variant effect prediction

AbTune: Layer-wise selective fine-tuning of protein language models for antibodies

AbTune improves protein language model performance for antibody-related tasks through depth-selective fine-tuning, outperforming baselines in structure prediction and mutation effect prediction.

Decoding the regulatory genetic architecture of endometriosis using AlphaGenome

This paper uses AlphaGenome to prioritize endometriosis-associated variants with strong uterus-specific regulatory effects, identifying new candidate genes and refining GWAS loci.

Evaluation of Dorado v5.2.0 de novo basecalling models for the detection of tRNA modifications using RNA004 chemistry

This study evaluates Dorado v5.2.0 basecalling models for detecting tRNA modifications using RNA004 chemistry, finding improved pseudouridine detection but challenges in complex modification environments.

Rare-variant risk scores complement common-variant polygenic scores for disease risk prediction and stratification

This paper develops rare-variant polygenic risk scores (rvPRSs) using whole-genome sequencing data from the UK Biobank, showing they improve disease risk stratification and biological interpretability beyond common-variant PRSs.

Evaluating Long-Range Temporal Structure in Foundation Model-Based Forecasts of Heartbeat Dynamics

This study evaluates how well Time-Series Foundation Models predict heartbeat dynamics and finds they fail to capture long-range temporal dependencies, leading to increasing prediction errors over time.

Inference of fitness landscapes with heterogeneous patterns of epistasis across sites

This paper introduces a framework to infer fitness landscapes with structured epistasis and applies it to protein and RNA mutagenesis data, revealing complex genetic interactions.

Genomic insights into bacterial kidney disease resistance in Arctic charr (Salvelinus alpinus) via a 72k SNP array

This study develops a 72k SNP array to assess BKD resistance in Arctic charr and finds genomic prediction is feasible with moderate accuracy.

Inhibition of RNA splicing is a novel therapeutic strategy for disruption of nuclear replicating viruses

This study shows that inhibiting RNA splicing reduces viral replication in splicing-dependent viruses like adenovirus, HSV-1, and influenza A, suggesting a new antiviral strategy.

Defining Pseudo-Haplotype Analysis Reveals Multi-Gene Genetic Pattern Across BAF Chromatin Remodeling Complexes

This study introduces pseudo-haplotype analysis to characterize multi-variant configurations in BAF chromatin remodeling genes, revealing common and rare variant co-occurrence patterns across populations.

A Generalised Epigenetic Clock Reveals Therapeutic Vulnerabilities Linked to Ageing in Cancer Cells

This paper develops GepiClock, an epigenetic clock for cancer cells, revealing age-related therapeutic vulnerabilities in cancer cell lines.

Acquiring Improved Protein Variants With Probabilistic Preferential Learning

This paper introduces a probabilistic preferential learning model for variant effect prediction, showing that uncertainty-aware strategies improve acquisition performance on single-mutation datasets.

Overexpression of Eaf1, a subunit of the NuA4 lysine acetyltransferase complex, rescues growth defects in the budding yeast H3K36M oncohistone model via histone H4 tail acetylation

This paper shows that overexpressing Eaf1, a NuA4 subunit, rescues growth defects in yeast with H3K36M mutations by acetylating histone H4 tails.

An empirical Bayes framework for burden and dispersion association tests helps prioritize rare variants associated with Alzheimer's disease

The paper introduces parmigiano, an empirical Bayesian framework that improves rare variant association testing in Alzheimer's disease by integrating functional annotations, identifying 23 candidate genes including 19 new ones.

Defining the molecular tolerance-to-damage landscape of SMARCA4 helicase genetic alterations

This study develops a helicase-specific variant effect predictor to classify SMARCA4 variants as damaging or tolerated, improving interpretation of genetic variants of uncertain significance.

Exploring MAPT-containing H1 and H2 haplotypes in Parkinson's disease across diverse populations

The paper investigates the association of MAPT haplotypes H1 and H2 with Parkinson's disease risk across diverse populations using genetic data from multiple cohorts.

Downregulation is the dominant effect of new regulatory mutations in a fungal pathogen

The paper analyzes genome sequencing data of Zymoseptoria tritici to show that new regulatory mutations predominantly cause gene downregulation.

ASMS: finding allele specific methylation in human genomes without phasing

ASMS detects allele-specific methylation without phasing by analyzing methylation data directly, offering a faster approach for studying gene regulation and imprinting.

Polygenic risk scores for incident dementia in the Multi-Ethnic Study of Atherosclerosis

The paper evaluates polygenic risk scores for dementia prediction in diverse populations, finding that a model with fewer SNPs outperforms one with more SNPs in multiple ethnic groups.

predNMD: prediction of nonsense-mediated mRNA decay for improved clinical variant pathogenicity classification

predNMD improves clinical variant pathogenicity classification by predicting nonsense-mediated mRNA decay (NMD) more accurately than the 50nt rule, using a random forest model trained on diverse datasets.

Mapping active cis-regulatory elements from transcription initiation events

The paper introduces nucCAGE and PRIME to identify active cis-regulatory elements with high sensitivity and applies them to create a cell-type-resolved CRE atlas.

Multi-Scale Machine Learning for Antibody-Antigen Binding Affinity Prediction Using Deep Mutational Scanning and Structural Features

This paper develops a multi-scale machine learning framework to predict antibody-antigen binding affinity using deep mutational scanning and structural features, achieving improved performance over single-modality approaches.

Functional Effect Predictions For Ion Channel Missense Variants Using a Protein Language Model

The paper introduces MissION, a protein language model-based classifier for predicting functional effects of ion channel missense variants, achieving higher accuracy than existing models.

nanoASM: Long-Read Allele-Specific DNA Methylation Profiling Enables Functional Annotation of Regulatory Noncoding Variants in Human Prostate Tissues

The paper introduces nanoASM, a method for allele-specific methylation analysis using long-read sequencing, identifying functional noncoding variants in prostate cancer.

NERINE reveals rare variant associations in gene networks across phenotypes and implicates an SNCA-PRL-LRRK2 subnetwork in Parkinson's disease

NERINE tests gene network hypotheses with rare variant associations, identifying a subnetwork linked to Parkinson's disease.

Rare loss-of-function variants in POLD1, PMS1 and FAN1 modify age at onset of motor symptoms in Huntington's disease

Population-Scale, Genotype-First Characterization of Monogenic Diabetes in 374,973 Multi-Ancestry Individuals from the All of Us Research Program

The paper identifies MODY gene variants in a large multi-ancestry cohort, showing incomplete penetrance and comparable diabetes risk between carriers of lower-penetrance variants and high polygenic risk non-carriers.

CACNA2D4 variants are associated with exertional heat stroke susceptibility

The paper identifies CACNA2D4 variants associated with exertional heat stroke susceptibility and shows their impact on calcium signaling in skeletal muscle.

Allostery is a widespread cause of loss-of-function variant pathogenicity

The paper shows allostery is a common cause of loss-of-function variants in human genetic diseases and identifies a distance-dependent decay of mutational effects.

Integrated Clinicogenomic Risk Modeling for Metachronous Second Primary Cancers

The paper develops and validates a clinicogenomic risk model to predict second primary cancers in cancer survivors using genetic, clinical, and lifestyle factors.

A Scalable Framework to Integrate Social Determinants of Health into Disease Risk Models using Biobank Survey Data

This paper introduces a framework to integrate social determinants of health into disease risk models using biobank survey data, showing improved prediction beyond genetic factors.