variant effect prediction

Using sequence-to-function models to interpret archaic hominin introgression

The paper uses sequence-to-function models to predict the functional impact of archaic hominin introgression in Papuan individuals, identifying genes associated with introgressed haplotypes.

Single-Cell Analytics for Dose Response (SCADR) discriminates PTEN missense variants by lipid and protein phosphatase dysfunction

SCADR assesses PTEN missense variants' effects on signaling pathways through single-cell phospho-antibody analysis, revealing variant-specific dysfunction profiles.

LDLR variant classification through activity-normalized prime editing screening

This paper uses prime editing to classify LDLR variants by measuring their impact on LDL-C uptake, reclassifying many previously unclassified variants.

Calibration-free compression brings Evo 2 to its full million-token context on a single GPU

The paper introduces TurboQuant-Bio, a toolkit that compresses Evo 2's weights and attention cache to four bits without calibration data, enabling genome-scale analysis on single GPUs.

BARCS: beta-binomial regression for multivariate CRISPR screen design

BARCS extends beta-binomial regression to handle complex CRISPR screen designs, showing improved essential gene recovery but calibration issues in gene-level summaries.

Climate-driven niche tracking and genomic resilience shape future distribution of a widespread agricultural weed

The paper examines how blackgrass adapts to climate change by tracking its ecological niche and showing polygenic adaptation, suggesting resilience in agricultural systems.

Machine learning methodology using a masked neural network for robust genetic risk score calculation from noisy and missing data

The paper introduces a masked-MLP neural network to improve genetic risk score calculation from noisy and missing data, showing better robustness than standard methods.

T-Rex: Standardized Analysis of Germline Variants in Whole-Exome Sequencing Trios

T-Rex provides a standardized, no-programming-required tool for analyzing whole-exome sequencing trio data, achieving high precision and sensitivity in variant calling and filtering.

Genomic Language Model for Predicting Enhancers and Their Allele-Specific Activity in the Human Genome

The paper develops DNABERT-Enhancer, a genomic language model for enhancer prediction, achieving high accuracy and identifying allele-specific activity and candidate SNPs.

A Curated Pharmacogenomic Allele Catalog for Sub-Saharan African Populations

The paper curates a pharmacogenomic allele catalog for Sub-Saharan African populations, highlighting population-specific frequencies and functional annotations for six pharmacogenes.

S2F-Agent: Harnessing sequence-to-function models for verifiable genome interpretation

S2F-Agent improves genome interpretation by orchestrating sequence-to-function models with verifiable execution and interpretation.

Lineage-specific X chromosome inactivation escape and skew underlie sex-biased immune gene dosage and deleterious variant exposure

This paper introduces scDaisyChain to analyze X chromosome inactivation escape and skew in immune cells, revealing lineage-specific effects on gene dosage and variant exposure in healthy and autoimmune disease contexts.

A neuronal CRISPRi screen identifies PQLC2 as a lysosomal pH regulator controlling tau homeostasis

The paper identifies PQLC2 as a lysosomal pH regulator that affects tau homeostasis through a CRISPRi screen in iPSC-derived neurons.

A comprehensive atlas of somatic mutation rates and mutational signatures in normal human cells

The paper reports mutation rates and mutational signatures across 53 normal human cell types, revealing variation in mutation accumulation and identifying known and unknown mutational processes.

aiDIVA - Diagnostics of Rare Genetic Diseases Using Large Language Models

aiDIVA uses AI and LLMs to prioritize causal genetic variants in rare diseases, achieving high accuracy in identifying top candidates.

Sequence architecture shapes human allele frequencies through ectopic gene conversion

The paper shows that ectopic gene conversion, influenced by genome architecture, significantly shapes human allele frequencies, affecting both rare and common variants.

Integrative optical genome mapping and long-read sequencing resolve constitutional complex rearrangements at nucleotide resolution

The paper uses optical genome mapping and long-read sequencing to resolve complex rearrangements at nucleotide resolution, revealing additional complexity and enabling accurate genotype-phenotype correlations.

Locus-specific gene-context interactions improve polygenic prediction

This paper introduces PGSC, a polygenic score framework that incorporates locus-specific gene-context interactions, showing improved prediction across multiple traits and ancestries.

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.

PMPNN-DDG: an accurate machine learning-based {triangleup}{triangleup}G prediction pipeline trained on a novel interpretable feature set extracted from ProteinMPNN

PMPNN-DDG is a Random Forest model predicting single-point mutation-induced protein stability changes using features from ProteinMPNN, achieving high accuracy on independent test sets.

Sequence-to-function deep learning decodes human cis-regulatory evolution

This study uses sequence-to-function deep learning to identify lineage-specific cis-regulatory elements in human evolution, finding they are shorter, less conserved, and enriched in neurodevelopmental pathways.

Genomize-SEQ: An NGS data analysis platform for genomic variant classification and prioritization

Genomize-SEQ is a web-based platform for genomic variant classification and prioritization, achieving high accuracy in identifying causative variants for rare diseases.

The BAF complex works with FOS to regulate human neuronal activity-dependent ASD-associated gene programs

This study identifies BAF complex interaction with FOS in regulating ASD-associated gene programs through enhancer activation and shows how genetic variants disrupt this process.

Benchmarking nanopore-based strategies for antimicrobial resistance prediction

This study benchmarks in silico AMR prediction tools using nanopore data, finding that assembly strategy and data volume impact accuracy, but no tool perfectly matches lab-based AST results.

XMAn Update - A Database of Homo sapiens Mutated Peptides

XMAn Update expands a database of mutated peptides by integrating cancer-related variants from COSMIC and CGC datasets to improve variant detection in mass spectrometry analyses.

Why variant effect predictors and multiplexed assays agree and disagree

The paper compares variant effect predictors and MAVEs to understand their agreement and disagreement in assessing genetic variant impacts.

Estimating the contribution of coding mutations to autism

The paper estimates the contribution of de novo coding mutations to autism using data from 38,680 trios, finding they explain 3.4% of autism variance.

AI-driven framework modeling perturbation in brain organoids reveals candidate genes for autism

The paper uses an AI-driven framework to model perturbations in brain organoids and identifies candidate genes for autism using genomic and clinical data.

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.

MONTE enables unified pan-cancer tumor purity estimation andmethylation correction from bulk DNA methylation arrays

MONTE provides a unified framework for tumor purity estimation and methylation correction from bulk DNA methylation data, improving accuracy and generalizability across cancer types.