Endotoxins are lipopolysaccharides that are found in the outer membrane of gram-negative bacteria and that are accountable for many health hazards such as endotoxemia (a septic shock caused severe immune response). A number of methods have been proposed to detect the presence of endotoxins with a remarkably high sensitivity. However, available methods do not provide a quantitative estimation of concentration and/or are incapable of classifying endotoxin type.<br/>Liquid crystal (LC) droplets dispersed in water are sensitive to the presence of endotoxins and undergo ordering transitions when varying endotoxin species and concentrations. Specifically, LC shifts from a tangential orientation at the droplet surface (bipolar configuration) to orientating perpendicular to the droplet surface (radial configuration) under a higher concentration of endotoxins. Different internal configurations of LC droplets have distinct optical properties. As such, flow cytometry of LC droplets can be used to generate rich forward scattering/side scattering (FSC/SSC) data to characterizes optical properties. Counting methods used in the analysis of FSC/SSC data can be used to predict endotoxin concentration. However, such counting methods are not robust (they are subject to significant variability).<br/>In this work, we demonstrate that machine learning techniques can be used to accurately predict endotoxin concentrations and species from FSC/SSC data. Our approach uses a convolutional neural network (CNN) to extract pattern information (features) from FSC/SSC density data. Our framework reveals that significant amounts of hidden information is available in FSC/SSC data. We also add prior knowledge of the counting method to the CNN by introducing a regularization term on trainable parameters and have achieved better results.

Endotoxin detection using liquid crystal droplets and machine learning

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.