Predicting Ion Mobility Collision Cross-Sections Using a Deep Neural Network: DeepCCS

Abstract

Untargeted metabolomic measurements using mass spectrometry are a powerful tool for uncovering new small molecules with environmental and biological importance. The small molecule identification step, however, still remains an enormous challenge due to fragmentation difficulties or unspecific fragment ion information. Current methods to address this challenge are often dependent on databases or require the use of nuclear magnetic resonance (NMR), which have their own difficulties. The use of the gas-phase collision cross section (CCS) values obtained from ion mobility spectrometry (IMS) measurements were recently demonstrated to reduce the number of false positive metabolite identifications. While promising, the amount of empirical CCS information currently available is limited, thus predictive CCS methods need to be developed. In this article, we expand upon current experimental IMS capabilities by predicting the CCS values using a deep learning algorithm. We successfully developed and trained a prediction model for CCS values requiring only information about a compound's SMILES notation and ion type. The use of data from five different laboratories using different instruments allowed the algorithm to be trained and tested on more than 2400 molecules. The resulting CCS predictions were found to achieve a coefficient of determination of 0.97 and median relative error of 2.7% for a wide range

Deep metabolome: Applications of deep learning in metabolomics

“…Similarities between unknow and reference compounds’ data are typically estimated based on correlation [63] , weighted cosine similarity [64] and Euclidean distance [65] which are used to rank the matching candidate hits [66] . This approach is limited by availability of known compounds and their spectral coverage in the reference databases [67] . Recently, Fan et.…”

“…ML algorithms including DNN models have also been used to predict collision cross section (CCS) value [57] , [67] , [75] , [76] , a chemical property of ion separation that can be directly obtained from ion mobility-MS (IM-MS) [70] . The CCS is exploited to narrow down the search space for unknown compound identification [77] .…”

“…al. [67] proposed CNN-based model (DeepCCS) for predicting the CCS value of a compound given the simplified molecular-input line-entry system (SMILES) representation and the ion type. Colby et.…”

Deep Learning to Generate in Silico Chemical Property Libraries and Candidate Molecules for Small Molecule Identification in Complex Samples

“…Recent interest in chemical structure-based deep learning approaches have shown promise [17][18][19][20][21][22][23][24] , particularly in the application of variational autoencoders (VAEs) 25 and other generative approaches for learning a continuous numerical, or latent, representation of molecular structure 17,[20][21]23 . These networks take SMILES (simplified molecular line entry system) strings as input and, in a semi-supervised configuration, predict the same sequence of characters as output, after perturbation by noise.…”

Probabilistic Framework for Integration of Mass Spectrum and Retention Time Information in Small Molecule Identification

“…Sources of additional information include, e.g. RT (Ruttkies et al, 2016;Bach et al, 2018;Samaraweera et al, 2018), collision crosssection (Plante et al, 2019), or prior knowledge on the data generating process, such as the source organism's metabolic characteristics (Rutz et al, 2019). Retention time, that is, the time that a molecule takes to elute from the LC column, is readily available in all LC-MS pipelines, and is frequently used in aiding annotation (Stanstrup et al, 2015).…”