Retention time information is used for metabolite annotation in metabolomic experiments. But its usefulness is hindered by the availability of experimental retention time data in metabolomic databases, and by the lack of reproducibility between different chromatographic methods. Accurate prediction of retention time for a given chromatographic method would be a valuable support for metabolite annotation. We have trained state-of-the-art machine learning regressors using the 80, 038 experimental retention times from the METLIN Small Molecule Retention Tim (SMRT) dataset. The models included deep neural networks, deep kernel learning, several gradient boosting models, and a blending approach. 5, 666 molecular descriptors and 2, 214 fingerprints (MACCS166, Extended Connectivity, and Path Fingerprints fingerprints) were generated with the alvaDesc software. The models were trained using only the descriptors, only the fingerprints, and both types of features simultaneously. Bayesian hyperparameter search was used for parameter tuning. To avoid data-leakage when reporting the performance metrics, nested cross-validation was employed. The best results were obtained by a heavily regularized deep neural network trained with cosine annealing warm restarts and stochastic weight averaging, achieving a mean and median absolute errors of [Formula: see text] and [Formula: see text], respectively. To the best of our knowledge, these are the most accurate predictions published up to date over the SMRT dataset. To project retention times between chromatographic methods, a novel Bayesian meta-learning approach that can learn from just a few molecules is proposed. By applying this projection between the deep neural network retention time predictions and a given chromatographic method, our approach can be integrated into a metabolite annotation workflow to obtain z-scores for the candidate annotations. To this end, it is enough that just as few as 10 molecules of a given experiment have been identified (probably by using pure metabolite standards). The use of z-scores permits considering the uncertainty in the projection when ranking candidates, and not only the accuracy. In this scenario, our results show that in 68% of the cases the correct molecule was among the top three candidates filtered by mass and ranked according to z-scores. This shows the usefulness of this information to support metabolite annotation. Python code is available on GitHub at https://github.com/constantino-garcia/cmmrt.
Keywords: Bayesian methods; Deep learning; Machine learning; Metabolomics; Retention time.
© 2022. The Author(s).