variant effect prediction

ProteoCast predicts the functional impact of missense variants using evolutionary information, achieving high accuracy across the Drosophila proteome.

MuSIC predicts cross-species RBP-RNA interactions using evolutionary conservation and label smoothing, outperforming existing methods and quantifying variant effects on binding.

This study identifies a single amino acid mutation in norovirus NS4 that rescues replication defects of a specialist virus, enabling it to spread more efficiently in vitro.

The paper uses a modified MPRA to assess CYP3A4 enhancer variants with their native promoter, identifying variants with significant regulatory impact on drug response and cancer severity.

This study evaluates compressed sensing in TOF-MRA at 3T and 7T, finding significant differences in CNR and vessel diameter measurements across CS factors.

This paper computationally designs a PAM-relaxed SaCas9 variant, KRH, with expanded targeting capability and enhanced editing efficiency.

This study shows genetic compensation in ACTB mutants occurs via SRF/MRTF-A transcriptional feedback, independent of mutant mRNA expression or degradation.

This paper introduces SCEG-HiC, a machine learning method that predicts enhancer-gene links using single-cell multi-omics data and Hi-C prior knowledge, showing improved performance over existing models.

The paper identifies CAD risk variants that alter VSMC gene programs via ox-LDL-induced enhancer remodelling using multi-omics approaches.

CD8scape predicts viral escape from CD8+ T cell response using HLA genotype and within-host sequence variation to identify immune escape potential.

This paper introduces fluProfiler, a framework using viral sequences to predict antigenic relationships and improve vaccine strain selection by reducing reliance on time-consuming HI assays.

The paper identifies Kacme as a histone modification marking accessible chromatin that resists compaction, particularly at regulatory regions and insulator elements.

The paper develops a structure-informed Siamese GNN to classify CirA missense variants affecting cefiderocol susceptibility using synthetic data.

EXaCT-2 is a whole exome sequencing platform that detects various cancer-related genomic features with high accuracy and sensitivity, outperforming standard assays in detecting sub-clonal mutations and molecular metrics.

The paper introduces UKBioBERT, a DNA language model pre-trained on UK BioBank variants, which improves gene expression prediction and enables eQTL identification when combined with sequence-to-function models.

The paper uses AlphaFold3 to predict GLI-SUFU complex structures, identifies binding-defective SUFU variants from patients, and validates their functional impact.

The paper develops embeRNA, a method to predict microbial functions from 16S rRNA sequences without reference databases, showing better performance in novel environments.

CCAFE estimates case and control allele frequencies from GWAS summary statistics using odds ratios and sample sizes, improving reusability of genetic data.

The paper predicts phage receptor specificity from genome data using large-scale genetic screens and machine learning, achieving high accuracy for E. coli phages.

This paper introduces REVi-SCOPE, a platform that rapidly characterizes cardiac variants' functional impact, enabling precision cardiology by analyzing VUSs in 10 days.

EasyCAPS is a web tool that integrates dCAPS primer design with CRISPR-Cas9 strategies to improve genotyping and gene editing efficiency.

This study calibrates in-frame indel variant effect predictors for clinical classification, showing they reach multiple evidence levels but perform worse than missense predictors.

The paper identifies a functional SNV in Versican associated with Cerebral Small Vessel Disease using MPRA and validates its effect on transcriptional activity.

The paper evaluates individual-level performance of polygenic risk scores (PRSs) using a benchmark cohort of early-onset coronary artery disease patients, showing variability in PRS accuracy and highlighting the need for individual-level validation.

The paper identifies prognostic genomic interactions (PGIs) across multiple cancer types by analyzing pairwise genomic alterations and their association with patient outcomes.

The paper investigates how partial disruption of lactate metabolism, specifically through LDHB loss, synergizes with ALS genetic risk factors to accelerate motor decline.

NAViFluX is a web-based platform for analyzing and designing genome-scale metabolic networks, enabling interactive visualization, refinement, and flux analysis of metabolic models.

UK BioCoin enables trait-specific covariate adjustment for UK Biobank summary statistics without individual-level data, achieving high correlation with full GWAS results.

The paper identifies cis-acting genetic variants affecting enhancer function in Parkinson's Disease using multi-omics data and develops models to predict their regulatory impact.

The paper develops a predictive framework to optimize metabolic pathways in yeast by leveraging chromosomal position effects.