Pathogenicity Predictor for Ion Channel Mutations (PPICM)

Description of This Tool

The Bilbao Computational Biophysics (BCB) group has developed this tool to facilitate the analysis of the pathogenicity of gene variants. By utilizing advanced computational methods, the tool evaluates and predicts the potential effects of gene variants based on user-provided data. Follow these simple steps to use the tool:

  1. Select a Gene: Pick from the dropdown.
  2. Optionally download all the variants: Click to download a file with every variant prediction.
  3. Input Method: Choose how to enter data.
  4. Enter Data: Provide variant details.
  5. Predict: Click to analyze.

Our predictive analysis is grounded in the latest research and aims to provide insightful results that aid in understanding the implications of genetic variations.



Disclaimer: This application is intended solely as a supplementary tool for predicting gene mutation pathogenicity and should not be used as a diagnostic device. Its outputs are informational and require interpretation and confirmation by qualified healthcare professionals. Users are advised that the application does not replace comprehensive medical evaluation, including clinical assessments and laboratory testing. All application findings should be corroborated with professional medical advice and up-to-date clinical data. The developers and distributors of this application disclaim any liability for reliance on the application's outputs. Use of this application implies acceptance of these terms.

About the Method

Our project employs a streamlined approach for predicting gene mutation pathogenicity in potassium ion channels. Initially, essential data is aggregated from renowned databases such as ClinVar and gnomAD, followed by meticulous curation. Subsequently, significant features, including those obtained through Molecular Dynamics simulations and AlphaFold, are extracted and analyzed. These features, encompassing crucial molecular aspects, inform a Machine Learning model, which subsequently predicts mutation pathogenicity, assigning a quantitative certainty value to elucidate the likelihood of each mutation’s pathogenic outcome.

Citations

If you use this tool in your research, please cite the following papers:

  1. Alba Saez-Matia, et al. (2024). MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants . International Journal of Molecular Sciences, 2024, 25(5), 2910, https://www.mdpi.com/1422-0067/25/5/2910

Contact us

Would you like to complement your experiments with simulations and need some help? Do you have data that needs postprocessing?

Write us: contact@bcb.eus

Funded By

DIPC EHU/UPV Biofisika Institutua