variant effect prediction

The paper evaluates genomic methods to detect outbreaks of a vancomycin-resistant Enterococcus faecium lineage, finding that lower allelic thresholds improve outbreak detection.

SARDINE uses EWAS summary statistics to estimate epigenetic clock-phenotype associations without individual-level data, revealing heterogeneity in biomarker associations with aging and diseases.

This paper introduces MirrorDNA, a DNA language model with a strand-equivariant tokenizer that improves prediction consistency across DNA strands.

memVar links human membrane protein variants to molecular contexts and disease, revealing enrichment of pathogenic variants in transmembrane regions and interaction sites.

The paper evaluates how small reference sample sizes affect substructure estimation and proposes bias corrections for improved accuracy.

This study identifies genetic polymorphisms in NKG2C, CD16a, and HLA-E that influence NKG2C expression and ADCC capacity in HCMV-infected individuals.

The paper shows that neural RNA splicing models rely on reading frame information that the splicing machinery cannot access, leading to errors in predicting poison exons.

This paper adapts ACMG/AMP variant classification criteria for the non-protein-coding gene RMRP, resulting in a framework for classifying variants in cartilage-hair hypoplasia.

This paper improves variant-effect prediction in sequence-to-function models using synthetic MPRA data generated from distilled model predictions.

The paper introduces eQIF, an unsupervised machine-learning method that integrates Enformer predictions to prioritize gene-regulatory variants, showing strong performance in predicting eQTLs and GWAS variants.

This study uses deep learning to predict cis-regulatory effects of human-specific mutations across 305 tissues, revealing their role in gene expression evolution.

SHADES, a deep learning framework, distinguishes evolutionary processes like neutrality, selection, and introgression using haplotype data from humans, outperforming existing methods.

The paper develops deep learning models to predict transcription initiation patterns from DNA sequences across human tissues and cancers.

Scooby-2 fine-tunes AlphaGenome to predict single-cell genomic tracks, improving correlation and variant effect prediction compared to Scooby and AlphaGenome.

The paper introduces Bvalcalc, a tool to calculate B-values, which quantify the effect of background selection on genetic diversity, and validates it using simulations and public data.

CODMA-A3 is a high-throughput assay for screening APOBEC3 variants, detecting substrate competition and activity changes without protein purification.

The paper develops a cell-free system using Xenopus egg extracts to study TMEJ, showing that Pol theta and Cyclin B-CDK1 are essential for efficient DNA joining.

OddCAPS improves dCAPS by using three primers in one PCR reaction to detect SNVs with more engineered base changes and flexibility in restriction enzyme selection.

The paper introduces MEMAR, a Maximum Entropy model for predicting m6A methylation in human transcripts and influenza A viral segments, showing improved performance over existing methods.

The paper analyzes parasite genotypes in sympatric mosquito species to show divergent selection on Plasmodium falciparum mediated by different vectors.

Sorting S-phase cells by Cyclin A2 rather than DNA content exposes a uniform genome-wide delay after CDC7 inhibition and a broad replication timing advance in RIF1 knockout.

This study identifies miR-29 as a key regulator of age-related epigenetic changes, showing it promotes fidelity but reduces plasticity in methylome maintenance and adaptation.

EG-BINN improves epigenetic age estimation by combining parameter-efficient ensembling of biologically informed neural networks with sample-specific gating, achieving lower error rates than existing methods.

The paper identifies a specific mutation pattern in mismatch-repair-deficient cancers linked to DNA hole delocalization and oxidation, showing enrichment at 5' guanines and depletion at 3' guanines.

The paper assesses genetic structure and inbreeding in Andrena flavipes bees using SNPs, finding isolation-by-distance and high inbreeding despite high genetic variation.

The paper develops a high-throughput minigene assay to identify pseudoexon-activating variants in the NF1 gene and benchmarks splicing prediction tools.

Bolero predicts cell-state-specific gene regulation from DNA across species by integrating cell-state embeddings and biological variables.

This study identifies NEIL2 as a regulator of RNA polymerase II dynamics that suppresses transcription replication conflicts in pancreatic cancer cells.

The paper analyzes single nucleotide substitutions in the CYP21A2 gene using AlphaGenome to connect clinical annotations, population data, splicing predictions, and enzyme function.

DNA-LLM2Vec adapts decoder DNA models to bidirectional context for genomic tasks, improving performance on extended-context tasks but varying by task and backbone.