variant effect prediction

This study identifies metabolic factors associated with disease activity and complications in Crohn's disease using regression analysis and predictive models.

This paper estimates the global prevalence of GSD IV and APBD by analyzing GBE1 variants across nine genetic groups, finding 1 in 235,784 individuals are affected.

This paper introduces GenoJEPA, a genomic representation learning framework that improves efficiency and performance in downstream tasks by focusing on semantic alignment rather than nucleotide-level reconstruction.

The paper identifies mutation-specific impairments in TET2 and DNMT3A enzymatic activity as predictors of clonal hematopoiesis disease risk using methylation-based activity scores.

Berrylyzer is a variant prioritization system for prenatal genetic diagnosis that outperforms existing tools in ranking diagnostic variants and recall rates.

This study uses genetic analysis of skeletal remains from Columbus' descendants to provide indirect evidence about his origins and place of birth.

OncoMORPHIA provides an interactive web platform for visualizing and annotating cancer mutations using 3D structures and clinical data from multiple sources.

OncoVI is a Python-based tool that automates oncogenicity classification of somatic variants using guidelines, achieving 80% accuracy on test data and 79% agreement with expert assessments.

This study develops a model to predict optimal growth temperature in prokaryotes using genomic data, finding that incorporating gene presence/absence improves accuracy for psychrophiles.

This paper improves genomic prediction accuracy for maize flowering-time traits using an ensemble approach, revealing novel insights into trait genetic variation.

The paper validates variant effect predictions in a Brachypodium distachyon mutant population using burden and purging tests, showing ESM outperforms SIFT and PlantCAD for missense variants.

The paper identifies exonic enhancers as dual-function regulatory elements that influence gene expression and are associated with disease and evolution.

This study identifies stable QTL for adaxial stomatal anatomy under drought and heat in wheat, offering targets for improving climate resilience.

The paper examines GT>GC 5' splice-site variants, showing they can retain wild-type transcript and challenge variant classification.

This study identifies a SNP in CaPAT1 that enables full-length GRAS domain formation, enhancing shoot regeneration in pepper through dimerization and overexpression.

This study benchmarks somatic mutation detection using the human pangenome reference and finds improved accuracy, especially in East Asian individuals.

The paper integrates AMGs and phage assembly into a genome-scale metabolic model to predict their impact on host metabolism and phage production, revealing synergistic and antagonistic effects.

BioWorldModel predicts phenotype from genotype across four kingdoms by modeling biological processes, achieving higher accuracy than traditional methods.

This study uses genomic prediction to select resilient sessile oak genotypes based on foliar physiological traits, showing high heritability and across-provenance predictability.

This paper introduces a Bayesian marker-based principal component ridge regression framework for estimating quantitative genetic parameters in wild study systems, showing efficient estimation of additive genetic variance and accurate breeding value prediction.

SILO improves detection of disease susceptible variants in short IBD segments, outperforming existing models in simulated and real data.

This paper introduces GroupSig, a framework to overcome sparsity in clinical targeted-panel sequencing data, identifying inherited determinants of mutational signatures in cancer.

This paper improves variant effect predictors by calibrating them gene- and domain-aware, increasing evidence assignment and accuracy for variant classification.

The paper introduces BlueSTARR, a predictive modeling framework trained on whole-genome STARR-seq data to assess variant effects on regulatory functions, revealing purifying selection against loss-of-function and gain-of-function variants.

The paper identifies biallelic variants in RNU2-2 as a common cause of recessive neurodevelopmental disorders, showing higher prevalence than the dominant form in England.

The paper introduces methbiome, a tool for reference-based DNA methylation profiling of long-read metagenomic data, enabling cross-platform and between-sample comparison of methylation signals in microbiomes.

The paper shows that humanized Traf6 promoter sequences in mice affect immune responses but not fertility, revealing distinct roles for germ and immune cells in gene regulatory evolution.

This paper introduces StructureDCA, a method that improves mutational landscape predictions by integrating structural information into direct coupling analysis.

The paper uses a convolutional neural network to predict chromatin organization disruptions caused by somatic structural variants in pediatric tumors, identifying high-impact SVs and regions associated with cancer.

This study evaluates bulk ATAC-seq's ability to detect genomic variants, CNVs, and telomere repeats, showing its potential as an integrative tool for cancer research.