Abstract

Gas chromatography is a widely used method in analytical chemistry and metabolomics. Using gas chromatography, vaporizable compounds can be separated for their further identification. Retention indices are standardized values that depend only on a chemical structure of a compound and on a stationary phase and characterize the retention of a compound in a chromatographic system. Retention index prediction is an important task because databases contain experimental values for a small fraction of all possible molecules, while this information is usable for untargeted analysis. In this work, we consider four machine learning models for retention index prediction: 1D and 2D convolutional neural networks, deep residual multilayer perceptron, and gradient boosting. String representation of the molecule, 2D representation of the chemical structure, molecular descriptors and fingerprints, and molecular descriptors are used as inputs of these four models, respectively, along with information about the stationary phase. The first and third models show the best performance, while the other two perform slightly worse. The models predict retention index values for various standard and semi-standard non-polar stationary phases. Further improvement in performance was achieved using a linear model that uses the results of four previous models as inputs (model stacking). The models were tested using various diverse data sets: flavor compounds, essential oils, metabolomics-related compounds. Achieved accuracy: median absolute and percentage errors – 6–40 units and 0.8-2.2%. Accuracy depends on a test data set. The stacking model outperforms previously reported approaches for all test data sets. Parameters of a pre-trained model and some source code are provided.

Highlights

  • Gas chromatography (GC) is an important method for separating compounds and chemical analysis and is widely used in metabolomics, environmental analysis and other fields

  • We tried multiple setups for single-input multi-layer perceptron with two inputs (MLP): we varied the number of layers in the range 2-5, nodes per layer, activation functions, regularization methods (L2, L1, dropout), residual connections

  • In all cases that we considered, single-input MLP performs worse than gradient boosting using the same data set and using the same feature set

Read more

Summary

Introduction

Gas chromatography (GC) is an important method for separating compounds and chemical analysis and is widely used in metabolomics, environmental analysis and other fields. Mixtures of vaporizable compounds can be efficiently and rapidly separated for their further detection and identification using electron ionization mass spectrometry (MS) or other methods. A mixture of vapors of the compounds to be separated moves with a stream of gas (mobile phase) along the surface of a non-volatile liquid (stationary phase). Separation is achieved due to different volatility and affinity of different compounds to the stationary phase. This leads to the fact that different compounds are retained in the chromatographic system for a different periods of time.

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call