EUVIMEDEUVIMED entdecken
Crossref

An AI-Optimized Dual-Column LC-MS Workflow for High-Throughput Metabolite Profiling and Cost-Efficient Analytical Service Entrepreneurship

Bright Amankwah, Lawrence Anebi Enyejo

International Journal of Innovative Science and Research Technology · 29.05.2026 · 2209

DOI: 10.38124/ijisrt/26may1819 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 29.05.2026. Verfasst von Bright Amankwah und 1 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-throughput metabolomics remains constrained by analytical bottlenecks including prolonged chromatographic cycle times, inefficient instrument utilization, high solvent consumption, limited predictive maintenance capability, and escalating per-sample operational costs that restrict scalable analytical service commercialization. This study proposes a novel intelligent metabolomics framework termed AIDCL-MS (Artificial Intelligence-Driven Dual-Column Liquid Chromatography–Mass Spectrometry System) for accelerated metabolite profiling and economically optimized analytical laboratory entrepreneurship. The framework integrates a synchronized dual-column LC architecture with machine learning-guided sample routing, adaptive gradient scheduling, predictive instrument health diagnostics, and automated spectral deconvolution to maximize throughput while maintaining analytical precision. The proposed intelligent control engine incorporates a hybrid optimization algorithm named Reinforced Bayesian Chromatographic Orchestration Network (RBCON), combining Deep Reinforcement Learning (DRL), Bayesian Optimization, and temporal anomaly prediction for dynamic workflow control. RBCON continuously optimizes column switching intervals, solvent gradient parameters, injection timing, ion source stability, and queue prioritization using real-time telemetry from pump pressure, retention drift, ion suppression indicators, and detector response profiles. Comparative benchmarking is conducted against conventional single-column LC-MS workflows, static dual-column switching systems, Random Forest-based scheduling, XGBoost optimization pipelines, and Long Short-Term Memory (LSTM)-driven chromatographic prediction models.

Zitieren

APA

Amankwah, B., & Enyejo, L. A. (2026). An AI-Optimized Dual-Column LC-MS Workflow for High-Throughput Metabolite Profiling and Cost-Efficient Analytical Service Entrepreneurship. International Journal of Innovative Science and Research Technology, 2209. https://doi.org/10.38124/ijisrt/26may1819

Vancouver

Amankwah B, Enyejo LA. An AI-Optimized Dual-Column LC-MS Workflow for High-Throughput Metabolite Profiling and Cost-Efficient Analytical Service Entrepreneurship. International Journal of Innovative Science and Research Technology. 2026:2209. doi:10.38124/ijisrt/26may1819

BibTeX
@article{Amankwah2026,
  author = {Amankwah, Bright and Enyejo, Lawrence Anebi},
  title = {An AI-Optimized Dual-Column LC-MS Workflow for High-Throughput Metabolite Profiling and Cost-Efficient Analytical Service Entrepreneurship},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  pages = {2209},
  doi = {10.38124/ijisrt/26may1819}
}
Kostenlos starten →