variant effect prediction

MELD: Mutation Effect Learning through Differential embeddings

MELD predicts SNV functional effects by directly training on wild-type versus mutant differences, outperforming post-hoc in-silico mutagenesis methods with fewer parameters.

Learning Strand-Equivariant Tokenizations of DNA with MirrorDNA

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

Structural Variant Aware Identity-by-Descent Detection on Pangenome Graphs

GIBD detects IBD segments in pangenome graphs and annotates them with structural variants, outperforming existing methods in accuracy and speed.

A protein language model for domain, functional site, and variant effect prediction

PALM, a protein language model, predicts domain, functional site, and variant effects with high accuracy using curated sequence data and outperforms existing models in multiple benchmarks.

Decoding Cell-type Specific Gene Regulation with CellReg3D by Integrating DNA Large Language Models and 3D Genome Structure

CellReg3D integrates DNA language models and 3D genome structure to model cell-type-specific gene regulation, achieving state-of-the-art performance in predicting epigenetic marks and gene expression.

MicrobeRT: A Framework and Suite of Fine-tuned Language Models for Genomic Sequences

MicrobeRT is a framework of fine-tuned language models for metagenomic analysis, achieving strong performance in taxonomic classification, antibiotic resistance detection, and pathogenicity assessment.

SeverYX: An ensemble framework for robust variant severity classification

SeverYX is an ensemble framework that classifies genetic variants into severity tiers, achieving high concordance with ClinVar and improving predictive accuracy through threshold optimization and additional predictors.

Perturbation-induced gene programs map the hidden regulatory architecture of complex diseases

This paper introduces Perturbscape, a framework that uses perturbation-induced gene programs to identify disease-relevant genes and pathways, showing higher heritability informativeness than steady-state approaches.

Neural RNA splicing models rely on reading frame information unavailable to the splicing machinery

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.

CNVision: a computational framework for functional interpretation of intragenic copy number variants

CNVision is a computational framework that automates the interpretation of intragenic copy number variants by standardizing input parsing, transcript mapping, and reading-frame classification.

Synthetic MPRA perturbation supervision improves variant-effect prediction in sequence-to-function models

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

Intra-DNA k-mer Conservation Patterns Encode Evolutionary Selection of Variants

The paper introduces kGain, a metric quantifying k-mer frequency shifts due to mutations, and shows it predicts adaptive potential across species and experimental systems.

Reconstructing human gene regulatory evolution using deep learning

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

Neanderthal introgressed ancestry reveals human genomic regions enriched with recessive deleterious mutations

The paper uses Neanderthal ancestry patterns to identify genomic regions enriched with recessive deleterious mutations using a machine learning classifier.

Multi-scale haplotype signatures distinguish among evolutionary processes

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

A comprehensive map of the sequence basis of transcription initiation in humans

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

Scooby-2: fine-tuning AlphaGenome for single-cell genomic track prediction

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

ESMRank reveals a transferable axis of protein mutational constraint from overlapping variant effect assays

ESMRank is a sequence-based predictor that integrates protein language models and physicochemical features to rank mutational constraint across proteins, outperforming existing methods and capturing disease-relevant variants.

Integrating sequence-to-omics predictions and personal multi-omics for rare variant prioritization

The paper introduces Watershed-DL, a framework integrating sequence-to-omics predictions and multi-omics data to prioritize rare variants, finding it increases prioritized variants by 61.4% and identifies candidate disease alleles.

In silico prediction of metabolic trait robustness in microbial cells

This paper introduces TRAEV, a computational framework to predict the evolutionary robustness of metabolic traits in microbial cells, validated using yeast strains in controlled environments.

Using SpliceAI to triage splice-altering variants in 7,220 individuals with rare conditions highlights limitations of the precomputed scores

The paper evaluates precomputed SpliceAI scores for splice-altering variant prioritization in NDD cohorts, finding inaccuracies and providing a tool to improve variant triage.

VenusGenome: Genome-Aware Masked Autoencoding for Microbial Genome Representation Learning

VenusGenome improves microbial genome representation learning by using a genome-aware masked autoencoder, achieving high performance in phenotype prediction and gene-level tasks.

HERCULES: a deep-learning framework for RNA-binding region localization and mutation-effect prediction

HERCULES predicts RNA-binding regions and mutation effects using a deep-learning framework combining language models and physicochemical descriptors.

MPFIL: Multi-Level Protein Feature Integration for Predicting Mutation-Induced Protein-Protein Binding Affinity Changes

MPFIL predicts mutation-induced changes in protein-protein binding affinity by integrating structural and sequential features across multiple levels.

Functional and acid-stability constraints on the Junin virus glycoprotein complex

This study uses deep mutational scanning to analyze how amino-acid mutations affect the pH stability and cell entry function of the Junin virus glycoprotein complex.

EG-BINN: Parameter-Efficient Ensembling of Gated Biologically Informed Neural Networks for Epigenetic Age Estimation

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.

DEEP: Extracting Latent Energetic Landscapes from Protein Structure Predictors

The paper introduces DEEP-Boltz, a framework that extracts energetic potentials from protein structure predictors, outperforming existing methods in predicting mutation-induced stability changes.

A genomic foundation model for interpreting human genetic diversity

The paper introduces hEVO, a genomic foundation model trained on human haplotype sequences, achieving top performance in variant interpretation and functional annotation across multiple benchmarks.

Predicting cell-state-specific gene regulation from DNA across species

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

Distinct activation mechanisms underlie ligand efficacy at a GPCR

This study uses deep mutational pharmacology to show how different residues in the -opioid receptor determine the efficacy of opioids by shaping distinct activation mechanisms.