Explainable AI-SERS Approach for Highly Accurate Discrimination of Escherichia coli Pathotypes and Shigella Species

 Highlights

  • •
    XAI–SERS platform enables accurate discrimination of E. coli pathotypes and Shigella.
  • •
    1D-CNN model achieved 97.7% accuracy, surpassing traditional classifiers.
  • •
    SHAP analysis identified key spectral features linked to molecular components.
  • •
    Provides a precise, interpretable approach for bacterial diagnostics.

Abstract

Pathogenic Escherichia coli and Shigella species cause severe diarrheal diseases with high mortality but remain difficult to distinguish using conventional methods due to their close genetic and proteomic relatedness. To address this challenge, we propose an explainable artificial intelligence (XAI) with surface-enhanced Raman spectroscopy (SERS) platform for rapid and accurate identification of E. coli pathotypes and Shigella species. We generated 7819 SERS spectra from 294 strains, including 195 representing five pathotypes of E. coli and 99 of Shigella species. This dataset was analyzed within an XAI framework using deep learning models, including a one-dimensional convolutional neural network (1D-CNN) and a multilayer perceptron, and compared with traditional machine learning classifiers. The 1D-CNN achieved 97.7% accuracy, outperforming conventional classifiers. SHapley Additive exPlanations analysis revealed the specific features and molecular components contributing to classification, providing biochemical interpretability. This study demonstrates the potential of XAI–SERS for precise, explainable identification of E. coli pathotypes and Shigella species.

Read full article for free (open access):
https://www.sciencedirect.com/science/article/pii/S266651742600043X


Popular posts from this blog

Salivary microbiome diversity is associated with oral health and disease

Image
The oral microbiome is a complex community of bacteria, fungi, and viruses that inhabit the oral cavity. Microbes of the oral microbiome are implicated in health and disease. We collected 220 unstimulated saliva samples from patients with periodontal disease and varying degrees of dental caries, as well as from subjects with no signs of oral disease. Metagenomic analysis of saliva revealed significantly higher abundance of periodontal pathogens in people with gum disease, and significantly higher abundance of cariogenic species in people with dental caries. We also found that salivary microbiome diversity was significantly higher in people with periodontal disease, but not in those with only caries. Furthermore, oral microbiome diversity is affected by oral hygiene habits such as flossing frequency, but not brushing frequency. Clustering and differential analysis allowed us to identify specific commensal species, such as  Prevotella pallens and Veillonella atypica , which are signi...
Read more

Pacific has one of most successful years for grants in school history

Image
University of the Pacific secured 62 grants from federal, state and county agencies totaling more than $36 million—one of the best years for government grants in school history. The dramatic increase in fiscal year 2023—double the amount awarded to Pacific in 2022—was largely driven by three of the university’s largest grants, which include $6 million for the School of Health Sciences to  expand the social work program , $5.6 million for Benerd College to  support mental health services in K-12 schools  and $5 million to McGeorge School of Law to  improve mental health services in California . This was the best year for grants at Pacific in 15 years. “This is a reflection of the exceptional work our faculty are doing to address pressing issues,” said David Ojcius, assistant provost for research and scholarship. “These grants will have a significant impact on the community.”   Read full article at: https://www.pacific.edu/pacific-newsroom/pacific-has-on...
Read more