Prediction of Chromatographic Retention Time in High-Resolution Anti-Doping Screening Data Using Artificial Neural Networks

Data-Driven Compound Identification in Atmospheric Mass Spectrometry

Aerosol particles found in the atmosphere affect the climate and worsen air quality. To mitigate these adverse impacts, aerosol particle formation and aerosol chemistry in the atmosphere need to be better mapped out and understood. Currently, mass spectrometry is the single most important analytical technique in atmospheric chemistry and is used to track and identify compounds and processes. Large amounts of data are collected in each measurement of current time-of-flight and orbitrap mass spectrometers using modern rapid data acquisition practices. However, compound identification remains a major bottleneck during data analysis due to lacking reference libraries and analysis tools. Data-driven compound identification approaches could alleviate the problem, yet remain rare to non-existent in atmospheric science. In this perspective, the authors review the current state of data-driven compound identification with mass spectrometry in atmospheric science and discuss current challenges and possible future steps toward a digital era for atmospheric mass spectrometry.

Machine learning liquid chromatography retention time prediction model augments the dansylation strategy for metabolite analysis of urine samples

Herein, a standalone software equipped with a graphic user interface (GUI) is developed to predict liquid chromatography mass spectrometry (LC-MS) retention times (RTs) of dansylated metabolites. Dansylation metabolomics strategy developed by Li et al. narrows down a vast chemical space of metabolites into the metabolites containing amines and phenolic hydroxyls. Combined with differential isotope labeling, e.g., 12C-reagent labeled individual samples spiked with a 13C-reagent labeled reference or pooled sample, LC-MS analysis of the dansylated samples enables accurate relative quantification of all labeled metabolites. Herein, the LC-RTs for dansylated metabolites are predicted using an artificial neural network (ANN) machine-learning model. For the ANN modeling, 315 dansylated urine metabolites obtained from the DnsID database are used. The ANN LC-RT prediction model was reliable, with a mean absolute deviation of 0.74 min for the 30 min LC run. In the RT model, a deviation of more than 2 min was observed in only 3.2% of the total 315 metabolites, while a deviation of 1.5 min or more was observed in 11% of the metabolites. Furthermore, it was found that the LC-RT prediction was also reliable even for metabolites containing both amine and phenolic functional groups that can undergo dansylation on either one of the two functional groups, resulting in the generation of two isomeric forms. This RT-prediction model is embedded into a user-friendly GUI and can be used for identifying nontargeted dansylated metabolites with unknown RTs, along with accurate mass measurements. Furthermore, it is demonstrated that the developed software can help identify metabolites from a urine sample of an anonymous healthy pregnant woman.

Developments in high-resolution mass spectrometric analyses of new psychoactive substances

The proliferation of new psychoactive substances (NPS) has necessitated the development and improvement of current practices for the detection and identification of known NPS and newly emerging derivatives. High-resolution mass spectrometry (HRMS) is quickly becoming the industry standard for these analyses due to its ability to be operated in data-independent acquisition (DIA) modes, allowing for the collection of large amounts of data and enabling retrospective data interrogation as new information becomes available. The increasing popularity of HRMS has also prompted the exploration of new ways to screen for NPS, including broad-spectrum wastewater analysis to identify usage trends in the community and metabolomic-based approaches to examine the effects of drugs of abuse on endogenous compounds. In this paper, the novel applications of HRMS techniques to the analysis of NPS is reviewed. In particular, the development of innovative data analysis and interpretation approaches is discussed, including the application of machine learning and molecular networking to toxicological analyses.

Development of a single retention time prediction model integrating multiple liquid chromatography systems: Application to new psychoactive substances

Database-driven suspect screening has proven to be a useful tool to detect new psychoactive substances (NPS) outside the scope of targeted screening; however, the lack of retention times specific to a liquid chromatography (LC) system can result in a large number of false positives. A singular stream-lined, quantitative structure-retention relationship (QSRR)-based retention time prediction model integrating multiple LC systems with different elution conditions is presented using retention time data (n = 1281) from the online crowd-sourced database, HighResNPS. Modelling was performed using an artificial neural network (ANN), specifically a multi-layer perceptron (MLP), using four molecular descriptors and one-hot encoding of categorical labels. Evaluation of test set predictions (n = 193) yielded coefficient of determination (R²) and mean absolute error (MAE) values of 0.942 and 0.583 min, respectively. The model successfully differentiated between LC systems, predicting 54%, 81% and 97% of the test set within ±0.5, ±1 and ±2 min, respectively. Additionally, retention times for an analyte not previously observed by the model were predicted within ±1 min for each LC system. The developed model can be used to predict retention times for all analytes on HighResNPS for each participating laboratory's LC system to further support suspect screening.

Suspect screening of environmental contaminants by UHPLC-HRMS and transposable Quantitative Structure-Retention Relationship modelling

A Quantitative Structure-Retention Relationship (QSRR) model is proposed and aims at increasing the confidence level associated to the identification of organic contaminants by Ultra-High Performance Liquid Chromatography hyphenated to High Resolution Mass Spectrometry (UHPLC-HRMS) in environmental samples under a suspect screening approach. The model was built from a selection of 8 easily accessible physicochemical descriptors, and was validated from a set of 274 organic compounds commonly found in environmental samples. The proposed predictive figure approach is based on the mobile phase composition at solute elution (expressed as % acetonitrile), that has the major advantage of making the model reusable by other laboratories, since the elution composition is independent of both the column geometry and the UHPLC-system. The model quality was assessed and was altered neither by the columns from different lots, nor by the complex matrices of environmental water samples. Then, the solute retention of any organic compound present in water samples is expected to be predicted within ± 14.3% acetonitrile by our model. Solute retention can therefore be used as a supplementary tool for the identification of environmental contaminants by UHPLC-HRMS, in addition to mass spectrometry data already used in the suspect screening approach.

Benchmarking of the quantification approaches for the non-targeted screening of micropollutants and their transformation products in groundwater

A wide range of micropollutants can be monitored with non-targeted screening; however, the quantification of the newly discovered compounds is challenging. Transformation products (TPs) are especially problematic because analytical standards are rarely available. Here, we compared three quantification approaches for non-target compounds that do not require the availability of analytical standards. The comparison is based on a unique set of concentration data for 341 compounds, mainly pesticides, pharmaceuticals, and their TPs in 31 groundwater samples from Switzerland. The best accuracy was observed with the predicted ionization efficiency-based quantification, the mean error of concentration prediction for the groundwater samples was a factor of 1.8, and all of the 74 micropollutants detected in the groundwater were quantified with an error less than a factor of 10. The quantification of TPs with the parent compounds had significantly lower accuracy (mean error of a factor of 3.8) and could only be applied to a fraction of the detected compounds, while the mean performance (mean error of a factor of 3.2) of the closest eluting standard approach was similar to the parent compound approach.

Rapid direct analysis of river water and machine learning assisted suspect screening of emerging contaminants in passive sampler extracts

A novel and rapid approach to characterise the occurrence of contaminants of emerging concern (CECs) in river water is presented using multi-residue targeted analysis and machine learning-assisted in silico suspect screening of passive sampler extracts. Passive samplers (Chemcatcher®) configured with hydrophilic-lipophilic balanced (HLB) sorbents were deployed in the Central London region of the tidal River Thames (UK) catchment in winter and summer campaigns in 2018 and 2019. Extracts were analysed by; (a) a rapid 5.5 min direct injection targeted liquid chromatography-tandem mass spectrometry (LC-MS/MS) method for 164 CECs and (b) a full-scan LC coupled to quadrupole time of flight mass spectrometry (QTOF-MS) method using data-independent acquisition over 15 min. From targeted analysis of grab water samples, a total of 33 pharmaceuticals, illicit drugs, drug metabolites, personal care products and pesticides (including several EU Watch-List chemicals) were identified, and mean concentrations determined at 40 ± 37 ng L^-1. For targeted analysis of passive sampler extracts, 65 unique compounds were detected with differences observed between summer and winter campaigns. For suspect screening, 59 additional compounds were shortlisted based on mass spectral database matching, followed by machine learning-assisted retention time prediction. Many of these included additional pharmaceuticals and pesticides, but also new metabolites and industrial chemicals. The novelty in this approach lies in the convenience of using passive samplers together with machine learning-assisted chemical analysis methods for rapid, time-integrated catchment monitoring of CECs.

Towards compound identification of synthetic opioids in nontargeted screening using machine learning techniques

The constant evolution of the illicit drug market makes the identification of unknown compounds problematic. Obtaining certified reference materials for a broad array of new analogues can be difficult and cost prohibitive. Machine learning provides a promising avenue to putatively identify a compound before confirmation against a standard. In this study, machine learning approaches were used to develop class prediction and retention time prediction models. The developed class prediction model used a naïve Bayes architecture to classify opioids as belonging to either the fentanyl analogues, AH series or U series, with an accuracy of 89.5%. The model was most accurate for the fentanyl analogues, most likely due to their greater number in the training data. This classification model can provide guidance to an analyst when determining a suspected structure. A retention time prediction model was also trained for a wide array of synthetic opioids. This model utilised Gaussian process regression to predict the retention time of analytes based on multiple generated molecular features with 79.7% of the samples predicted within ±0.1 min of their experimental retention time. Once the suspected structure of an unknown compound is determined, molecular features can be generated and input for the prediction model to compare with experimental retention time. The incorporation of machine learning prediction models into a compound identification workflow can assist putative identifications with greater confidence and ultimately save time and money in the purchase and/or production of superfluous certified reference materials.

Prediction of liquid chromatographic retention time using quantitative structure-retention relationships to assist non-targeted identification of unknown metabolites of phthalates in human urine with high-resolution mass spectrometry

The non-targeted analysis and identification of contaminant metabolites such as metabolites of phthalates and their alternatives in human biofluid samples constitutes a growing research field in human biomonitoring because of their importance as biomarkers of human exposure to the parent compounds. High-resolution mass spectrometry (HRMS) combined with high-performance liquid chromatography (HPLC) can provide fast separation and sensitive analysis using this application. However, the diversity of potential metabolites, especially isomers, in human samples, makes mass spectrometry-based structural identification very challenging, even with high-resolution and accurate mass. In this study, we present a retention time (t_R) prediction model based on quantitative structure-retention relationship (QSRR). This model can predict the retention time of a given structure of phthalates including isomers. Twenty-three molecular descriptors were used in the development of the multivariate linear regression QSRR model. The regression coefficient (R²) between predicted and experimental retention times of 26 training set compounds was 0.9912. The combination of the retention time prediction model with identification via accurate mass search and target MS/MS spectrum interpretation can enhance the identification confidence in the lack of reference standards. Two previously unreported phthalate metabolites were identified in human urine, using this model. The results of this study showed that the developed QSRR model could be a useful tool to predict the retention times of unknown metabolites of phthalates and their alternatives in future non-targeted screening analysis. The concentration of these two unknown compounds was also estimated using a quantitative structure-ion intensity relationship (QSIIR) model.

Recent applications of chemometrics in one- and two-dimensional chromatography

The proliferation of increasingly more sophisticated analytical separation systems, often incorporating increasingly more powerful detection techniques, such as high-resolution mass spectrometry, causes an urgent need for highly efficient data-analysis and optimization strategies. This is especially true for comprehensive two-dimensional chromatography applied to the separation of very complex samples. In this contribution, the requirement for chemometric tools is explained and the latest developments in approaches for (pre-)processing and analyzing data arising from one- and two-dimensional chromatography systems are reviewed. The final part of this review focuses on the application of chemometrics for method development and optimization.

Towards early monitoring of chemotherapy-induced drug resistance based on single cell metabolomics: Combining single-probe mass spectrometry with machine learning

Despite the presence of methods evaluating drug resistance during chemotherapies, techniques, which allow for monitoring the degree of drug resistance in early chemotherapeutic stage from single cells in their native microenvironment, are still absent. Herein, we report an analytical approach that combines single cell mass spectrometry (SCMS) based metabolomics with machine learning (ML) models to address the existing challenges. Metabolomic profiles of live cancer cells (HCT-116) with different levels (i.e., no, low, and high) of chemotherapy-induced drug resistance were measured using the Single-probe SCMS technique. A series of ML models, including random forest (RF), artificial neural network (ANN), and penalized logistic regression (LR), were constructed to predict the degrees of drug resistance of individual cells. A systematic comparison of performance was conducted among multiple models, and the method validation was carried out experimentally. Our results indicate that these ML models, especially the RF model constructed on the obtained SCMS datasets, can rapidly and accurately predict different degrees of drug resistance of live single cells. With such rapid and reliable assessment of drug resistance demonstrated at the single cell level, our method can be potentially employed to evaluate chemotherapeutic efficacy in the clinic.

Systematic Isolation and Structure Elucidation of Urinary Metabolites Optimized for the Analytical-Scale Molecular Profiling Laboratory

Annotation and identification of metabolite biomarkers is critical for their biological interpretation in metabolic phenotyping studies, presenting a significant bottleneck in the successful implementation of untargeted metabolomics. Here, a systematic multistep protocol was developed for the purification and de novo structural elucidation of urinary metabolites. The protocol is most suited for instances where structure elucidation and metabolite annotation are critical for the downstream biological interpretation of metabolic phenotyping studies. First, a bulk urine pool was desalted using ion-exchange resins enabling large-scale fractionation using precise iterations of analytical scale chromatography. Primary urine fractions were collected and assembled into a “fraction bank” suitable for long-term laboratory storage. Secondary and tertiary fractionations exploited differences in selectivity across a range of reversed-phase chemistries, achieving the purification of metabolites of interest yielding an amount of material suitable for chemical characterization. To exemplify the application of the systematic workflow in a diverse set of cases, four metabolites with a range of physicochemical properties were selected and purified from urine and subjected to chemical formula and structure elucidation by respective magnetic resonance mass spectrometry (MRMS) and NMR analyses. Their structures were fully assigned as tetrahydropentoxyline, indole-3-acetic-acid-O-glucuronide, p-cresol glucuronide, and pregnanediol-3-glucuronide. Unused effluent was collected, dried, and returned to the fraction bank, demonstrating the viability of the system for repeat use in metabolite annotation with a high degree of efficiency.

The role of analytical chemistry in exposure science: Focus on the aquatic environment

Exposure science, in its broadest sense, studies the interactions between stressors (chemical, biological, and physical agents) and receptors (e.g. humans and other living organisms, and non-living items like buildings), together with the associated pathways and processes potentially leading to negative effects on human health and the environment. The aquatic environment may contain thousands of compounds, many of them still unknown, that can pose a risk to ecosystems and human health. Due to the unquestionable importance of the aquatic environment, one of the main challenges in the field of exposure science is the comprehensive characterization and evaluation of complex environmental mixtures beyond the classical/priority contaminants to new emerging contaminants. The role of advanced analytical chemistry to identify and quantify potential chemical risks, that might cause adverse effects to the aquatic environment, is essential. In this paper, we present the strategies and tools that analytical chemistry has nowadays, focused on chromatography hyphenated to (high-resolution) mass spectrometry because of its relevance in this field. Key issues, such as the application of effect direct analysis to reduce the complexity of the sample, the investigation of the huge number of transformation/degradation products that may be present in the aquatic environment, the analysis of urban wastewater as a source of valuable information on our lifestyle and substances we consumed and/or are exposed to, or the monitoring of drinking water, are discussed in this article. The trends and perspectives for the next few years are also highlighted, when it is expected that new developments and tools will allow a better knowledge of chemical composition in the aquatic environment. This will help regulatory authorities to protect water bodies and to advance towards improved regulations that enable practical and efficient abatements for environmental and public health protection.

Development and application of retention time prediction models in the suspect and non-target screening of emerging contaminants

Hydrophilic interaction liquid chromatography (HILIC) and reversed phase LC (RPLC) coupled to high resolution mass spectrometry (HRMS) are widely used for the identification of suspects and unknown compounds in the environment. For the identification of unknowns, apart from mass accuracy and isotopic fitting, retention time (t_R) and MS/MS spectra evaluation is required. In this context, a novel comprehensive workflow was developed to study the t_R behavior of large groups of emerging contaminants using Quantitative Structure-Retention Relationships (QSRR). 682 compounds were analyzed by HILIC-HRMS in positive Electrospray Ionization mode (ESI). Moreover, an extensive dataset was built for RPLC-HRMS including 1830 and 308 compounds for positive and negative ESI, respectively. Support Vector Machines (SVM) was used to model the t_R data. The applicability domains of the models were studied by Monte Carlo Sampling (MCS) methods. The MCS method was also used to calculate the acceptable error windows for the predicted t_R from various LC conditions. This paper provides validated models for predicting t_R in HILIC/RPLC-HRMS platforms to facilitate identification of new emerging contaminants by suspect and non-target HRMS screening, and were applied for the identification of transformation products (TPs) of emerging contaminants and biocides in wastewater and sludge.

A review of the pharmaceutical exposome in aquatic fauna

Pharmaceuticals have been considered 'contaminants of emerging concern' for more than 20 years. In that time, many laboratory studies have sought to identify hazard and assess risk in the aquatic environment, whilst field studies have searched for targeted candidates and occurrence trends using advanced analytical techniques. However, a lack of a systematic approach to the detection and quantification of pharmaceuticals has provided a fragmented literature of serendipitous approaches. Evaluation of the extent of the risk for the plethora of human and veterinary pharmaceuticals available requires the reliable measurement of trace levels of contaminants across different environmental compartments (water, sediment, biota - of which biota has been largely neglected). The focus on pharmaceutical concentrations in surface waters and other exposure media have therefore limited both the characterisation of the exposome in aquatic wildlife and the understanding of cause and effect relationships. Here, we compile the current analytical approaches and available occurrence and accumulation data in biota to review the current state of research in the field. Our analysis provides evidence in support of the 'Matthew Effect' and raises critical questions about the use of targeted analyte lists for biomonitoring. We provide six recommendations to stimulate and improve future research avenues.

Mass spectrometric strategies for the investigation of biomarkers of illicit drug use in wastewater

The analysis of illicit drugs in urban wastewater is the basis of wastewater-based epidemiology (WBE), and has received much scientific attention because the concentrations measured can be used as a new non-intrusive tool to provide evidence-based and real-time estimates of community-wide drug consumption. Moreover, WBE allows monitoring patterns and spatial and temporal trends of drug use. Although information and expertise from other disciplines is required to refine and effectively apply WBE, analytical chemistry is the fundamental driver in this field. The use of advanced analytical techniques, commonly based on combined chromatography-mass spectrometry, is mandatory because the very low analyte concentration and the complexity of samples (raw wastewater) make quantification and identification/confirmation of illicit drug biomarkers (IDBs) troublesome. We review the most-recent literature available (mostly from the last 5 years) on the determination of IDBs in wastewater with particular emphasis on the different analytical strategies applied. The predominance of liquid chromatography coupled to tandem mass spectrometry to quantify target IDBs and the essence to produce reliable and comparable results is illustrated. Accordingly, the importance to perform inter-laboratory exercises and the need to analyze appropriate quality controls in each sample sequence is highlighted. Other crucial steps in WBE, such as sample collection and sample pre-treatment, are briefly and carefully discussed. The article further focuses on the potential of high-resolution mass spectrometry. Different approaches for target and non-target analysis are discussed, and the interest to perform experiments under laboratory-controlled conditions, as a complementary tool to investigate related compounds (e.g., minor metabolites and/or transformation products in wastewater) is treated. The article ends up with the trends and future perspectives in this field from the authors' point of view. © 2016 Wiley Periodicals, Inc. Mass Spec Rev 37:258-280, 2018.

A comparison of three liquid chromatography (LC) retention time prediction models

High-resolution mass spectrometry (HRMS) data has revolutionized the identification of environmental contaminants through non-targeted analysis (NTA). However, chemical identification remains challenging due to the vast number of unknown molecular features typically observed in environmental samples. Advanced data processing techniques are required to improve chemical identification workflows. The ideal workflow brings together a variety of data and tools to increase the certainty of identification. One such tool is chromatographic retention time (RT) prediction, which can be used to reduce the number of possible suspect chemicals within an observed RT window. This paper compares the relative predictive ability and applicability to NTA workflows of three RT prediction models: (1) a logP (octanol-water partition coefficient)-based model using EPI Suite™ logP predictions; (2) a commercially available ACD/ChromGenius model; and, (3) a newly developed Quantitative Structure Retention Relationship model called OPERA-RT. Models were developed using the same training set of 78 compounds with experimental RT data and evaluated for external predictivity on an identical test set of 19 compounds. Both the ACD/ChromGenius and OPERA-RT models outperformed the EPI Suite™ logP-based RT model (R² = 0.81-0.92, 0.86-0.83, 0.66-0.69 for training-test sets, respectively). Further, both OPERA-RT and ACD/ChromGenius predicted 95% of RTs within a ± 15% chromatographic time window of experimental RTs. Based on these results, we simulated an NTA workflow with a ten-fold larger list of candidate structures generated for formulae of the known test set chemicals using the U.S. EPA's CompTox Chemistry Dashboard (https://comptox.epa.gov/dashboard), RTs for all candidates were predicted using both ACD/ChromGenius and OPERA-RT, and RT screening windows were assessed for their ability to filter out unlikely candidate chemicals and enhance potential identification. Compared to ACD/ChromGenius, OPERA-RT screened out a greater percentage of candidate structures within a 3-min RT window (60% vs. 40%) but retained fewer of the known chemicals (42% vs. 83%). By several metrics, the OPERA-RT model, generated as a proof-of-concept using a limited set of open source data, performed as well as the commercial tool ACD/ChromGenius when constrained to the same small training and test sets. As the availability of RT data increases, we expect the OPERA-RT model's predictive ability will increase.

Facilitating high resolution mass spectrometry data processing for screening of environmental water samples: An evaluation of two deconvolution tools

A screening approach was applied to influent and effluent wastewater samples. After injection in a LC-LTQ-Orbitrap, data analysis was performed using two deconvolution tools, MsXelerator (modules MPeaks and MS Compare) and Sieve 2.1. The outputs were searched incorporating an in-house database of >200 pharmaceuticals and illicit drugs or ChemSpider. This hidden target screening approach led to the detection of numerous compounds including the illicit drug cocaine and its metabolite benzoylecgonine and the pharmaceuticals carbamazepine, gemfibrozil and losartan. The compounds found using both approaches were combined, and isotopic pattern and retention time prediction were used to filter out false positives. The remaining potential positives were reanalysed in MS/MS mode and their product ions were compared with literature and/or mass spectral libraries. The inclusion of the chemical database ChemSpider led to the tentative identification of several metabolites, including paraxanthine, theobromine, theophylline and carboxylosartan, as well as the pharmaceutical phenazone. The first three of these compounds are isomers and they were subsequently distinguished based on their product ions and predicted retention times. This work has shown that the use deconvolution tools facilitates non-target screening and enables the identification of a higher number of compounds.

The First Attempt at Non-Linear in Silico Prediction of Sampling Rates for Polar Organic Chemical Integrative Samplers (POCIS)

Modeling and prediction of polar organic chemical integrative sampler (POCIS) sampling rates (Rs) for 73 compounds using artificial neural networks (ANNs) is presented for the first time. Two models were constructed: the first was developed ab initio using a genetic algorithm (GSD-model) to shortlist 24 descriptors covering constitutional, topological, geometrical and physicochemical properties and the second model was adapted for Rs prediction from a previous chromatographic retention model (RTD-model). Mechanistic evaluation of descriptors showed that models did not require comprehensive a priori information to predict Rs. Average predicted errors for the verification and blind test sets were 0.03 ± 0.02 L d(-1) (RTD-model) and 0.03 ± 0.03 L d(-1) (GSD-model) relative to experimentally determined Rs. Prediction variability in replicated models was the same or less than for measured Rs. Networks were externally validated using a measured Rs data set of six benzodiazepines. The RTD-model performed best in comparison to the GSD-model for these compounds (average absolute errors of 0.0145 ± 0.008 L d(-1) and 0.0437 ± 0.02 L d(-1), respectively). Improvements to generalizability of modeling approaches will be reliant on the need for standardized guidelines for Rs measurement. The use of in silico tools for Rs determination represents a more economical approach than laboratory calibrations.

Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations

With the proliferation of multivariate calibration methods based on artificial neural networks, expressions for the estimation of figures of merit such as sensitivity, prediction uncertainty, and detection limit are urgently needed. This would bring nonlinear multivariate calibration methodologies to the same status as the linear counterparts in terms of comparability. Currently only the average prediction error or the ratio of performance to deviation for a test sample set is employed to characterize and promote neural network calibrations. It is clear that additional information is required. We report for the first time expressions that easily allow one to compute three relevant figures: (1) the sensitivity, which turns out to be sample-dependent, as expected, (2) the prediction uncertainty, and (3) the detection limit. The approach resembles that employed for linear multivariate calibration, i.e., partial least-squares regression, specifically adapted to neural network calibration scenarios. As usual, both simulated and real (near-infrared) spectral data sets serve to illustrate the proposal.

Five-descriptor model to predict the chromatographic sequence of natural compounds

Despite the recent introduction of mass detection techniques, ultraviolet detection is still widely applied in the field of the chromatographic analysis of natural medicines. Here, a neural network cascade model consisting of nine small artificial neural network units was innovatively developed to predict the chromatographic sequence of natural compounds by integrating five molecular descriptors as the input. A total of 117 compounds of known structure were collected for model building. The order of appearance of each compound was determined in gradient chromatography. Strong linear correlation was found between the predicted and actual chromatographic position orders (Spearman's rho = 0.883, p < 0.0001). Application of the model to the external validation set of nine natural compounds was shown to dramatically increase the prediction accuracy of the real chromatographic order of multiple compounds. A case study shows that chromatographic sequence prediction based on a neural network cascade facilitated compound identification in the chromatographic fingerprint of Radix Salvia miltiorrhiza. For natural medicines of known compound composition, our method provides a feasible means for identifying the constituents of interest when only ultraviolet detection is available.

MetFrag relaunched: incorporating strategies beyond in silico fragmentation

BACKGROUND

The in silico fragmenter MetFrag, launched in 2010, was one of the first approaches combining compound database searching and fragmentation prediction for small molecule identification from tandem mass spectrometry data. Since then many new approaches have evolved, as has MetFrag itself. This article details the latest developments to MetFrag and its use in small molecule identification since the original publication.

RESULTS

MetFrag has gone through algorithmic and scoring refinements. New features include the retrieval of reference, data source and patent information via ChemSpider and PubChem web services, as well as InChIKey filtering to reduce candidate redundancy due to stereoisomerism. Candidates can be filtered or scored differently based on criteria like occurence of certain elements and/or substructures prior to fragmentation, or presence in so-called "suspect lists". Retention time information can now be calculated either within MetFrag with a sufficient amount of user-provided retention times, or incorporated separately as "user-defined scores" to be included in candidate ranking. The changes to MetFrag were evaluated on the original dataset as well as a dataset of 473 merged high resolution tandem mass spectra (HR-MS/MS) and compared with another open source in silico fragmenter, CFM-ID. Using HR-MS/MS information only, MetFrag2.2 and CFM-ID had 30 and 43 Top 1 ranks, respectively, using PubChem as a database. Including reference and retention information in MetFrag2.2 improved this to 420 and 336 Top 1 ranks with ChemSpider and PubChem (89 and 71 %), respectively, and even up to 343 Top 1 ranks (PubChem) when combining with CFM-ID. The optimal parameters and weights were verified using three additional datasets of 824 merged HR-MS/MS spectra in total. Further examples are given to demonstrate flexibility of the enhanced features.

CONCLUSIONS

In many cases additional information is available from the experimental context to add to small molecule identification, which is especially useful where the mass spectrum alone is not sufficient for candidate selection from a large number of candidates. The results achieved with MetFrag2.2 clearly show the benefit of considering this additional information. The new functions greatly enhance the chance of identification success and have been incorporated into a command line interface in a flexible way designed to be integrated into high throughput workflows. Feedback on the command line version of MetFrag2.2 available at http://c-ruttkies.github.io/MetFrag/ is welcome.

Suspect screening of large numbers of emerging contaminants in environmental waters using artificial neural networks for chromatographic retention time prediction and high resolution mass spectrometry data analysis

The recent development of broad-scope high resolution mass spectrometry (HRMS) screening methods has resulted in a much improved capability for new compound identification in environmental samples. However, positive identifications at the ng/L concentration level rely on analytical reference standards for chromatographic retention time (tR) and mass spectral comparisons. Chromatographic tR prediction can play a role in increasing confidence in suspect screening efforts for new compounds in the environment, especially when standards are not available, but reliable methods are lacking. The current work focuses on the development of artificial neural networks (ANNs) for tR prediction in gradient reversed-phase liquid chromatography and applied along with HRMS data to suspect screening of wastewater and environmental surface water samples. Based on a compound tR dataset of >500 compounds, an optimized 4-layer back-propagation multi-layer perceptron model enabled predictions for 85% of all compounds to within 2min of their measured tR for training (n=344) and verification (n=100) datasets. To evaluate the ANN ability for generalization to new data, the model was further tested using 100 randomly selected compounds and revealed 95% prediction accuracy within the 2-minute elution interval. Given the increasing concern on the presence of drug metabolites and other transformation products (TPs) in the aquatic environment, the model was applied along with HRMS data for preliminary identification of pharmaceutically-related compounds in real samples. Examples of compounds where reference standards were subsequently acquired and later confirmed are also presented. To our knowledge, this work presents for the first time, the successful application of an accurate retention time predictor and HRMS data-mining using the largest number of compounds to preliminarily identify new or emerging contaminants in wastewater and surface waters.

Potential application of compliance constants in predicting the mass spectral fragmentation of metabolites

RATIONALE

Metabolomics is a qualitative and quantitative measurement of the metabolite content of any biological system under a given physiological status. Due to the chemically diverse nature of these samples, metabolite identification is a difficult task, and development of alternative approaches, such as those based on mass spectrometry (MS), aimed at proper metabolite identification is required.

METHODS

Compliance constants, a direct measure of mechanical bond strength, were used for the first time to predict the MS fragmentation patterns of different regional isomers of a ubiquitous plant metabolite, caffeoylquinic acid (CQA). The compliance constant of an ester bond linking caffeic acid and a quinic acid molecule in CQA was calculated using density functional theory and Wilson's G-matrix formalism to distinguish the isomers. The predicted fragmentation patterns were compared with mass spectra obtained using negative ion electrospray ionization ultra-high-performance liquid chromatography quadrupole time-of-flight mass spectrometry (UHPLC/QTOFMS).

RESULTS

Our in silico results were found to be in correlation with our UHPLC/QTOFMS results, suggesting a potential application of compliance constant algorithms for the rationalization of complex mass spectrometric data. The results also show that the different configurations in stereochemistry that exist between different regional isomers contribute to the underlying energy of the surrounding bonds and the fragmentation thereof.

CONCLUSIONS

The results of our pilot study suggest that computational modelling can be applied for metabolite identification during metabolomic data mining and Natural Product research in general.

PredRet: prediction of retention time by direct mapping between multiple chromatographic systems

Demands in research investigating small molecules by applying untargeted approaches have been a key motivator for the development of repositories for mass spectrometry spectra and automated tools to aid compound identification. Comparatively little attention has been afforded to using retention times (RTs) to distinguish compounds and for liquid chromatography there are currently no coordinated efforts to share and exploit RT information. We therefore present PredRet; the first tool that makes community sharing of RT information possible across laboratories and chromatographic systems (CSs). At http://predret.org , a database of RTs from different CSs is available and users can upload their own experimental RTs and download predicted RTs for compounds which they have not experimentally determined in their own experiments. For each possible pair of CSs in the database, the RTs are used to construct a projection model between the RTs in the two CSs. The number of compounds for which RTs can be predicted and the accuracy of the predictions are dependent upon the compound coverage overlap between the CSs used for construction of projection models. At the moment, it is possible to predict up to 400 RTs with a median error between 0.01 and 0.28 min depending on the CS and the median width of the prediction interval ranging from 0.08 to 1.86 min. By comparing experimental and predicted RTs, the user can thus prioritize which isomers to target for further characterization and potentially exclude some structures completely. As the database grows, the number and accuracy of predictions will increase.

Retention Time Prediction Improves Identification in Nontargeted Lipidomics Approaches

Identification of lipids in nontargeted lipidomics based on liquid-chromatography coupled to mass spectrometry (LC-MS) is still a major issue. While both accurate mass and fragment spectra contain valuable information, retention time (tR) information can be used to augment this data. We present a retention time model based on machine learning approaches which enables an improved assignment of lipid structures and automated annotation of lipidomics data. In contrast to common approaches we used a complex mixture of 201 lipids originating from fat tissue instead of a standard mixture to train a support vector regression (SVR) model including molecular structural features. The cross-validated model achieves a correlation coefficient between predicted and experimental test sample retention times of r = 0.989. Combining our retention time model with identification via accurate mass search (AMS) of lipids against the comprehensive LIPID MAPS database, retention time filtering can significantly reduce the rate of false positives in complex data sets like adipose tissue extracts. In our case, filtering with retention time information removed more than half of the potential identifications, while retaining 95% of the correct identifications. Combination of high-precision retention time prediction and accurate mass can thus significantly narrow down the number of hypotheses to be assessed for lipid identification in complex lipid pattern like tissue profiles.

Multi-target screening of biological samples using LC–MS/MS: focus on chromatographic innovations

Multi-target screening of biological fluids is a key tool in clinical and forensic toxicology. A complete toxicological analysis encompasses the sample preparation, the chromatographic separation and the detection. The present review briefly covers the new trends in sample preparation and detection and mainly focuses on the chromatographic stage, since a lot of technical improvements have been proposed over the last years. Among them, columns packed with sub-2 μm fully porous particles and sub-3 μm core-shell particles allow for significant improvements of resolution and higher throughput. Even if reversed-phase LC remains the most widely used chromatographic mode for toxicological screening, hydrophilic interaction chromatography and supercritical fluid chromatography appear as promising alternatives for attaining orthogonal selectivity, retention of polar compounds, and enhanced MS sensitivity.