Machine Learning-Guided Generation of Novel Pseudo-Natural Products: Applications to Accelerate Drug Discovery
- 18 October 2025
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 65 (21) , 11701-11715
Abstract
Natural products (NPs) are a critical source for drug discovery, and artificial intelligence (AI) is utilized to improve the efficiency of NP-based drug discovery. However, the existing AI-driven models typically generate a library of pseudo-natural products that only covers a small portion of the chemical space and the compounds were also restricted by poor drug-likeness profiles. Herein, the GPT1 is developed to generate diverse pseudo-natural products with excellent validity, uniqueness, and novelty while retaining molecular features similar to the training set. Subsequently, the Augmented Hill-Climb (AHC) strategy is employed to generate synthetically accessible compounds with enhanced drug-likeness. Using the integrated NPDL-GEN model (GPT1 + AHC), compounds G1-G5 were obtained, exhibiting significantly improved drug-likeness profiles. Furthermore, the pseudo-natural products H1-H3 generated via transfer learning also possess potent anti-inflammatory activities. Thus, our developed machine learning models can accelerate NP-based drug discovery.Keywords
Funding Information
- Graduate Research and Innovation Projects of Jiangsu Province (KYCX24 2146)
- Nanjing University of Chinese Medicine (01303801902, JBGS202407, NZY81703342, ZYXJC2024-007, ZYXJC2024-010, ZYXYL2024-007)
- Natural Science Foundation of Jiangsu Province (BK20211301)
- Shanghai Municipal Education Commission (SHJWAIJK241205)
- National Natural Science Foundation of China (32400527, U2102201, U24A20785)
- Open Project of Jiangsu Province Engineering Research Center of TCM Intelligence Health Service (ZHZYY202413)
- Chinese Medicine Leading Talent Project of Jiangsu Province (SLJ0321)
This publication has 63 references indexed in Scilit:
- Deep reinforcement learning in chemistry: A reviewJournal of Computational Chemistry, 2024
- RM-GPT: Enhance the comprehensive generative ability of molecular GPT model via LocalRNN and RealFormerArtificial Intelligence in Medicine, 2024
- Generation of focused drug molecule library using recurrent neural networkJournal of Molecular Modeling, 2023
- Artificial intelligence: Machine learning approach for screening large database and drug discoveryAntiviral Research, 2023
- Computer especially AI-assisted drug virtual screening and design in traditional Chinese medicinePhytomedicine, 2022
- FTIR spectroscopic study of two isostructural statins: Simvastatin and Lovastatin as authentic and in pharmaceuticalsSpectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021
- Natural Language Processing2020
- Piceatannol: A natural stilbene for the prevention and treatment of cancerPharmacological Research, 2020
- Structural Simplification of Natural ProductsChemical Reviews, 2019
- Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings 1PII of original article: S0169-409X(96)00423-1. The article was originally published in Advanced Drug Delivery Reviews 23 (1997) 3–25. 1Advanced Drug Delivery Reviews, 2001