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

Computational predictions of mass spectra from molecules have enabled thediscovery of clinically relevant metabolites. However, such predictive toolsare still limited as they occupy one of two extremes, either operating (a) byfragmenting molecules combinatorially with overly rigid constraints onpotential rearrangements and poor time complexity or (b) by decoding lossy andnonphysical discretized spectra vectors. In this work, we use a newintermediate strategy for predicting mass spectra from molecules by treatingmass spectra as sets of molecular formulae, which are themselves multisets ofatoms. After first encoding an input molecular graph, we decode a set ofmolecular subformulae, each of which specify a predicted peak in the massspectrum, the intensities of which are predicted by a second model. Our keyinsight is to overcome the combinatorial possibilities for molecularsubformulae by decoding the formula set using a prefix tree structure,atom-type by atom-type, representing a general method for ordered multisetdecoding. We show promising empirical results on mass spectra prediction tasks.

Prefix-Tree Decoding for Predicting Mass Spectra from Molecules