Differentiation and classification of bacterial endotoxins based on surface enhanced Raman scattering and advanced machine learning

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

A rapid and simple method was proposed for differentiation and classification of eleven bacterial endotoxins based on surface enhanced Raman scattering (SERS) and advanced machine learning algorithms.

Abstract

Bacterial endotoxin, a major component of the Gram-negative bacterial outer membrane leaflet, is a lipopolysaccharide shed from bacteria during their growth and infection and can be utilized as a biomarker for bacterial detection. Here, the surface enhanced Raman scattering (SERS) spectra of eleven bacterial endotoxins with an average detection amount of 8.75 pg per measurement have been obtained based on silver nanorod array substrates, and the characteristic SERS peaks have been identified. With appropriate spectral pre-processing procedures, different classical machine learning algorithms, including support vector machine, k-nearest neighbor, random forest, etc., and a modified deep learning algorithm, RamanNet, have been applied to differentiate and classify these endotoxins. It has been found that most conventional machine learning algorithms can attain a differentiation accuracy of >99%, while RamanNet can achieve 100% accuracy. Such an approach has the potential for precise classification of endotoxins and could be used for rapid medical diagnoses and therapeutic decisions for pathogenic infections.

Related collections

Most cited references 43

Record: found
Abstract: found
Article: not found

Probing Single Molecules and Single Nanoparticles by Surface-Enhanced Raman Scattering

Nie, Emory (1997)

Optical detection and spectroscopy of single molecules and single nanoparticles have been achieved at room temperature with the use of surface-enhanced Raman scattering. Individual silver colloidal nanoparticles were screened from a large heterogeneous population for special size-dependent properties and were then used to amplify the spectroscopic signatures of adsorbed molecules. For single rhodamine 6G molecules adsorbed on the selected nanoparticles, the intrinsic Raman enhancement factors were on the order of 10(14) to 10(15), much larger than the ensemble-averaged values derived from conventional measurements. This enormous enhancement leads to vibrational Raman signals that are more intense and more stable than single-molecule fluorescence.

0 comments Cited 377 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: not found
Article: not found

Single Molecule Detection Using Surface-Enhanced Raman Scattering (SERS)

Katrin Kneipp, Yang Wang, Harald Kneipp … (1997)

0 comments Cited 341 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

The structural basis of lipopolysaccharide recognition by the TLR4-MD-2 complex.

Beom Park, Dong Hyun Song, Ho Kim … (2009)

The lipopolysaccharide (LPS) of Gram negative bacteria is a well-known inducer of the innate immune response. Toll-like receptor (TLR) 4 and myeloid differentiation factor 2 (MD-2) form a heterodimer that recognizes a common 'pattern' in structurally diverse LPS molecules. To understand the ligand specificity and receptor activation mechanism of the TLR4-MD-2-LPS complex we determined its crystal structure. LPS binding induced the formation of an m-shaped receptor multimer composed of two copies of the TLR4-MD-2-LPS complex arranged symmetrically. LPS interacts with a large hydrophobic pocket in MD-2 and directly bridges the two components of the multimer. Five of the six lipid chains of LPS are buried deep inside the pocket and the remaining chain is exposed to the surface of MD-2, forming a hydrophobic interaction with the conserved phenylalanines of TLR4. The F126 loop of MD-2 undergoes localized structural change and supports this core hydrophobic interface by making hydrophilic interactions with TLR4. Comparison with the structures of tetra-acylated antagonists bound to MD-2 indicates that two other lipid chains in LPS displace the phosphorylated glucosamine backbone by approximately 5 A towards the solvent area. This structural shift allows phosphate groups of LPS to contribute to receptor multimerization by forming ionic interactions with a cluster of positively charged residues in TLR4 and MD-2. The TLR4-MD-2-LPS structure illustrates the remarkable versatility of the ligand recognition mechanisms employed by the TLR family, which is essential for defence against diverse microbial infection.