Genomics and Rare Diseases

AFQuery computes capture-aware allele frequencies for clinical genomics cohorts, reducing errors and bias in variant classification.

MARRVEL-MCP enables natural language variant interpretation by allowing LLMs to autonomously construct workflows using curated genomic tools, improving performance over models without tool access.

The paper recalibrates BAP1 MAVE data for different disease phenotypes to enable accurate variant classification across related disorders.

The paper predicts gene-rare disease associations using a network-based algorithm to improve variant prioritization and guide functional validation.

CharacTERT classifies hTERT missense variants using machine learning models that integrate sequence and structure-based features, achieving high accuracy and sensitivity in predicting pathogenicity.

This study evaluates a nanopore sequencing workflow for detecting complex variants in hereditary disease genes across multiple labs, finding high agreement with standard methods.

This paper introduces ClinVar-BERT, a model that prioritizes variants for clinical review by analyzing variant summaries and distinguishing functional evidence, achieving high accuracy in predicting loss of function.

The paper compares automated and manual reanalysis of rare disease genome sequencing data, finding automated methods achieve similar results with less effort.

The paper introduces a data model and dataset for rare disease research, enabling interoperable multi-omic data integration across clinical sites.

This paper develops a calibrated electrophysiological framework to classify CACNA1G missense variants, identifying two variants as likely pathogenic and others as benign.

This study reclassifies four novel mtDNA variants using single-cell NGS analysis, highlighting the need for functional evidence and standardized criteria in variant interpretation.

The paper combines enriched case data with population-based case-control analyses using a likelihood-ratio methodology to classify variants in breast cancer susceptibility genes.

This paper evaluates Evo 2's ability to predict pathogenicity and mechanisms of cardiomyopathy variants, showing high accuracy and structural feature identification.

This study explores patient experiences with genetic variant reclassifications, finding that re-contact practices significantly impact trust and perceived value of genetic testing.

The paper creates a genome-wide map of homozygous deletions in 125,730 individuals, identifying novel rare disease genes and variants.

Bio-BLIP is a multimodal architecture that integrates DNA, genes, proteins, and text to improve variant interpretation without task-specific fine-tuning, achieving better performance in variant prioritization and target gene prediction.

mehari predicts variant effects with a strict HGVS-first approach, achieving high speed and accuracy compared to existing tools.

This study evaluates a universal whole-genome sequencing protocol in a cardiac intensive care unit, finding that 19.4% of neonates with congenital heart defects had clinically relevant variants identified.

This study compares deep learning splice prediction algorithms, finding open-source reimplementations match the original SpliceAI in performance while outperforming traditional methods.

MucOneUp generates MUC1-VNTR reference sequences and simulated sequencing reads to benchmark variant calling tools across platforms.

The paper introduces VIS-seq, an image-based method to assess variant effects on cellular phenotypes, revealing multidimensional variant impacts across different diseases.

G-SPRI predicts cancer driver events from missense mutations by integrating structural and mutation-specific features using a graph model.

The paper uses AVITI sequencing to analyze homopolymer mutation rates in a CEPH/Utah pedigree, confirming lower mutation rates and no significant paternal age effect compared to other STRs.

AnnotateMissense integrates and benchmarks missense variant pathogenicity predictors using genome-wide data, achieving high performance with XGBoost.

VUStruct analyzes genetic variants of unknown significance by integrating 3D protein structure data and machine learning to improve clinical and research interpretation of rare genetic disorders.

This study evaluates the diagnostic yield of whole-genome sequencing in 8966 patients with suspected rare diseases, finding a 35.8% diagnostic rate and additional variant detection.

The paper describes the development of variant classification specifications for the VHL gene using ACMG/AMP guidelines, resulting in updated evidence codes and improved classification consistency.

The paper describes international workshops training variant scientists on the ClinGen Variant Curation Interface (VCI) and reports on its usage and costs.

The paper develops MDmis, a method using molecular dynamics simulations of intrinsically disordered regions to predict variant pathogenicity, finding Long IDRs show stronger pathogenic effects than Short IDRs.

The paper introduces Cat-VRS, a framework for computable representation of genomic variant categories to improve data interoperability and clinical interpretation.