Smart Prediction of Molecular Behavior in Liquid Chromatography for Better Compound Detection
- Authors
-
-
Richa Singh
Author
-
- Keywords:
- Molecular Property Prediction, Lipophilicity (logP), Retention Time, Graph Neural Networks (GNNs), Multi- task Learning, Cheminformatics
- Abstract
-
Identifying unknown chemical structures using mass spectrometry remains a complex task, especially when dealing with diverse biological compounds. This work presents a machine-learning-guided approach that anticipates how long a molecule will take to travel through a liquid chromatography system, helping narrow down structural possibilities. By combining this predicted timing with fragmentation data, we improve the prioritization of potential matches. The approach is tested on several real-world datasets, showing measurable gains in accuracy and speed for molecular identification tasks. This fusion of temporal and spectral insights lays the groundwork for smarter, data-driven compound analysis in chemical research.
- References
- Cover Image
-
- Downloads
- Published
- 2026-05-06
- Issue
- Vol. 1 No. 1 (2026)
- Section
- Articles
- License
-
Copyright (c) 2026 International Journal of Clinical Research and Medical Sciences
This work is licensed under a Creative Commons Attribution 4.0 International License.
