Denis C. Bauer

The paper evaluates AlphaGenome's cross-species performance on mouse data, showing varying accuracy for different functional tasks and introduces a confidence scoring method for AI predictions.

The paper introduces synerOmics, a machine learning framework to identify synergistic protein interactions, finding ATL3 as a biomarker for lapatinib resistance in breast cancer.

The paper identifies an epistatic interaction between RBMS3 and CDKN2B-AS1 in CAD risk using VariantSpark and BitEpi, with validation in UK Biobank and All of Us.

The paper fine maps CAD loci in UK Biobank whole genome sequencing data using PolyFun and ML tools, showing improved sensitivity over traditional methods and demonstrating cost and speed benefits of cloud-based analysis.

Crackling Cloud is a cloud-based tool for designing CRISPR-Cas9 guide RNAs, offering scalability and accessibility without requiring local high-performance computing resources.

This study identifies novel Alzheimer's disease genes and epistasis using machine learning GWAS tools, capturing more phenotypic variance and discovering new loci with epistatic interactions.

The paper uses machine learning to improve Cas12a guide RNA efficiency prediction by analyzing nucleotide bias and mismatches relative to the PAM site.

RFlocalfdr thresholds variable importance from Random Forests using an empirical Bayes approach, achieving high accuracy and speed for high-dimensional datasets.

This paper develops PEA1 plasmids and PE-nuclease systems for efficient prime editing in human and mouse cells, achieving high editing efficiency in some cell lines and fetal mice.

BitEpi efficiently identifies higher-order epistatic interactions among SNVs in genetic data, outperforming existing methods in speed and accuracy.

TRIBES detects genomic relatedness up to 7th degree relatives and identifies disease susceptibility loci using a single pipeline.

This paper introduces CursedForest, a Random Forest implementation that scales to millions of features and outperforms existing methods in speed.

The paper identifies high-efficiency HDR target sites using machine learning and develops a tool to design optimal nucleotide editing strategies.