In the context of carbon neutrality and carbon peaking, molecular management has become a focus of the petrochemical industry. The key to achieving molecular management is molecular reconstruction, which relies on rapid and accurate calculation of oil properties. Focusing on naphtha, we proposed a novel property prediction model construction procedure (MDs-NP) employing molecular dynamics simulations for property collections and gamma distribution from real analytical data for calculating mole fractions of simulation mixtures. We calculated 348 sets of mixture properties data in the range of 273 K-300 K by molecular dynamics simulations. Molecular feature extraction was based on molecular descriptors. In addition to descriptors based on open-source toolkits (RDKit and Mordred), we designed 12 naphtha knowledge (NK) descriptors with a focus on naphtha. Three machine learning algorithms (support vector regression, extreme gradient boosting and artificial neural network) were applied and compared to establish models for the prediction of the density and viscosity of naphtha. Mordred and NK descriptors + support vector regression algorithm achieved the best performance for density. The selected RDKFp and NK descriptors + artificial neural network algorithm achieved the best performance for viscosity. Using ablation studies, T, P_w and CC(C)C are three effective descriptors in NK that can improve the performance of the property prediction models. MDs-NP has the potential to be extended to more properties as well as more-complex petroleum systems. The models from MDs-NP can be used for rapid molecular reconstruction to facilitate construction of data-driven models and intelligent transformation of petrochemical processes.

Auto-ignition temperature (AIT) is one of the crucial exponents in the design of fire and explosion safety measures. Therefore, in this study, quantitative structure-property relationship approach was used to predict the AIT of ternary hybrid liquids based on molecular structure information. The optimal molecular descriptors were calculated and filtered using Mordred software. Twelve mixing rules were proposed for calculating molecular descriptors of mixtures. A prediction model for the AIT value of binary liquid mixtures was developed, validated and evaluated using a back propagation neural network (BPNN) and a one-dimensional convolutional neural network (1DCNN). The relative contribution and positive and negative correlations between individual molecular descriptors and AIT in the model were interpreted using the shapley additive explanations method. The results show that BPNN and 1DCNN models using mixing rule 1 have the best fitting ability, stability and prediction ability. The determination coefficient of the BPNN and 1DCNN models in the training set were 0.996 and 0.992, the root mean square errors were 3.613 °C and 5.284 °C, the mean absolute errors were 2.483 °C and 4.144 °C, the nash efficiency coefficient was 0.996 and 0.992, respectively, the willmott index was 0.999 and 0.998. and the values of the top three molecular descriptors of relative contribution, SssCH2, SsOH and SsCH3, were negatively correlated with the AIT values. The BPNN and 1DCNN models provide an accurate and reliable method for predicting ternary mixing liquid AIT.

UNASSIGNED: The solubility of drugs in water and organic solvents is a crucial factor in numerous pharmaceutical processes. In recent years, a new type of solvent called deep eutectic solvents (DESs) has been developed as a useful solvent for drugs. Choline chloride-glycerol/urea (ChCl-G/U) systems are DESs recognized as a novel category of environmentally friendly solvents. One recent application of this type of DES in water is the solubilization of drugs.
UNASSIGNED: This study aimed to investigate the solubility of certain drugs in ChCl-G/U. In addition, the solubilization mechanisms of the DESs studied, and quantitative structure-property relationship (QSPR) models for solubilization were proposed.
UNASSIGNED: The solubility of 13 drugs in an aqueous solution of the ChCl-G/U system was investigated using the shake flask method. The study was conducted at 10% and 50% mass fractions of the studied systems. Multiple linear regression models were used to develop mathematical relationships between the solubilization of the studied compounds in the presence of ChCl-G/U + water mixture using QSPR models.
UNASSIGNED: The solubility of the compounds showed a significant increase upon adding ChCl-G/U to the aqueous solutions. Based on the data obtained, QSPR models were developed using solubilization ratio and structural descriptors.
UNASSIGNED: The experimental data demonstrates the potential of utilizing ChCl-G/U as a medium to enhance the solubility of poorly soluble drugs in water. Solubilization of solutes in ChCl-G/U + water mixtures could be correlated with the structural properties of drugs. Moreover, the final pH of the solutions in ChCl-U is a critical factor that must be considered when using this system for solubilization.

Topological indices relate chemical structure to chemical reactivity, physical properties, and biological activity. Quantitative structure-activity relationships (QSPR) are mathematical models proposed for the correlation of various types of chemical reactivity, biological activity, and physical properties with topological indices/entropies. In this article, we have proposed the QSPR between the ve-degree of end vertices of edge based entropies and the physiochemical properties of benzene derivatives. We have designed a Maple-based algorithm for the computation of entropies. The relationship was analyzed using SPSS. We have shown that the physiochemical properties such as critical pressure, Henry\'s law, critical temperature, Gibb\'s energy, logP, critical volume, and molar refractivity can be predicted by entropies. All the results were highly positive and significant. The Randić, Balaban, and redefined third Zagreb entropies showed the best relations with physiochemical properties.Communicated by Ramaswamy H. Sarma.

BACKGROUND: The thermal hazard of reactions caused by the structural instability of aromatic nitro compounds is a major concern in the field of chemical process safety and one of the main causes of major thermal runaway (TR) accidents such as fire and explosion. Among them, the self-accelerating decomposition temperature (SADT), as an important parameter, has been widely used to evaluate the thermal hazards of aromatic nitro compounds in actual storage and transportation processes. However, the control temperature (CT) and emergency temperature (ET), which depend on and are associated with SADT, have been rarely reported in previous studies. In this work, multiple linear regression (MLR) and artificial neural network (ANN) models for CT and ET were constructed based on the molecular descriptors corresponding to the stable structures of 27 monadic/binary aromatic nitro compounds, combined with advanced adiabatic accelerating calorimetric experiments and quantitative structure-property relationship (QSPR). The optimal subset of descriptors with significant contributions was screened out while the fit, predictive ability, and robustness of the four types of models were evaluated with internal and external validation parameters, and finally, two types of parameters (R2 and ARE) were selected as the main indicators for a comprehensive comparative analysis. The results show that the four models fit the experimental data well. During this period, the accuracy of ANN models is slightly higher than that of MLR models, and the QSPR models under the two modes (linear and nonlinear) are more inclined toward ET in prediction ability. Based on simplifying the calculation process and realizing rapid parameter prediction, this study is expected to provide technical support for engineering applications such as safe operation, safe storage and transportation of substances, and emergency response in the chemical industry.
METHODS: In this work, we tested and calculated the thermal safety parameters of 27 monadic/binary aromatic nitro compounds by ARC and AKTS and further used the PubChem database and Gaussian 09 software program to obtain and optimize their corresponding molecular structures. The geometric optimization process adopts DFT on the B3LYP level and the 6-31 + G(d, p) basis set, while the same functional and basis set was used for vibration analysis. The OpenBabel toolbox and ChemDES platform were used for transformation coding and descriptor calculation. Finally, IBM SPSS Statistics 24 and MATLAB software were used to construct MLR models and ANN models, respectively.

In this study, the power of machine learning was harnessed to probe the link between molecular structures of peptide-based hydrogels and their viscoplastic properties. The selection of compounds was attempted in accordance with the prescribed full list of peptide-based materials exhibiting hydrogel functionality in the literature. In this pursuit, a complete set of molecular descriptors and fingerprints was considered - accounting for an entry of size 17,968 for each peptide-based structure analyzed. The elastic and viscous moduli response of materials were mapped over a wide frequency spectrum in the range [0.1-100] (rad/s). In general, the results indicate that the frequency-dependent mechanical response of peptide-based hydrogels is statistically correlated with its (inter)molecular attributes, such as charge, first ionization potential (or equivalently electronegativity), surface area, number of chemical substrates, bond type, and intermolecular interactions. The performance of several (supervised) soft computing techniques was measured, for our quantitative structure property relationships model. In addition, the hypothesis of mapping our databank to a new system of principal components was tested, by using an unsupervised methodology, which resulted in enhancement of the prediction accuracy. In terms of significance, the present article provides the first report of frequency-dependent elastic and viscous moduli, for a set of 70 peptide-based formulations with hydrogel functionality.Communicated by Ramaswamy H. Sarma.

The development of fluorescent pigments is an area of interest in several research fields due to their high sensitivity. In the current study-eight known and three new N,N-dimethylamino-chalcones (12a-k) were synthesized with good yields using the Claisen-Schmidt reaction. For each molecular system, the photophysical properties, including the maximum absorption wavelength (λAbsorption), molar absorption coefficient (ε), maximum excitation wavelength (λExcitation), maximum emission wavelength (λEmission), Stokes Shift (Δλ), fluorescence quantum yield (Φfl), fluorescence lifetime (τfl), radiative and non-radiative rate constants (kR and kNR, respectively) were evaluated. Variations in each of these properties were analyzed depending on the substituents present on each compound. To relate the chemical structures of the synthesized compounds to their photophysical properties, Hansch analysis (2D-QSPR) was applied. As a result of Hansch analysis, we found different photophysical properties related to molecular orbitals and the energy of their derivatives (Highest Occupied Molecular Orbital-HOMO, Lowest Unoccupied Molecular Orbital-LUMO, Difference between LUMO-HOMO-ΔLH, Chemical potential-µ, Hardness-η, Softness-S, and electrophilic global index-ω) as well as to the atomic charges on atoms C5, Cα, Cβ, and CO. The application of this type of analysis has made it possible to understand and subsequently design new molecules with defined photophysical properties. Finally, the compounds were use as fluorescent pigment to get living cell imaging on breast cancer cells, obtaining the compound 12a as promissory alternative.

Random Forest (RF) QSPR models were developed with a data set of homolytic bond dissociation energies (BDE) previously calculated by B3LYP/6-311++G(d,p)//DFTB for 2263 sp3C-H covalent bonds. The best set of attributes consisted in 114 descriptors of the carbon atom (counts of atom types in 5 spheres around the kernel atom and ring descriptors). The optimized model predicted the DFT-calculated BDE of an independent test set of 224 bonds with MAE=2.86 kcal/mol. A new data set of 409 bonds from the iBonD database (http://ibond.nankai.edu.cn) was predicted by the RF with a modest MAE (5.36 kcal/mol) but a relatively high R2 (0.75) against experimental energies. A prediction scheme was explored that corrects the RF prediction with the average deviation observed for the k nearest neighbours (KNN) in an additional memory of experimental data. The corrected predictions achieved MAE=2.22 kcal/mol for an independent test set of 145 bonds and the corresponding experimental bond energies.

Given the difficult of experimental determination, quantitative structure-property relationship (QSPR) and deep learning (DL) provide an important tool to predict physicochemical property of chemical compounds. In this paper, partial least squares (PLS), genetic function approximation (GFA), and deep neural network (DNN) were used to predict the Lee retention index (Lee-RI) of PAHs in SE-52 and DB-5 stationary phases. Four molecular descriptors, molecular weight (MW), quantitative estimate of drug-likeness (QED), atomic charge weighted negative surface area (Jurs_PNSA_3), and relative negative charge (Jurs_RNCG) were selected to construct regression models based on genetic algorithm. For SE-52, PLS model showed best prediction power, followed by DNN and GFA. The relative error (RE), root mean square error (RMSE), and regression coefficient (R2 ) of best PLS regression model are 1.228%, 5.407, and 0.980. For DB-5, DNN model showed best prediction power, followed by GFA and PLS. The RE, RMSE and R2 of best DNN regression model for DB-5-1 and DB-5-2 are 1.058%, 4.325%, 0.976%, 0.821%, 3.795%, and 0.970%, respectively. The three regression models not only show good predictive ability, but also highlight the stability and ductility of the models.

The increasing environmental problems due to various organic micropollutants in water cause the search of suitable additional water treatment methods. Gaining experimental data for the large amount and variety of pollutants would consume a lot of time as well as economic and ecologic resources. An alternative approach is predictive quantitative structure-property relationship (QSPR) modeling, which establishes a correlation between the structural properties of a molecules with a biological, physical, or chemical property. Therefore, in this study, QSPR modeling has been conducted using extensive validation techniques and statistical test to investigate the structural influence on the degradability of organic micropollutants with ozonation. In contrast to most of the other studies, the underlying dataset - rate constants for 92 organic molecules - were obtained under standardized conditions with defined experimental parameters. QSPR modeling was executed using a combination of the software PaDEL for descriptor calculation and QSARINS for the modeling process respecting all five OECD-requirements for applicable QSAR/QSPR-models. The final model was selected using a multi-criteria decision-making tool to evaluate the model quality based on all calculated statistical quality parameters. The model included 10 selected descriptors and fingerprints and showed good regression abilities, predictive power, and stability (R² = 0.8221, CCCtr = 0.9024, Q²loo = 0.7436, R²ext = 0.8420, Q²F1 = 0.8104). The applicability domain of the QSPR model was defined and an interpretation of selected model descriptors has been connected to previous experimental studies. A significant influence of the interpretable descriptors was put into experimental context and compared with previous studies and models. For example, the molar refractivity as a measure of size and polarizability of a molecule and the occurrence of important substructures such as a formamide group seem to decrease the removal rate constant. The contribution of lone electrons entering into resonance as well as the occurrence of fused rings were identified as influences for the increase of the degradability of micropollutants by ozonation.