Search Results (128)

Machine learning (ML) is a powerful tool in drug design, enabling the rapid analysis of large and complex molecular graphs that represent the structural and chemical properties of medications. It enhances the precision and speed with which molecular interactions are predicted, drug candidates are refined, and potential therapeutic targets are identified. When combined with graph theory, ML allows for the prediction of structural properties, molecular behaviour, and the performance of chemical compounds. This integration promotes drug development, reduces costs, and increases the likelihood of producing effective medicines. In this study, we focus on the efficacy of medications used in the treatment of coronary artery disease (CAD) using graph-theoretical methodologies, such as topological indices. We computed several degree-based topological descriptors from chemical graphs, capturing essential connectivity and structural properties. These variables were incorporated into a machine learning framework to develop predictive models that identify structural factors influencing medication performance. Our study explores a dataset of known CAD drugs using supervised learning techniques to estimate their potential efficacy and support improved molecular design. The findings highlight the utility of graph-theoretical descriptors in enhancing prediction accuracy and providing insights into fundamental structural elements related to drug efficacy. Furthermore, this work emphasises the synergy between chemical graph theory and machine learning in accelerating drug development for CAD, offering a scalable and interpretable framework for future pharmaceutical applications. Full article

Ester-based lubricants have been widely used owing to their excellent overall performance. In this study, the quantitative structure–property relationship (QSPR) approach was combined with molecular descriptors, a genetic algorithm (GA), and an artificial neural network (ANN) to systematically predict the key properties—kinematic viscosity at 40 °C and 100 °C, viscosity index, pour point, and flash point—of 64 diester-based lubricants. Quantum chemical calculations were first performed to obtain the equilibrium geometries and electronic information of the molecules. Geometry optimizations and frequency analyses were carried out using the Gaussian 16 software at the B3LYP/6-31G (d, p) level, providing a reliable foundation for molecular descriptor computation. Subsequently, topological, geometrical, and electronic descriptors were calculated using the RDKit toolkit, and the optimal feature subsets were selected by GA and used as ANN inputs for property prediction. The results showed that the ANN models exhibited good performance in predicting viscosity and flash point, with R² values of 0.9455 and 0.8835, respectively, indicating that the ANN effectively captured the nonlinear relationships between molecular structure and physicochemical properties. In contrast, the prediction accuracy for pour point was relatively lower (R² = 0.6155), suggesting that it is influenced by complex molecular packing and crystallization behaviors at low temperatures. Overall, the study demonstrates the feasibility of integrating quantum chemical calculations with the QSPR–ANN framework for lubricant property prediction, providing a theoretical basis and data-driven tool for molecular design and performance optimization of ester-based lubricants. Full article

The rational design of polyimides (PIs) with targeted glass transition temperature (T_g) is crucial for advanced microelectronics applications. While data-driven approaches offer promise, there is a pressing need for models that are not only predictive but also physically interpretable, especially with limited datasets. Herein, we present a highly interpretable Quantitative Structure-Property Relationship (QSPR) model for accurate T_g prediction of PIs. Employing a Genetic Algorithm combined with Multiple Linear Regression (GA-MLR), we identified an optimal set of seven molecular descriptors from a curated dataset. The model demonstrates robust predictive performance and strong generalization ability, validated through rigorous statistical tests. Crucially, we provide a deep physicochemical interpretation of the descriptors, unifying their influence under the framework of free volume theory. We show that key descriptors govern T_g by modulating the fractional free volume through distinct mechanisms: descriptors like Chi0n increase free volume by introducing molecular branching that disrupts chain packing, while MinPartialCharge influences T_g through its effect on intermolecular interactions. This mechanistic understanding is translated into clear molecular design guidelines, distinguishing strategies for achieving high-T_g versus processable, low-T_g polymers. Our work establishes a reliable and transparent computational tool that bridges data-driven prediction with fundamental chemical insight for accelerating PIs development. Full article

Predicting the solubility of active pharmaceutical ingredients (APIs) in binary solvent mixtures is a major challenge in formulation science, as physics-based models often fail to capture complex, non-additive mixing effects. This study presents a robust machine learning (ML) framework to overcome this limitation, enabling accurate predictions from pure solvent data alone and molecular descriptors derived from COSMO-RS (computed with COSMOtherm). Firstly, our experimental knowledge of binary solvent mixtures solubility was expanded through newly measured data of caffeic and ferulic acids in aqueous mixtures of DMF, DMSO, and 4-formylmorpholine (4-FM). These new data, combined with values in the literature, formed a comprehensive dataset of 1636 points for ten phenolic and benzoic acids. To build a predictive model, a systematic methodology was developed, with the acronym of DOO-IT (Dual-Objective Optimization with ITerative features pruning), which automates descriptor selection and hyperparameter optimization to yield a maximally parsimonious and generalizable model. An exhaustive, multi-run stability analysis identified a final 10-descriptor nuSVR model as the optimal solution. This model demonstrated outstanding predictive power, achieving an R² of 0.988 and MAE equal to 0.0514 on a held-out test set, vastly outperforming standard COSMO-RS approaches. Interpretation of the selected descriptors revealed that the model successfully learns to correct for non-ideal mixing by integrating a baseline solubility reference with specific solute–solvent and solvent–solvent interaction terms. This work delivers both a practical tool for reducing experimental screening and a powerful, transferable methodology for developing robust QSPR models for complex chemical systems. Full article

This study developed a QSPR model to predict the n-octanol/water partition coefficient (log Kow) of 56 pesticides. Molecular descriptors were calculated using Dragon software. A genetic algorithm and variable subset selection identified key descriptors. The model, built by multiple linear regression, showed strong performance (R² = 0.9322, Q²_LOO = 0.9089, Q²_ext = 0.9277). The dataset was split using the Kennard-Stone algorithm to ensure representative sampling. Internal and external validations confirmed robustness and predictive power. This model offers a reliable tool for estimating log Kow, supporting environmental risk assessment and the evaluation of pesticide behavior and toxicity. Full article

We present a systematic machine learning study of the solubility of diverse pharmaceutical acids in deep eutectic solvents (DESs). Using an automated Dual-Objective Optimization with Iterative feature pruning (DOO-IT) framework, we analyze a solubility dataset compiled from the literature for ten pharmaceutically important carboxylic acids and augment it with new measurements for mefenamic and niflumic acids in choline chloride- and menthol-based DESs, yielding N = 1020 data points. The data-driven multi-criterion measure is applied for final model selection among all collected accurate and parsimonious models. This three-step procedure enables extensive exploration of the model’s hyperspace and effective selection of models fulfilling notable accuracy, simplicity, and also persistency of the descriptors selected during model development. The dual-solution landscape clarifies the trade-off between complexity and cost in QSPR for DES systems and shows that physically meaningful energetic descriptors can replace or enhance explicit COSMO-RS predictions depending on the application. Full article

In this paper, we study the detour eccentric sum index (DESI) to obtain the Quantitative Structure–Property Relationship (QSPR) for different molecular structures. We establish theoretical bounds for this index and compute its values across fundamental graph families. Through correlation analyses between the physicochemical properties of molecular structures representing anti-malarial and breast cancer drugs, we show the high predictive value of two topological parameters, detour diameter (DD) and detour radius (DR). Specifically, DR shows strong positive correlations with boiling point, enthalpy, and flash point (up to 0.94), while DD is highly correlated with properties such as molar volume, molar refraction, and polarizability (up to 0.97). The DESI was then selected for detailed curvilinear regression modeling and comparison against the established eccentric distance sum index. For anti-malarial drugs, the second-order model yields the best fit. The DESI provides optimal prediction for boiling point, enthalpy, and flash point. In breast cancer drugs, the second-order model is again favored for properties except for melting point, best described by a third-order model. The results highlight how well the index captures subtle structural characteristics. Full article

Per- and polyfluoroalkyl substances (PFAS) are environmentally persistent organofluorines linked to cancer, organ dysfunction, and other health problems. This study used quantitative structure–property relationship (QSPR) and quantitative structure–activity relationship (QSAR) modeling to examine the binding of PFAS to estrogen receptor alpha (ERα) and beta (ERβ). Molecular docking of 14,591 PFAS compounds was performed, and docking scores were used as a measure of receptor affinity. QSPR models were built for two datasets: the ERα and ERβ top binders (TBs), and a set of commonly exposed (CE) PFAS. These models quantified how chemical descriptors influence binding affinity. Across the models, higher density and electrophilicity indicated positive correlations with affinity, while surface tension indicated negative correlations. Electrostatic descriptors, including HOMO energy and positive Fukui index (F⁺ max), were part of the models but showed inconsistent trends. The CE QSPR models displayed correlations that conflicted with those of the TB models. Following QSPR analysis, 66 QSAR models were developed using a mix of top binders and experimental data. These models achieved strong performance, with R² values averaging 0.95 for training sets and 0.78 for test sets, that indicated reliable predictive ability. To improve generalizability, large-set QSAR models were created for each receptor. After outlier removal, these models reached R² values of 0.68–0.71, which supports their use in screening structurally diverse PFAS. Overall, QSPR and QSAR analyses reveal key chemical features that influence PFAS–ER binding. This predictive approach provides a scalable framework to assess the binding interactions of structurally diverse PFAS to ERs and other nuclear receptors. All the codes, data, and the GUI visualization of the results are freely available at sivaGU/QSPR-QSAR-Molecular-Visualization-Tool. Full article

Efficiently identifying suitable solvents for active pharmaceutical ingredients (APIs) is critical in drug formulation, yet the vast number of possible solvent-solute combinations presents a significant experimental challenge. This study addresses this by developing a robust machine learning (ML) model for accurately predicting the solubility of three phenolic acids (syringic, p-coumaric, and caffeic) in various deep eutectic solvents (DESs), integrating both experimental and computational investigations. Measured solubility data showed that the choline chloride combined with triethylene glycol in a 1:2 molar ratio was the most efficient system for the dissolution of the studied APIs. Different ML models, utilizing nu-Support Vector Regression (nuSVR) as the core regressor and based on descriptor sets derived from COSMO-RS (Conductor-like Screening Model for Real Solvents) computations, were systematically evaluated. A novel methodology termed DOO-IT (Dual-Objective Optimization with ITerative feature pruning) was employed to address the common challenges of model development with limited, high-value datasets. The final optimal 10-descriptor nuSVR model, selected from an exhaustive, multi-run search, demonstrated outstanding predictive power, offering a highly reliable computational tool for guiding experimental screening, significantly accelerating the exploration of DES-based formulations. This research also provides a strong foundation for future machine learning-guided discovery of chemicals, offering an effective and transferable framework for developing QSPR models for various chemical systems. Full article

Modern dentistry depends on polymer composite materials for a wide range of applications. These materials, mainly composed of polymer resins and reinforced with inorganic fillers, offer mechanical strength, wear resistance, and durability for restorations and prosthetics. This study concentrated on the density and surface tension of monomers often used in dental resins and employed Quantitative Structure–Property Relationship (QSPR) modeling to investigate the influence of monomers’ structural features on these properties. Two main and two auxiliary models to predict both density and surface tension were built and validated. Additionally, two models based on CircuS descriptors were built and analyzed. Molecular descriptors from the models were interpreted and structural characteristics of dental monomers influencing their physicochemical properties were identified. It was found that the presence of heteroatoms increases both of the analyzed properties, while all of the other identified structural features exert an opposite influence on density and surface tension. Furthermore, the study showed that the density of dental monomers can be reliably predicted using the database containing regular organic compounds, but the surface tension requires the database containing specific monomers in order to perform satisfactorily. Full article

Background: We studied in silico models of both organic and inorganic substances. In most cases, these in silico models are used for organic substances only. The following endpoints were taken for the case studies: the octanol–water coefficient (three models), the enthalpies of formation of organometallic compounds, and rat acute toxicity. Methods: The correlation weights were optimized using the Monte Carlo method with two special training and validation sets. The training set was structured into three subsets of active and passive training, as well as a calibration set. The division into these four subsets was carried out using the Las Vegas algorithm. It is assumed that considering groups of different splits into these four subsets is more informative than considering only a single split. Results: Models were built for the octanol–water coefficient for a set containing organic and inorganic substances or for a subset of the original data; other models were developed for a set containing only specially defined inorganic substances for platinum complexes. In addition, models of the enthalpy of formation and for toxicity in rats were built using the same approach for two sets of inorganic substances. Conclusions: A comparison of different methods for the optimization of correlation weights using the Monte Carlo method showed that optimization can be improved using the coefficient of conformism of a correlative prediction (CCCP) or the index of the ideality of correlation (IIC). Optimization with CCCP was the best option for the models of the octanol–water partition coefficient for the set of organic compounds, the octanol–water partition coefficient of the inorganic set, and the enthalpy of formation of the inorganic compounds. However, optimization with IIC was the best option in terms of the toxicity of the inorganic compounds in rats. Full article

Cheminformatics bridges chemistry, computer science, and information technology to predict chemical behaviors using quantitative structure–property relationships (QSPRs). This study advances QSPR modeling by introducing novel connection-based graphical invariants, specifically designed to enhance the predictive accuracy for physicochemical properties (PCPs) of benzenoid hydrocarbons (BHs). Employing cutting-edge computational methods, we evaluate these invariants against established descriptors in modeling the normal boiling point and standard heat of formation. The findings reveal superior predictive performance by newly proposed invariants, such as the sum-connectivity connection index, outperforming traditional indices like the Zagreb connection indices. Furthermore, we extend these methods to model the physicochemical properties of coumarin-related anti-cancer drugs, demonstrating their potential in drug development. The statistical analysis suggests that the most appropriate structure–property models are nonlinear. This work not only proposes robust tools for PCP estimation but also advocates for rigorous testing of descriptors to ensure relevance in cheminformatics. Full article

Chemical graph theory connects the analysis of molecular structures with mathematical graph theory, allowing for the prediction of chemical and physical properties through the use of topological indices. Among these, the recently introduced Harmonic–Arithmetic (HA) index, proposed by Abeer M. Albalahi et al. in 2023, offers a novel method to quantify molecular and graph structures. It is defined as $HA\left(G\right)={\sum }_{\mu \omega \in E\left(G\right)}{\displaystyle \frac{4d_G\left(\mu \right)d_G\left(\omega \right)}{{(d_G\left(\mu \right)+d_G\left(\omega \right))}^2}}$, where $d_G\left(\mu \right)$ and $d_G\left(\omega \right)$ are degrees of nodes $\mu$ and $\omega$ in G. In this paper, the HA index examines the bounds for a tree T of order n, with a maximum degree $∆$. The application of the HA index extends to QSPR/QSAR analyses, where topological indices play a crucial role in predicting the relationship between molecular structures and physicochemical properties, such as in Parkinson’s, disease-related antibiotics by calculating their topological indices and analyzing them using QSPR models. Comparative analyses were performed between linear regression models and curvilinear-approach quadratic and cubic regression models to identify the minimal RMSE and enhance predictive accuracy for physicochemical properties. The results demonstrate that the HA index effectively connects mathematical graph theory with molecular characterization, offering reliable predictions, dependable bounds for tree graphs, and meaningful insights into molecular properties. These findings highlight the HA index’s potential as a versatile and innovative tool in advancing chemical graph theory and its applications to real-world problems in chemistry. Full article

Using the Monte Carlo technique via CORAL-2024 software, models of aromatic substance adsorption on multi-walled nanotubes were constructed. Possible mechanistic interpretations of such models and the corresponding applicability domains were investigated. In constructing the models, criteria of the predictive potential such as the iIndex of Ideality of Correlation (IIC), the Correlation Intensity Index (CII), and the Coefficient of Conformism of a Correlative Prediction (CCCP) were used. It was assumed that the CCCP could serve as a tool for increasing the predictive potential of adsorption models of organic substances on the surface of nanotubes. The developed models provided good predictive potential. The perspectives on the improvement of the nano-QSPR/QSAR were discussed. Full article

In this study, models for NOEL (No Observed Effect Level) and NOEC (No Observed Effect Concentration) related to long-term/reproduction toxicity of various organic pesticides are built up, evaluated, and compared with similar models proposed in the literature. The data have been obtained from the EFSA OpenFoodTox database, collecting only data for the Bobwhite quail (Colinus virginianus). Models have been developed using the CORAL-2023 program, which can be used to develop quantitative structure–property/activity relationships (QSPRs/QSARs) and the Monte Carlo method for the optimization of the model. The software provided a model which may be considered useful for the practice. The determination coefficient of the best models for the external validation set was 0.665. Full article