Prediction Of Retention Times Research Articles

A multi-target QSRR approach to model retention times of small molecules in RPLC

Quantitative structure-retention relationship models (QSRR) have been utilized as an alternative to costly and time-consuming separation analyses and associated experiments for predicting retention time. However, achieving 100 % accuracy in retention prediction is unrealistic despite the existence of various tools and approaches. The limitations of vast data availability and time complexity hinder the use of most algorithms for retention prediction. Therefore, in this study, we examined and compared two approaches for modelling retention time using a dataset of small molecules with retention times obtained at multiple conditions, referred to as multi-targets (five pH levels: 2.7, 3.5, 5, 6.5, and 8 at gradient times of 20 min of mobile phase). The first approach involved developing separate models for predicting retention time at each condition (single-target approach), while the second approach aimed to learn a single model for predicting retention across all conditions simultaneously (multi-target approach). Our findings highlight the advantages of the multi-target approach over the single-target modelling approach. The multi-target models are more efficient in terms of size and learning speed compared to the single-target models. These retention prediction models offer two-fold benefits. Firstly, they enhance knowledge and understanding of retention times, identifying molecular descriptors that contribute to changes in retention behaviour under different pH conditions. Secondly, these approaches can be extended to address other multi-target property prediction problems, such as multi-quantitative structure Property(X) relationship studies (mt-QS(X)R).

Anomalous Retention Prediction Using Modelling Software in Gradient Reversed-Phase Liquid Chromatography: Why it Can Occur and How to Prevent It

Anomalous Retention Prediction Using Modelling Software in Gradient Reversed-Phase Liquid Chromatography: Why it Can Occur and How to Prevent It

A method for the sensitive targeted screening of synthetic cannabinoids and opioids in whole blood by LC-QTOF-MS with simultaneous suspect screening using HighResNPS.com.

A sensitive method for the qualitative screening of synthetic cannabinoids and opioids in whole blood was developed and validated using alkaline liquid-liquid extraction (LLE) and liquid chromatography - time-of-flight mass spectrometry (LC-QTOF-MS). Estimated limits of detection for validated compounds ranged from 0.03-0.29 µg/L (median, 0.04 µg/L) for the 27 opioids and from 0.04-0.5 µg/L (median, 0.07 µg/L) for the 23 synthetic cannabinoids. Data processing occurred in two stages; first a targeted screen was performed using an in-house database containing retention times, accurate masses and MS/MS spectra for 79 cannabinoids and 53 opioids. Suspect screening was then performed using a database downloaded from the crowd sourced NPS data website HighResNPS.com which contains mass, consensus MS/MS data and laboratory-specific predicted retention times for a far greater number of compounds. The method was applied to 61 forensic cases where synthetic cannabinoid or opioid screening was requested by the client or their use was suspected due to case information. CUMYL-PEGACLONE was detected in two cases and etodesnitazine, 5F-MDMB-PICA, 4-cyano-CUMYL-BUTINACA and carfentanil were detected in one case each. These compounds were within the targeted scope of the method but were also detected through the suspect screening workflow. The method forms a solid base for expansion as more compounds emerge onto the illicit drug market.

A supervised machine-learning approach for the efficient development of a multi method (LC-MS) for a large number of drugs and subsets thereof: focus on oral antitumor agents.

Accumulating evidence argues for a more widespread use of therapeutic drug monitoring (TDM) to support individualized medicine, especially for therapies where toxicity and efficacy are critical issues, such as in oncology. However, development of TDM assays struggles to keep pace with the rapid introduction of new drugs. Therefore, novel approaches for faster assay development are needed that also allow effortless inclusion of newly approved drugs as well as customization to smaller subsets if scientific or clinical situations require. We applied and evaluated two machine-learning approaches i.e.,a regression-based approach and an artificial neural network (ANN) to retention time (RT) prediction for efficient development of a liquid chromatography mass spectrometry (LC-MS) method quantifying 73 oral antitumor drugs (OADs) and five active metabolites. Individual steps included training, evaluation, comparison, and application of the superior approach to RT prediction, followed by stipulation of the optimal gradient. Both approaches showed excellent results for RT prediction (mean difference ± standard deviation: 2.08 % ± 9.44 % ANN; 1.78 % ± 1.93 % regression-based approach). Using the regression-based approach, the optimum gradient (4.91 % MeOH/min) was predicted with a total run time of 17.92 min. The associated method was fully validated following FDA and EMA guidelines. Exemplary modification and application of the regression-based approach to a subset of 14 uro-oncological agents resulted in a considerably shortened run time of 9.29 min. Using a regression-based approach, a multi drug LC-MS assay for RT prediction was efficiently developed, which can be easily expanded to newly approved OADs and customized to smaller subsets if required.

Impact of structural similarity on the accuracy of retention time prediction

Quantitative Structure-Retention Relationships offer a valuable tool for de-risking chromatographic methods in relation to newly formed or hypothetical compounds, arising from synthetic processes or formulation activities. They can also be used to identify optimal separation conditions, or in support of structural elucidation. In this contribution, we provide a systematic study of the relationship between the accuracy of the retention model, the size of the training set and its structural similarity to the predicted compound. We compare structural similarity expressed either on a fingerprint basis (e.g., Tanimoto index), or by Euclidean distance calculated from of subset of molecular descriptors. The results presented indicate that accurate and predictive models can be built from a small dataset containing as few as 25 compounds, provided that the training set is structurally similar to the test compound. When the training set contains compounds selected by minimizing the Euclidean distance calculated from 3 descriptors most correlated with the retention time, root mean square error of 0.48 min and correlation coefficient of 0.9464 were observed for the test sets of 104 compounds. Moreover, these models meet the Tropsha predictivity criteria. These findings potentially bring the prediction of retention times within the practical reach of pharmaceutical analysts involved in chromatographic method development. We also present an optimisation approach to select algorithm settings in order to minimize the prediction error and ensure model predictivity.

Computer-driven optimization of complex gradients in comprehensive two-dimensional liquid chromatography

Method development in comprehensive two-dimensional liquid chromatography (LC × LC) is a complicated endeavor. The dependency between the two dimensions and the possibility of incorporating complex gradient profiles, such as multi-segmented gradients or shifting gradients, renders method development by “trial-and-error” time-consuming and highly dependent on user experience. In this work, an open-source algorithm for the automated and interpretive method development of complex gradients in LC × LC-mass spectrometry (MS) was developed. A workflow was designed to operate within a closed-loop that allowed direct interaction between the LC × LC-MS system and a data-processing computer which ran in an unsupervised and automated fashion. Obtaining accurate retention models in LC × LC is difficult due to the challenges associated with the exact determination of retention times, curve fitting because of the use of gradient elution, and gradient deformation. Thus, retention models were compared in terms of repeatability of determination. Additionally, the design of shifting gradients in the second dimension and the prediction of peak widths were investigated. The algorithm was tested on separations of a tryptic digest of a monoclonal antibody using an objective function that included the sum of resolutions and analysis time as quality descriptors. The algorithm was able to improve the separation relative to a generic starting method using these complex gradient profiles after only four method-development iterations (i.e., sets of chromatographic conditions). Further iterations improved retention time and peak width predictions and thus the accuracy in the separations predicted by the algorithm.

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.

Relation between characteristic temperature and elution temperature in temperature programmed gas chromatography - part I: Influence of initial temperature and heating rate

The development of new analytical methods can save resources, time and costs if there are prediction tools like computer simulation which support the optimization process. In GC the distribution-centric 3-parameter model (K-centric model) is well established for prediction of retention factors k and retention times but laborious isothermal measurements for determination of the characteristic parameters are needed. For the most important parameter, the characteristic temperature Tchar, the search for simpler determination methods or even estimates is an interesting research topic.In this work the elution temperatures for 37 fatty acid methyl esters, 6 BTEXs and 40 other volatile substances are determined by measurements under variable heating rates, initial temperatures, constant pressure mode and constant flow mode. The relationship between the measured elution temperature and the characteristic temperature was investigated. The novel multivariate curve fit model presented in this study describes accurately the relation between the characteristic temperature Tchar and elution temperatures Telu under variable heating rates RT, respectively, and initial temperature Tinit conditions. The novel model shows good accordance to earlier estimation models and expands the prediction range, especially for high volatile compounds. The model is suitable for determination of Tchar by estimated Telu and vice versa. Predictions of retention times of simple temperature programs were also possible by using the model with relative deviations < 5% compared to measurements.

Development of a gas chromatography system coupled to a metal-oxide semiconductor (MOS) sensor, with compensation of the temperature effects on the column for the measurement of ethene

Abstract. A possible way to reduce the size and complexity of common gas chromatography (GC) systems is the economization of the column temperature regulation system. To this end, a temperature compensation method was developed and validated on a benchtop GC-PDD (pulsed discharge detector) with ethene. An in-house-developed algorithm correlates the retention index of a test gas to the retention index of a previously selected reference gas. To investigate further methods of cost reduction, commercial gas sensors were tested as cheap, sensitive, and versatile detectors. Therefore, CO2 was chosen as a naturally occurring reference gas, while ethene was chosen as a maturity marker for climacteric fruits and hence as a test gas. A demonstrator, consisting of a simple syringe injection system, a PLOT (porous layer open tubular) column boxed in a polystyrene-foam housing, a commercial MOS (metal-oxide semiconductor) sensor for the test gas, and a CO2-specific IR (infrared) sensor, was used to set up a simple GC system and to apply this method on test measurements. Sorption parameters for ethene and CO2 were determined via a van 't Hoff plot, where the entropy S was −11.982 J mol−1 K−1 ΔSEthene0 and 1.351 J mol−1 K−1 ΔSCarbondioxide0, and the enthalpy H was −20.622 kJ mol−1 ΔHEthene0 and −14.792 kJ mol−1 ΔHCarbondioxide0, respectively. Ethene (100 ppm) measurements revealed a system-specific correction term of 0.652 min. Further measurements of ethene and interfering gases revealed a mean retention time for ethene of 3.093 min; the mean predicted retention time is 3.099 min. The demonstrator was able to identify the test gas, ethene, as a function of the reference gas, CO2, in a first approach, without a column heating system and in a gas mixture by applying a temperature compensation algorithm and a system-specific holdup time correction term.

A deep learning-based simulator for comprehensive two-dimensional GC applications.

Among the main approaches for predicting the spatial positions of eluates in comprehensive two-dimensional gas chromatography, the still under-explored computational models based on deep learning algorithms emerge as robust and reliable options due to their high adaptability to the structure and complexity of the data. In this work, an open-source program based on deep neural networks was developed to optimize chromatographic methods and simulate operating conditions outside the laboratory. The deep neural networks models were fit to convenient experimental predictors, resulting in scaled losses (mean squared error) equivalent to 0.006 (relative average deviation=8.56%, R2 =0.9202) and 0.014 (relative average deviation=1.67%, R2 =0.8009) in the prediction of the first- and second-dimension retention times, respectively. Good compliance was observed for the main chemical classes, such as environmental contaminants: volatile, semivolatile organic compounds, and pesticides; biochemistry molecules: amino acids and lipids; pharmaceutical industry and personal care products and residues: drugs and metabolites; among others. On the other hand, there is a need for continuous database updates to predict retention times of less common compounds accurately. Thus, forming a collaborative database is proposed, gathering voluntary findings from other users.

Towards an accurate method for column void volume determination using liquid chromatography-mass spectrometry

Prediction of analyte retention times requires prior knowledge of the column void volume, the measurement of which is still highly contested within the literature and therefore experimental based prediction is often used. In this study, we investigated deuterated acetonitrile as an isotopically labelled mobile phase component to observe its elution behaviour in a binary mixture with water at 25 different mobile phase compositions (from 5 to 95 vol.% of acetonitrile), on two stationary phases (C8 and C18), and at two temperatures (30 and 40 °C) using LC-MS. The same experimental design was additionally used for three commonly used neutral void volume markers: uracil, phloroglucinol and N,N-dimethylformamide. Temperature was observed to influence the elution of acetonitrile in an inversely proportional manner with higher temperatures coinciding with lower elution times. By utilizing a three-way ANOVA, the composition of the mobile phase has been shown to have a significant effect on deuterated acetonitrile and other investigated void volume markers, demonstrating the fact that both void volume markers and acetonitrile itself exhibit retention-like behaviour. Excess adsorption isotherms for acetonitrile were calculated using deuterated acetonitrile elution data. The comparison of void volumes, obtained with conventional neutral void volume markers, revealed the former to be 24–36% lower than the void volume obtained using deuterated acetonitrile, as an isotopically labelled mobile phase component. For a water:acetonitrile mobile phase, the minor disturbance method using deuterated acetonitrile to obtain an integral average void volume (2.08 and 2.05 mL for C18 at 30 and 40 °C, respectively and 2.16 and 2.13 mL for C8 at 30 and 40 °C, respectively) was found to be the most appropriate method for determining the elusive column void volume.

Complementary methods for structural assignment of isomeric candidate structures in non-target liquid chromatography ion mobility high-resolution mass spectrometric analysis

Non-target screening with LC/IMS/HRMS is increasingly employed for detecting and identifying the structure of potentially hazardous chemicals in the environment and food. Structural assignment relies on a combination of multidimensional instrumental methods and computational methods. The candidate structures are often isomeric, and unfortunately, assigning the correct structure among a number of isomeric candidate structures still is a key challenge both instrumentally and computationally. While practicing non-target screening, it is usually impossible to evaluate separately the limitations arising from (1) the inability of LC/IMS/HRMS to resolve the isomeric candidate structures and (2) the uncertainty of in silico methods in predicting the analytical information of isomeric candidate structures due to the lack of analytical standards for all candidate structures. Here we evaluate the feasibility of structural assignment of isomeric candidate structures based on in silico–predicted retention time and database collision cross-section (CCS) values as well as based on matching the empirical analytical properties of the detected feature with those of the analytical standards. For this, we investigated 14 candidate structures corresponding to five features detected with LC/HRMS in a spiked surface water sample. Considering the predicted retention times and database CCS values with the accompanying uncertainty, only one of the isomeric candidate structures could be deemed as unlikely; therefore, the annotation of the LC/IMS/HRMS features remained ambiguous. To further investigate if unequivocal annotation is possible via analytical standards, the reversed-phase LC retention times and low- and high-resolution ion mobility spectrometry separation, as well as high-resolution MS2 spectra of analytical standards were studied. Reversed-phase LC separated the highest number of candidate structures while low-resolution ion mobility and high-resolution MS2 spectra provided little means for pinpointing the correct structure among the isomeric candidate structures even if analytical standards were available for comparison. Furthermore, the question arises which prediction accuracy is required from the in silico methods to par the analytical separation. Based on the experimental data of the isomeric candidate structures studied here and previously published in the literature (516 retention time and 569 CCS values), we estimate that to reduce the candidate list by 95% of the structures, the confidence interval of the predicted retention times would need to decrease to below 0.05 min for a 15-min gradient while that of CCS values would need to decrease to 0.15%. Hereby, we set a clear goal to the in silico methods for retention time and CCS prediction.Graphical abstract

Potential of Negative-Ion-Mode Proteomics: An MS1-Only Approach.

Current proteomics approaches rely almost exclusively on using the positive ionization mode, resulting in inefficient ionization of many acidic peptides. This study investigates protein identification efficiency in the negative ionization mode using the DirectMS1 method. DirectMS1 is an ultrafast data acquisition method based on accurate peptide mass measurements and predicted retention times. Our method achieves the highest rate of protein identification in the negative ion mode to date, identifying over 1000 proteins in a human cell line at a 1% false discovery rate. This is accomplished using a single-shot 10 min separation gradient, comparable to lengthy MS/MS-based analyses. Optimizing separation and experimental conditions was achieved by utilizing mobile buffers containing 2.5 mM imidazole and 3% isopropanol. The study emphasized the complementary nature of data obtained in positive and negative ion modes. Combining the results from all replicates in both polarities increased the number of identified proteins to 1774. Additionally, we analyzed the method's efficiency using different proteases for protein digestion. Among the four studied proteases (LysC, GluC, AspN, and trypsin), trypsin and LysC demonstrated the highest protein identification yield. This suggests that digestion procedures utilized in positive-mode proteomics can be effectively applied in the negative ion mode. Data are deposited to ProteomeXchange: PXD040583.

High-Throughput Chromatographic Separation of Oligonucleotides: A Proof of Concept Using Ultra-Short Columns.

Ion-pairing reversed-phase liquid chromatography (IP-RPLC) is the reference separation technique for characterizing oligonucleotides (ONs) and their related impurities. The aim of this study was to better understand the retention mechanism of ONs, evaluate the applicability of the linear solvent strength (LSS) retention model, and explore the potential of ultra-short columns having a length of only 5 mm for the separation of model ONs. First, the validity of the LSS model was evaluated for ONs having sizes comprised between 3 and 30 kDa, and the accuracy of retention time predictions was assessed. It was found that ONs in IP-RPLC conditions follow an "on-off" elution behavior, despite a molecular weight lower than that of proteins. For most linear gradient separation conditions, a column length between 5 and 35 mm was found to be appropriate. Ultra-short columns of only 5 mm were therefore explored to speed up separations by considering the impact of the instrumentation on the efficiency. Interestingly, the impacts of injection volume and post-column connection tubing on peak capacity were found to be negligible. Finally, it was demonstrated that longer columns would not improve selectivity or separation efficiency, but baseline separation of three model ONs mixtures was enabled in as little as 30 s on the 5 mm column. This proof-of-concept work paves the way for future investigations using more complex therapeutic ONs and their related impurities.

Quantitative structure-retention relationship by databases of illegal additives

The importance of small molecule retention time in detecting illegal additives cannot be overstated. In order to provide a basis for identification in small-scale databases lacking corresponding chemical standards, a quantitative structure-retention relationship (QSRR) model was developed using two liquid chromatography databases under the same column but with different mobile phases. The QSRR model workflow includes feature extraction, feature selection, model construction and evaluation. Molecular descriptors were calculated by molecules optimized using Consistent force field (CFF) and Chemistry at HARvard Macromolecular Mechanicets (CHARMm) force field during the feature extraction stage. Two selection algorithms, minimum redundancy-maximum relevance (MRMR) and F-test, were compared during the feature selection stage. Five categories of machine learning algorithms, Regression Trees (Reg-T), Support Vector Machines (SVM), Gaussian Process Regression Models (GPR), Ensembles of Trees, and Kernel approximation models, were compared during the model construction phase resulting in 14 models being obtained. The best-performing model was found to be the Exponential Gaussian Process Regression Model (E-GPR). This was tested on Database 1 with coefficient of determination (R2)= 0.84 ± 0.02 and on Database 2 with R2 = 0.83 ± 0.03. The results indicate that this QSRR model can accurately predict retention times for small molecules within small-scale databases.

A chemical derivatization-based pseudotargeted LC-MS/MS method for high coverage determination of dipeptides

Dipeptides (DPs) have attracted more and more attention in many research fields due to their important biological functions and promising roles as disease biomarkers. However, the determination of DPs in biological samples is very challenging owing to the limited availability of commercial standards, high structure diversity, distinct physical and chemical characteristics, wide concentration range, and the extensive existence of isomers. In this study, a pseudotargeted liquid chromatography-tandem mass spectrometry (LC-MS/MS) method coupled with chemical derivatization for the simultaneous analysis of 400 DPs and their constructing amino acids (AAs) in biospecimens is established. Dansyl chloride (Dns-Cl) chemical derivatization was introduced to provide characteristic MS fragments for annotation and improve the chromatographic separation of DP isomers. A retention time (RT) prediction model was constructed using 83 standards (63 DPs and 20 AAs) based on their quantitative structural retention relationship (QSRR) after the Dns-Cl labeling, which largely facilitated the annotation of the DPs without standards. Finally, we applied this method to investigate the profile change of DPs in a cisplatin-induced acute kidney injury (AKI) rat model. The established workflow provides a platform to profile DPs and expand our understanding of these little-studied metabolites.

Volume-Corrected Free Energy as a New Criterion for Structural Elucidation in Chemical-Tagging-Based Metabolomics.

Chemical tagging via possible derivatization reagents alters metabolites' retention times, leading to different retention behavior during liquid chromatography-mass spectrometry (LC-MS) analysis. Incorporation of the retention time dimension can dramatically reduce false-positive structural elucidation in chemical-tagging-based metabolomics. However, few studies predict the retention times of chemically labeled metabolites, especially requiring a simple, easy-to-access, accurate, and universal predictor or descriptor. This pilot study demonstrates the application of volume-corrected free energy (VFE) calculation and region mapping as a new criterion to describe the retention time for structure elucidation in chemical-tagging-based metabolomics. The universality of VFE calculation is first evaluated with four different types of submetabolomes including hydroxyl-group-, carbonyl-group-, carboxylic-group-, and amino-group-containing compounds and oxylipins with similar chemical structures and complex isomers on reverse-phase LC. Results indicate a good correlation (r > 0.85) between VFE values and their corresponding retention times using different technicians, instruments, and chromatographic columns, describing retention behavior in reverse-phase LC. Finally, the VFE region mapping is described for identifying 1-pentadecanol from aged camellia seed oil using three proposed steps, including public database searching, VFE region mapping for its 12 isomers, and chemical standard matching. The possibility of VFE calculation of nonderivatized compounds in retention time prediction is also investigated, demonstrating its effectiveness on retention times with different influence factors.

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.

Harnessing data science to improve molecular structure elucidation from tandem mass spectrometry

Compound structural identification for non-targeted screening of organic molecules in complex mixtures is commonly carried out using liquid chromatography coupled to tandem mass spectrometry (UHPLC-HRMS/MS and related techniques). Instrumental developments in recent years have increased the quality and quantity of data available; however, using current data analysis methods, structures can be assigned to only a small fraction of compounds present in typical mixtures. We present a new data analysis pipeline, “MSEI”, that harnesses data science methodologies to improve structural identification capabilities from tandem mass spectrometry data. In particular, feature vectors for fingerprint calculation are found directly from tandem mass spectra, strongly reducing computational costs, and fingerprint comparison uses an optimised methodology accounting for uncertainty to improve distinction between matching and non-matching compounds. MSEI builds on the identification of a small number of compounds through current state-of-the-art data analysis on UHPLC-HRMS/MS measurements and uses targeted training and tailored molecular fingerprints to focus identification to a particular molecular space of interest. Initial compound identifications are used as training data for a set of random forests which directly predict a custom 75-digit molecular fingerprint from a vectorised MS/MS spectrum. Kendrick mass defects (KMDs) for peaks as well as “lost” fragments removed during fragmentation were found to be useful information for fingerprint prediction. Fingerprints are then compared to potential matches from the PubChem structural database using Euclidean distance, with fingerprint digit weights determined using an SVM to maximise distance between matching and non-matching compounds. Potential matches are additionally filtered for hydrophobicity based on measured retention time, using a newly developed machine learning method for retention time prediction. MSEI was able to correctly assign > 50% of structures in a test dataset and showed > 10% better performance than current state-of-the-art methods, while using an order of magnitude less computational power and a fraction of the training data.

Predictive Quantitative Read-Across Structure-Property Relationship Modeling of the Retention Time (Log tR) of Pesticide Residues Present in Foods and Vegetables.

The retention time (log tR) of pesticidal compounds in a reverse-phase high-performance liquid chromatography (HPLC) analysis has a direct relationship with lipophilicity, which could be related to the ecotoxicity potential of the compounds. The novel quantitative read-across structure-property relationship (q-RASPR) modeling approach uses similarity-based descriptors for predictive model generation. These models have been shown to enhance external predictivity in previous studies for several end points. The current study describes the development of a q-RASPR model using experimental retention time data (log tR) in the HPLC experiments of 823 environmentally significant pesticide residues collected from a large compound database. To model the retention time (log tR) end point, 0D-2D descriptors have been used along with the read-across-derived similarity descriptors. The developed partial least squares (PLS) model was rigorously validated by various internal and external validation metrics as recommended by the Organization for Economic Co-operation and Development (OECD). The final q-RASPR model is proven to be a good fit, robust, and externally predictive (ntrain = 618, R2 = 0.82, Q2LOO = 0.81, ntest = 205, and Q2F1 = 0.84) that literally outperforms the external predictivity of the previously reported quantitative structure-property relationship (QSPR) model. From the insights of modeled descriptors, lipophilicity is found to be the most important chemical property, which positively correlates with the retention time (log tR). Various other characteristics, such as the number of multiple bonds (nBM), graph density (GD), etc., have a substantial and inversely proportionate relationship with the retention time end point. The software tools utilized in this study are user-friendly, and most of them are free, which makes our methodology quite cost-effective when compared to experimentation. In a nutshell, to obtain better external predictivity, interpretability, and transferability, q-RASPR is an efficient technique that has the potential to be employed as a good alternative approach for retention time prediction and ecotoxicity potential identification.