MolTech, UTARTU http://hdl.handle.net/10967/1 2026-04-16T16:04:46Z 2026-04-16T16:04:46Z http://hdl.handle.net/10967/269 2025-05-30T15:24:49Z 2025-05-07T13:27:28Z

Some adverse effects of hydroxylated polychlorinated biphenyls (OH-PCBs) in humans are presumed to be initiated via thyroid hormone receptor (TR) binding. Due to the trial-and-error approach adopted for OH-PCB selection in previous studies, experiments designed to test the TR binding hypothesis mostly utilized inactive OH-PCBs, leading to considerable waste of time, effort and other material resources. In this paper, linear discriminant analysis (LDA) and binary logistic regression (LR) were used to develop classification models to group OH-PCBs into active and inactive TR agonists using radial distribution function (RDF) descriptors as predictor variables. The classifications made by both LDA and LR models on the training set compounds resulted in an accuracy of 84.3%, sensitivity of 72.2% and specificity of 90.9%. The areas under the ROC curves, constructed with the training set data, were found to be 0.872 and 0.880 for LDA and LR models, respectively. External validation of the models revealed that 76.5% of the test set compounds were correctly classified by both LDA and LR models. These findings suggest that the two models reported in this paper are good and reliable for classifying OH-PCB congeners into active and inactive TR agonists.

2025-05-07T13:27:28Z http://hdl.handle.net/10967/266 2025-07-29T15:03:36Z 2025-03-17T11:45:47Z

Ionic liquids are known as green solvents, which makes accurate prediction of gas–ionic liquid partition coefficients (log K) important from the perspective of various industrial applications. A gas–ionic liquid is a multicomponent system, but is usually modelled by the structural properties of one component, the solute. The integration of structural descriptors of all three components, solute, cation, and anion, into a single computational model has not been achieved. To do this, a machine learning approach was applied to a large collected dataset consisting of 6,531 experimental log K values, including data series for 170 solutes and 138 ionic liquids. The Multiple Linear Regression (MLR) and Random Forest Regression (RF) approaches were compared, both of which applied stepwise forward descriptor selection. The best MLR model achieved a cross-validated coefficient of determination (Rcv2) of 0.795 and an external validation coefficient of determination (R2) of 0.801, while the RF model demonstrated significant increase in performance with cross-validated Rcv2 of 0.965 and external validation R2 of 0.957. The descriptors included in the models showed that the description and prediction of log K is significantly improved when structural properties of all three components of the system (solute, cation, and anion) are taken into account. When comparing the linear and non-linear RF models, the presence of molecular descriptors of different components was significantly increased in the latter. The molecular descriptors in the models highlighted the roles of dispersion forces, dipolar interactions, and hydrogen bonding in solute–ionic liquid partitioning. The study provides thoroughly-analyzed predictive models for estimating gas–ionic liquid partition coefficients and provides structure-level insights into solute–ionic-liquid interactions, facilitating the rational design of ionic liquids and expanding the range of solutes for various applications.

2025-03-17T11:45:47Z http://hdl.handle.net/10967/265 2025-05-30T15:24:03Z 2024-10-25T07:41:49Z

Drug substances in water bodies and groundwater have become a significant threat to the surrounding environment. This study focuses on the ability of the nanoporous carbon materials to remove ciprofloxacin from aqueous solutions under specific experimental conditions and on the development of the mathematical model that would allow describing the molecular interactions of the adsorption process and calculating the adsorption capacity of the material. Thus, based on the adsorption measurements of the 87 carbon materials, it was found that, depending on the porosity and pore size distribution, adsorption capacity values varied between 55 and 495 mg g-1. For a more detailed analysis of the effects of different carbon textures and pores characteristics, a Quantitative nano-Structure-Property Relationship (QnSPR) was developed to describe and predict the ability of a nanoporous carbon material to remove ciprofloxacin from aqueous solutions. The adsorption capacity of potential nanoporous carbon-based adsorbents for the removal of ciprofloxacin was shown to be sufficiently accurately described by a three-parameter multi-linear QnSPR equation (R² = 0.70). This description was achieved only with parameters describing the texture of the carbon material such as specific surface area (Sdft) and pore size fractions of 1.1-1.2 nm (𝑉𝑁2[1.1−1.2]) and 3.3-3.4 nm (𝑉𝑁2[3.3−3.4]) for pores

2024-10-25T07:41:49Z http://hdl.handle.net/10967/263 2025-02-20T19:27:42Z 2024-10-09T12:03:43Z

The earthworm is a key indicator species in soil ecosystems. This makes the reproductive toxicity of chemical compounds to earthworms a desired property of determination and makes computational models necessary for descriptive and predictive purposes. Thus, the aim was to develop an advanced Quantitative Structure–Activity Relationship modeling approach for this complex property with imbalanced data. The approach integrated gradient-boosted decision trees as classifiers with a genetic algorithm for feature selection and Bayesian optimization for hyperparameter tuning. An additional goal was to analyze and interpret, using SHAP values, the structural features encoded by the molecular descriptors that contribute to pesticide toxicity and nontoxicity, the most notable of which are solvation entropy and a number of hydrolyzable bonds. The final model was constructed as a stacked ensemble of models and combined the strengths of the individual models. Evaluation of this model with an external test set of 147 compounds demonstrated a well-defined applicability domain and sufficient predictive capabilities with a Balanced Accuracy of 77%. The model representation follows FAIR principles and is available on QsarDB.org.

2024-10-09T12:03:43Z