Serotyping <i>Salmonella</i> Enteritidis and Typhimurium Using Whole Cell Matrix Assisted Laser Desorption Ionization – Time of Flight Mass Spectrometry (MALDI-TOF MS) through Multivariate Analysis and Artificial Intelligence
Bibliographic record
Abstract
Abstract Salmonella is one of the most frequent food-borne zoonoses, while Salmonella Typhimurium and Enteritidis are the major serovars of concern in public health. 113 Salmonella strains including 38 S . Enteritidis (SE), 38 S . Typhimurium (ST) and 37 strains of 32 other Salmonella serovars (SG) were tested in quadruplicate by whole-cell MALDI-TOF MS. Ions were studied and aligned from the raw data of mzXML files using Mass-Up ( http://www.sing-group.org/mass-up ), resulting in 1,741 aligned peaks. Datasets of ions (presence/absence) selected using a home-developed criteria on their specificity and detectability were subjected to multivariate analyses and artificial intelligence tools. Principle Component Analysis based on 88 selected ions separated SE, ST and SG without overlap on the first three principle components. The network and forest based deep learning tools were more sophisticated than the decision tree-based models. Neural Network carried out consistently well in training model, but no advantage was gained over the other models in validation results. HP (high performance) Neural, Support Vector Machine, HP Forest and Gradient Boasting were able to identify SE, ST and SG up to 100% correctly in both training and validation when 88 selected ions were used in analysis. Among them, HP Neural seemed to perform slightly better and relatively stable. Selection of serovar specific ions helps develop serotyping by increasing signal to noise. MALDI-TOF MS used with appropriate data processing strategies and classification tools could be applied to quickly alert when Salmonella serotypes of concern are suspected among routinely processed samples.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".