English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Microbial identification is a central issue in microbiology, in particular inthe fields of infectious diseases diagnosis and industrial quality control. Theconcept of species is tightly linked to the concept of biological and clinicalclassification where the proximity between species is generally measured interms of evolutionary distances and/or clinical phenotypes. Surprisingly, theinformation provided by this well-known hierarchical structure is rarely usedby machine learning-based automatic microbial identification systems.Structured machine learning methods were recently proposed for taking intoaccount the structure embedded in a hierarchy and using it as additional apriori information, and could therefore allow to improve microbialidentification systems. We test and compare several state-of-the-art machinelearning methods for microbial identification on a new Matrix-Assisted LaserDesorption/Ionization Time-of-Flight mass spectrometry (MALDI-TOF MS) dataset.We include in the benchmark standard and structured methods, that leverage theknowledge of the underlying hierarchical structure in the learning process. Ourresults show that although some methods perform better than others, structuredmethods do not consistently perform better than their "flat" counterparts. Wepostulate that this is partly due to the fact that standard methods alreadyreach a high level of accuracy in this context, and that they mainly confusespecies close to each other in the tree, a case where using the known hierarchyis not helpful.

Benchmark of structured machine learning methods for microbial identification from mass-spectrometry data