Related Experiment Video
Updated: Jul 24, 2026
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
Epigenetic target identification strategy based on multi-feature learning
Lingfeng Chen1, Rui Gu1, Yuanyuan Li1
1Laboratory of Molecular Design and Drug Discovery, School of Science, China Pharmaceutical University, Nanjing, China.
Abstract:
The identification of potential epigenetic targets for a known bioactive compound is essential and promising as more and more epigenetic drugs are used in cancer clinical treatment and the availability of chemogenomic data related to epigenetics increases. In this study, we introduce a novel epigenetic target identification strategy (ETI-Strategy) that integrates a multi-task graph convolutional neural network prior model and a protein-ligand interaction classification discriminating model using large-scale bioactivity data for a panel of 55 epigenetic targets. Our approach utilizes machine learning techniques to achieve an AUC value of 0.934 for the prior model and 0.830 for the discriminating model, outperforming inverse docking in predicting protein-ligand interactions. When comparing with other open-source target identification tools, it was found that only our tool was able to accurately predict all the targets corresponding to each compound. This further demonstrates the ability of our strategy to take full advantage of molecular-level information as well as protein-level information in molecular activity prediction. Our work highlights the contribution of machine learning in the identification of potential epigenetic targets and offers a novel approach for epigenetic drug discovery and development.Communicated by Ramaswamy H. Sarma.
Insights
This study introduces a novel epigenetic target identification strategy (ETI-Strategy) using machine learning. The ETI-Strategy accurately predicts epigenetic targets for drug discovery, outperforming existing methods.
Area of Science:
- Biochemistry
- Computational Biology
- Pharmacology
Background:
- Epigenetic drugs are increasingly vital in cancer treatment.
- Identifying epigenetic targets for bioactive compounds is crucial for drug discovery.
- Advances in chemogenomic data necessitate improved target identification methods.
Purpose of the Study:
- To introduce a novel epigenetic target identification strategy (ETI-Strategy).
- To leverage machine learning for predicting protein-ligand interactions and identifying epigenetic targets.
- To enhance the accuracy and efficiency of epigenetic drug discovery.
Main Methods:
- Integration of a multi-task graph convolutional neural network prior model.
- Utilization of a protein-ligand interaction classification discriminating model.
- Training and validation using large-scale bioactivity data for 55 epigenetic targets.
Main Results:
- Achieved an AUC of 0.934 for the prior model and 0.830 for the discriminating model.
- Outperformed inverse docking in predicting protein-ligand interactions.
- Demonstrated superior accuracy compared to other open-source target identification tools.
Conclusions:
- The ETI-Strategy effectively utilizes molecular and protein-level information for accurate activity prediction.
- Machine learning significantly contributes to identifying potential epigenetic targets.
- This approach offers a novel pathway for epigenetic drug discovery and development.
