Karsten Michael Borgwardt

FastaLake constructs compact metaproteomic databases from sequence resources to improve peptide identification without requiring matched metagenomic sequencing.

A structure-conditioned nucleotide-level Potts model designs protein and coding sequences jointly, enabling tRNA adaptation and RNA motif embedding beyond synonymous codons with designability comparable to Caliby.

The paper develops a machine learning model to detect pOXA-48-carrying Enterobacterales using MALDI-TOF MS spectra, achieving high accuracy across different cohorts.

This paper uses machine learning on MALDI-TOF mass spectrometry data to detect ampicillin susceptibility in Enterococcus faecium, achieving high accuracy across datasets.

This study uses single-cell spatial proteomics to map human liver zonation patterns and shows their disruption in fibrosis.

DeepEST predicts bacterial protein functions using a multimodal deep learning framework combining gene expression, localization, and structure data, outperforming existing methods on a 25-species benchmark.

This study uses 1D-CNNs to predict PCR amplification bias from DNA sequences, identifying self-priming as a previously overlooked mechanism.

This paper introduces FDDC, a method for inferring connectivity in neuronal networks, showing it outperforms existing methods and reveals a negative correlation between small-worldness and network synchrony.

networkGWAS improves network-based GWAS by using mixed models and permutation schemes to detect genetic associations with better statistical control.

SIMBSIG enables scalable similarity search and clustering for large biobank datasets using a GPU-enabled Python package.

The paper improves antimicrobial resistance prediction using MALDI-TOF MS by incorporating phylogenetic structure through hierarchical clustering, increasing average precision for specific resistance predictions.

The paper introduces DeePhys, a tool for functional phenotyping of neurons using electrophysiological data, and shows it can predict genotype and age in iPSC-derived DA neurons with the A53T SNCA mutation.

reComBat removes batch effects from large-scale, multi-source omics data while preserving biological variation, outperforming existing methods for public gene expression data of Pseudomonas aeruginosa.

The paper introduces DNA-based phenotypic recording to generate large-scale sequence-function datasets and uses deep learning to predict gene regulatory element function with high accuracy.