Quantitative Structure-property Relationship Method Research Articles

Polymer expert – A software tool for de novo polymer design

A versatile and user-friendly “expert system” for de novo polymer design, named Polymer Expert, has been developed and implemented. Polymer Expert can be used to rapidly generate novel candidate polymer repeat units to meet desired performance targets. It is anticipated to accelerate innovation through materials science in industries that use polymers and polymer matrix composites. It was implemented by (1) generating an initial repeat unit database, (2) expanding this initial database into a large analog repeat unit database, (3) performing calculations for all repeat units in the large analog database by using quantitative structure–property relationships (QSPR) of broad applicability, and (4) integrating the resulting searchable library of repeat units and their predicted properties (PEARL, acronym for Polymer Expert Analog Repeat-unit Library) as a new module in a materials modeling and simulation software suite. Its use is illustrated by identifying biobased alternatives for poly(ethylene terephthalate) (PET) and bisphenol-A polycarbonate (BPAPC), alternatives for highly crystalline polypropylene homopolymer (PPHP) and 10% glass fiber containing polypropylene (PP10GF), and polymers that may provide unusually high dielectric constants. Many promising candidates were unobvious and unlikely to have been identified without using a polymer informatics approach. Future work will focus on improving the quality of candidate repeat units by refining the QSPR method, enhancing the diversity of candidate repeat units by expanding PEARL, providing additional interactive search options, and converting Polymer Expert into a versatile R&D platform that users can customize for their own needs.

Predicting the Potentiometric Sensitivity of Membrane Sensors Based on Modified Diphenylphosphoryl Acetamide Ionophores with QSPR Modeling.

While potentiometric, plasticized membrane sensors are known as convenient, portable and inexpensive analytical instruments, their development is time- and resource-consuming, with a poorly predictable outcome. In this study, we investigated the applicability of the QSPR (quantitative structure–property relationship) method for predicting the potentiometric sensitivity of plasticized polymeric membrane sensors, using the ionophore chemical structure as model input. The QSPR model was based on the literature data on sensitivity, from previously studied, structurally similar ionophores, and it has shown reasonably good metrics in relating ionophore structures to their sensitivities towards Cu2+, Cd2+ and Pb2+. The model predictions for four newly synthesized diphenylphosphoryl acetamide ionophores were compared with real potentiometric experimental data for these ionophores, and satisfactory agreement was observed, implying the validity of the proposed approach.

Simple Approach for Reliable Prediction of Solubility of Polymers in Environmentally Compatible Solvents

This work presents a simple approach for predicting the solubility parameter (δ) of polymers. It is based on the number of moles of hydrogen, nitrogen, oxygen, sulfur, fluorine, and silicon atoms per mole of repeating unit structures as well as two correcting functions based on the contributions of hydrogen bonding and polar groups. The largest available experimental data including the δ values of 163 amorphous polymers and amorphous phases of semicrystalline polymers are used to derive and test the new model. Different statistical parameters are used to confirm the high reliability of the novel method through internal and external validations as well as by comparing with two of the best existing quantitative structure–property relationship (QSPR) approaches containing complex descriptors. Since the available QSPR methods are restricted to polymers with repeating unit structures −(C1H2–C2R3R4)–, the results of the new method are compared with the outputs of QSPR methods for 97 polymers. The value of root-mean-square error (RMSE) of the novel approach for external validation of test data (57 different polymers) is 0.91 MPa1/2, which is close to RMSE values of the computed outputs of two complex QSPR methods, that is, 0.90 and 0.88 MPa1/2.

Anticorrosive Properties of Theophylline on Aluminium Corrosion in 1 M HCl: Experimental, and Computational Assessment of Iodide Ions Synergistic Effect

Aims : The aim of this study is to show the anti-corrosive properties of 1,3- dimethyl-7H-purine-2,6-dione on aluminium corrosion in 1 M hydrochloric acid and to study the synergy effect between iodide ions and this molecule. Background: There is a need for a research on eco-friendly, low toxic, and biodegradable corrosion inhibitors capable of protecting metals in order to support industrialists who spend large sums of money on replacing their corroded equipment. Objective: The main objective is to study the anti-corrosive properties of theophylline on aluminium corrosion in 1 M HCl. Methods: The anti-corrosive properties of theophylline on aluminium corrosion in 1 M HCl were evaluated using mass loss, Density Functional Theory at B3LYP/6-31G (d), and Quantitative Structure-Property Relationship methods. Results: The results obtained show that theophylline inhibition efficiency increases with concentration but decreases with increasing temperature with a maximum value of 88% for 5.10-3M at T = 298 K. The result from absorption isotherms reveals that theophylline adsorbs to the aluminium surface according to the modified Langmuir isotherm. Adejo Ekwenshi's isotherm has shown that the molecule adsorption on aluminium is essentially of a physical nature. Thermodynamic adsorption and activation parameters were calculated and analyzed. A synergistic effect between the studied molecule and the iodide ions was found. Furthermore, global and local reactivity were analyzed through density functional theory calculations. The quantitative structure-property relationship model has been used to correlate experimental and theoretical inhibition efficiencies. Conclusion: Theophylline is an excellent aluminum corrosion inhibitor in the current studied solution. Theoretical results were in agreement with the experimental data. Other: Theophylline is an excellent aluminum corrosion inhibitor in the current studied solution. Theoretical results were in agreement with the experimental data. Other: Finally, the best set of parameters to model the inhibition efficiency of analogous molecules were found.

Progress in QSPR modelling methods

<p indent="0mm">With the introduction of Materials Genome Initiative (MGI) in 2011, high-throughput material computation and material prediction have gradually become a hot topic in materials research. MGI has strong guiding significance and high practical application value as the deepening of the concept of environmental protection, low-consumption, faster, and high-throughput. MGI aims to convert the traditional “Trial Experiment” to “Computation to Experiment”, which has become the trend of materials research. There are two main ways to realize the MGI, the first one is the development of quantum chemical calculations and statistical mechanics, while the other one is the establishment of Quantitative Structure-Property Relationship (QSPR). Among them, the QSPR method has been widely used in recent years due to its excellent predictive properties. Combining data-driven and machine learning algorithms, the QSPR method has undergone major changes today, the most prominent of which is the change in the calculation method used in the QSPR method. Reasonable use of calculation methods in QSPR can greatly increase the speed of QSPR model formation and the accuracy of prediction, which is critical to predicting new materials. The calculation methods are the main factors that determine the accuracy and construction speed of the QSPR model. Choosing the best calculation method is very important to improve the prediction accuracy and calculation speed of the QSPR model. Therefore, this article first summarizes the QSPR model, briefly introduces the calculation steps of the QSPR method, focuses on the calculation methods of molecular descriptors and model optimization algorithms in QSPR, and analyzes the advantages and disadvantages of each method. Finally, this article summarizes the application trend of various calculation methods in QSPR in recent years, and concludes as follow: (1) There are many kinds of molecular descriptor calculation software, and most of the software calculation speed is quite fast. At the same time, the calculated number of molecular descriptors is pretty large, which can achieve better calculation results. However, each software still has its own limitations. Researchers can choose one or some software to calculate molecular descriptors according to their needs. (2) The preprocessing algorithms are mainly screening algorithms, including statistical methods, informatics methods, and biological methods. Evolutionary algorithms, which are developed by biological methods, are increasingly being used because of their excellent global screening capabilities. While the number of molecular descriptors obtained by calculation increase significantly, the global influence of molecular descriptors has been gradually emphasized. Therefore, in recent years, evolutionary algorithms have gradually become a popular choice for molecular descriptor screening. (3) The optimization methods mainly include machine learning algorithms, which can be classified into linear methods, nonlinear methods, and hybrid methods. The first two methods have their own advantages for linear methods can show directly the importance of each molecular descriptor and the nonlinear methods’ models are more accurate. In order to improve the efficiency of algorithm parameter calculation, in recent years, more and more global optimization algorithms have been introduced into machine learning algorithms as parameter optimization methods, which forms the third method—Hybrid optimization method.

Assessment of Recent Researches for Reliable Prediction of Density of Organic Compounds as well as Ionic Liquids and Salts Containing Energetic Groups at Room Temperature

AbstractOrganic and ionic compounds containing energetic groups have wide applications in industries because they can release their stored chemical energy upon external stimuli. Many different methods have been developed in recent years for reliable prediction of the densities of these compounds at room temperature because their detonation performance depends strongly on density. This work reviews the best available predictive models for important classes of energetic organic and ionic compounds that reduce the high costs of synthesis and development of the new proposed compounds. The advantages and limitations of different methods are discussed and compared for different kinds of neutral and ionic energetic compounds. Among different approaches, quantum‐chemical methods based on molecular surface electrostatic potential (MESP) and quantitative structure‐property relationship (QSPR) approaches are attractive for scientists and industries in recent years because they can be applied for a wide range of various types of compounds. For 25 neutral energetic organic compounds and 11 energetic ionic compounds where the percentages of deviations of the outputs of quantum‐chemical MESP‐based methods are large, it is shown that the outputs of the best available QSPR methods, which were embedded in new computer code (EMDB_1.0), are more accurate.

Singlet oxygen generation by porphyrins and metalloporphyrins revisited: A quantitative structure-property relationship (QSPR) study

Porphyrins and metalloporphyrins are used as photosensitizers in photocatalysis, photodynamic therapy (PDT), disinfection, degradation of persistent pollutants and other applications. Their mechanism of action involves intersystem crossing to triplet excited state followed by formation of singlet oxygen (1O2), which is a highly reactive species and mediates various oxidative processes. The design of advanced sensitizers based on porphyrin compounds have attracted significant attention in recent years. However, it is still difficult to predict the efficiency of singlet oxygen generation for a given structure. Our goal was to develop a quantitative structure-property relationship (QSPR) model for the fast virtual screening and prediction of singlet oxygen quantum yields for pophyrins and metalloporphyrins. We performed QSPR analysis of a dataset containing 32 compounds, including various porphyrins and their analogues (chlorins and bacteriochlorins). Quantum-chemical descriptors were calculated using Density Functional Theory (DFT), namely B3LYP and M062X functionals. Three different machine learning methods were used to develop QSPR models: random forest regression (RFR), support vector regression (SVR), and multiple linear regression (MLR). The optimal QSPR model «structure – singlet oxygen generation quantum yield» obtained using RFR method demonstrated high determination coefficient for the training set (R2 = 0.949) and the highest predicting ability for the test set (pred_R2 = 0.875). This proves that the developed QSPR method is realiable and can be directly applied in the studies of singlet oxygen generation both for free base porphyrins and their metal complexes. We believe that QSPR approach developed in this study can be useful for the search of new poprhyrin photosensitizers with enhanced singlet oxygen generation ability.

Thermal conductivity estimation of nitrogen-containing liquid organic compounds using QSPR methods from molecular structures

Thermal conductivity is an essential thermodynamic property. Therefore, the development of method for predicting thermal conductivity is utmost importance. In this study, 142 thermal conductivity data were collected which was divided into training set, validation set and prediction set. The structures of compounds were optimized in Gaussian 09W and the molecular descriptors were extracted by the Dragon software. And then we developed a new quantitative structure-property relationship (QSPR) linear model with 6 parameters for predicting the thermal conductivity of nitrogen-containing liquid organic compounds using multiple linear regression method (MLR). The squared correlation coefficient of training set, validation set and prediction set were 0.9685, 0.9808 and 0.9713, respectively. And the average absolute relative deviations (AARD) of each subset were 5.52%, 8.78% and 8.56%, respectively. In addition, the applicability domain of the developed model was analysed with Williams plot. This work can provide guidance for calculating the thermal conductivity of nitrogen-containing liquid organic compounds.

Thermal Conductivity Estimation of Diverse Liquid Aliphatic Oxygen-Containing Organic Compounds Using the Quantitative Structure-Property Relationship Method.

Thermal conductivity is an essential thermodynamic data in chemical engineering applications. Liquid aliphatic oxygen-containing organic compounds are important organic intermediates and raw materials. As a result, estimating thermal conductivity of liquid aliphatic oxygen-containing organic compounds is of significance in industry production. In this study, the genetic function approximation method was applied to screen descriptors and develop a 6-descriptor linear quantitative structure–property relationship model. The entire data set of these compounds covering 1064 thermal conductivity values was divided into 694-member training set, 298-member test set, and 72-member prediction set. The average absolute relative deviation of the training set, test set, and prediction set were 4.14, 4.41, and 4.16%, respectively. Model validation and Y-randomization test proved that the developed model has goodness-of-fit, predictive power, and robustness. In addition, the applicability domain of the developed model was visualized by the Williams plot. This study can provide a convenient method to estimate the thermal conductivity for researchers in chemical engineering production.

Solubility parameters and solvent affinities for polycaprolactone: A comparison of methods

ABSTRACTIntrinsic viscosity measurements were used in combination with the functional solubility parameter (FSP) and Hansen solubility parameter (HSP) fitting methods to determine the solubility parameters (SPs) of polycaprolactone (PCL). Despite using only eight solvents, a simple similarity criteria approach showed that the HSPs and FSPs were good predictors of the relative solvent‐PCL affinity compared to HSPs available in the literature and SPs calculated using additive group contribution methods. Three complementary computational methodologies—Conductor‐like Screening MOdel for Real Solvents (COSMO‐RS), partial solvation parameters (PSPs), and a thermodynamic quantitative structure–property relationship (QSPR) approach—were used to substantiate the relative solvent–PCL affinities revealed by the intrinsic viscosity measurements. The solvent affinities predicted by all three techniques were in good agreement with the trend observed in the experimental intrinsic viscosity data, but the COSMO‐RS activity coefficients, ln(γPCL), were slightly superior to the PSP and thermodynamic QSPR methods, particularly when incorporating the Elbro free‐volume combinatorial correction in the COSMO‐RS calculations. As part of this study, the FSP fitting algorithm was modified to obtain the PSPs for PCL in terms of the intrinsic viscosity data, thereby, presenting a promising new way to calculate the PSPs of polymers from empirical solubility and solvent affinity data. © 2020 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2020, 137, 48908.

QSPR versus fragment-based methods to predict octanol-air partition coefficients: Revisiting a recent comparison of both approaches

The octanol-air partition coefficient (KOA) is useful to assess the fate of organic chemicals in the environment. Very recently, an interesting comparison of current methods to predict this property (Chemosphere 148 (2016) 118-125) highlighted a newly introduced Quantitative Structure-Property Relationship (QSPR), as a group-contribution (GC) method and a quantum chemical solvation model were reported to yield significantly less accurate results. Based on the observation that the so-called GC method investigated in this earlier study was inconsistent with the temperature dependence of KOA, the previously recommended QSPR is presently compared to the geometrical fragment (GF) additivity scheme. In addition to providing some improvement in terms of accuracy, this fragment-based procedure exhibits many advantages in terms of simplicity, interpretability, applicability and availability.

Proton transfer reaction confined within carbon nanotubes: Density functional theory and quantitative structure–property relationship analysis

In this work, we focus our attention on chemical reactions confined within carbon nanotubes. As a result of the confinement within carbon nanotubes, novel physical and chemical properties are found for the confined materials. We consider the feasibility of proton transfer inside carbon nanotubes. To do that, we have chosen formamide as the simplest real model for exhibiting the tautomerization in DNA. We have used the quantitative structure–property relationship method, based on geometry optimization and quantum chemical structural descriptors, to illustrate the potential of using the confined space inside carbon nanotubes, which will provide comprehensive information about carbon nanotubes. All calculations have been carried out using density functional theory quantum calculations with the B3LYP functional. The geometries optimized by the Gaussian program were transferred to the computer software DRAGON to calculate pertinent descriptors that could be used in the quantitative structure–property relationship model.

Neural Networks Are Promising Tools for the Prediction of the Viscosity of Unsaturated Polyester Resins.

Unsaturated polyester resins are widely used for the preparation of composite materials and fulfill the majority of practical requirements for industrial and domestic applications at low cost. These resins consist of a highly viscous polyester oligomer and a reactive diluent, which allows its process ability and its crosslinking. The viscosity of the initial polyester and the reactive diluent mixture is critical for practical applications. So far, these viscosities were determined by trial and error which implies a time-consuming succession of manipulations, to achieve the targeted viscosities. In this work, we developed a strategy for predicting the viscosities of unsaturated polyesters formulation based on neural networks. In a first step 15 unsaturated polyesters have been synthesized through high-temperature polycondensation using usual monomers. Experimental Hansen solubility parameters (HSP) were determined from solubility experiment with HSPiP software and glass transition temperatures (Tg) were measured by Differential Scanning Calorimetry (DSC). Quantitative Structure—Property Relationship (QSPR) coupled to multiple linear regressions have been used to get a prediction of Hansen solubility parameters δd, δp, and δh from structural composition. A second QSPR regression has been done on glass transition temperature (prediction vs. experimental coefficient of determination R2 = 0.93) of these unsaturated polyesters. These unsaturated polyesters were next diluted in several solvents with different natures (ethers, esters, alcohol, aromatics for example) at different concentrations. Viscosities at room temperature of these polyesters in solution were finally measured in order to create a database of 220 entries with 7 descriptors (polyester molecular weight, Tg, dispersity index Ð, polyester-solvent HSP RED, molar volume of the solvent, δh of the solvent, concentration of polyester in solvent). The QSPR method for predicting the viscosity from these 6 descriptors proved to be ineffective (R2 = 0.56) as viscosities exhibit non-linear phenomena. A Neural Network with an optimized number of 12 hidden neurons has been trained with 179 entries to predict the viscosity. A correlation between experimental and predicted viscosities based on 41 testing instances gave a correlation coefficient R2 of 0.88 and a predicted vs. measured slope of 0.98. Thanks to Neural Networks, new developments with eco-friendly reactive diluents can be accelerated.

Atom Pair Contribution Method: Fast and General Procedure To Predict Molecular Formation Enthalpies.

An atom pair contribution (APC) model aimed at predicting the gas-phase formation enthalpy (ΔfH°) of molecules is reported. In contrast to bond contribution (BC) or group contribution (GC) methods, it relies on increments associated with pairs of bonded and geminal atoms along with 15 structural corrections. Another distinctive feature of the present APC method is the large amount of experimental and high-level theoretical data specially compiled in this work to fit and validate the model (2671 entries). Unlike GC methods, the present APC model has wide applicability with the number of adjustable parameters limited to 68. Although it requires only a structural formula as input and involves only back-of-the-envelope calculations, it is more reliable than state-of-the-art quantitative structure-property relationship methods, popular semiempirical Hamiltonians, and even low-level density functional theory approaches based on gradient-corrected functionals. It is therefore a valuable tool for fast screening applications or whenever chemical accuracy is not necessary.

COEFFICIENT PARTITION PREDICTION OF SATURATED MONOCARBOXYLIC ACIDS USING THE MOLECULAR DESCRIPTORS

Carboxylic acids have clearly been absent from the quantitative structure-property relationship literature. The studies of the quantitative structure-property relationships (QSPR) involve various chemometric methods in which the physico-chemical behavior of a compound is correlated with its structure represented by the structural indices. For example, QSPR methods are applied for the prediction of octanol-water partition coefficient of an organic compound. In this study, the relationship between the octanol/water coefficient partition and molecular descriptors was investigated. Also, the multiple linear-regression method based on QSPR methodology was applied to predict the Log P of saturated mono-carboxylic acids C1-C22. On the other hand, the relation [Log P = – 0.426 (Platt) + 0.190 (V/ A°3) – 0.155 (Max.P.A/ A°2) – 1.914 (X) – 1.576; N = 22, R2 = 0.995, F = 917.005, DW =1.391] was generated for selected mono-carboxylic acids. The results of study indicated that the Platt, Randic, Volume and Maximum-Projection-Area descriptors have an important role in predicting the octanol/water coefficient partition of saturated monocarboxylic acids (C1-C22).

Revealing chemophoric sites in organophosphorus insecticides through the MIA-QSPR modeling of soil sorption data

Soil sorption of insecticides employed in agriculture is an important parameter to probe the environmental fate of organic chemicals. Therefore, methods for the prediction of soil sorption of new agrochemical candidates, as well as for the rationalization of the molecular characteristics responsible for a given sorption profile, are extremely beneficial for the environment. A quantitative structure-property relationship method based on chemical structure images as molecular descriptors provided a reliable model for the soil sorption prediction of 24 widely used organophosphorus insecticides. By means of contour maps obtained from the partial least squares regression coefficients and the variable importance in projection scores, key molecular moieties were targeted for possible structural modification, in order to obtain novel and more environmentally friendly insecticide candidates. The image-based descriptors applied encode molecular arrangement, atoms connectivity, groups size, and polarity; consequently, the findings in this work cannot be achieved by a simple relationship with hydrophobicity, usually described by the octanol-water partition coefficient.

From theoretical energy barriers to decomposition temperatures of organic peroxides

Stimulated by the needs arising from new regulatory frameworks, a number of equations have been proposed in recent years in view of predicting onset decomposition temperatures ( $$T_{\text{onset}}$$ ) of chemical compounds on the basis of quantitative structure–property relationships (QSPRs). The present study investigates an alternative route based on theoretical activation energies. For a set of 38 peroxides, this strategy outperforms state-of-the-art QSPR models, thus providing an attractive alternative to predict the stability of new compounds. Furthermore, it yields valuable insight into reaction mechanisms, pointing to a concerted decomposition pathway less energetically costly than the genuine O–O homolytic bond scission for dialkylperoxides with an ester group in $$\beta$$ position with respect to the peroxide group. In addition, a model similar in spirit to group contribution methods is put forward. The interest of the present approach is further illustrated by a comparison between present predictions and self-accelerating decomposition temperatures. This work demonstrates some limitations of popular QSPR methods for reactive hazards and should encourage less empirical approaches based on the systematic exploration of decomposition mechanisms. Indeed, according to present results, the key to improved models for predicting the thermal stability of organic compounds clearly lies in properly accounting for the most relevant paths to decomposition.

Ion conduction and chemical and physical properties of sulfonated polyetherimide as membrane: Theoretical study

Molecular dynamics and mechanical simulations were performed to investigate the mechanism of ionic conductivity in sulfonated polyether imides membranes with various sulfonyl groups (n-sPEI), where n is the number of sulfonyl groups in the polymer backbone. A comparative theoretical study was performed to explore the effect of sulfonating degree (n = 2, 3, 4 and 5) on the proton exchange in sulfonated membranes of polyether imides at the hydrated state. Geometry optimization of the membranes in the presence of 200 water molecules revealed that the membrane with n = 5 has a higher ionic conductivity than other cases. We also calculate some chemical and physical properties of each n-sPEI polymer using advanced Quantitative Structure-Property Relationships (QSPRs) which rapidly screened candidate polymers for a broad range of properties, and allowed the property prediction of copolymer blends. All calculations using the QSPRs method were performed with dry molecular structures. The drive mechanism was determined and analyzed, finding that the sulfonyl groups position in the polymer backbone greatly influences in the value of ionic conductivity. The membrane model was built using polymeric chains oriented in three dimensions. The ionic species used in the simulations were hydronium and hydroxyl. The theoretical results are compared with experimental results reported in the literature. The study aimed at finding the polymer that presented the best conduction mechanism to enhance the efficiency of Proton Exchange Membrane Fuel Cell (PEMFC). The ionic conductivity parameter does not necessarily have a linear relationship with the number of sulfonated groups.

Are the Sublimation Thermodynamics of Organic Molecules Predictable?

We compare a range of computational methods for the prediction of sublimation thermodynamics (enthalpy, entropy, and free energy of sublimation). These include a model from theoretical chemistry that utilizes crystal lattice energy minimization (with the DMACRYS program) and quantitative structure property relationship (QSPR) models generated by both machine learning (random forest and support vector machines) and regression (partial least squares) methods. Using these methods we investigate the predictability of the enthalpy, entropy and free energy of sublimation, with consideration of whether such a method may be able to improve solubility prediction schemes. Previous work has suggested that the major source of error in solubility prediction schemes involving a thermodynamic cycle via the solid state is in the modeling of the free energy change away from the solid state. Yet contrary to this conclusion other work has found that the inclusion of terms such as the enthalpy of sublimation in QSPR methods does not improve the predictions of solubility. We suggest the use of theoretical chemistry terms, detailed explicitly in the Methods section, as descriptors for the prediction of the enthalpy and free energy of sublimation. A data set of 158 molecules with experimental sublimation thermodynamics values and some CSD refcodes has been collected from the literature and is provided with their original source references.

A quantitative structure-property relationship (QSPR) study of singlet oxygen generation by pteridines.

The QSPR method is used in photochemistry for the prediction of the absorption wavelength, fluorescence intensity, photolysis quantum yield, etc. However, to our knowledge, no attempts have been made to use the quantum yield of singlet oxygen ((1)O2) generation (ΦΔ) as an analyzed parameter in a QSPR study. We performed QSPR analysis of 29 pteridine compounds (including pterin and flavin sensitizers) for their ability to produce singlet oxygen in aqueous (D2O) solutions. Pteridines are ubiquitously present in living systems (mostly as coenzymes), possess high photochemical activity and have multiple applications as photosensitizers. Our goal was to develop a QSPR model for the fast virtual screening and prediction of the (1)O2 generation quantum yield of pteridines. Quantum-chemical descriptors were calculated using the AM1 semi-empirical method. The ability of pteridines to generate singlet oxygen was found to be significantly correlated with the HOMO orbital energy (R(2) = 0.806) and electronegativity (R(2) = 0.840). The best QSPR model obtained using electronegativity, dipole density and electrostatic charge of the N3 atom of the pteridine system allows us to predict ΦΔ of pterin and flavin photosensitizers. The model possesses high internal stability (q(2) = 0.881), as well as high predicting ability for the external dataset (pred_R(2) = 0.873). More QSPR analysis is needed for the prediction of ΦΔ of pteridines and other groups of sensitizers in aqueous as well as in non-polar solutions.