Automated tuning of denoising algorithms for noise removal in chromatograms.

Different algorithms, such as the Savitzky-Golay filter and Whittaker smoother, have been proposed to improve the quality of experimental chromatograms. These approaches avoid excessive noise from hampering data analysis and as such allow an accurate detection and quantification of analytes. These algorithms require fine-tuning of their hyperparameters to regulate their roughness and flexibility. Traditionally, this fine-tuning is done manually until a signal is obtained that removes the noise while conserving valuable peak information. More objective and automated approaches are available, but these are usually method specific and/or require previous knowledge. In this work, the L-and V-curve, k-fold cross-validation, autocorrelation function and residual variance estimation approach are introduced as alternative automated and generally applicable parameter tuning methods. These methods do not require any previous information and are compatible with a multitude of denoising methods. Additionally, for k-fold cross-validation, autocorrelation function and residual variance estimation, a novel implementation based on median estimators is proposed to handle the specific shape of chromatograms, typically composed of alternating flat baselines and sharp peaks. These tuning methods are investigated in combination with four denoising methods; the Savitsky-Golay filter, Whittaker smoother, sparsity assisted signal smoother and baseline estimation and denoising using sparsity approach. It is demonstrated that the median estimators approach significantly improves the denoising and information conservation performance of relevant smoother-tuner combinations up to a factor 4 for simulated datasets and even up to a factor 10 for an experimental chromatogram. Moreover, the parameter tuning methods relying on residual variance estimation, k-fold cross-validation and autocorrelation function lead to similar small root-mean squared errors on the different simulated datasets and experimental chromatograms. The sparsity assisted signal smoother and baseline estimation and denoising using sparsity approach, which both rely on the use of sparsity, systematically outperform the two other methods and are hence most appropriate for chromatograms.

Convolutional neural network for automated peak detection in reversed-phase liquid chromatography.

Although commercially available software provides options for automatic peak detection, visual inspection and manual corrections are often needed. Peak detection algorithms commonly employed require carefully written rules and thresholds to increase true positive rates and decrease false positive rates. In this study, a deep learning model, specifically, a convolutional neural network (CNN), was implemented to perform automatic peak detection in reversed-phase liquid chromatography (RPLC). The model inputs a whole chromatogram and outputs predicted locations, probabilities, and areas of the peaks. The obtained results on a simulated validation set demonstrated that the model performed well (ROC-AUC of 0.996), and comparably or better than a derivative-based approach using the Savitzky-Golay algorithm for detecting peaks on experimental chromatograms (8.6% increase in true positives). In addition, predicted peak probabilities (typically between 0.5 and 1.0 for true positives) gave an indication of how confident the CNN model was in the peaks detected. The CNN model was trained entirely on simulated chromatograms (a training set of 1,000,000 chromatograms), and thus no effort had to be put into collecting and labeling chromatograms. A potential major drawback of this approach, namely training a CNN model on simulated chromatograms, is the risk of not capturing the actual "chromatogram space" well enough that is needed to perform accurate peak detection in real chromatograms.

Graph Convolutional Networks for Improved Prediction and Interpretability of Chromatographic Retention Data.

Machine learning is a popular technique to predict the retention times of molecules based on descriptors. Descriptors and associated labels (e.g., retention times) of a set of molecules can be used to train a machine learning algorithm. However, descriptors are fixed molecular features which are not necessarily optimized for the given machine learning problem (e.g., to predict retention times). Recent advances in molecular machine learning make use of so-called graph convolutional networks (GCNs) to learn molecular representations from atoms and their bonds to adjacent atoms to optimize the molecular representation for the given problem. In this study, two GCNs were implemented to predict the retention times of molecules for three different chromatographic data sets and compared to seven benchmarks (including two state-of-the art machine learning models). Additionally, saliency maps were computed from trained GCNs to better interpret the importance of certain molecular sub-structures in the data sets. Based on the overall observations of this study, the GCNs performed better than all benchmarks, either significantly outperforming them (5-25% lower mean absolute error) or performing similar to them (<5% difference). Saliency maps revealed a significant difference in molecular sub-structures that are important for predictions of different chromatographic data sets (reversed-phase liquid chromatography vs hydrophilic interaction liquid chromatography).

Deep convolutional autoencoder for the simultaneous removal of baseline noise and baseline drift in chromatograms.

Enhancement of chromatograms, such as the reduction of baseline noise and baseline drift, is often essential to accurately detect and quantify analytes in a mixture. Current methods have been well studied and adopted for decades and have assisted researchers in obtaining reliable results. However, these methods rely on relatively simple statistics of the data (chromatograms) which in some cases result in significant information loss and inaccuracies. In this study, a deep one-dimensional convolutional autoencoder was developed that simultaneously removes baseline noise and baseline drift with minimal information loss, for a large number and great variety of chromatograms. To enable the autoencoder to denoise a chromatogram to be almost, or completely, noise-free, it was trained on data obtained from an implemented chromatogram simulator that generated 190.000 representative simulated chromatograms. The trained autoencoder was then tested and compared to some of the most widely used and well-established denoising methods on testing datasets of tens of thousands of simulated chromatograms; and then further tested and verified on real chromatograms. The results show that the developed autoencoder can successfully remove baseline noise and baseline drift simultaneously with minimal information loss; outperforming methods like Savitzky-Golay smoothing, Gaussian smoothing and wavelet smoothing for baseline noise reduction (root mean squared error of 1.094 mAU compared to 2.074 mAU, 2.394 mAU and 2.199 mAU) and Savitkzy-Golay smoothing combined with asymmetric least-squares or polynomial fitting for baseline noise and baseline drift reduction (root mean absolute error of 1.171 mAU compared to 3.397 mAU and 4.923 mAU). Evidence is presented that autoencoders can be utilized to enhance and correct chromatograms and consequently improve and alleviate downstream data analysis, with the drawback of needing a carefully implemented simulator, that generates realistic chromatograms, to train the autoencoder.

Evaluation of the performance of commercially available polysaccharide-based chiral stationary phases after multicycle operation in multimodal elution mode.

The performance of four commercially available polysaccharide-based chiral stationary phases, Chiralcel OD, Chiralcel OJ, Chiralpak AD and Chiralpak AS was evaluated after several cycles of extended multimodal operations. Acetonitrile, methanol, ethanol and their mixtures were chosen for polar-organic mobile phases, ethanol-n-heptane mixture and n-heptane were selected for normal-phase mode. Retention factor (k), selectivity (alpha), resolution (Rs) and theoretical plate count (N) were the chosen parameters to describe the column performance. One racemate for which all four columns have shown enantioselectivity was chosen as test compound. After 15 cycles of multimodal operations a slight decrease was seen in the retention factors (k) however, column efficiency, selectivity (alpha) and resolution (Rs) were maintained.