Quantitative Structure Retention Relationship (QSRR) Modelling for Analytes’ Retention Prediction in LC-HRMS by Applying Different Machine Learning Algorithms and Evaluating Their Performance

Artificial Intelligence in Metabolomics: A Current Review

Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.

Machine learning models and performance dependency on 2D chemical descriptor space for retention time prediction of pharmaceuticals

The predictive modeling of liquid chromatography methods can be an invaluable asset, potentially saving countless hours of labor while also reducing solvent consumption and waste. Tasks such as physicochemical screening and preliminary method screening systems where large amounts of chromatography data are collected from fast and routine operations are particularly well suited for both leveraging large datasets and benefiting from predictive models. Therefore, the generation of predictive models for retention time is an active area of development. However, for these predictive models to gain acceptance, researchers first must have confidence in model performance and the computational cost of building them should be minimal. In this study, a simple and cost-effective workflow for the development of machine learning models to predict retention time using only Molecular Operating Environment 2D descriptors as input for support vector regression is developed. Furthermore, we investigated the relative performance of models based on molecular descriptor space by utilizing uniform manifold approximation and projection and clustering with Gaussian mixture models to identify chemically distinct clusters. Results outlined herein demonstrate that local models trained on clusters in chemical space perform equivalently when compared to models trained on all data. Through 10-fold cross-validation on a comprehensive set containing 67,950 of our company's proprietary analytes, these models achieved coefficients of determination of 0.84 and 3 % error in terms of retention time. This promising statistical significance is found to translate from cross-validation to prospective prediction on an external test set of pharmaceutically relevant analytes. The observed equivalency of global and local modeling of large datasets is retained with METLIN's SMRT dataset, thereby confirming the wider applicability of the developed machine learning workflows for global models.

Critical review on in silico methods for structural annotation of chemicals detected with LC/HRMS non-targeted screening

Non-targeted screening with liquid chromatography coupled to high-resolution mass spectrometry (LC/HRMS) is increasingly leveraging in silico methods, including machine learning, to obtain candidate structures for structural annotation of LC/HRMS features and their further prioritization. Candidate structures are commonly retrieved based on the tandem mass spectral information either from spectral or structural databases; however, the vast majority of the detected LC/HRMS features remain unannotated, constituting what we refer to as a part of the unknown chemical space. Recently, the exploration of this chemical space has become accessible through generative models. Furthermore, the evaluation of the candidate structures benefits from the complementary empirical analytical information such as retention time, collision cross section values, and ionization type. In this critical review, we provide an overview of the current approaches for retrieving and prioritizing candidate structures. These approaches come with their own set of advantages and limitations, as we showcase in the example of structural annotation of ten known and ten unknown LC/HRMS features. We emphasize that these limitations stem from both experimental and computational considerations. Finally, we highlight three key considerations for the future development of in silico methods.

Estimation of passive gastrointestinal absorption of new dual DNA gyrase and topoisomerase IV inhibitors using PAMPA and biopartitioning micellar chromatography and quantitative structure-retention relationship analysis

DNA gyrase and topoisomerase IV play significant role in maintaining the correct structure of DNA during replication and they have been identified as validated targets in antibacterial drug discovery. Inadequate pharmacokinetic properties are responsible for many failures during drug discovery and their estimation in the early phase of this process maximizes the chance of getting useful drug candidates. Passive gastrointestinal absorption of a selected group of thirteen dual DNA gyrase and topoisomerase IV inhibitors was estimated using two in vitro tests - parallel artificial membrane permeability assay (PAMPA) and biopartitioning micellar chromatography (BMC). Due to good correlation between obtained results, passive gastrointestinal absorption of remaining ten compounds was estimated using only BMC. With this experimental setup, it was possible to identify compounds with high values of retention factors (k) and highest expected passive gastrointestinal absorption, and compounds with low values of k for which low passive gastrointestinal absorption is predicted. Quantitative structure-retention relationship (QSRR) modelling was performed by creating multiple linear regression (MLR), partial least squares (PLS) and support vector machines (SVM) models. Descriptors with the highest influence on retention factor were identified and their interpretation can be used for the design of new compounds with improved passive gastrointestinal absorption.

Enhancing compound confidence in suspect and non-target screening through machine learning-based retention time prediction

The retention time (RT) of contaminants of emerging concern (CECs) in liquid chromatography-high-resolution mass spectrometry (LC-HRMS) is crucial for database matching in non-targeted screening (NTS) analysis. In this study, we developed a machine learning (ML) model to predict RTs of CECs in NTS analysis. Using 1051 CEC standards, we evaluated Random Forest (RF), XGBoost, Support Vector Regression (SVR), and Artificial Neural Network (ANN) with molecular fingerprints and chemical descriptors to establish an optimal model. The SVR model utilizing chemical descriptors resulted in good predictive capacity with R2ext = 0.850 and r2 = 0.925. The model was further validated through laboratory NTS compound characterization. When applied to examine CEC occurrence in a large wastewater treatment plant, we identified 40 level S1 CECs (confirmed structure by reference standard) and 234 level S2 compounds (probable structure by library spectrum match). The model predicted RTs for level S2 compounds, leading to the classification of 153 level S2 compounds with high confidence (ΔRT <2 min). The model served as a robust filtering mechanism within the analytical framework. This study emphasizes the importance of predicted RTs in NTS analysis and highlights the potential of prediction models. Our research introduces a workflow that enhances NTS analysis by utilizing RT prediction models to determine compound confidence levels.

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.

An improved workflow for the development of MS-compatible liquid chromatography assay purity and purification methods by using automated LC Screening instrumentation and in silico modeling

The development of liquid chromatography UV and mass spectrometry (LC-UV-MS) assays in pharmaceutical analysis is pivotal to improve quality control by providing critical information about drug purity, stability, and presence and identity of byproducts and impurities. Analytical method development of these assays is time-consuming, which often causes it to become a bottle neck in drug development and poses a challenge for process chemists to quickly improve the chemistry. In this study, a systematic and efficient workflow was designed to develop purity assay and purification methods for a wide range of compounds including peptides, proteins, and small molecules with MS-compatible mobile phases (MP) by using automated LC screening instrumentation and in silico modeling tools. Initial LC MPs and chromatography column screening experiments enabled quick identification of conditions which provided the best resolution in the vicinity of the target compounds, which is further optimized using computer-assisted modeling (LC Simulator from ACD/Labs). The experimental retention times were in good agreement with the predicted retention times from LC Simulator (ΔtR < 7%). This workflow presents a practical workflow to significantly expedite the time needed to develop optimized LC-UV-MS methods, allowing for a facile, automatic method optimization and reducing the amount of manual work involved in developing new methods during drug development.

Structure Based Machine Learning Prediction of Retention Times for LC Method Development of Pharmaceuticals

PURPOSE

Significant resources are spent on developing robust liquid chromatography (LC) methods with optimum conditions for all project in the pipeline. Although, data-driven computer assisted modelling has been implemented to shorten the method development timelines, these modelling approaches require project-specific screening data to model retention time (RT) as function of method parameters. Sometimes method re-development is required, leading to additional investments and redundant laboratory work. Cheminformatics techniques have been successfully used to predict the RT of metabolites & other component mixtures for similar use cases. Here we will show that these techniques can be used to model structurally diverse molecules and predictions of these models trained on multiple LC conditions can be used for downstream data-driven modelling.

METHODS

The Molecular Operating Environment (MOE) was used to calculate over 800 descriptors using the strucutres of the analytes. These descriptors were used to model the RT of the analytes under four chromatographic conditions. These models were then used to create data-driven models using LC-SIM.

RESULTS

A structural-based Random Forest (RF) model outperformed other techniques in cross-validation studies and predicted the RTs of a randomized test set with a median percentage error less than 4% for all LC conditions. RTs predicted by this structure-based model were used to fit a data-driven model that identifies optimum LC conditions without any additional experimental work.

CONCLUSIONS

These results show that small training sets yield pharmaceutically relevant models when used in a combination of structure-based and data-driven model.

Predicting Retention Time in Unified-Hydrophilic-Interaction/Anion-Exchange Liquid Chromatography High-Resolution Tandem Mass Spectrometry (Unified-HILIC/AEX/HRMS/MS) for Comprehensive Structural Annotation of Polar Metabolome

The accuracy of the structural annotation of unidentified peaks obtained in metabolomic analysis using liquid chromatography/tandem mass spectrometry (LC/MS/MS) can be enhanced using retention time (RT) information as well as precursor and product ions. Unified-hydrophilic-interaction/anion-exchange liquid chromatography high-resolution tandem mass spectrometry (unified-HILIC/AEX/HRMS/MS) has been recently developed as an innovative method ideal for nontargeted polar metabolomics. However, the RT prediction for unified-HILIC/AEX has not been developed because of the complex separation mechanism characterized by the continuous transition of the separation modes from HILIC to AEX. In this study, we propose an RT prediction model of unified-HILIC/AEX/HRMS/MS, which enables the comprehensive structural annotation of polar metabolites. With training data for 203 polar metabolites, we ranked the feature importance using a random forest among 12,420 molecular descriptors (MDs) and constructed an RT prediction model with 26 selected MDs. The accuracy of the RT model was evaluated using test data for 51 polar metabolites, and 86.3% of the ΔRTs (difference between measured and predicted RTs) were within ±1.50 min, with a mean absolute error of 0.80 min, indicating high RT prediction accuracy. Nontargeted metabolomic data from the NIST SRM 1950-Metabolites in frozen human plasma were analyzed using the developed RT model and in silico MS/MS prediction, resulting in a successful structural estimation of 216 polar metabolites, in addition to the 62 identified based on standards. The proposed model can help accelerate the structural annotation of unknown hydrophilic metabolites, which is a key issue in metabolomic research.

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.

Prediction of a Large-Scale Database of Collision Cross-Section and Retention Time Using Machine Learning to Reduce False Positive Annotations in Untargeted Metabolomics

Metabolite identification in untargeted metabolomics is complex, with the risk of false positive annotations. This work aims to use machine learning to successively predict the retention time (Rt) and the collision cross-section (CCS) of an open-access database to accelerate the interpretation of metabolomic results. Standards of metabolites were tested using liquid chromatography coupled with high-resolution mass spectrometry. In CCSBase and QSRR predictor machine learning models, experimental results were used to generate predicted CCS and Rt of the Human Metabolome Database. From 542 standards, 266 and 301 compounds were detected in positive and negative electrospray ionization mode, respectively, corresponding to 380 different metabolites. CCS and Rt were then predicted using machine learning tools for almost 114,000 metabolites. R² score of the linear regression between predicted and measured data achieved 0.938 and 0.898 for CCS and Rt, respectively, demonstrating the models' reliability. A CCS and Rt index filter of mean error ± 2 standard deviations could remove most misidentifications. Its application to data generated from a toxicology study on tobacco cigarettes reduced hits by 76%. Regarding the volume of data produced by metabolomics, the practical workflow provided allows for the implementation of valuable large-scale databases to improve the biological interpretation of metabolomics data.

Retention Time Prediction with Message-Passing Neural Networks

Retention time prediction, facilitated by advances in machine learning, has become a useful tool in untargeted LC-MS applications. State-of-the-art approaches include graph neural networks and 1D-convolutional neural networks that are trained on the METLIN small molecule retention time dataset (SMRT). These approaches demonstrate accurate predictions comparable with the experimental error for the training set. The weak point of retention time prediction approaches is the transfer of predictions to various systems. The accuracy of this step depends both on the method of mapping and on the accuracy of the general model trained on SMRT. Therefore, improvements to both parts of prediction workflows may lead to improved compound annotations. Here, we evaluate capabilities of message-passing neural networks (MPNN) that have demonstrated outstanding performance on many chemical tasks to accurately predict retention times. The model was initially trained on SMRT, providing mean and median absolute cross-validation errors of 32 and 16 s, respectively. The pretrained MPNN was further fine-tuned on five publicly available small reversed-phase retention sets in a transfer learning mode and demonstrated up to 30% improvement of prediction accuracy for these sets compared with the state-of-the-art methods. We demonstrated that filtering isomeric candidates by predicted retention with the thresholds obtained from ROC curves eliminates up to 50% of false identities.

Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial

Developing risk assessment tools for CAD prediction remains challenging nowadays. We developed an ML predictive algorithm based on metabolic and clinical data for determining the severity of CAD, as assessed via the SYNTAX score. Analytical methods were developed to determine serum blood levels of specific ceramides, acyl-carnitines, fatty acids, and proteins such as galectin-3, adiponectin, and APOB/APOA1 ratio. Patients were grouped into: obstructive CAD (SS > 0) and non-obstructive CAD (SS = 0). A risk prediction algorithm (boosted ensemble algorithm XGBoost) was developed by combining clinical characteristics with established and novel biomarkers to identify patients at high risk for complex CAD. The study population comprised 958 patients (CorLipid trial (NCT04580173)), with no prior CAD, who underwent coronary angiography. Of them, 533 (55.6%) suffered ACS, 170 (17.7%) presented with NSTEMI, 222 (23.2%) with STEMI, and 141 (14.7%) with unstable angina. Of the total sample, 681 (71%) had obstructive CAD. The algorithm dataset was 73 biochemical parameters and metabolic biomarkers as well as anthropometric and medical history variables. The performance of the XGBoost algorithm had an AUC value of 0.725 (95% CI: 0.691−0.759). Thus, a ML model incorporating clinical features in addition to certain metabolic features can estimate the pre-test likelihood of obstructive CAD.

Strategies for structure elucidation of small molecules based on LC–MS/MS data from complex biological samples

LC–MS/MS is a major analytical platform for metabolomics, which has become a recent hotspot in the research fields of life and environmental sciences. By contrast, structure elucidation of small molecules based on LC–MS/MS data remains a major challenge in the chemical and biological interpretation of untargeted metabolomics datasets. In recent years, several strategies for structure elucidation using LC–MS/MS data from complex biological samples have been proposed, these strategies can be simply categorized into two types, one based on structure annotation of mass spectra and for the other on retention time prediction. These strategies have helped many scientists conduct research in metabolite-related fields and are indispensable for the development of future tools. Here, we summarized the characteristics of the current tools and strategies for structure elucidation of small molecules based on LC–MS/MS data, and further discussed the directions and perspectives to improve the power of the tools or strategies for structure elucidation.