Predicting clinical antimicrobial resistance

Antimicrobial resistance was named one of the top ten public health threats to humanity by the World Health Organization. To identify microbial species in infected patients, clinicians rely on MALDI-TOF mass-spectrometry and subsequent in vitro experiments. Could machine learning speed up the clinical identification of resistant microbes? Discover the database built by the team for that purpose, and the new method to retrieve even more information from MS data. This should be of particular interest to researchers working in the application of phenotype prediction algorithms, especially on vector represented data, collected across from different domains. The talk is presented by Caroline Weis, former member of the SIB Group of Karsten Borgwardt at ETH Zurich, and the paper discussed in this talk is also one of the SIB Remarkable Outputs of 2021.