variant effect prediction

CoNVict is an agentic AI system that prioritizes copy number variants in rare disease diagnosis by ranking candidates through structured reasoning, outperforming existing methods in identifying causal variants.

This study uses tensor decomposition to analyze CRISPR-Cas9 knockout screens, distinguishing essential from non-essential genes with performance comparable to JACKS without requiring control samples or logarithmic transformations.

The paper introduces ENGINE, a method to infer gene-environment interactions from large-scale biobank data, finding that combining multiple exposures increases detected GxE variance.

This paper introduces DiffEvol, a constrained diffusion framework to model evolution, and applies it to SARS-CoV-2 data to reconstruct fitness trends and vaccine-induced phase transitions.

This paper introduces an explainable boosting machine model to identify and filter variant artifacts caused by formalin-fixed paraffin embedding in cancer genomics.

The paper identifies stop-loss mutations in cancer genomes, showing enrichment in cancer-related genes and potential immunological consequences.

The paper introduces a method to compute Bayes factors for linear mixed models in genetic association studies using Bayesian regression and demonstrates its equivalence to BLUP predictions.

The paper establishes frequency criteria for secondary findings genes to improve variant classification consistency by setting disease allele frequency thresholds for 58 monogenic disease entities.

This paper introduces MR-UBRA, a Bayesian framework for analyzing genetic heterogeneity in Mendelian randomization, showing it can resolve multi-component structures in causal effect space.

ACENet predicts enzyme pHmin using a graph neural network integrating structural and evolutionary features, achieving high accuracy and stability across conditions.

This paper evaluates neural network-based methods for local ancestry inference in challenging admixture scenarios and finds they perform best with specialized preprocessing.

The paper applies a Sire MGS model to partition genetic variance into paternal and maternal components for lifetime productivity in tropical dairy cattle, finding significant maternal contributions.

Rosalind, a DNA foundation model, predicts variant-gene regulatory relationships without proximity bias, identifying distal genes as more impactful in osteoporosis.

The paper introduces Tν, a metric to quantify directional asymmetry in amino acid substitutions using kernel regression on MSAs, and applies it to human glutamate transporters to identify high-tension sites and pathogenic variants.

This study benchmarks DNA foundation models like Evo2, revealing blind spots in variant-effect prediction and highlighting reliance on sequence regularities over biological constraints.

BICEP extends its Bayesian model to include indels and copy number variants for rare variant prioritization in pedigrees, showing comparable performance to the original single nucleotide variant model.

HAETAE predicts tissue-specific histone modifications with high accuracy using a 5-base framework and long-read sequencing data.

The paper investigates whether genome size, replichore organization, and nucleotide skew predict bacterial growth rates, finding that skew improves predictive accuracy.

The paper identifies functional variants and VNTRs at the 5p15.33 locus using fine-mapping, MPRA, and CRISPRi screens, revealing their role in cancer susceptibility through antagonistic pleiotropy.

The paper develops a framework to train supervised models on MAVE data by accounting for experimental protocol differences, improving variant effect prediction across datasets.

AMR-GNN predicts antimicrobial resistance using a graph neural network framework that integrates multiple genomic representations from whole-genome sequencing data.

The paper develops machine learning models to predict pathogenicity of BRCA1 and BRCA2 variants using cancer genomic profiles, improving classification of variants of uncertain significance.

This paper reviews sparse autoencoders applied to biological foundation models, finding they recover interpretable biological features but lack experimental validation of mechanistic understanding.

The paper introduces Gene Portals, a framework that integrates clinical, functional, and structural data for rare disease variant classification, demonstrating its utility across five gene-specific portals.

The paper identifies rare noncoding variants associated with Parkinson's disease using multi-omic data from over 3.3 million nuclei.

The paper identifies unreliable confidence metrics in AlphaFold2 predictions for fold-switching proteins and introduces a screening method to detect false positives.

EvoStructCLIP predicts missense variant effects by integrating 3D structure and evolutionary data, showing transferability across gene-specific functions and biological tasks.

This study identifies 6mA demethylases as key regulators of virulence in plant-parasitic nematodes and shows their potential as targets for sustainable control.

The paper uses deep-learning models to identify functional motifs in intrinsically disordered proteins by analyzing pathogenic variants from ClinVar.