oncology.
Objective:
Current computational research efforts focus primarily on molecular docking simulations, though datasets involving three-dimensional molecular structures are often hard to curate and computationally expensive to store and process. We propose the use of simplified molecular input line entry system (SMILES) chemical representations to train supervised machine learning (ML) models, aiming to predict potential Tdp1 inhibitors.
Methods:
An open-sourced consensus dataset containing the inhibitory activity of numerous chemicals against Tdp1 was obtained from Kaggle. Various ML algorithms were trained, ranging from simple algorithms to ensemble methods and deep neural networks. For algorithms requiring numerical data, SMILES were converted to chemical descriptors using RDKit, an open-sourced Python cheminformatics library.
Results:
Out of 13 optimized ML models with rigorously tuned hyperparameters, the random forest model gave the best results, yielding a receiver operating characteristics-area under curve of 0.7421, testing accuracy of 0.6815, sensitivity of 0.6444, specificity of 0.7156, precision of 0.6753, and F1 score of 0.6595.
Conclusions:
Ensemble methods, especially the bootstrap aggregation mechanism adopted by random forest, outperformed other ML algorithms in classifying Tdp1 inhibitors from non-inhibitors using SMILES. The discovery of Tdp1 inhibitors could unlock more treatment regimens for cancer patients, allowing for therapies tailored to the patient's condition.
Insights
Machine learning models using simplified molecular input line entry system (SMILES) effectively predict Tyrosyl-DNA phosphodiesterase 1 (Tdp1) inhibitors. This approach can advance precision oncology by identifying novel cancer therapies.
Area of Science:
- Cheminformatics and Computational Chemistry
- Machine Learning in Drug Discovery
- Oncology Research
Background:
- Tyrosyl-DNA phosphodiesterase 1 (Tdp1) is crucial for DNA repair, and its inhibition can impede cancer cell division.
- Targeting Tdp1 offers a potential strategy to enhance existing chemotherapy efficacy.
- Developing Tdp1 inhibitors is key to advancing precision medicine in oncology.
Purpose of the Study:
- To develop a computational method for predicting Tdp1 inhibitors using machine learning.
- To utilize simplified molecular input line entry system (SMILES) for chemical representation, overcoming limitations of 3D structures.
- To identify novel chemical entities with potential Tdp1 inhibitory activity.
Main Methods:
- A consensus dataset of Tdp1 inhibitors was curated from Kaggle.
- Various machine learning algorithms, including deep neural networks and ensemble methods, were trained.
- Simplified molecular input line entry system (SMILES) strings were converted to chemical descriptors using RDKit for model input.
Main Results:
- The random forest model, an ensemble method, demonstrated the best performance among 13 optimized models.
- The random forest model achieved a receiver operating characteristics-area under the curve of 0.7421.
- Key performance metrics included an accuracy of 0.6815 and an F1 score of 0.6595.
Conclusions:
- Ensemble methods, particularly random forest, are effective for classifying Tdp1 inhibitors using SMILES data.
- This machine learning approach facilitates the discovery of Tdp1 inhibitors.
- Identifying Tdp1 inhibitors can lead to new cancer treatment regimens and personalized therapies.
More Related Videos
08:31Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
07:35Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018