Related Experiment Video
Updated: Jan 18, 2026
11:59
Competitive Genomic Screens of Barcoded Yeast Libraries
Published on: August 11, 2011
18.7K
Combating Counterfeit Drugs via Machine Learning-Enabled Array Screening of Multilayer Evolutionary Combinatorial
Huihai Li1, Hao Chen2, Weiwei Ni1
1State Key Laboratory of Natural Medicines, National R&D Center for Chinese Herbal Medicine Processing, Jiangsu Key Laboratory of Drug Design and Optimization, College of Engineering, China Pharmaceutical University, Nanjing 211109, China.
ACS Applied Materials & Interfaces
|September 12, 2025
Summary
A new machine learning strategy rapidly identifies optimal sensor arrays for detecting counterfeit nonsteroidal anti-inflammatory drugs (NSAIDs). This method ensures 100% accuracy in distinguishing genuine from fake NSAIDs within minutes.
Area of Science:
- Analytical Chemistry
- Materials Science
- Computational Chemistry
Background:
- Counterfeit drugs pose significant global health risks, impacting patient morbidity and mortality.
- Sensor arrays offer potential for discriminating drug molecules but face challenges in rapid library generation.
- Developing efficient methods to identify optimal sensor combinations is crucial for drug authenticity verification.
Purpose of the Study:
- To develop a machine learning-guided strategy for rapidly generating optimal sensor arrays.
- To identify a minimal set of sensing elements for detecting counterfeit nonsteroidal anti-inflammatory drugs (NSAIDs).
- To establish a foundation for broad application in drug authenticity verification.
Main Methods:
- A three-layer screening strategy guided by machine learning was employed.
- A combinatorially designed library of 100 candidate sensing elements was synthesized and screened.
- A pruned 5-element array was constructed and validated for NSAID discrimination.
Main Results:
- The 5-element array achieved 100% accuracy in distinguishing nine NSAIDs and their analogs.
- Quantitative and multiplexed differentiation of two key NSAIDs was successfully demonstrated.
- The array accurately identified five commercial over-the-counter (OTC) NSAIDs from two counterfeit versions within 5 minutes with 100% accuracy.
Conclusions:
- The machine learning-guided strategy enables rapid construction of optimal combinatorial sensing libraries.
- The developed sensor array provides a highly accurate and efficient method for counterfeit NSAID detection.
- This approach lays the groundwork for versatile drug authenticity verification systems.
