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

Identifying a small molecule from its mass spectrum is the primary openproblem in computational metabolomics. This is typically cast as informationretrieval: an unknown spectrum is matched against spectra predictedcomputationally from a large database of chemical structures. However, currentapproaches to spectrum prediction model the output space in ways that force atradeoff between capturing high resolution mass information and tractablelearning. We resolve this tradeoff by casting spectrum prediction as a mappingfrom an input molecular graph to a probability distribution over molecularformulas. We discover that a large corpus of mass spectra can be closelyapproximated using a fixed vocabulary constituting only 2% of all observedformulas. This enables efficient spectrum prediction using an architecturesimilar to graph classification - GrAFF-MS - achieving significantly lowerprediction error and orders-of-magnitude faster runtime than state-of-the-artmethods.

Efficiently predicting high resolution mass spectra with graph neural networks