Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

ProToxin, a Predictor of Protein Toxicity

Yang, Yang LU ; Zhang, Haohan and Vihinen, Mauno LU orcid (2025) In Toxins 17(10).
Abstract

Toxins are naturally poisonous small compounds, peptides and proteins that are produced in all three kingdoms of life. Venoms are animal toxins and can contain even hundreds of different compounds. Numerous approaches have been used to detect toxins, including prediction methods. We developed a novel machine learning-based predictor for detecting protein toxins from their sequences. The gradient boosting method was trained on carefully selected training data. Initially, we tested 2614 features, which were reduced to 88 after a comprehensive feature selection procedure. Out of the four tested algorithms, XGBoost was chosen to train the final predictor. Comparison to available predictors indicated that ProToxin showed significant... (More)

Toxins are naturally poisonous small compounds, peptides and proteins that are produced in all three kingdoms of life. Venoms are animal toxins and can contain even hundreds of different compounds. Numerous approaches have been used to detect toxins, including prediction methods. We developed a novel machine learning-based predictor for detecting protein toxins from their sequences. The gradient boosting method was trained on carefully selected training data. Initially, we tested 2614 features, which were reduced to 88 after a comprehensive feature selection procedure. Out of the four tested algorithms, XGBoost was chosen to train the final predictor. Comparison to available predictors indicated that ProToxin showed significant improvement compared to state-of-the-art predictors. On a blind test dataset, the accuracy was 0.906, the Matthews correlation coefficient was 0.796, and the overall performance measure was 0.796. ProToxin is a fast and efficient method and is freely available. It can be used for small and large numbers of sequences.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
artificial intelligence, machine learning, protein toxin, toxin, toxin prediction
in
Toxins
volume
17
issue
10
article number
489
publisher
MDPI AG
external identifiers
  • pmid:41150190
  • scopus:105020069399
ISSN
2072-6651
DOI
10.3390/toxins17100489
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2025 by the authors.
id
7ef3bcd2-7f76-486f-a7eb-07d868184ef0
date added to LUP
2025-12-17 13:55:06
date last changed
2025-12-18 03:00:08
@article{7ef3bcd2-7f76-486f-a7eb-07d868184ef0,
  abstract     = {{<p>Toxins are naturally poisonous small compounds, peptides and proteins that are produced in all three kingdoms of life. Venoms are animal toxins and can contain even hundreds of different compounds. Numerous approaches have been used to detect toxins, including prediction methods. We developed a novel machine learning-based predictor for detecting protein toxins from their sequences. The gradient boosting method was trained on carefully selected training data. Initially, we tested 2614 features, which were reduced to 88 after a comprehensive feature selection procedure. Out of the four tested algorithms, XGBoost was chosen to train the final predictor. Comparison to available predictors indicated that ProToxin showed significant improvement compared to state-of-the-art predictors. On a blind test dataset, the accuracy was 0.906, the Matthews correlation coefficient was 0.796, and the overall performance measure was 0.796. ProToxin is a fast and efficient method and is freely available. It can be used for small and large numbers of sequences.</p>}},
  author       = {{Yang, Yang and Zhang, Haohan and Vihinen, Mauno}},
  issn         = {{2072-6651}},
  keywords     = {{artificial intelligence; machine learning; protein toxin; toxin; toxin prediction}},
  language     = {{eng}},
  number       = {{10}},
  publisher    = {{MDPI AG}},
  series       = {{Toxins}},
  title        = {{ProToxin, a Predictor of Protein Toxicity}},
  url          = {{http://dx.doi.org/10.3390/toxins17100489}},
  doi          = {{10.3390/toxins17100489}},
  volume       = {{17}},
  year         = {{2025}},
}