Shridhar Parthasarathy

The paper analyzes a large DNM1 cohort to identify mutational hotspots and genotype-phenotype correlations in DNM1-related disorder.

The paper analyzes 11,125 trio exomes to explore the relationship between genetic variants and phenotypic features in neurodevelopmental disorders, finding significant clinical similarities and phenotypic gradients.

This study identifies clinical features preceding genetic epilepsy diagnosis in EMR data from 32,000 individuals, showing early signs can inform earlier treatment.

The paper develops a Bayesian framework to integrate functional evidence into clinical variant interpretation for epilepsy-related ion channel genes, identifying key parameters that influence pathogenicity classification.

This study analyzes 52,143 individuals to characterize paediatric speech and language disorders, identifying genetic associations and clinical patterns.

The paper introduces para-PS1/PM5 criteria by incorporating pathogenic paralogous variants to improve variant classification under ACMG guidelines, increasing classifiable amino acids 3.6-fold.

The paper introduces a phenotype embedding technique using 53 million patient notes to enhance representation learning, showing improved phenotypic similarity and alignment with domain experts.

The paper identifies a recurrent de novo splice site variant in DNM1 exon 10a causing severe DEE through a dominant-negative mechanism, highlighting the importance of considering alternative isoforms in disease causation.

This paper identifies and characterizes the SCN1A p.R1636Q gain-of-function variant, showing it causes early-onset epileptic encephalopathy with distinct clinical and electrophysiological features.

This paper develops a multi-task learning model to predict the functional effects of voltage-gated potassium channel variants, achieving improved accuracy over standard methods.