Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 2, 2025Nature CommunicationsOpen Access

Expanding the utility of variant effect predictions with phenotype-specific models

View Full Paper
Ask AI
Bookmark
Share

Authors

MKMeltem Ece KarsDCD.N. CooperPZPeng Zhang

Discussion

Loading...

Member takes

Overview

Machine learning improves variant pathogenicity predictions in genomic data, suggesting enhanced accuracy in identifying disease variants.

Key Points

  • Initial characteristics reveal how variant effect relates to disease phenotype and genotype.
  • Multi-task approach leverages human phenotype ontology for refined predictions of pathogenic variants.
  • Evaluative comparisons demonstrate the superiority of this model over existing variant predictors across datasets.
  • A complete mapping of genetic variants to disease phenotypes may enhance diagnostic capabilities in genomic medicine.

Cite This Study

Kars et al. (2025) studied this question.

synapsesocial.com/papers/692e3da16c9b3ab28c187bc6https://doi.org/10.1038/s41467-025-66607-w
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. 1ClinVar: improvements to accessing data2019 · 1,117 citations
  2. 2The mutational constraint spectrum quantified from variation in 141,456 humans2020 · 10,435 citations
  3. 3Regional missense constraint improves variant deleteriousness prediction2017 · 404 citations
  4. 4Genic Intolerance to Functional Variation and the Interpretation of Personal Genomes2013 · 1,003 citations
  5. 5Effective gene expression prediction from sequence by integrating long-range interactions2021 · 1,410 citations