Machine learning anomaly detection of automated HPLC experiments in the cloud laboratory
Filipp Gusev, Benjamin C. Kline, Ryan Quinn, Anqin Xu, Ben Smith, Brian Frezza, Olexandr Isayev
Highlight
Autonomous experiments are vulnerable to unforeseen adverse events.
Abstract
Autonomous experiments are vulnerable to unforeseen adverse events. We developed a transferable ML framework that flags affected HPLC runs in real time and provides expert-level quality control without human oversight.
Keywords
Cite This Paper
@article{Gusev2025a,
author = {Gusev, Filipp and Kline, Benjamin C. and Quinn, Ryan and Xu, Anqin and Smith, Ben and Frezza, Brian and Isayev, Olexandr},
title = {Machine learning anomaly detection of automated HPLC experiments in the cloud laboratory},
year = {2025},
journal = {Digital Discovery},
volume = {4},
number = {12},
pages = {3445--3454},
doi = {10.1039/d5dd00253b},
url = {http://dx.doi.org/10.1039/D5DD00253B},
publisher = {Royal Society of Chemistry (RSC)},
keywords = {machine learning},
researchAreas = {experiment-automation},
highlight = {Autonomous experiments are vulnerable to unforeseen adverse events.}
} Copied to clipboard!
Related Research Areas
Related Publications
Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential
Nature Chemistry 16 , 727–734
Abstract Atomistic simulation has a broad range of applications from drug design to materials discovery.
The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules
Scientific Data 7
Abstract Maximum diversification of data is a central theme in building generalized and accurate machine learning (ML) models.
Less is more: Sampling chemical space with active learning
The Journal of Chemical Physics 148
The development of accurate and transferable machine learning (ML) potentials for predicting molecular energetics is a challenging task.
Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using Complementary DFT and Machine Learning Approaches
Advanced Theory and Simulations 2
Abstract There are now, in principle, a limitless number of hybrid van der Waals (vdW) heterostructures that can be built from the rapidly growing number of 2D layers.
Transferable Machine Learning Interatomic Potential for Pd-Catalyzed Cross-Coupling Reactions
Finding efficient substrate-catalyst combinations for palladium-catalyzed cross-coupling reactions remains a critical challenge in synthetic chemistry, with broad implications for pharmaceutical and materials manufacturing.