MIST-CF: Chemical formula inference from tandem mass spectra

TL;DR

MIST-CF is a neural network-based method that improves chemical formula inference from tandem mass spectra by learning to rank candidate formulas without relying on traditional fragmentation tree construction, achieving higher accuracy.

Contribution

The paper introduces MIST-CF, a novel energy-based neural network framework that enhances chemical formula annotation from MS/MS data without expert-parameterized fragmentation trees.

Findings

10% absolute improvement in top 1 accuracy over previous neural methods

Achieved near state-of-the-art performance on CASMI2022 dataset

Circumvents the need for manual curation and post-processing

Abstract

Chemical formula annotation for tandem mass spectrometry (MS/MS) data is the first step toward structurally elucidating unknown metabolites. While great strides have been made toward solving this problem, the current state-of-the-art method depends on time-intensive, proprietary, and expert-parameterized fragmentation tree construction and scoring. In this work we extend our previous spectrum Transformer methodology into an energy based modeling framework, MIST-CF, for learning to rank chemical formula and adduct assignments given an unannotated MS/MS spectrum. Importantly, MIST-CF learns in a data dependent fashion using a Formula Transformer neural network architecture and circumvents the need for fragmentation tree construction. We train and evaluate our model on a large open-access database, showing an absolute improvement of 10% top 1 accuracy over other neural network architectures. We further validate our approach on the CASMI2022 challenge dataset, achieving nearly equivalent performance to the winning entry within the positive mode category without any manual curation or post-processing of our results. These results demonstrate an exciting strategy to more powerfully leverage MS2 fragment peaks for predicting MS1 precursor chemical formula with data driven learning.