Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 15, 2025BioengineeringOpen Access

Disease-Specific Prediction of Missense Variant Pathogenicity with DNA Language Models and Graph Neural Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

MGMohamed GhadieSSSameer SardaarYTYannis Trakadis

Discussion

Loading...

Member takes

Overview

Machine learning models predict missense variant pathogenicity in specific diseases, highlighting precision medicine potential.

Key Points

  • The model predicts disease-specific pathogenicity with an accuracy of 85.6%, offering insights for clinical applications.
  • Using a comprehensive knowledge graph of biomedical entities enhances the classification of missense variants.
  • A two-stage architecture integrates bioBERT embeddings and graph convolutional networks to analyze variant-disease relationships.
  • These advancements may improve the identification of clinically significant variants, addressing the challenge of variants of uncertain significance.

Cite This Study

Ghadie et al. (2025) studied this question.

synapsesocial.com/papers/68efbd16d61273c8652d8289https://doi.org/10.3390/bioengineering12101098
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Disease-specific variant pathogenicity prediction using multimodal biomedical language models2025
  2. 2Disease- and gene-specific deep learning for pathogenicity prediction of rare missense variants in cancer predisposition genes2026
  3. 3Enhancing missense variant pathogenicity prediction with protein language models using VariPred2024 · 25 citations
  4. 4PathoPredictor: A Machine Learning Framework for Predicting Pathogenic Missense Variants in the Human Genome2026 · 1 citations
  5. 5Precision in prediction: tailoring machine learning models for breast cancer missense variants pathogenicity prediction2025