Molecular Descriptor Subset Selection in Theoretical Peptide Quantitative Structure–Retention Relationship Model Development Using Nature-Inspired Optimization Algorithms

Annotation of Dipeptides and Tripeptides Derivatized via Dansylation Based on Liquid Chromatography-Mass Spectrometry and Iterative Quantitative Structure Retention Relationship

Small peptides such as dipeptides and tripeptides show various biological activities in organisms. However, methods for identifying dipeptides/tripeptides from complex biological samples are lacking. Here, an annotation strategy involving the derivatization of dipeptides and tripeptides via dansylation was suggested based on liquid chromatography-mass spectrometry (LC-MS) and iterative quantitative structure retention relationship (QSRR) to choose dipeptides/tripeptides by using a small number of standards. First, the LC-autoMS/MS method and initial QSRR model were built based on 25 selected grid-dipeptides and 18 test-dipeptides. To achieve high-coverage detection, dipeptide/tripeptide pools containing abundant dipeptides/tripeptides were then obtained from four dansylated biological samples including serum, tissue, feces, and soybean paste by using the parameter-optimized LC-autoMS/MS method. The QSRR model was further optimized through an iterative train-by-pick strategy. Based on the specific fragments and t_R tolerances, 198 dipeptides and 149 tripeptides were annotated. The dipeptides at lower annotation levels were verified by using authentic standards and grid-correlation analysis. Finally, variation in serum dipeptides/tripeptides of three different liver diseases including hepatitis B infection, liver cirrhosis, and hepatocellular carcinoma was characterized. Dipeptides with N-prolinyl, C-proline, N-glutamyl, and N-valinyl generally increased with disease severity. In conclusion, this study provides an efficient strategy for annotating dipeptides/tripeptides from complex samples.

Predicting liquid chromatography-electrospray ionization/mass spectrometry signal from the structure of model compounds and experimental factors; case study of aripiprazole and its impurities

A priori estimation of analyte response is crucial for the efficient development of liquid chromatography-electrospray ionization/mass spectrometry (LC-ESI/MS) methods, but remains a demanding task given the lack of knowledge about the factors affecting the experimental outcome. In this research, we address the challenge of discovering the interactive relationship between signal response and structural properties, method parameters and solvent-related descriptors throughout an approach featuring quantitative structure-property relationship (QSPR) and design of experiments (DoE). To systematically investigate the experimental domain within which QSPR prediction should be undertaken, we varied LC and instrumental factors according to the Box-Behnken DoE scheme. Seven compounds, including aripiprazole and its impurities, were subjected to 57 different experimental conditions, resulting in 399 LC-ESI/MS data endpoints. To obtain a more standard distribution of the measured response, the peak areas were log-transformed before modeling. QSPR predictions were made using features selected by Genetic Algorithm (GA) and providing Gradient Boosted Trees (GBT) with training data. Proposed model showed satisfactory performance on test data with a RMSEP of 1.57 % and a of 96.48 %. This is the first QSPR study in LC-ESI/MS that provided a holistic overview of the analyte's response behavior across the experimental and chemical space. Since intramolecular electronic effects and molecular size were given great importance, the GA-GBT model improved the understanding of signal response generation of model compounds. It also highlighted the need to fine-tune the parameters affecting desolvation and droplet charging efficiency.

Quantitative Structure Retention-Relationship Modeling: Towards an Innovative General-Purpose Strategy

Reversed-Phase Liquid Chromatography (RPLC) is a common liquid chromatographic mode used for the control of pharmaceutical compounds during their drug life cycle. Nevertheless, determining the optimal chromatographic conditions that enable this separation is time consuming and requires a lot of lab work. Quantitative Structure Retention Relationship models (QSRR) are helpful for doing this job with minimal time and cost expenditures by predicting retention times of known compounds without performing experiments. In the current work, several QSRR models were built and compared for their adequacy in predicting the retention times. The regression models were based on a combination of linear and non-linear algorithms such as Multiple Linear Regression, Support Vector Regression, Least Absolute Shrinkage and Selection Operator, Random Forest, and Gradient Boosted Regression. Models were built for five pH conditions, i.e., at pH 2.7, 3.5, 6.5, and 8.0. In the end, the model predictions were combined using stacking and the performances of all models were compared. The k-nearest neighbor-based application domain filter was established to assess the reliability of the prediction for further compound prioritization. Altogether, this study can be insightful for analytical chemists working with RPLC to begin with the computational prediction modeling such as QSRR to predict the separation of small molecules.

In silico prediction of siRNA ionizable-lipid nanoparticles In vivo efficacy: Machine learning modeling based on formulation and molecular descriptors

In silico prediction of the in vivo efficacy of siRNA ionizable-lipid nanoparticles is desirable as it can save time and resources dedicated to wet-lab experimentation. This study aims to computationally predict siRNA nanoparticles in vivo efficacy. A data set containing 120 entries was prepared by combining molecular descriptors of the ionizable lipids together with two nanoparticles formulation characteristics. Input descriptor combinations were selected by an evolutionary algorithm. Artificial neural networks, support vector machines and partial least squares regression were used for QSAR modeling. Depending on how the data set is split, two training sets and two external validation sets were prepared. Training and validation sets contained 90 and 30 entries respectively. The results showed the successful predictions of validation set log (siRNA dose) with R_val ²= 0.86-0.89 and 0.75-80 for validation sets one and two, respectively. Artificial neural networks resulted in the best R_val ² for both validation sets. For predictions that have high bias, improvement of R_val ² from 0.47 to 0.96 was achieved by selecting the training set lipids lying within the applicability domain. In conclusion, in vivo performance of siRNA nanoparticles was successfully predicted by combining cheminformatics with machine learning techniques.

Development of QSRR model for hydroxamic acids using PCA-GA-BP algorithm incorporated with molecular interaction-based features

As a potent zinc chelator, hydroxamic acid has been applied in the design of inhibitors of zinc metalloenzyme, such as histone deacetylases (HDACs). A series of hydroxamic acids with HDAC inhibitory activities were subjected to the QSRR (Quantitative Structure–Retention Relationships) study. Experimental data in combination with calculated molecular descriptors were used for the development of the QSRR model. Specially, we employed PCA (principal component analysis) to accomplish dimension reduction of descriptors and utilized the principal components of compounds (16 training compounds, 4 validation compounds and 7 test compounds) to execute GA (genetic algorithm)-BP (error backpropagation) algorithm. We performed double cross-validation approach for obtaining a more convincing model. Moreover, we introduced molecular interaction-based features (molecular docking scores) as a new type of molecular descriptor to represent the interactions between analytes and the mobile phase. Our results indicated that the incorporation of molecular interaction-based features significantly improved the accuracy of the QSRR model, (R2 value is 0.842, RMSEP value is 0.440, and MAE value is 0.573). Our study not only developed QSRR model for the prediction of the retention time of hydroxamic acid in HPLC but also proved the feasibility of using molecular interaction-based features as molecular descriptors.

Development and Application of Liquid Chromatographic Retention Time Indices in HRMS-Based Suspect and Nontarget Screening

There is an increasing need for comparable and harmonized retention times (t_R) in liquid chromatography (LC) among different laboratories, to provide supplementary evidence for the identity of compounds in high-resolution mass spectrometry (HRMS)-based suspect and nontarget screening investigations. In this study, a rigorously tested, flexible, and less system-dependent unified retention time index (RTI) approach for LC is presented, based on the calibration of the elution pattern. Two sets of 18 calibrants were selected for each of ESI+ and ESI-based on the maximum overlap with the retention times and chemical similarity indices from a total set of 2123 compounds. The resulting calibration set, with RTI set to range between 1 and 1000, was proposed as the most appropriate RTI system after rigorous evaluation, coordinated by the NORMAN network. The validation of the proposed RTI system was done externally on different instrumentation and LC conditions. The RTI can also be used to check the reproducibility and quality of LC conditions. Two quantitative structure-retention relationship (QSRR)-based models were built based on the developed RTI systems, which assist in the removal of false-positive annotations. The applicability domains of the QSRR models allowed completing the identification process with higher confidence for substances within the domain, while indicating those substances for which results should be treated with caution. The proposed RTI system was used to improve confidence in suspect and nontarget screening and increase the comparability between laboratories as demonstrated for two examples. All RTI-related calculations can be performed online at http://rti.chem.uoa.gr/.

Development and Application of a Novel Semi-quantification Approach in LC-QToF-MS Analysis of Natural Products

Use of high-resolution mass spectrometry (HRMS) including a MS calibration method has enabled simultaneous identification and quantification of knowns/unknowns. This has expanded our knowledge about the existing sample relevant chemical space in a way beyond reconciliation with a quantification task. This is largely due to fact that reference standards are not always available to achieve quantitative analysis. In this scenario, a semi-quantitative approach can fill the gap and provide a rough estimation of concentration. This research aimed to develop and compare several semi-quantification approaches based on chemical similarity or properties. The ionization efficiency scale was created for several groups of natural products. Advanced modeling approach based on a support vector machine was conducted to learn from the experimental ionization efficiency and apply it to unknowns or suspected compounds to predict their ionization efficiency in electrospray ionization mode. The developed semi-quantification workflows could be useful in most HRMS based "omics" areas, especially in natural products discovery.

Perspective on the Future Approaches to Predict Retention in Liquid Chromatography

The demand for rapid column screening, computer-assisted method development and method transfer, and unambiguous compound identification by LC/MS analyses has pushed analysts to adopt experimental protocols and software for the accurate prediction of the retention time in liquid chromatography (LC). This Perspective discusses the classical approaches used to predict retention times in LC over the last three decades and proposes future requirements to increase their accuracy. First, inverse methods for retention prediction are essentially applied during screening and gradient method optimization: a minimum number of experiments or design of experiments (DoE) is run to train and calibrate a model (either purely statistical or based on the principles and fundamentals of liquid chromatography) by a mere fitting process. They do not require the accurate knowledge of the true column hold-up volume V₀, system dwell volume V_dwell (in gradient elution), and the retention behavior (k versus the content of strong solvent φ, temperature T, pH, and ionic strength I) of the analytes. Their relative accuracy is often excellent below a few percent. Statistical methods are expected to be the most attractive to handle very complex retention behavior such as in mixed-mode chromatography (MMC). Fundamentally correct retention models accounting for the simultaneous impact of φ, I, pH, and T in MMC are needed for method development based on chromatography principles. Second, direct methods for retention prediction are ideally suited for accurate method transfer from one column/system configuration to another: these quality by design (QbD) methods are based on the fundamentals and principles of solid-liquid adsorption and gradient chromatography. No model calibration is necessary; however, they require universal conventions for the accurate determination of true retention factors (for 1 < k < 30) as a function of the experimental variables (φ, T, pH, and I) and of the true column/system parameters (V₀, V_dwell, dispersion volume, σ, and relaxation volume, τ, of the programmed gradient profile at the column inlet and gradient distortion at the column outlet). Finally, when the molecular structure of the analytes is either known or assumed, retention prediction has essentially been made on the basis of statistical approaches such as the linear solvation energy relationships (LSERs) and the quantitative structure retention relationships (QSRRs): their ability to accurately predict the retention remains limited within 10-30%. They have been combined with molecular similarity approaches (where the retention model is calibrated with compounds having structures similar to that of the targeted analytes) and artificial intelligence algorithms to further improve their accuracy below 10%. In this Perspective, it is proposed to adopt a more rigorous and fundamental approach by considering the very details of the solid-liquid adsorption process: Monte Carlo (MC) or molecular dynamics (MD) simulations are promising tools to explain and interpret retention data that are too complex to be described by either empirical or statistical retention models.

Improvement of quantitative structure-retention relationship models for chromatographic retention prediction of peptides applying individual local partial least squares models

In Reversed-Phase Liquid Chromatography, Quantitative Structure-Retention Relationship (QSRR) models for retention prediction of peptides can be built, starting from large sets of theoretical molecular descriptors. Good predictive QSRR models can be obtained after selecting the most informative descriptors. Reliable retention prediction may be an aid in the correct identification of proteins/peptides in proteomics and in chromatographic method development. Traditionally, global QSRR models are built, using a calibration set containing a representative range of analytes. In this study, a strategy is presented to build individual local Partial Least Squares (PLS) models for peptides, based on selected local calibration samples, most similar to the specific query peptide to be predicted. Similar local calibration peptides are selected from a possible calibration set. The calibration samples with the lowest Euclidian distances to the query peptide are considered as most similar. Two Euclidian distances are investigated as similarity parameter, (i) in the autoscaled descriptor space and, (ii) in the PLS factor space of the global calibration samples, both after variable selection by the Final Complexity Adapted Models (FCAM) method. The predictive abilities of individual local QSRR PLS models for peptides, developed with both Euclidian distances, are found significantly better than those of two global models, i.e. before and after FCAM variable selection. The predictive abilities of the local models, developed with distances calculated in the PLS factor space, were best.

Understanding performance of 3D-printed sorbent in study of metabolic stability

Metabolic stability tests are one of the fundamental steps at the preclinical stages of new drug development. Microsomes, used as a typical enzymatic model of liver biotransformation, can be a challenging matrix for analytical scientists due to a high concentration of cellular proteins and membrane lipids. In the work, we propose a new procedure integrating biotransformation reaction with SPME-like protocol for sample clean-up. It is beneficial to increase the overall quality of results in contrary to the typical protein precipitation approach. A set of ten arylpiperazine analogs, six of which are considered promising drug candidates (and four are accepted drugs) were used as a probe to assess the goodness of the newly proposed approach. In order to promote an efficient extraction protocol, a new, miniaturized shape of a sorbent, suitable to perform the extraction in 100 µL of the sample has been designed. Termination of the biotransformation process by protein denaturation with hot water was additionally evaluated. A quantitative structure-property relationship (QSPR) study using Orthogonal Partial Least Squares (OPLS) technique to reveal insights to the sorption mechanism was also performed. The obtained results showed the new 3D-printed sorbent can be an attractive basis for the new sample preparation approach for metabolic stability studies and an alternative for commercially available protocols based on solid-phase microextraction (SPME) or solid-phase extraction (SPE) principles.

Prediction of Chromatographic Elution Order of Analytical Mixtures Based on Quantitative Structure-Retention Relationships and Multi-Objective Optimization

Prediction of the retention time from the molecular structure using quantitative structure-retention relationships is a powerful tool for the development of methods in reversed-phase HPLC. However, its fundamental limitation lies in the fact that low error in the prediction of the retention time does not necessarily guarantee a prediction of the elution order. Here, we propose a new method for the prediction of the elution order from quantitative structure-retention relationships using multi-objective optimization. Two case studies were evaluated: (i) separation of organic molecules in a Supelcosil LC-18 column, and (ii) separation of peptides in seven columns under varying conditions. Results have shown that, when compared to predictions based on the conventional model, the relative root mean square error of the elution order decreases by 48.84%, while the relative root mean square error of the retention time increases by 4.22% on average across both case studies. The predictive ability in terms of both retention time and elution order and the corresponding applicability domains were defined. The models were deemed stable and robust with few to no structural outliers.

Mechanistic Chromatographic Column Characterization for the Analysis of Flavonoids Using Quantitative Structure-Retention Relationships Based on Density Functional Theory

This work aimed to unravel the retention mechanisms of 30 structurally different flavonoids separated on three chromatographic columns: conventional Kinetex C18 (K-C18), Kinetex F5 (K-F5), and IAM.PC.DD2. Interactions between analytes and chromatographic phases governing the retention were analyzed and mechanistically interpreted via quantum chemical descriptors as compared to the typical 'black box' approach. Statistically significant consensus genetic algorithm-partial least squares (GA-PLS) quantitative structure retention relationship (QSRR) models were built and comprehensively validated. Results showed that for the K-C18 column, hydrophobicity and solvent effects were dominating, whereas electrostatic interactions were less pronounced. Similarly, for the K-F5 column, hydrophobicity, dispersion effects, and electrostatic interactions were found to be governing the retention of flavonoids. Conversely, besides hydrophobic forces and dispersion effects, electrostatic interactions were found to be dominating the IAM.PC.DD2 retention mechanism. As such, the developed approach has a great potential for gaining insights into biological activity upon analysis of interactions between analytes and stationary phases imitating molecular targets, giving rise to an exceptional alternative to existing methods lacking exhaustive interpretations.

Lipophilicity Determination of Antifungal Isoxazolo[3,4-b]pyridin-3(1H)-ones and Their N1-Substituted Derivatives with Chromatographic and Computational Methods

The lipophilicity of a molecule is a well-recognized as a crucial physicochemical factor that conditions the biological activity of a drug candidate. This study was aimed to evaluate the lipophilicity of isoxazolo[3,4-b]pyridine-3(1H)-ones and their N1-substituted derivatives, which demonstrated pronounced antifungal activities. Several methods, including reversed-phase thin layer chromatography (RP-TLC), reversed phase high-performance liquid chromatography (RP-HPLC), and micellar electrokinetic chromatography (MEKC), were employed. Furthermore, the calculated logP values were estimated using various freely and commercially available software packages and online platforms, as well as density functional theory computations (DFT). Similarities and dissimilarities between the determined lipophilicity indices were assessed using several chemometric approaches. Principal component analysis (PCA) indicated that other features beside lipophilicity affect antifungal activities of the investigated derivatives. Quantitative-structure-retention-relationship (QSRR) analysis by means of genetic algorithm-partial least squares (GA-PLS)-was implemented to rationalize the link between the physicochemical descriptors and lipophilicity. Among the studied compounds, structure 16 should be considered as the best starting structure for further studies, since it demonstrated the lowest lipophilic character within the series while retaining biological activity. Sum of ranking differences (SRD) analysis indicated that the chromatographic approach, regardless of the technique employed, should be considered as the best approach for lipophilicity assessment of isoxazolones.

Quantitative Structure-Retention Relationships with Non-Linear Programming for Prediction of Chromatographic Elution Order

In this work, we employed a non-linear programming (NLP) approach via quantitative structure–retention relationships (QSRRs) modelling for prediction of elution order in reversed phase-liquid chromatography. With our rapid and efficient approach, error in prediction of retention time is sacrificed in favor of decreasing the error in elution order. Two case studies were evaluated: (i) analysis of 62 organic molecules on the Supelcosil LC-18 column; and (ii) analysis of 98 synthetic peptides on seven reversed phase-liquid chromatography (RP-LC) columns with varied gradients and column temperatures. On average across all the columns, all the chromatographic conditions and all the case studies, percentage root mean square error (%RMSE) of retention time exhibited a relative increase of 29.13%, while the %RMSE of elution order a relative decrease of 37.29%. Therefore, sacrificing %RMSE(t_R) led to a considerable increase in the elution order predictive ability of the QSRR models across all the case studies. Results of our preliminary study show that the real value of the developed NLP-based method lies in its ability to easily obtain better-performing QSRR models that can accurately predict both retention time and elution order, even for complex mixtures, such as proteomics and metabolomics mixtures.

Fiber-Optic Raman Spectroscopy with Nature-Inspired Genetic Algorithms Enhances Real-Time in Vivo Detection and Diagnosis of Nasopharyngeal Carcinoma

Raman spectroscopy is an optical vibrational spectroscopic technique capable of probing specific biochemical structures and conformation of tissue and cells in biomedical systems. This work aims to assess the clinical utility of a fiber-optic Raman spectroscopy with nature-inspired genetic algorithms for enhancing in vivo detection and diagnosis of nasopharyngeal carcinoma (NPC) patients. The Raman diagnostic platform is developed based on simultaneous fingerprint (FP) and high-wavenumber (HW) fiber-optic Raman endoscopy associated with genetic algorithms-partial least-squares-linear discriminant analysis (GA-PLS-LDA). A total of 2126 in vivo FP/HW Raman spectra (598 NPC, 1528 normal) acquired from 113 tissue sites of 14 NPC patients and 48 healthy subjects during nasopharyngeal endoscopic examinations. Distinct Raman peaks have been identified (853 cm^-1 - proteins, 1209 cm^-1 - phenylalanine, 1265 cm^-1 - proteins, 1335 cm^-1 - proteins and nucleic acids, 1554 cm^-1 - tryptophan, porphyrin, 2885 cm^-1 - lipids, 2940 cm^-1 - proteins, 3009 cm^-1 - lipids, and 3250 cm^-1 - water) that are related to the significant biochemical changes ( p < 1 × 10^-5) in NPC compared to normal tissue. Raman diagnostic performance is evaluated through the leave-one-object (tissue site)-out cross-validation (LOOCV) method. A statistically significant GA-PLS-LDA model ( p < 1 × 10^-5) on FP/HW Raman yields a CV diagnostic accuracy of 98.23% (111/113), sensitivity of 93.33% (28/30), and specificity of 100% (83/83) for NPC classification. This work demonstrates that the fiber-optic FP/HW Raman diagnostic platform developed has great promise for improving real-time in vivo detection and diagnosis of NPC at the molecular level during clinical nasopharyngeal endoscopy.

Non-Linear Quantitative Structure⁻Activity Relationships Modelling, Mechanistic Study and In-Silico Design of Flavonoids as Potent Antioxidants

In this work, we developed quantitative structure-activity relationships (QSAR) models for prediction of oxygen radical absorbance capacity (ORAC) of flavonoids. Both linear (partial least squares-PLS) and non-linear models (artificial neural networks-ANNs) were built using parameters of two well-established antioxidant activity mechanisms, namely, the hydrogen atom transfer (HAT) mechanism defined with the minimum bond dissociation enthalpy, and the sequential proton-loss electron transfer (SPLET) mechanism defined with proton affinity and electron transfer enthalpy. Due to pronounced solvent effects within the ORAC assay, the hydration energy was also considered. The four-parameter PLS-QSAR model yielded relatively high root mean square errors (RMSECV = 0.783, RMSEE = 0.668, RMSEP = 0.900). Conversely, the ANN-QSAR model yielded considerably lower errors (RMSEE = 0.180 ± 0.059, RMSEP1 = 0.164 ± 0.128, and RMSEP2 = 0.151 ± 0.114) due to the inherent non-linear relationships between molecular structures of flavonoids and ORAC values. Five-fold cross-validation was found to be unsuitable for the internal validation of the ANN-QSAR model with a high RMSECV of 0.999 ± 0.253; which is due to limited sample size where resampling with replacement is a considerably better alternative. Chemical domains of applicability were defined for both models confirming their reliability and robustness. Based on the PLS coefficients and partial derivatives, both models were interpreted in terms of the HAT and SPLET mechanisms. Theoretical computations based on density functional theory at ωb97XD/6-311++G(d,p) level of theory were also carried out to further shed light on the plausible mechanism of anti-peroxy radical activity. Calculated energetics for simplified models (genistein and quercetin) with peroxyl radical derived from 2,2'-azobis (2-amidino-propane) dihydrochloride suggested that both SPLET and single electron transfer followed by proton loss (SETPL) mechanisms are competitive and more favorable than HAT in aqueous medium. The finding is in good accord with the ANN-based QSAR modelling results. Finally, the strongly predictive ANN-QSAR model was used to predict antioxidant activities for a series of 115 flavonoids designed combinatorially with flavone as a template. Structural trends were analyzed, and general guidelines for synthesis of new flavonoid derivatives with potentially potent antioxidant activities were given.

Imputation of Assay Bioactivity Data Using Deep Learning

We describe a novel deep learning neural network method and its application to impute assay pIC₅₀ values. Unlike conventional machine learning approaches, this method is trained on sparse bioactivity data as input, typical of that found in public and commercial databases, enabling it to learn directly from correlations between activities measured in different assays. In two case studies on public domain data sets we show that the neural network method outperforms traditional quantitative structure-activity relationship (QSAR) models and other leading approaches. Furthermore, by focusing on only the most confident predictions the accuracy is increased to R² > 0.9 using our method, as compared to R² = 0.44 when reporting all predictions.

Building a Quantitative Structure-Property Relationship (QSPR) Model

Knowing the physicochemical and general biochemical properties of a compound is critical to understanding how it behaves in different biological environments and to anticipating what is likely to happen in situations where that behavior cannot be measured directly. Quantitative structure-property relationship (QSPR) models provide a way to predict those properties even before a compound has been synthesized simply by knowing what its structure would be. This chapter describes a general workflow for compiling the data upon which a useful QSPR model is built, curating it, evaluating that model's performance, and then analyzing the predictive errors with an eye toward identifying systematic errors in the input data. The focus here is on models for the absorption, distribution, metabolism, and excretion (ADME) properties of drugs and toxins, but the considerations explored are general and applicable to any QSPR.

Target-based drug discovery through inversion of quantitative structure-drug-property relationships and molecular simulation: CA IX-sulphonamide complexes

In this work, a target-based drug screening method is proposed exploiting the synergy effect of ligand-based and structure-based computer-assisted drug design. The new method provides great flexibility in drug design and drug candidates with considerably lower risk in an efficient manner. As a model system, 45 sulphonamides (33 training, 12 testing ligands) in complex with carbonic anhydrase IX were used for development of quantitative structure-activity-lipophilicity (property)-relationships (QSPRs). For each ligand, nearly 5,000 molecular descriptors were calculated, while lipophilicity (logk_w) and inhibitory activity (logK_i) were used as drug properties. Genetic algorithm-partial least squares (GA-PLS) provided a QSPR model with high prediction capability employing only seven molecular descriptors. As a proof-of-concept, optimal drug structure was obtained by inverting the model with respect to reference drug properties. 3509 ligands were ranked accordingly. Top 10 ligands were further validated through molecular docking. Large-scale MD simulations were performed to test the stability of structures of selected ligands obtained through docking complemented with biophysical experiments.

Retention Index Prediction Using Quantitative Structure-Retention Relationships for Improving Structure Identification in Nontargeted Metabolomics

Structure identification in nontargeted metabolomics based on liquid-chromatography coupled to mass spectrometry (LC-MS) remains a significant challenge. Quantitative structure-retention relationship (QSRR) modeling is a technique capable of accelerating the structure identification of metabolites by predicting their retention, allowing false positives to be eliminated during the interpretation of metabolomics data. In this work, 191 compounds were grouped according to molecular weight and a QSRR study was carried out on the 34 resulting groups to eliminate false positives. Partial least squares (PLS) regression combined with a Genetic algorithm (GA) was applied to construct the linear QSRR models based on a variety of VolSurf+ molecular descriptors. A novel dual-filtering approach, which combines Tanimoto similarity (TS) searching as the primary filter and retention index (RI) similarity clustering as the secondary filter, was utilized to select compounds in training sets to derive the QSRR models yielding R² of 0.8512 and an average root mean square error in prediction (RMSEP) of 8.45%. With a retention index filter expressed as ±2 standard deviations (SD) of the error, representative compounds were predicted with >91% accuracy, and for 53% of the groups (18/34), at least one false positive compound could be eliminated. The proposed strategy can thus narrow down the number of false positives to be assessed in nontargeted metabolomics.

Interpretation of ANN-based QSAR models for prediction of antioxidant activity of flavonoids

Quantitative structure-activity relationships (QSARs) built using machine learning methods, such as artificial neural networks (ANNs) are powerful in prediction of (antioxidant) activity from quantum mechanical (QM) parameters describing the molecular structure, but are usually not interpretable. This obvious difficulty is one of the most common obstacles in application of ANN-based QSAR models for design of potent antioxidants or elucidating the underlying mechanism. Interpreting the resulting models is often omitted or performed erroneously altogether. In this work, a comprehensive comparative study of six methods (PaD, PaD₂ , weights, stepwise, perturbation and profile) for exploration and interpretation of ANN models built for prediction of Trolox-equivalent antioxidant capacity (TEAC) QM descriptors, is presented. Sum of ranking differences (SRD) was used for ranking of the six methods with respect to the contributions of the calculated QM molecular descriptors toward TEAC. The results show that the PaD, PaD₂ and profile methods are the most stable and give rise to realistic interpretation of the observed correlations. Therefore, they are safely applicable for future interpretations without the opinion of an experienced chemist or bio-analyst. © 2018 Wiley Periodicals, Inc.

Exploring the peptide retention mechanism in molecularly imprinted polymers

Molecularly imprinted polymers (MIPs) have been used as useful sorbents in solid-phase extraction for a wide range of molecules and sample matrices. Their unique selectivity can be fine-tuned in the imprinting process and is crucial for the extraction of macromolecules from complex matrices such as serum. A relevant example of this is the application of MIPs to peptides in diagnostic assays. In this article the selectivity of MIPs, previously implemented in a quantitative mass-spectrometric assay for the biomarker pro-gastrin-releasing peptide, is investigated. Partial least squares regression was used to generate models for the evaluation and prediction of the retention mechanism of MIPs. A hypothesis on interactions of MIPs with the target peptide was verified by ad hoc experiments considering the relevant peptide physicochemical properties highlighted from the multivariate analysis. Novel insights into and knowledge of the driving forces responsible for the MIP selectivity have been obtained and can be directly used for further optimization of MIP imprinting strategies. Graphical Abstract Applied analytical strategy: the Solid Phase Extraction (SPE) of digested Bovin Serum Albumin (BSA), using Molecularly Imprinted Polymers (MIP), is followed by the liquid chromatography-mass spectrometry (LC-MS) analysis for the identification of the retained peptides. The further application of multivariate analysis allows setting up a Partial Least Square (PLS) model, which describes the peptide retention into the MIP and gives additional knowledge to be used in the optimization of the MIP and the whole SPE method.

Shuffling cross-validation-bee algorithm as a new descriptor selection method for retention studies of pesticides in biopartitioning micellar chromatography

Bee algorithm (BA) is an optimization algorithm inspired by the natural foraging behaviour of honey bees to find the optimal solution which can be proposed to feature selection. In this paper, shuffling cross-validation-BA (CV-BA) was applied to select the best descriptors that could describe the retention factor (log k) in the biopartitioning micellar chromatography (BMC) of 79 heterogeneous pesticides. Six descriptors were obtained using BA and then the selected descriptors were applied for model development using multiple linear regression (MLR). The descriptor selection was also performed using stepwise, genetic algorithm and simulated annealing methods and MLR was applied to model development and then the results were compared with those obtained from shuffling CV-BA. The results showed that shuffling CV-BA can be applied as a powerful descriptor selection method. Support vector machine (SVM) was also applied for model development using six selected descriptors by BA. The obtained statistical results using SVM were better than those obtained using MLR, as the root mean square error (RMSE) and correlation coefficient (R) for whole data set (training and test), using shuffling CV-BA-MLR, were obtained as 0.1863 and 0.9426, respectively, while these amounts for the shuffling CV-BA-SVM method were obtained as 0.0704 and 0.9922, respectively.

Rapid Method Development in Hydrophilic Interaction Liquid Chromatography for Pharmaceutical Analysis Using a Combination of Quantitative Structure-Retention Relationships and Design of Experiments

A design-of-experiment (DoE) model was developed, able to describe the retention times of a mixture of pharmaceutical compounds in hydrophilic interaction liquid chromatography (HILIC) under all possible combinations of acetonitrile content, salt concentration, and mobile-phase pH with R² > 0.95. Further, a quantitative structure-retention relationship (QSRR) model was developed to predict retention times for new analytes, based only on their chemical structures, with a root-mean-square error of prediction (RMSEP) as low as 0.81%. A compound classification based on the concept of similarity was applied prior to QSRR modeling. Finally, we utilized a combined QSRR-DoE approach to propose an optimal design space in a quality-by-design (QbD) workflow to facilitate the HILIC method development. The mathematical QSRR-DoE model was shown to be highly predictive when applied to an independent test set of unseen compounds in unseen conditions with a RMSEP value of 5.83%. The QSRR-DoE computed retention time of pharmaceutical test analytes and subsequently calculated separation selectivity was used to optimize the chromatographic conditions for efficient separation of targets. A Monte Carlo simulation was performed to evaluate the risk of uncertainty in the model's prediction, and to define the design space where the desired quality criterion was met. Experimental realization of peak selectivity between targets under the selected optimal working conditions confirmed the theoretical predictions. These results demonstrate how discovery of optimal conditions for the separation of new analytes can be accelerated by the use of appropriate theoretical tools.

On feature selection for supervised learning problems involving high-dimensional analytical information

Feature selection for supervised learning problems involving analytical information.