Related Experiment Video
Updated: Sep 6, 2025
Simultaneous Measurement of HDAC1 and HDAC6 Activity in HeLa Cells Using UHPLC-MS
Published on: August 10, 2017
Classification models and SAR analysis on HDAC1 inhibitors using machine learning methods
Rourou Li1, Yujia Tian1, Zhenwu Yang1
1State Key Laboratory of Chemical Resource Engineering, Department of Pharmaceutical Engineering, Beijing University of Chemical Technology, Beijing, China.
Abstract:
Histone deacetylase (HDAC) 1, a member of the histone deacetylases family, plays a pivotal role in various tumors. In this study, we collected 7313 human HDAC1 inhibitors with bioactivities to form a dataset. Then, the dataset was divided into a training set and a test set using two splitting methods: (1) Kohonen's self-organizing map and (2) random splitting. The molecular structures were represented by MACCS fingerprints, RDKit fingerprints, topological torsions fingerprints and ECFP4 fingerprints. A total of 80 classification models were built by using five machine learning methods, including decision tree (DT), random forest, support vector machine, eXtreme Gradient Boosting and deep neural network. Model 15A_2 built by the XGBoost algorithm based on ECFP4 fingerprints showed the best performance, with an accuracy of 88.08% and an MCC value of 0.76 on the test set. Finally, we clustered the 7313 HDAC1 inhibitors into 31 subsets, and the substructural features in each subset were investigated. Moreover, using DT algorithm we analyzed the structure-activity relationship of HDAC1 inhibitors. It may conclude that some substructures have a significant effect on high activity, such as N-(2-amino-phenyl)-benzamide, benzimidazole, AR-42 analogues, hydroxamic acid with a middle chain alkyl and 4-aryl imidazole with a midchain of alkyl whose α carbon is chiral.
Insights
This study identifies key structural features of potent Histone Deacetylase 1 (HDAC1) inhibitors. Machine learning models predicted the best inhibitor structures, aiding in the development of new cancer therapies.
Area of Science:
- Medicinal Chemistry
- Computational Chemistry
- Drug Discovery
Background:
- Histone deacetylase 1 (HDAC1) is a crucial target in various cancers.
- Understanding structure-activity relationships (SAR) of HDAC1 inhibitors is vital for drug development.
Purpose of the Study:
- To build predictive models for identifying potent HDAC1 inhibitors.
- To investigate the substructural features influencing HDAC1 inhibitor activity.
Main Methods:
- A dataset of 7313 HDAC1 inhibitors was curated.
- Molecular structures were represented using various fingerprints (e.g., ECFP4).
- Eighty classification models were built using five machine learning algorithms, including XGBoost.
Main Results:
- The XGBoost model (15A_2) using ECFP4 fingerprints achieved the highest accuracy (88.08%) and MCC (0.76).
- HDAC1 inhibitors were clustered into 31 subsets, revealing key substructural features.
- Specific substructures like benzimidazole and hydroxamic acid derivatives were linked to high activity.
Conclusions:
- Machine learning, particularly XGBoost, effectively predicts HDAC1 inhibitor activity.
- Identified substructures provide valuable insights for designing novel, high-activity HDAC1 inhibitors for cancer treatment.
