GOPET: A Tool for Predicting Gene Ontology Terms
Author Information
Author(s): Vinayagam Arunachalam, Val Coral, Schubert Falk, Eils Roland, Glatting Karl-Heinz, Suhai Sándor, König Rainer
Primary Institution: German Cancer Research Center (DKFZ)
Hypothesis
Can an automated system accurately predict Gene Ontology terms for various organisms?
Conclusion
GOPET provides a valuable tool for sequence annotation with reliable confidence values.
Supporting Evidence
- GOPET predicts both molecular function and biological process terms.
- The system was benchmarked with 36,771 GO annotated cDNA sequences.
- GOPET showed better precision compared to GOTcha in a comparison study.
Takeaway
GOPET is like a smart helper that guesses what a gene does based on its sequence, and it tells you how sure it is about its guesses.
Methodology
The system uses Support Vector Machines to classify sequences based on training with known Gene Ontology annotations.
Limitations
The prediction quality for biological process terms is lower compared to molecular function terms.
Statistical Information
P-Value
0.0006
Statistical Significance
p<0.0006
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website