Related Experiment Video
Updated: Sep 3, 2025
07:15
Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation
Published on: January 16, 2019
11.1K
X-CAP improves pathogenicity prediction of stopgain variants
Ruchir Rastogi1, Peter D Stenson2, David N Cooper2
1Department of Computer Science, Stanford University, Stanford, USA.
Genome Medicine
|July 29, 2022
Summary
A new tool, X-CAP, improves the prediction of disease-causing stopgain mutations. It shows better accuracy and fewer false positives than existing methods, aiding clinical diagnosis of genetic disorders.
Area of Science:
- Genetics
- Computational Biology
- Bioinformatics
Background:
- Stopgain substitutions are a significant cause of monogenic human diseases.
- Current computational tools for predicting stopgain pathogenicity lack the sensitivity for clinical applications.
Purpose of the Study:
- To develop and validate a novel classifier, X-CAP, for improved prediction of pathogenic stopgain mutations.
- To enhance the accuracy and reduce false positives in identifying disease-causing genetic variants.
Main Methods:
- Developed X-CAP using a novel training methodology and a unique feature set.
- Evaluated X-CAP's performance on large variant databases and in patient exomes.
- Compared X-CAP against existing computational pathogenicity predictors.
Main Results:
- X-CAP demonstrated an 18% improvement in AUROC (Area Under the Receiver Operating Characteristic curve).
- The false-positive rate was reduced 4-fold compared to existing methods.
- X-CAP showed superior prioritization of causal stopgains in patient exome data.
Conclusions:
- X-CAP offers improved clinical utility for identifying pathogenic stopgain mutations.
- The enhanced performance of X-CAP aids in the diagnosis of genetic diseases.
- X-CAP is publicly available for research and clinical use.
