Jeremy F. McRae

This paper introduces SpliceAI2, a deep learning model that improves identification and quantification of splice-altering variants and their effects on transcripts and disease.

This study functionally characterizes 221,412 trait-associated variants using MPRA in 5 cell types, identifying 12,025 regulatory variants and revealing widespread epistasis and non-TF mechanisms.

FlexRV improves gene discovery for complex traits by modeling nonlinear relationships between variant annotations and phenotypes, outperforming existing methods in association detection and replication.

The paper shows that highly parameterized polygenic scores overfit to population stratification by including random variants, reducing their generalizability.

The paper benchmarks PrimateAI-3D and AlphaMissense on real-world cohorts, finding PrimateAI-3D performs better in rare-disease and biobank settings.

The paper uses primate genetic data to predict human variant pathogenicity with a deep learning classifier trained on 4.3 million common missense variants.

The paper identifies rare variant polygenic risk scores as more effective than common variant polygenic risk scores in identifying individuals with outlier phenotypes in common human diseases and complex traits.

The paper identifies genetic and chemotherapeutic causes of germline hypermutation by analyzing genome-wide sequences of families with rare genetic diseases.

The paper analyzes X-linked coding variation in developmental disorders, finding similar rates in males and females and estimating pathogenicity of inherited variants.

The paper integrates healthcare and research exome sequences to identify 28 novel developmental disorder-associated genes using a simulation-based statistical test.

The paper identifies 299 new genes associated with developmental disorders using exome data from 31,058 trios and finds many more likely remain undiscovered.

The paper analyzes de novo mutations in developmental disorders using exome sequencing of 4,293 families, identifying 94 genes and estimating a birth prevalence of 0.22-0.47%.

The paper analyzes exome sequencing data to assess the contribution of splice site mutations to developmental disorders and estimates their pathogenicity and underrepresentation in public databases.

The paper estimates the contribution of recessive coding variants to developmental disorders using exome data from 7,448 families, finding low prevalence in European ancestry but higher in Pakistani ancestry.

The paper shows that common genetic variants contribute to risk and clinical variation in severe neurodevelopmental disorders, even in individuals with known monogenic diagnoses.

The paper identifies de novo mutations in fetal-brain active regulatory elements as a cause of 1-3% of neurodevelopmental disorders in patients without coding variants.