Researchgradient boostingprotein variantssequence deletionsvariants of uncertain significance
PON-Del Predicts Sequence-Retaining Protein Deletions Accurately
8.3
Zhang, Kabir and Vihinen publish PON-Del (Feb 25, 2026), a gradient boosting–based predictor for 1–10 amino acid sequence-retaining protein deletions. Trained on an extensive verified dataset, PON-Del is the first deletion tool to include three-state outputs (pathogenic, benign, variants of uncertain significance) and outperforms prior methods; code and data are publicly available.
Key Points
- 1Develops PON-Del using gradient boosting trained on verified 1–10 amino acid sequence-retaining deletions dataset
- 2Addresses prior tool limitations by including variants of uncertain significance and improving classification performance
- 3Enables three-state predictions (pathogenic, benign, VUS) and provides code and dataset for reproducible use
Scoring Rationale
Peer-reviewed new tool with reproducible data and VUS support, but algorithmic novelty is limited compared to deep-learning approaches.
Sources
Public references used for this report.
Practice with real Ad Tech data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
Active Search Campaigns by BudgetEasyHigh CPC Clicks & Poor Landing PagesMediumCampaign ROAS by Attribution ModelHard
250 free problems · No credit card
See all Ad Tech problems