Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 1, 2025Briefings in BioinformaticsOpen Access

Precision in prediction: tailoring machine learning models for breast cancer missense variants pathogenicity prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

RARahaf M. AhmadNANoura Al-DhaheriMMMohd Saberi Mohamad

Discussion

Loading...

Member takes

Overview

This research demonstrates enhanced pathogenicity prediction in breast cancer genetic variants using machine learning models, suggesting clinical applications for precision medicine.

Key Points

  • The aim is to improve prediction accuracy of breast cancer missense variants' pathogenicity through tailored machine learning models.
  • Trained and benchmarked nine machine learning models on a breast cancer gene-specific dataset.
  • Utilized features like conservation scores, functional annotations, and allele frequency.
  • Applied interpretability techniques to elucidate key predictors and ensure transparency.
  • Extra Trees model achieved an accuracy of 99.9% and 95% confidence interval.
  • On the independent ClinGen dataset, it reached 99.1% accuracy, outperforming general predictors.
  • Recursive feature elimination identified the most informative genomic features.

Cite This Study

Ahmad et al. (2025) studied this question.

synapsesocial.com/papers/69254f7dc0ce034ddc35912chttps://doi.org/10.1093/bib/bbaf611
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- and gene-specific deep learning for pathogenicity prediction of rare missense variants in cancer predisposition genes2026
  2. 2Transforming Breast Cancer Prediction: Advanced Machine Learning Models for Accurate Prediction and Personalized Care2025
  3. 3PathoPredictor: A Machine Learning Framework for Predicting Pathogenic Missense Variants in the Human Genome2026 · 1 citations
  4. 4Real-world evaluation of deep learning algorithms to classify functional pathogenic germline variants2024 · 1 citations
  5. 5A HYBRID EXPLAINABLE MULTI-OMICS MACHINE LEARNING FRAMEWORK FOR BREAST CANCER MUTATION PREDICTION AND CLINICAL RISK STRATIFICATION USING TCGA-BRCA DATA2026