# Non-Targeted Screening Method for Detecting Temporal Shifts in Spectral Patterns of Methicillin-Resistant Staphylococcus aureus and Post Hoc Description of Peak Features

## TL;DR

This paper introduces a new method to detect changes in bacterial mass spectrometry patterns over time, improving resistance detection accuracy.

## Contribution

A novel screening method combining CNNs and statistical techniques to detect temporal shifts in MALDI-TOF MS data for bacterial resistance.

## Key findings

- The method successfully detects temporal shifts in spectral patterns of MRSA and MSSA isolates.
- Grad-CAM provides biochemical insights into peak features associated with resistance mechanisms.
- The approach improves robustness of non-targeted methods for bacterial resistance detection.

## Abstract

Non-targeted methods (NTMs) using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) show promise in bacterial resistance detection, yet temporal variations in spectral features pose significant challenges. These proteomic patterns, which characterize bacterial phenotypes and pathological functions, may vary over time due to bacterial adaptation, virulence, or resistance mechanisms, resulting in large prediction uncertainties and potentially degrading NTM performance. We present a comprehensive screening method to detect temporal changes in MALDI-TOF spectral patterns, demonstrated using methicillin-resistant and -susceptible Staphylococcus aureus (MRSA/MSSA) isolates collected over several years. Our approach combines convolutional neural networks (CNNs) with statistical methods, including significance testing, kernel density estimation, and receiver operating characteristics for dataset shift detection. We employ Gradient-weighted Class Activation Mapping (Grad-CAM) for post hoc feature description, enabling biochemical characterization of temporal changes. This analysis reveals crucial insights into the dynamic relationship between spectral data patterns over time, addressing key challenges in developing robust NTMs for routine applications.