Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Generating Molecular Fragmentation Graphs with Autoregressive Neural Networks

About

The accurate prediction of tandem mass spectra from molecular structures has the potential to unlock new metabolomic discoveries by augmenting the community's libraries of experimental reference standards. Cheminformatic spectrum prediction strategies use a "bond-breaking" framework to iteratively simulate mass spectrum fragmentations, but these methods are (a) slow, due to the need to exhaustively and combinatorially break molecules and (b) inaccurate, as they often rely upon heuristics to predict the intensity of each resulting fragment; neural network alternatives mitigate computational cost but are black-box and not inherently more accurate. We introduce a physically-grounded neural approach that learns to predict each breakage event and score the most relevant subset of molecular fragments quickly and accurately. We evaluate our model by predicting spectra from both public and private standard libraries, demonstrating that our hybrid approach offers state of the art prediction accuracy, improved metabolite identification from a database of candidates, and higher interpretability when compared to previous breakage methods and black box neural networks. The grounding of our approach in physical fragmentation events shows especially high promise for elucidating natural product molecules with more complex scaffolds.

Samuel Goldman, Janet Li, Connor W. Coley• 2023

Related benchmarks

TaskDatasetResultRank
Molecular retrievalNIST 2020 (Scaffold)
Top-1 Accuracy22.9
16
Molecular retrievalNIST 2020 (Random split)
Top-1 Accuracy25.1
12
Spectral predictionNIST [M+H]+ adduct '20 (Random split)
Cosine Similarity0.754
8
Spectral predictionNIST [M+H]+ adduct '20 (Scaffold split)
Cosine Similarity70.1
8
Spectral predictionNIST positive mode 2020 (Random)
Cosine Similarity72.7
6
Spectral predictionNIST positive mode Scaffold 2020
Cosine Similarity0.698
6
RetrievalNIST 2020
Top-1 Accuracy18.9
5
Showing 7 of 7 rows

Other info

Follow for update