Breaking Down Structural Diversity for Comprehensive Prediction of Ion-Neutral Collision Cross Sections

Abstract

Identification of unknowns is a bottleneck for large-scale untargeted analyses like metabolomics or drug metabolite identification. Ion mobility-mass spectrometry (IM-MS) provides rapid two-dimensional separation of ions based on their mobility through a neutral buffer gas. The mobility of an ion is related to its collision cross section (CCS) with the buffer gas, a physical property that is determined by the size and shape of the ion. This structural dependency makes CCS a promising characteristic for compound identification, but this utility is limited by the availability of high-quality reference CCS values. CCS prediction using machine learning (ML) has recently shown promise in the field, but accurate and broadly applicable models are still lacking. Here we present a novel ML approach that employs a comprehensive collection of CCS values covering a wide range of chemical space. Using this diverse database, we identified the structural characteristics, represented by molecular quantum numbers (MQNs), that contribute to variance in CCS and assessed the performance of a variety of ML algorithms in predicting CCS. We found that by breaking down the chemical structural diversity using unsupervised clustering based on the MQNs, specific and accurate prediction models for each cluster can be trained, which showed superior performance than a single model trained with all data. Using this approach, we have robustly trained and characterized a CCS prediction model with high accuracy on diverse chemical structures. An all-in-one web interface () was built for querying the CCS database and accessing the predictive model to support unknown compound identifications.

Ion mobility collision cross-section atlas for known and unknown metabolite annotation in untargeted metabolomics

“…Different strategies have been developed for CCS calculation, such as MetCCS 27 , LipidCCS 29 , DeepCCS 30 , ISiCLE 31 , DarkChem 49 , CCSbase 50 etc. However, the efficiency, accuracy and generalization capability for these methods need further improvements.…”

Empowering Large Chemical Knowledge Bases for Exposomics: Pubchemlite Meets Metfrag

“…XlogP3 [54] in future versions of PubChemLite to integrate within the retention time model already present in MetFrag [25]. Further, an initial version of PubChemLite (January 14, 2020 tier1) with CCS values contributed by CCSbase [55,56] is also available on Zenodo [57] and in MetFrag web version [26] and is currently being evaluated in separate work.…”

High-Throughput Measurement and Machine Learning-Based Prediction of Collision Cross Sections for Drugs and Drug Metabolites

“…This problem can be addressed by leveraging structural trends in existing CCS databases to predict CCS for unknowns that are not in experimental databases, and this approach has been demonstrated by multiple groups, including us. [18][19][20][21][22][23][24][25] An important consideration in this approach, however, is the dependence of CCS prediction performance on the quality and coverage of chemical space in the data used to train the model. 24 Therefore, a drug metabolite-specific CCS database is needed for accurate prediction of CCS for drug metabolites.…”

“…[18][19][20][21][22][23][24][25] An important consideration in this approach, however, is the dependence of CCS prediction performance on the quality and coverage of chemical space in the data used to train the model. 24 Therefore, a drug metabolite-specific CCS database is needed for accurate prediction of CCS for drug metabolites. Another limitation in current machine learning (ML)-based CCS prediction models is that the 2D features used in previous work (e.g., molecular quantum numbers, MQNs) do not adequately capture more complex IM behavior arising from the presence of different protomers, conformers, or positional isomers that are common among drugs and drug metabolites.…”