ARGOT: A Tool for Predicting Gene Function Using Semantic Similarities
Author Information
Author(s): Fontana Paolo, Cestaro Alessandro, Velasco Riccardo, Formentin Elide, Toppo Stefano
Primary Institution: FEM-IASMA Research Center, San Michele all'Adige (TN), Italy
Hypothesis
Can a novel method using semantic similarities and a weighting scheme improve the prediction of gene functions from large-scale sequencing projects?
Conclusion
The ARGOT tool outperforms existing methods for predicting gene functions, demonstrating high sensitivity, specificity, and coverage.
Supporting Evidence
- ARGOT was tested on 10,000 protein sequences and outperformed existing tools.
- The tool has been used to annotate over 29,000 predicted gene sequences from a grapevine sequencing project.
- Manual validation confirmed the high quality of functional inferences made by ARGOT.
Takeaway
ARGOT is a computer program that helps scientists figure out what genes do by comparing them to known genes and using smart math to make sense of the data.
Methodology
ARGOT processes sequences using a combination of clustering GO terms based on semantic similarities and a weighting scheme derived from BLAST results.
Potential Biases
Potential for high false positive rates due to reliance on sequence similarity searches.
Limitations
The method relies on the quality of existing annotations and may propagate errors from the underlying databases.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website