Josch Konstantin Pauling

LipiDetective is a transformer model that accurately identifies molecular lipid species in tandem mass spectra using learned fragmentation patterns, improving comparability across experiments.

LipidLibrarian integrates lipidomics data from multiple databases to provide a unified search interface for lipid information.

The paper evaluates normalization methods in proteomics data, finding that some methods perform better than others and develops a tool to assess their impact.

The paper introduces Smile-to-Bert, a pre-trained BERT model for predicting molecular properties from SMILES strings, showing improved performance on several datasets.

The paper constructs a metabolite nutrition graph to explore interactions between diet, metabolites, and disease by integrating multiple ontologies and databases.

The paper introduces mantra, a method to estimate metabolic reaction activity changes from untargeted metabolomics data, demonstrating its utility in identifying biomarkers and enabling multi-omics integration.

The paper introduces LINEX2, a lipid network analysis framework that identifies enzymatic dysregulation from lipidomics data by integrating metabolic networks and graph algorithms.

MoSBi automates biclustering analysis across multi-omics data to identify robust molecular signatures for stratification and subtyping.