Tomáš Szemes

This study optimizes mixed sample analysis for Lynch Syndrome detection, finding that pooling whole blood samples before DNA isolation is cost-effective and detects pathogenic variants at 5% frequency.

The paper combines expert guideline-based and machine learning approaches to improve automated prediction of the clinical effect of copy number variations.

The paper presents a classifier to predict the clinical impact of structural copy number variations with over 98% accuracy.

The paper introduces Varlock, a method to securely store genomic data by masking personal alleles using population frequencies, ensuring privacy while preserving useful data for research.

This study evaluates the detection limits of chromosomal microdeletions in non-invasive prenatal testing using whole genome sequencing data and simulated datasets.

PHERI is a machine learning tool that predicts bacterial hosts for phages and identifies key protein sequences involved in host selection.

This study uses NIPT data to determine population-specific allelic frequencies of small DNA variants at low cost, showing high reliability through in silico and wet lab validation.

The paper introduces a method to reduce uninformative calls in NIPT by analyzing the length profile of circulating cell-free DNA, improving resolution of ambiguous results when combined with z-scores.