Artificial Intelligence-Assisted HPLC Method Development and Optimization: A Review
High-performance liquid chromatography (HPLC) continues to be the primary tool in pharmaceutical, environmental, food, and bioanalytical laboratories; however, creating a reliable method is still a gradual, repetitive, and skill-dependent process. Traditional approaches reliant on analyst expertise, sequential one-factor screening, retention modelling, and statistical design of experiments (DoE) are efficient but become ineffective as the number of essential technique parameters, analyte categories, or column chemistries increases. Artificial intelligence (AI), encompassing traditional machine learning (ML), deep learning (DL), Bayesian optimisation, and reinforcement learning (RL), is currently utilised at every phase of method development: forecasting retention behaviour based on molecular structure, choosing columns and mobile phases, refining gradients, and progressively directing automated experimentation. This critique encapsulates the principles of HPLC method formulation, delineates the primary AI frameworks and their chromatographic utilisations, juxtaposes retention-time forecasting models and optimisation techniques in a tabular format, explores the synergy with analytical quality by design (AQbD) and the ICH Q14 and Q2(R2) guidelines, and rigorously assesses constraints including data insufficiency, inadequate transferability across systems, absence of interpretability, and regulatory endorsement. Ultimately, novel trajectories such as transfer learning, closed-loop autonomous driving laboratories, and large language model (LLM) agents are delineated. The supporting sections encompass data representation and assessment metrics, a suggested AI-enhanced workflow, validation and model governance factors, along with a table outlining research deficiencies. HPLC; method development, artificial intelligence, machine learning, retention time prediction, Bayesian optimisation, reinforcement learning, analytical quality by design
Authors
- Anisha Ashish Lohiya
- Gauri Shalikram Mate
- Shruti Gajanan Raut
- Shradha Anilkumar Singhi
- Poonam Vishnu Mankar
- Pooja Dipak Tambare
- Ankita Santosh Shegokar
- Pratiksha Bhagwanrao Zambare
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-14
- DOI
- https://doi.org/10.5281/zenodo.24215622
- Primary Topic
- Spectroscopy and Chemometric Analyses
- Type
- article
- Field-Weighted Citation Impact
- 0.00