| Timetable |
| Download Conference Program |
| Download All Abstracts |
| Zoom Access |
| Corporate Program |
Oral Sessions
Day 3, June 24（Tue.） 14:10-14:25
Room B (Maesato Center)
- 3B-O2-1410
Development of LC-MS/MS Software for Controlled Substance Identification
(Sogang Univ.)
So Yeon Lee, oHan Bin Oh
The identification of unknown controlled substances presents analytical challenges. The use of liquid chromatography tandem mass spectrometry (LC-MS/MS) for comparison with existing databases is common, however, its effectiveness is being challenged by the increasing prevalence of synthetic analogues engineered to evade regulatory oversight while maintaining the core characteristics of the original drugs. To overcome these challenges, we have developed AI-SNPS2 (Artificial Intelligence Screener for Narcotic Drugs and Psychotropic Substances 2), a sophisticated screening software which is an upgraded version of our previous tool ‘AI-SNPS'. The software is structured into five multi-layered components: LC-MS/MS Viewer, AI Classifier, Identifier, MN Constructor, and RT Predictor.
The RT Predictor layer incorporates four advanced regression models: an artificial neural network (ANN), support vector regression (SVR), Random Forest (RF), and extreme gradient boosting (XGBoost). it features a customized RT calibration function that adapts to varying experimental conditions, ensuring precise retention time predictions across various analytical techniques. We believe that the AI-SNPS2 software will serve as a powerful tool for identifying unknown controlled substances and their analogs.