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

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial Intelligence-Assisted HPLC Method Development and Optimization: A Review

Anisha Ashish Lohiya, Gauri Shalikram Mate, Shruti Gajanan Raut, Shradha Anilkumar Singhi et al.
Zenodo (CERN European Organization for Nuclear Research)
Spectroscopy and Chemometric Analyses
article

Artificial Intelligence-Assisted HPLC Method Development and Optimization: A Review

Anisha Ashish Lohiya, Gauri Shalikram Mate, Shruti Gajanan Raut, Shradha Anilkumar Singhi, Poonam Vishnu Mankar, Pooja Dipak Tambare, Ankita Santosh Shegokar, Pratiksha Bhagwanrao Zambare
article en

Abstract

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

Zenodo (CERN European Organization for Nuclear Research)
Spectroscopy and Chemometric Analyses
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon