Probabilistic metabolite annotation using retention time prediction and meta-learned projections

Physicochemical modelling of the retention mechanism of temperature-responsive polymeric columns for HPLC through machine learning algorithms

Temperature-responsive liquid chromatography (TRLC) offers a promising alternative to reversed-phase liquid chromatography (RPLC) for environmentally friendly analytical techniques by utilizing pure water as a mobile phase, eliminating the need for harmful organic solvents. TRLC columns, packed with temperature-responsive polymers coupled to silica particles, exhibit a unique retention mechanism influenced by temperature-induced polymer hydration. An investigation of the physicochemical parameters driving separation at high and low temperatures is crucial for better column manufacturing and selectivity control. Assessment of predictability using a dataset of 139 molecules analyzed at different temperatures elucidated the molecular descriptors (MDs) relevant to retention mechanisms. Linear regression, support vector regression (SVR), and tree-based ensemble models were evaluated, with no standout performer. The precision, accuracy, and robustness of models were validated through metrics, such as r and mean absolute error (MAE), and statistical analysis. At 45 ∘ C , logP predominantly influenced retention, akin to reversed-phase columns, while at5 ∘ C , complex interactions with lipophilic and negative MDs, along with specific functional groups, dictated retention. These findings provide deeper insights into TRLC mechanisms, facilitating method development and maximizing column potential.

Performance and robustness of small molecule retention time prediction with molecular graph neural networks in industrial drug discovery campaigns

This study explores how machine-learning can be used to predict chromatographic retention times (RT) for the analysis of small molecules, with the objective of identifying a machine-learning framework with the robustness required to support a chemical synthesis production platform. We used internally generated data from high-throughput parallel synthesis in context of pharmaceutical drug discovery projects. We tested machine-learning models from the following frameworks: XGBoost, ChemProp, and DeepChem, using a dataset of 7552 small molecules. Our findings show that two specific models, AttentiveFP and ChemProp, performed better than XGBoost and a regular neural network in predicting RT accurately. We also assessed how well these models performed over time and found that molecular graph neural networks consistently gave accurate predictions for new chemical series. In addition, when we applied ChemProp on the publicly available METLIN SMRT dataset, it performed impressively with an average error of 38.70 s. These results highlight the efficacy of molecular graph neural networks, especially ChemProp, in diverse RT prediction scenarios, thereby enhancing the efficiency of chromatographic analysis.

Generic and accurate prediction of retention times in liquid chromatography by post-projection calibration

Retention time predictions from molecule structures in liquid chromatography (LC) are increasingly used in MS-based targeted and untargeted analyses, providing supplementary evidence for molecule annotation and reducing experimental measurements. Nevertheless, different LC setups (e.g., differences in gradient, column, and/or mobile phase) give rise to many prediction models that can only accurately predict retention times for a specific chromatographic method (CM). Here, a generic and accurate method is present to predict retention times across different CMs, by introducing the concept of post-projection calibration. This concept builds on the direct projections of retention times between different CMs and uses 35 external calibrants to eliminate the impact of LC setups on projection accuracy. Results showed that post-projection calibration consistently achieved a median projection error below 3.2% of the elution time. The ranking results of putative candidates reached similar levels among different CMs. This work opens up broad possibilities for coordinating retention times between different laboratories and developing extensive retention databases.

RT-Transformer: retention time prediction for metabolite annotation to assist in metabolite identification

MOTIVATION

Liquid chromatography retention times prediction can assist in metabolite identification, which is a critical task and challenge in nontargeted metabolomics. However, different chromatographic conditions may result in different retention times for the same metabolite. Current retention time prediction methods lack sufficient scalability to transfer from one specific chromatographic method to another.

RESULTS

Therefore, we present RT-Transformer, a novel deep neural network model coupled with graph attention network and 1D-Transformer, which can predict retention times under any chromatographic methods. First, we obtain a pre-trained model by training RT-Transformer on the large small molecule retention time dataset containing 80 038 molecules, and then transfer the resulting model to different chromatographic methods based on transfer learning. When tested on the small molecule retention time dataset, as other authors did, the average absolute error reached 27.30 after removing not retained molecules. Still, it reached 33.41 when no samples were removed. The pre-trained RT-Transformer was further transferred to 5 datasets corresponding to different chromatographic conditions and fine-tuned. According to the experimental results, RT-Transformer achieves competitive performance compared to state-of-the-art methods. In addition, RT-Transformer was applied to 41 external molecular retention time datasets. Extensive evaluations indicate that RT-Transformer has excellent scalability in predicting retention times for liquid chromatography and improves the accuracy of metabolite identification.

AVAILABILITY AND IMPLEMENTATION

The source code for the model is available at https://github.com/01dadada/RT-Transformer. The web server is available at https://huggingface.co/spaces/Xue-Jun/RT-Transformer.

Retention Time Prediction through Learning from a Small Training Data Set with a Pretrained Graph Neural Network

Graph neural networks (GNNs) have shown remarkable performance in predicting the retention time (RT) for small molecules. However, the training data set for a particular target chromatographic system tends to exhibit scarcity, which poses a challenge because the experimental process for measuring RT is costly. To address this challenge, transfer learning has been used to leverage an abundant training data set from a related source task. In this study, we present an improved transfer learning method to better predict the RT of molecules for a target chromatographic system by learning from a small training data set with a pretrained GNN. We use a graph isomorphism network as the architecture of the GNN. The GNN is pretrained on the METLIN-SMRT data set and is then fine-tuned on the target training data set for a fixed number of training iterations using the limited-memory Broyden-Fletcher-Goldfarb-Shanno optimizer with a learning rate decay. We demonstrate that the proposed method achieves superior predictive performance on various chromatographic systems compared with that of the existing transfer learning methods, especially when only a small training data set is available for use. A potential avenue for future research is to leverage multiple small training data sets from different chromatographic systems to further enhance the generalization performance.

RT-Ensemble Pred: A tool for retention time prediction of metabolites on different LC-MS systems

Liquid chromatography-mass spectrometry (LC-MS) could provide a large amount of information to assist in metabolites identification. Different liquid chromatographic methods (CMs) could produce different retention times to the same metabolite. To predict the retention time of local dataset by online datasets has become a trend, but the datasets downloaded from different databases were differences in quantity levels. And the imbalanced data could produce bad influence in model prediction. Thus, based on quantitative structure-retention relationships (QSRRs), an ensemble model, named RT-Ensemble Pred, has been successfully built to predict retention time of different LC-MS systems in this study. A total of 76, 807 metabolites (76, 909 retention times) have been collected across 9 CMs, and 19 natural products and 1 antifungal drug (20 retention times) have been collected to test the model applicability. An ensemble sampling was applied for the preprocessing procedure to solve the problem of imbalanced data. Based on the ensemble sampling, RT-Ensemble Pred could better utilize online datasets for the prediction of retention time. RT-Ensemble Pred was built based on the online datasets and tested by local dataset. The predictive accuracy of RT-Ensemble Pred was higher than the models without any sampling methods. The results showed that RT-Ensemble Pred could predict the metabolites which was not included in the database and the metabolites which were from new CMs. It could also be used for the prediction of other compounds beside metabolites. Furthermore, a tool of RT-Ensemble Pred was packed and can be freely downloaded at https://gitlab.com/mikic93/rt-ensemble-pred. It provides convenience for the users who need to predict the retention time of metabolites.

Metabolomics-centered mining of plant metabolic diversity and function: Past decade and future perspectives

Plants are natural experts in organic synthesis, being able to generate large numbers of specific metabolites with widely varying structures that help them adapt to variable survival challenges. Metabolomics is a research discipline that integrates the capabilities of several types of research including analytical chemistry, statistics, and biochemistry. Its ongoing development provides strategies for gaining a systematic understanding of quantitative changes in the levels of metabolites. Metabolomics is usually performed by targeting either a specific cell, a specific tissue, or the entire organism. Considerable advances in science and technology over the last three decades have propelled us into the era of multi-omics, in which metabolomics, despite at an earlier developmental stage than genomics, transcriptomics, and proteomics, offers the distinct advantage of studying the cellular entities that have the greatest influence on end phenotype. Here, we summarize the state of the art of metabolite detection and identification, and illustrate these techniques with four case study applications: (i) comparing metabolite composition within and between species, (ii) assessing spatio-temporal metabolic changes during plant development, (iii) mining characteristic metabolites of plants in different ecological environments and upon exposure to various stresses, and (iv) assessing the performance of metabolomics as a means of functional gene identification , metabolic pathway elucidation, and metabolomics-assisted breeding through analyzing plant populations with diverse genetic variations. In addition, we highlight the prominent contributions of joint analyses of plant metabolomics and other omics datasets, including those from genomics, transcriptomics, proteomics, epigenomics, phenomics, microbiomes, and ion-omics studies. Finally, we discuss future directions and challenges exploiting metabolomics-centered approaches in understanding plant metabolic diversity.

Good practices and recommendations for using and benchmarking computational metabolomics metabolite annotation tools

BACKGROUND

Untargeted metabolomics approaches based on mass spectrometry obtain comprehensive profiles of complex biological samples. However, on average only 10% of the molecules can be annotated. This low annotation rate hampers biochemical interpretation and effective comparison of metabolomics studies. Furthermore, de novo structural characterization of mass spectral data remains a complicated and time-intensive process. Recently, the field of computational metabolomics has gained traction and novel methods have started to enable large-scale and reliable metabolite annotation. Molecular networking and machine learning-based in-silico annotation tools have been shown to greatly assist metabolite characterization in diverse fields such as clinical metabolomics and natural product discovery.

AIM OF REVIEW

We highlight recent advances in computational metabolite annotation workflows with a special focus on their evaluation and comparison with other tools. Whilst the progress is substantial and promising, we also argue that inconsistencies in benchmarking different tools hamper users from selecting the most appropriate and promising method for their research. We summarize benchmarking strategies of the different tools and outline several recommendations for benchmarking and comparing novel tools.

KEY SCIENTIFIC CONCEPTS OF REVIEW

This review focuses on recent advances in mass spectral library-based and machine learning-supported metabolite annotation workflows. We discuss large-scale library matching and analogue search, the current bloom of mass spectral similarity scores, and how molecular networking has changed the field. In addition, the potentials and challenges of machine learning-supported metabolite annotation workflows are highlighted. Overall, recent developments in computational metabolomics have started to fundamentally change metabolomics workflows, and we expect that as a community we will be able to overcome current method performance ambiguities and annotation bottlenecks.

Contribution of allergy in the acquisition of uncontrolled severe asthma

Asthma is a multifactorial, heterogeneous disease that has a challenging management. It can be divided in non-allergic and allergic (usually associated with house dust mites (HDM) sensitization). There are several treatments options for asthma (corticosteroids, bronchodilators, antileukotrienes, anticholinergics,…); however, there is a subset of patients that do not respond to any of the treatments, who can display either a T2 or a non-T2 phenotype. A deeper understanding of the differential mechanisms underlying each phenotype will help to decipher the contribution of allergy to the acquisition of this uncontrolled severe phenotype. Here, we aim to elucidate the biological pathways associated to allergy in the uncontrolled severe asthmatic phenotype. To do so, twenty-three severe uncontrolled asthmatic patients both with and without HDM-allergy were recruited from Hospital Universitario de Gran Canaria Dr. Negrin. A metabolomic fingerprint was obtained through liquid chromatography coupled to mass spectrometry, and identified metabolites were associated with their pathways. 9/23 patients had uncontrolled HDM-allergic asthma (UCA), whereas 14 had uncontrolled, non-allergic asthma (UCNA). 7/14 (50%) of the UCNA patients had Aspirin Exacerbated Respiratory Disease. There were no significant differences regarding gender or body mass index; but there were significant differences in age and onset age, which were higher in UCNA patients; and in total IgE, which was higher in UCA. The metabolic fingerprint revealed that 103 features were significantly different between UCNA and UCA (p < 0.05), with 97 being increased in UCA and 6 being decreased. We identified lysophosphocholines (LPC) 18:2, 18:3 and 20:4 (increased in UCA patients); and deoxycholic acid and palmitoleoylcarnitine (decreased in UCA). These metabolites were related with a higher activation of phospholipase A2 (PLA2) and other phospholipid metabolism pathways. Our results show that allergy induces the activation of specific inflammatory pathways, such as the PLA2 pathway, which supports its role in the development of an uncontrolled asthma phenotype. There are also clinical differences, such as higher levels of IgE and earlier onset ages for the allergic asthmatic group, as expected. These results provide evidences to better understand the contribution of allergy to the establishment of a severe uncontrolled phenotype.