Peter D. Stenson

When splicing is not all or none: GT>GC 5' splice-site variants as a model for intermediate effects and challenges in variant classification

The paper examines GT>GC 5' splice-site variants, showing they can retain wild-type transcript and challenge variant classification.

Genome-wide prediction of pathogenic gain- and loss-of-function variants from ensemble learning of diverse feature set

LoGoFunc predicts pathogenic gain- and loss-of-function variants using ensemble learning with diverse biological features, outperforming existing tools.

A comprehensive knowledgebase of known and predicted human genetic variants associated with COVID-19 susceptibility and severity

The paper compiles 820 host genetic variants associated with COVID-19 susceptibility, develops a machine learning classifier to predict severity variants, and creates a web-based resource for exploring these variants.

Genome-wide detection of human variants that disrupt intronic branchpoints

The paper introduces BPHunter, a computational tool to detect intronic variants disrupting branchpoints, identifies known and novel mutations, and validates them experimentally.

Identification of Discriminative Gene-level and Protein-level Features Associated with Gain-of-Function and Loss-of-Function Mutations

The paper identifies gene- and protein-level features distinguishing gain-of-function and loss-of-function mutations using NLP and machine learning on a new database of pathogenic mutations.

AMELIE 3: Fully Automated Mendelian Patient Reanalysis at Under 1 Alert per Patient per Year

AMELIE 3 automatically reanalyzes undiagnosed Mendelian disease patients using new literature, achieving 80% diagnostic yield with 0.5-1 alerts per patient per year.

Identifying novel high-impact rare disease-causing mutations, genes and pathways in exomes of Ashkenazi Jewish inflammatory bowel disease patients

The paper identifies 7 novel IBD-causing genes in Ashkenazi Jewish IBD patients using exome sequencing and analyzes their overlap with early-onset IBD and other diseases.

PIVOTAL: Prioritizing variants of uncertain significance with spatial genomic patterns in the 3D proteome

PIVOTAL prioritizes variants of uncertain significance using 3D proteome spatial patterns, predicting pathogenicity for 140,000 VUS and providing a web tool for analysis.

Common homozygosity for predicted loss-of-function variants reveals both redundant and advantageous effects of dispensable human genes

The paper identifies 166 dispensable human genes with common loss-of-function variants that show relaxed selective constraints and some evidence of positive selection.

AMELIE 2 speeds up Mendelian diagnosis by matching patient phenotype & genotype to primary literature

AMELIE 2 improves Mendelian disorder diagnosis by matching patient phenotypes and genotypes to primary literature, achieving high accuracy and efficiency.

AVADA Enables Automated Genetic Variant Curation Directly from the Full Text Literature

AVADA automatically curates a database of pathogenic variants from full-text literature, outperforming existing methods and providing more variants than ClinVar.

SeqTailor: a user-friendly webserver for the extraction of DNA or protein sequences from next-generation sequencing data

SeqTailor extracts DNA or protein sequences from VCF files for genetic variant analysis, providing a user-friendly webserver to support sequence-based predictions.

S-CAP extends clinical-grade pathogenicity prediction to genetic variants that affect RNA splicing

S-CAP improves pathogenicity prediction for splicing-relevant variants by reducing uncertain variants by 41% with 95% sensitivity.

AMELIE accelerates Mendelian patient diagnosis directly from the primary literature

AMELIE automates Mendelian disorder diagnosis by analyzing literature and prioritizing candidate genes, achieving high diagnostic accuracy for singleton patients.