ECTyper: in silico Escherichia coli serotype and species prediction from raw and assembled whole-genome sequence data
Bibliographic record
Abstract
Escherichia coli is a priority foodborne pathogen of public health concern and phenotypic serotyping provides critical information for surveillance and outbreak detection activities. Public health and food safety laboratories are increasingly adopting whole-genome sequencing (WGS) for characterizing pathogens, but it is imperative to maintain serotype designations in order to minimize disruptions to existing public health workflows. Multiple in silico tools have been developed for predicting serotypes from WGS data, including SRST2, SerotypeFinder and EToKi EBEis, but these tools were not designed with the specific requirements of diagnostic laboratories, which include: speciation, input data flexibility (fasta/fastq), quality control information and easily interpretable results. To address these specific requirements, we developed ECTyper ( https://github.com/phac-nml/ecoli_serotyping ) for performing both speciation within Escherichia and Shigella , and in silico serotype prediction. We compared the serotype prediction performance of each tool on a newly sequenced panel of 185 isolates with confirmed phenotypic serotype information. We found that all tools were highly concordant, with 92–97 % for O-antigens and 98–100 % for H-antigens, and ECTyper having the highest rate of concordance. We extended the benchmarking to a large panel of 6954 publicly available E. coli genomes to assess the performance of the tools on a more diverse dataset. On the public data, there was a considerable drop in concordance, with 75–91 % for O-antigens and 62–90 % for H-antigens, and ECTyper and SerotypeFinder being the most concordant. This study highlights that in silico predictions show high concordance with phenotypic serotyping results, but there are notable differences in tool performance. ECTyper provides highly accurate and sensitive in silico serotype predictions, in addition to speciation, and is designed to be easily incorporated into bioinformatic workflows.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
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".