QSPR Models Research Articles

A QSPR Model for Henry's Law Constants of Organic Compounds in Water and Ethanol for Distilled Spirits.

Henry's law describes the vapor-liquid equilibrium for dilute gases dissolved in a liquid solvent phase. Descriptions of vapor-liquid equilibrium allow the design of improved separations in the food and beverage industry. The consumer experience of taste and odor are greatly affected by the liquid and vapor phase behavior of organic compounds. This study presents a machine learning (ML) based model that allows quick, accurate predictions of Henry's law constants (kH) for many common organic compounds. Users input only a Simplified Molecular-Input Line-Entry System (SMILES) string or a common English name, and the model returns Henry's law estimates for compounds in water and ethanol. Training was performed on 5,690 compounds. Training data were gathered from an existing database and were supplemented with quantum mechanical (QM) calculations. An extra trees regression model was generated that predicts kH with a mean absolute error of 1.3 in log space and an R2 of 0.98. The model is applied to common flavor and odor compounds in bourbon whiskey as a test case for food and beverage applications.

Distance based topological characterization, graph energy prediction, and NMR patterns of benzene ring embedded in P-type surface in 2D network

Nanostructures are tiny objects at the molecular and microscopic scale, with carbon nanotubes being the most notable among them. The elements possess exceptional microelectronic properties and other unique characteristics. Researchers have recently focused on the mathematical features of these materials. Molecular descriptors are crucial in mathematical chemistry, particularly in QSAR and QSPR modeling. Topological indices hold a significant position among them. This study presents the precise formulation of the ten most crucial topological indices for a benzene ring positioned on a P-type surface within the highly symmetric 2D lattice BCZ48\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\hbox {BCZ}_{48}$$\\end{document}. We have incorporated the computed indices to develop a predictive model for the graph energy of the 2D lattice and, in addition, provided the NMR patterns and the HOMO-LUMO gap.

M, NM-polynomials Based on Reverse, Reduced Reverse Degree and Neighborhood Degree Based Topological Indices with Applications to Bond Energy of Y-Junction Nanotubes.

In graph theory, M polynomials like the matching polynomial are very crucial in examining the matching structures within graphs, while NM polynomials extends this to analyze non-matching edges. These polynomials are important in many fields, including chemistry and network architecture. They support the derivation of topological indices for protein structure analysis, network communication optimization, and drug design in QSAR/QSPR investigations. The aim of this paper is to define novel M and NM polynomials for different topological indices and to derive their closed-form expressions, specifically for Y-junction nanotubes. These new polynomials and indices are employed to create a robust QSPR model to predict bond energy in Y-junction nanotubes, that provide high accuracy and reliability in the model's statistical performance. This paper introduces new forms of M and NM polynomials tailored to specific topological indices related to reverse and neighborhood reverse properties. We derive closed-form expressions for these indices in Y-junction nanotubes. Furthermore, we develop a QSPR model to predict bond energy in Y-junction nanotubes using the newly defined indices. We define novel M and NM polynomials for various topological indices and derive precise expressions for Y-junction nanotubes. Utilizing these indices, we construct a highly accurate QSPR model (R² = 0.999) for predicting bond energy in Y-junction nanotubes, confirming the validity of our polynomial definitions and indices. We have presented new M and NM polynomials for different topological indices and derive their expressions specifically for Y-junction nanotubes. With these newly defined indices, we have developed a highly precise QSPR model to predict bond energy, achieving an R² value of 0.999. This work underscores the effectiveness of our polynomial definitions and indices in predicting material properties.

QSPR models for pyrimidine-based corrosion inhibitors in acid medium

QSPR models for pyrimidine-based corrosion inhibitors in acid medium

QSPR-based prediction model for the melting point of polycyclic aromatic hydrocarbons using MLR and ANN methods

The melting point is an important property that helps generate specific compounds with desired thermos-physical properties. Much work has been done applying quantitative structure-property relationships to improve the melting-point correlations, but they are unreliable. This gap might come from the melting point's sensitivity for small molecular variations and descriptors, which currently do not fully consider all factors determining melting behavior. In this work, we provide a QSPR model for predicting the melting point of a heterogeneous polycyclic aromatic hydrocarbons dataset. The model was generated using a robust hybrid linear approach (Genetic Algorithm-Multiple Linear Regression) and a nonlinear approach named Artificial Neural Network (ANN). Three descriptors were chosen to explain the influence of molecular weight and symmetry on melting point. The resulting QSPR model can model melting-point behavior with an RMSE of 34.88K, a coefficient correlation value of R²=0.887, and a prediction coefficient of Q²LOO= 0.863. This study reveals that the results produced by MLR were appropriate and served to predict melting points. However, compared to the results obtained by the ANN model, we conclude that the latter is more effective and better than the MLR model. Based on the results, our suggested model may be effective in predicting melting points, and the selected descriptors play essential roles in determining melting points.

Integration of Nontarget Screening and QSPR Models to Identify Novel Organophosphate Esters of High Priority in Aquatic Environment.

With the development of large numbers of novel organophosphate esters (OPEs) alternatives, it is imperative to screen and identify those with high priority. In this study, surface water, biofilms, and freshwater snails were collected from the flow-in rivers of Taihu Lake Basin, China. Screened by target, suspect, and nontarget analysis, 11 traditional and 14 novel OPEs were identified, of which 5 OPEs were first discovered in Taihu Lake Basin. The OPE concentrations in surface water ranged from 196 to 2568 ng/L, with the primary homologue tris(2,4-ditert-butylphenyl) phosphate (TDtBPP) being newly identified, which was likely derived from the transformation of tris(2,4-ditert-butylphenyl) phosphite. The majority of the newly identified OPEs displayed substantially higher bioaccumulation and biomagnification potentials in the biofilm-snail food chain than the traditional ones. Quantitative structure-property relationship models revealed both hydrophobicity and polarity influenced the bioaccumulation and biomagnification of the OPEs, while electrostatic attraction also had a contribution to the bioaccumulation in the biofilm. TDtBPP was determined as the utmost priority by toxicological priority index scheme, which integrated concentration, bioaccumulation, biomagnification, acute toxicity, and endocrine disrupting potential of the identified OPEs. These findings provide novel insights into the behaviors of OPEs and scientific bases for better management of high-risk pollutants in aquatic ecosystem.

Gas/particle partitioning of PCDD/Fs: Distributions and implications for available models

Polychlorinated dibenzo-p-dioxins/furans (PCDD/Fs) are semi-volatile organic compounds (SVOCs) existing in the atmosphere in the gas and particulate phase, remain persistent for a long time and pose a high risk to the environment and human health. In this study, PCDD/F measurements were made in an urban area between June 2022 and April 2023. In order to understand the fate of PCDD/Fs, the gas/particle (G/P) partitioning was studied. Although various models have been developed to determine the G/P partitioning of SVOCs, only logKp-logPL0, Junge-Pankow and Harner-Bidleman models are generally used for PCDD/Fs. In this study, nine different models (Junge-Pankow, Harner-Bidleman, Dachs-Eisenreich, Li-Ma-Yang, pp-LFER, mp-pp-LFER, QSPR, logKp-logPL0, logKp-logKOA) were employed to determine the G/P partitioning. To the best of our knowledge, pp-LFER, mp-pp-LFER and QSPR models were evaluated for PCDD/Fs for the first time in this study. In addition, the performance of the models within the equilibrium (EQ), non-equilibrium (NE) and maximum partitioning (MP) domain was investigated for PCDD/Fs for the first time in this study. Accordingly, models based on absorption in the EQ domain, adsorption in the NE domain and adsorption and absorption mechanisms in the MP domain were found to be effective in explaining the G/P transitions. It was determined that there is no equilibrium situation in the G/P partitioning. The Junge-Pankow, pp-LFER, Li-Ma-Yang and QSPR models under-predicted the particle fraction values while the other models showed a high prediction profile. The Li-Ma-Yang model showed the closest results to the measured particle fraction values, and it determined that deposition mechanisms are of non-negligible importance in the G/P partitioning of PCDD/Fs. One of the new models, the pp-LFER model, has shown remarkable success at high logKOA values. The mp-pp-LFER model, which overestimated the contribution of the adsorption mechanism, showed a very high prediction profile compared to the measured values.

A Framework for Developing Tools to Predict PFAS Physical–Chemical Properties and Mass-Partitioning Parameters

A framework for developing predictive models for PFAS physical–chemical properties and mass-partitioning parameters is presented. The framework is based on the objective of developing tools that are of sufficient simplicity to be used rapidly and routinely for initial site investigations and risk assessments. This is accomplished by the use of bespoke PFAS-specific QSPR models. The development of these models entails aggregation and curation of measured data sets for a target property or parameter, supplemented by estimates produced with quantum–chemical ab initio predictions. The application of bespoke QSPR models for PFAS is illustrated with several examples, including partitioning to different interfaces, uptake by several fish species, and partitioning to four different biological materials. Reasonable correlations to molar volume were observed for all systems. One notable observation is that the slopes of all of the regression functions are similar. This suggests that the partitioning processes in all of these systems are to some degree mediated by the same mechanism, namely hydrophobic interaction. Special factors and elements requiring consideration in the development of predictive models are discussed, including differences in bulk-phase versus interface partitioning processes.

Accurate & simple open-sourced no-code machine learning and CDFT predictive models for the antioxidant activity of phenols

Phenolic compounds (PC) are important antioxidant biomolecules for medicine and foods industries. The DDPH test is used for testing antioxidant capacity. A fully No-Code methodology is presented for building QSPR models for the anti-DPPH activity of 202 PC. Machine learning (ML) algorithms were used for dimensionality reduction (PCA, InfoGain, GainRatio, CfsSubset) and predictive model training (J48, RandomTree, JCHAID*). Conceptual Density Functional Theory (CDFT) descriptors are calculated at the GFN1-xTB and GFN2-xTB levels of theory and the resulting global reactivity descriptors are used to train the ML models. The obtained Decision Tree (DT) models all present over 85% accuracy and Substantial Agreement with Reality, both for the internal and external validation. All the developed models adhere to the OECD guidelines for regulatory QSPR developments and are discussed in a mechanistic context. This research presents a novel, simple and codeless methodology for developing highly precise predictive models for the anti-DPPH activity of PC, successfully bridging the gap between experimental chemistry, theoretical physical chemistry, and ML.

Implementation of quantum machine learning in predicting corrosion inhibition efficiency of expired drugs

This study explores the potential of quantum machine learning (QML) 's potential in predicting expired pharmaceutical compounds' corrosion inhibition capacity. This investigation utilized a QSPR model where features derived from density functional theory (DFT) calculations are used as input, while the corrosion inhibition efficiency (CIE) values derived from the experimental study are used as target output. The proposed QML model exhibits varying performance through evaluation metrics, particularly concerning encoding and ansatz design. Notably, the quantum support vector machine (QSVM) demonstrates superior predictive performance compared to the variational quantum circuit (VQC) and quantum neural network (QNN). Specifically, the QSVM model achieves the highest scores in evaluation metrics, with a root mean squared error (RMSE) of 4.36, mean absolute error (MAE) of 3.19, and mean absolute deviation (MAD) of 3.08. The research highlights the importance of larger datasets to improve predictability and emphasizes the potential of QML in investigating anti-corrosion materials. Despite its limitations, this study establishes a foundational framework for utilizing QML to forecast anti-corrosive qualities.

Development of an interpretable QSPR model to predict the octanol-water partition coefficient based on three artificial intelligence algorithms

This study aims to significantly improve existing quantitative structure-property relationship (QSPR) models for predicting the octanol-water partition coefficient (KOW). This is because accurate predictions of KOW are crucial for assessing the environmental behavior and bioaccumulation potential of chemicals. Previous models have reported determination coefficient (R2) values between 0.9451 and 0.9681, and this research seeks to exceed these benchmarks. Three machine learning (ML) models are explored, i.e., feed-forward neural networks (FNN), Extreme Gradient Boosting (XGBoost), and random forest (RF). Using a dataset of 14,610 solvents (14,580 after data cleaning) and 21 molecular descriptors derived from SMILES representations, we rigorously evaluate these models based on R2, mean absolute error (MAE), root mean squared error (RMSE), and mean relative error (MRE). Notably, the best model developed, the XGBoost-based QSPR, demonstrated exceptional performance, exhibiting an impressive R2 value of 0.9772, surpassing benchmarks set by prior research models. Additionally, shapley additive explanation (SHAP) analysis is also employed for model interpretation, and it is revealed that the top five influential input features include SMR_VSA8, SMR_VSA3, Kappa2, HeavyAtomCount, and fr_furan. This study not only sets a new benchmark for KOW prediction accuracy but also enhances the interpretability of QSPR models.

QSPR analysis for physiochemical properties of new potential antimalarial compounds involving topological indices

AbstractMalaria has a wide impact on the healthcare system, affecting everyone from hyperendemic areas who dearth access to medical treatment to international tourists returning to nonendemic regions with tertiary referral care. Implementing timely and accurate diagnosis is necessary to stop malaria's growing global effect, which is attributed to the development of antimalarial medication resistance. In this research, potential antimalarial compounds, including quinine, primaquine, artemether, artelinic acid, triazoles‐modified, and so forth are examined with topological indices (TI) and linear regression modeling of said compounds. Some degree based topological indices are assembled for these drugs' chemical graphs. We compute the topological descriptors with the limiting behaviors associated with these pharmaceutical drugs. Moreover, in this study some of the physicochemical features of the drugs are estimated using these TIs in the QSPR models. These indices better reflect chemical properties such as boiling point, complexity, polarity, and so forth and the outcomes of regression technique acquired QSPR studies may aid in the creation of fresh medicines for the treatment of malaria. These indices and antimalarial activity were discovered to be related. Other compound series do very well with this relationship. The TIs could be a key component in creating and synthesizing new antimalarial drugs.

Multicriteria decision making attributes and estimation of physicochemical properties of kidney cancer drugs via topological descriptors.

Based on topological descriptors, QSPR analysis is an incredibly helpful statistical method for examining many physical and chemical properties of compounds without demanding costly and time-consuming laboratory tests. Firstly, we discuss and provide research on kidney cancer drugs using topological indices and done partition of the edges of kidney cancer drugs which are based on the degree. Secondly, we examine the attributes of nineteen drugs casodex, eligard, mitoxanrone, rubraca, and zoladex, etc and among others, using linear QSPR model. The study in the article not only demonstrates a good correlation between TIs and physical characteristics with the QSPR model being the most suitable for predicting complexity, enthalpy, molar refractivity, and other factors and a best-fit model is attained in this study. This theoretical approach might benefit chemists and professionals in the pharmaceutical industry to forecast the characteristics of kidney cancer therapies. This leads towards new opportunities to paved the way for drug discovery and the formation of efficient and suitable treatment options in therapeutic targeting. We also employed multicriteria decision making techniques like COPRAS and PROMETHEE-II for ranking of said disease treatment drugs and physicochemical characteristics.

Characteristic structures of liquid crystal monomers in EI-MS analysis and the potential application in suspect screening

Liquid crystal monomers (LCMs) are of emerging concern due to their ubiquitous presence in indoor and outdoor environments and their potential negative impacts on human health and ecosystems. Suspect screening approaches have been developed to monitor thousands of LCMs that could enter the environment, but an updated suspect list of LCMs is difficult to maintain given the rapid development of material innovations. To facilitate suspect screening for LCMs, in-silico mass fragmentation model and quantitative structure-activity relationship (QSPR) models were applied to predict electron ionization (EI) mass spectra of LCMs. The in-silico model showed limited predictive power for EI mass spectra, while the QSPR models trained with 437 published mass spectra of LCMs achieved an acceptable absolute error of 12 percentage points in predicting the relative intensity of the molecular ion, but failed to predict the mass-to-charge ratio of the base peak. A total of 41 characteristic structures were identified from an updated suspect list of 1606 LCMs. Multi-phenyl groups form the rigid cores of 85% of LCMs and produce 154 characteristic peaks in EI mass spectra. Monitoring the characteristic structures and fragments of LCMs may help identify new LCMs with the same rigid cores as those in the suspect list.

Docking study of ferulic acid derivates on FGFR1, ADME prediction, and QSPR analysis

Background: FGFR-1 is an angiogenic receptor that plays a huge role in the cancer growth pathway. Angiogenesis inhibitory drugs released have significant side effects. Therefore, research into discovering anti-angiogenic agents to achieve good health and well-being is still necessary. Objective: To design the novel anti-angiogenic candidates from ferulic acid (FA) by docking study on FGFR1, to predict the ADME profile, and to find out the structural relationship of their pharmacokinetic properties as QSPR analysis. Method: Autodock Tools performed a docking study. ADME prediction was conducted using SwissADME. The MLR approach determined the QSPR model. Result: The docking results showed that FA-8 and FA-18 had the lowest free energy binding, inhibition constant, and GI absorption. The QSPR analysis obtained the equation model: Log HIA = 0,018 Log P2 + 0,069 Log P + 0,020 CMR + 0,001 Etotal + 1,771 with n = 24, correlation coefficient (r)= 0.621, p-value= 0.046 and F-value= 2.975. Conclusion: Modifying FA on the phenolic moiety replaced by an ester increased the activity and ADME profile. The predicted bioavailability was supported by high Log P, molar refractivity (CMR), and electronic factor (Etotal). It is recommended that lipophilicity be increased to achieve better pharmacokinetic properties.

A QSPR analysis of physical properties of antituberculosis drugs using neighbourhood degree-based topological indices and support vector regression

Topological indices are molecular descriptors used in QSPR modelling to predict the physicochemical properties of molecules. Topological indices are used in numerous applications in drug design. In this work, we compute the neighbourhood degree-based topological indices of 15 antituberculosis drugs, we studied the QSPR analysis of these drugs using support vector regression. The efficiency of support vector regression is determined by comparing it with the classical linear regression. Our QSPR model further shows the superiority of the SVR model as a better predictive model in QSPR analysis of the physical properties of antituberculosis drugs. The findings in this study are a further contribution to the field of chemical graph theory and drug design, providing a deeper understanding of neighbourhood degree-based topological indices and their predictive capabilities in QSPR model.

Determination of experimental solute descriptor values for methyl 3-nitrobenzoate by liquid–liquid partitioning and gas chromatography

ABSTRACT In this study, methyl 3-nitrobenzoate, a popular compound used to protect crops and in the textile industry, was studied using liquid–liquid partitioning and gas chromatography and the Abraham solvation parameter descriptor values were determined for potential applications in QSPR. The solver algorithm in Excel was used to determine the descriptor values for methyl 3-nitrobenzoate, resulting in E = 1.0616, S = 1.4170, A = 0.00, L = 6.1354, B = 0.6198, and V = 1.2468 with a standard deviation of 0.076. In the situations when toxicity and exposure assessment data are scarce, the application of QSPR models, such as the Abraham solvation parameter model, can aid in the estimation of the environmental impact of chemicals. With the objective to facilitate physicochemical property estimations of methyl 3-nitrobenzoate widely used in the textile and agricultural industries, this study offers experimental solute descriptor values of the Abrham’s solvation parameter model.

Machine-Learning-Based Prediction of Plant Cuticle-Air Partition Coefficients for Organic Pollutants: Revealing Mechanisms from a Molecular Structure Perspective.

Accurately predicting plant cuticle-air partition coefficients (Kca) is essential for assessing the ecological risk of organic pollutants and elucidating their partitioning mechanisms. The current work collected 255 measured Kca values from 25 plant species and 106 compounds (dataset (I)) and averaged them to establish a dataset (dataset (II)) containing Kca values for 106 compounds. Machine-learning algorithms (multiple linear regression (MLR), multi-layer perceptron (MLP), k-nearest neighbors (KNN), and gradient-boosting decision tree (GBDT)) were applied to develop eight QSPR models for predicting Kca. The results showed that the developed models had a high goodness of fit, as well as good robustness and predictive performance. The GBDT-2 model (Radj2 = 0.925, QLOO2 = 0.756, QBOOT2 = 0.864, Rext2 = 0.837, Qext2 = 0.811, and CCC = 0.891) is recommended as the best model for predicting Kca due to its superior performance. Moreover, interpreting the GBDT-1 and GBDT-2 models based on the Shapley additive explanations (SHAP) method elucidated how molecular properties, such as molecular size, polarizability, and molecular complexity, affected the capacity of plant cuticles to adsorb organic pollutants in the air. The satisfactory performance of the developed models suggests that they have the potential for extensive applications in guiding the environmental fate of organic pollutants and promoting the progress of eco-friendly and sustainable chemical engineering.

Exploring the relationships between physiochemical properties of nanoparticles and cell damage to combat cancer growth using simple periodic table-based descriptors.

A comprehensive knowledge of the physical and chemical properties of nanomaterials (NMs) is necessary to design them effectively for regulated use. Although NMs are utilized in therapeutics, their cytotoxicity has attracted great attention. Nanoscale quantitative structure-property relationship (nano-QSPR) models can help in understanding the relationship between NMs and the biological environment and provide new ways for modeling the structural properties and bio-toxic effects of NMs. The goal of the study is to construct fully validated property-based models to extract relevant features for estimating and influencing the zeta potential and obtaining the toxicity profile regarding cell damage in the treatment of cancer cells. To achieve this, QSPR modeling was first performed with 18 metal oxide (MeOx) NMs to measure their materials properties using periodic table-based descriptors. The features obtained were later applied for zeta potential calculation (imputation for sparse data) for MeOx NMs that lack such information. To further clarify the influence of the zeta potential on cell damage, a QSPR model was developed with 132 MeOx NMs to understand the possible mechanisms of cell damage. The results showed that zeta potential, along with seven other descriptors, had the potential to influence oxidative damage through free radical accumulation, which could lead to changes in the survival rate of cancerous cells. The developed QSPR and quantitative structure-activity relationship models also give hints regarding safer design and toxicity assessment of MeOx NMs.

QSPR Models Based on Multiple Linear Regression and Back-Propagation Artificial Neural Network for Predicting Electrical Conductivity of Ionic Liquids

QSPR Models Based on Multiple Linear Regression and Back-Propagation Artificial Neural Network for Predicting Electrical Conductivity of Ionic Liquids