arXiv:2512.08175v1 Announce Type: new
Abstract: Summary: We present needLR, a structural variant (SV) annotation tool that can be used for filtering and prioritization of candidate pathogenic SVs from long-read sequencing data using population allele frequencies, annotations for genomic context, and gene-phenotype associations. When using population data from 500 presumably healthy individuals to evaluate nine test cases with known pathogenic SVs, needLR assigned allele frequencies to over 97.5% of all detected SVs and reduced the average number of novel genic SVs to 121 per case while retaining all known pathogenic variants. Availability and Implementation: needLR is implemented in bash with dependencies including Truvari v4.2.2, BEDTools v2.31.1, and BCFtools v1.19. Source code, documentation, and pre-computed population allele frequency data are freely available at https://github.com/jgust1/needLR under an MIT license.
CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs
arXiv:2512.12914v1 Announce Type: cross Abstract: Large Language Models (LLMs) are often fine-tuned to adapt their general-purpose knowledge to specific tasks and domains such as cyber