variant effect prediction

2C-RT Quantifies Genome-Wide DNA Replication Perturbations and Redefines RIF1-CDC7 Regulation of Replication Timing

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.

MetaDome 2027: a comprehensively updated resource for aggregating missense variant evidence across homologous human protein domains

MetaDome now supports GRCh38 alongside GRCh37, adds coordinate lookup, and identifies 52,463 GRCh38 ClinVar missense variants of uncertain significance with uncontradicted pathogenic evidence at homologous Pfam-domain positions.

Learning Dynamic Protein Representations at Scale with Distograms

Adding Boltz2 distogram edges and features to protein and RNA graph networks beats MD-correlation graphs on binding tasks and improves stability, interaction and RNA predictions without simulation.

Human-specific CCG-repeat insertion in the RBFOX1 promoter implicated in autism and speech enhances EGR1-responsive activity

A human-specific CCG insertion in the RBFOX1 promoter boosts EGR1-driven reporter activity in HEK293T cells, as does an autism-linked CCG-gaining duplication in PTCHD1.

BOTANIC-1: a series of long-context plant genomic foundation models in the agentic era

Bidirectional Mamba2 plant genomic language models (318M to 3.2B parameters) trained on 320 land-plant genomes top a 22-task frozen-model aggregate; a small variant reaches 131,072 bp context.

The Genomic Landscape of Post-Black Death Epidemics in Northern Europe and the Caucasus

Twenty-three new Yersinia pestis genomes from Scandinavia, the Netherlands, Iceland and Armenia extend the Second Plague Pandemic phylogeny, with the first Icelandic plague genome and eastward-spreading pestis secunda strains.

A multi-tissue epigenomic atlas links the sheep non-coding genome to domestication and complex traits

SheepEpimap combines 516 histone CUT&Tag, ATAC-seq and RNA-seq datasets from 43 sheep tissues to annotate 2.93 million cis-regulatory elements and 145,407 allele-specific variants for trait interpretation.

Spanning-Tree Thermostatistics of Protein Allostery: An Exact Kirchhoff Framework with Application to Oncogenic KRAS

Kirchhoff matrix-tree evaluation of residue-contact spanning-tree ensembles yields exact allosteric thermodynamics; KRAS G12D conserves global and channel heat capacity but reroutes paths via Q61 and F156.

AlphaVaR: an R framework for the statistical interpretation of AlphaGenome variant-effect predictions

AlphaVaR structures AlphaGenome's per-track variant scores in R and adds multiple-testing-corrected enrichment and shift tests, a tissue-specificity index and transparent ranking; on rs1427407 it recovers BCL11A erythroid-enhancer biology.

mV2G: a multiomic atlas for tissue-specific variant-to-gene prioritization

A web atlas counts evidence from 24 types for 188,634,118 variant-gene pairs across 50 human tissues; 1,530,420 pairs pass a high-confidence cutoff, 87% of them tissue-specific.

FrustrAI-Seq: Scaling Local Energetic Frustration to the Protein Sequence Space

A fine-tuned ProtT5 protein language model predicts per-residue energetic frustration from sequence (Pearson r 0.86 on unseen CATH topologies) and profiles the human proteome in ~17 minutes on one GPU.

GFMBench-API: A Standardized Interface for Benchmarking Genomic Foundation Models

Wrap a genomic foundation model's inference methods once to score it on supervised and zero-shot GUE, VariantBenchmarks, BEND, TraitGym and ClinVar tasks; code is promised upon acceptance.

FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications

FLIP2 adds seven protein fitness datasets and 16 splits for enzymes, light-sensitive proteins, and interactions; simple ridge and zero-shot baselines often rival fine-tuned protein language models.

Functional pocketomes and complete allosteric maps of five protein kinases

Energy-model maps of five human kinases show conserved distance-dependent decay of inhibitory allostery, but distal allosteric pockets and activating sites diverge between kinases.

Evo 2's Perception of Single Nucleotide Substitutions in the Genes of Two Plant Model Organisms

Evo 2 7B assigns higher perplexity to plant gene alleles carrying randomly simulated single-nucleotide substitutions than to those observed in vivo, in Arabidopsis and rice; significant but small effect.

Machine learning-based prediction of human structural variation and characterization of associated sequence determinants

A sequence-only convolutional neural network and an annotation-based random forest predict human structural variant breakpoints from 400 bp windows (AUROC 0.903, 0.904); their ensemble reaches 0.916.

Genotype-Based Severity Scoring System in Wolfram Syndrome: Correlation with Onset of Cardinal Symptoms and WFS1 Gene Variant Types

Higher WFS1 genotype scores (variant frame, transmembrane location) tracked earlier diabetes mellitus and optic atrophy onset in 324 Wolfram patients, not hearing loss or diabetes insipidus.

ARSENAL: Learning Transferable Regulatory DNA Representations with Targeted Short-Context Language Models

A 350 bp masked DNA language model trained on ENCODE cCREs with a frequency-domain regularizer recovers TF motifs zero-shot, scores regulatory variants, improves ChromBPNet inputs, and guides sequence design.

Interpretable variant effect prediction from genomic foundation model embeddings

A low-rank covariance probe on Evo 2 embeddings predicts ClinVar pathogenicity across SNVs and indels, while annotation probes plus an LLM produce mechanistic hypotheses; scores released for 4.2 million variants.

Humans homozygous for rare or common hypomorphic IL23R variants are prone to tuberculosis

Homozygosity for hypomorphic IL23R variants (G149R, G300V, R381Q) partly impairs IL-23-dependent IFN-γ production in patient cells; with L372F (effect inferred), they are enriched in tuberculosis, not MSMD or CMC patients.

An integrated, scaled approach to resolve TSC2 variants of uncertain significance

Abundance scores for 8,891 TSC2 missense variants, plus mTOR pathway activity scores for 391, were calibrated to ACMG/AMP evidence. They putatively reclassify 212 of 276 clinical-cohort missense VUS.

Integrating 730,947 exome sequences with clinical literature improves gene discovery

gnomAD v4 (730,947 exomes) brings LOFTEE-2 loss-of-function annotation (0.90 precision, strict mode), missense-aware constraint, and LLM-mined literature evidence combined with constraint to rank disease genes.

Whole-genome prediction of bacterial pathogenic capacity on novel bacteria using protein language models, with PathogenFinder2

A ProtT5-embedding, ConvNext-plus-attention ensemble predicts human pathogenic capacity from whole bacterial genomes, outperforming prior predictors on species absent from training and flagging influential proteins.

High-efficiency, transgene-free plant genome editing by viral delivery of an engineered TnpB

Tobacco rattle virus delivery of engineered ISDra2 variant eTnpBc and its guide RNA as a single transcript achieves up to 90% somatic and 100% heritable editing in Nicotiana benthamiana.

Automating the Clinical Interpretation of LDLR, APOB, and PCSK9 Variants: A Web-Based Platform for FH Diagnosis

A Shiny web platform pulls together gnomAD frequencies, UK Biobank LDL-C associations, AlphaMissense, LDLR deep mutational scanning and ClinVar/HGMD to draft ACMG/AMP evidence for familial hypercholesterolemia variants.

Computational design of conformation-biasing mutations to alter protein functions

Contrastive scoring of protein variants across alternative backbone structures with inverse folding models (Conformational Biasing) predicts mutations that shift conformational equilibria and tune effector binding, catalysis, and labeling specificity.

Medium-sized protein language models perform well at transfer learning on realistic datasets

Medium-sized protein language models (e.g. ESM C 600M) with mean embeddings nearly match ESM-2 15B and ESM C 6B in transfer learning on mutational scanning and PISCES data.

Antigenic and Virological Characteristics of SARS-CoV-2 Variant BA.3.2, XFG, and NB.1.8.1

SARS-CoV-2 variant BA.3.2 strongly evades neutralizing antibodies but exhibits low infectivity due to a closed spike conformation, whereas NB.1.8.1 combines high ACE2 affinity with humoral immune escape.

Inference and visualization of complex genotype-phenotype maps with gpmap-tools

gpmap-tools uses Gaussian processes to infer and visualize genotype-phenotype maps with higher-order epistasis; across 262,144 Shine-Dalgarno variants it reveals register-specific peaks linked by three-nucleotide-offset ridges.

Genome modeling and design across all domains of life with Evo 2

A 40B-parameter DNA model trained on 9.3 trillion tokens scores coding and noncoding variants zero-shot, exposes interpretable sequence features, and writes chromosome-scale sequences.