The abstract is read at the publisher; the summary is JClub's.
CADD-SV v2.0 delivers a unified Random Forest framework that scores deleteriousness of deletions, insertions, duplications, and inversions using both coordinates and flanking sequence context.
- Why it matters: Structural variant interpretation is difficult because functional impact is hard to infer from genome structure alone, limiting prioritization for disease and evolutionary studies.
- What they did: The method trains on expanded proxy-neutral and proxy-deleterious variants from human and non-human primate genomes, adds updated constraint, regulatory, and chromatin architecture annotations, and incorporates SegmentNT-derived nucleotide-resolution sequence signals.
- The result: CADD-SV v2.0 outperforms its prior version and other tools for prioritizing deleterious SVs across major SV types, including some previously unsupported, while improving genome-wide computational workflow and predictive power.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.