Related Experiment Video
Updated: Aug 5, 2026
09:59
Application of AlDeSense to Stratify Ovarian Cancer Cells Based on Aldehyde Dehydrogenase 1A1 Activity
Published on: March 31, 2023
A synergistic deep learning and machine learning framework for screening heterocyclic compounds against ALDH1A1
Shu-Chi Cho1, Yi-Wen Wang2, Chien-An Chu3
1Department of Biological Sciences and Technology, National University of Tainan, 33, Sec. 2, Shu-Lin St., West Central Dist., Tainan City, 700, Taiwan, ROC.
Molecular Diversity
|July 30, 2026
Summary
Researchers developed an integrated AI-CADD framework to discover selective Aldehyde dehydrogenase 1A1 (ALDH1A1) inhibitors. This approach successfully identified LDN-27219 as a promising lead candidate for cancer stem cell therapy.
Area of Science:
- Biochemistry
- Pharmacology
- Computational Chemistry
Background:
- Aldehyde dehydrogenase 1A1 (ALDH1A1) is a key target in cancer stem cell maintenance and chemoresistance.
- Developing selective ALDH1A1 inhibitors is difficult due to structural similarities with ALDH2 and ALDH1A2 isoforms.
Purpose of the Study:
- To create an integrated computer-aided drug design (CADD) and artificial intelligence (AI) framework for identifying selective ALDH1A1 inhibitors.
- To prioritize novel inhibitors for further experimental validation.
Main Methods:
- A multistage virtual screening workflow combining deep learning-assisted molecular docking and convolutional neural network (CNN)-based scoring.
- Isoform selectivity filtering and LightGBM-based classification for prioritizing candidate compounds.
- Molecular dynamics simulations and MM/PBSA calculations for dynamic validation of binding characteristics.
Main Results:
- The AI-CADD framework successfully identified potential selective ALDH1A1 inhibitors from a heterocyclic compound library.
- LDN-27219 and TUG-1375 were advanced for dynamic validation.
- Computational analyses indicated that LDN-27219 possesses favorable binding characteristics, suggesting it as a promising lead candidate.
Conclusions:
- The integrated AI-CADD framework offers an efficient strategy for discovering structurally novel, isoform-selective ALDH1A1 inhibitors.
- LDN-27219 is a promising lead compound for further experimental investigation in cancer therapy.
- This approach accelerates the identification and prioritization of drug candidates for ALDH1A1-related diseases.
