Peder Worning

TL;DR: The difference in predictive performance between the neural network methods and that of the matrix‐driven methods is found to be most significant for peptides that bind strongly to the HLA molecule, confirming that the signal of higher order sequence correlation is most strongly present in high‐binding peptides.

TL;DR: This work has generated Artificial Neural Networks capable of performing sensitive, quantitative predictions of peptide binding to the MHC class I molecule, HLA-A*0204, and it is an example of an iterative feedback loop whereby advanced, computational bioinformatics optimize experimental strategy, and vice versa.

TL;DR: In this article, the functional relationship between all known HLA molecules with known specificities was studied in a uniform and automated way, and a method for clustering sequence motifs was developed.

TL;DR: A novel Gibbs motif sampler method ideally suited for recognizing weak sequence motifs of MHC class II binding, based on the Gibbs sampling method, is described and a consensus solution obtained from an ensemble average over suboptimal solutions is shown to outperform the use of a single optimal solution.

TL;DR: Evaluated spa typing of methicillin-resistant Staphylococcus aureus isolates from new MRSA patients in Denmark found a 97% agreement between spa types obtained by the two methods, showing that WGS is a reliable method to determine the spa type of MRSA.