Molecular Structure Descriptors Research Articles

Analysis of octane isomer properties via topological descriptors of line graphs

Currently, graph-based molecular structure descriptors are frequently used in QSAR (Quantitative Structure-Activity Relationship) and QSPR (Quantitative Structure-Property Relationship) modeling of the properties of chemical compounds. Octane isomers have an important role in the testing of such relationships. In this study, we compute some well-known topological descriptors of the molecular graphs of isomeric octanes and their line graphs, both indices and coindices. Then we analyze the correlation coefficients between the physicochemical properties of the octane isomers and some well-known topological indices and their coindices of the molecular graphs and the line molecular graphs of the octane isomers, to find the particular topological descriptors that have the best predictive values.

Prediction of Melting and Solid Phase Transitions Temperatures and Enthalpies for Triacylglycerols using Artificial Neural Networks

Triacylglycerols (TAG) are the main components of vegetable oils and any attempt to simulate vegetable oils processes will demand knowledge of their properties. However, experimental values are scarce, considering that several TAG in their pure forms are unavailable or too expensive for experimental measurements. On the other hand, correlating physical properties with TAG molecular structure is not simple. TAG is a molecule composed of 3 fatty acids (FA) esterified to a glycerol (GL) backbone, making properties dependent on carbon number (CN) of each FA, number of unsaturations (UN) of each FA, and position of the FA in the GL backbone. Few models are available in literature for prediction of TAG melting properties, with a special attention to melting temperature (Tfus) and enthalpy (ΔHfus) and solid-solid transition properties of the TAG polymorphic forms. Wesdorp's, Moorthy's et al. and Zeberg-Mikkelsen and Stenby's works present models based on the Group-Contribution theory nowadays used, despite some flaws, particularly considering the polymorphic transitions. Therefore, this work was aimed at evaluating Artificial Neural Network (ANN) models for prediction of TAG's Tfus and ΔHfus (β-form) as well as temperature and enthalpy transitions of molecule polymorphic forms (α and β’). Database was composed of temperature and enthalpy experimental data from literature. For each TAG, 7 input data were provided: total CN, as well as CN and UN at sn-1, 2 and 3 TAG position. The Multilayer Perceptron Feed Forward (MPL) model was used, and the topology was evaluated for number of hidden layers (HL), number of neurons (NN) and activation function at each hidden layer, and convergence algorithm. Number of HL and NN was screened by using a Central Composite Rotatable Design (CCRD). Models were further evaluated by Explainable Artificial Intelligence (XAI) and feature evaluation strategies. Architectures showed a significant higher accuracy for calculation and prediction of TAG's melting properties of the 3 polymorphic forms, with R2 higher to 0.91 for all databases when compared to literatures’ models (excepted for the prediction of the melting temperature of the β form, where Wesdorp's model presented a better predictive ability, despite great similarity). Good results were probably related to the well-defined physicochemical relationship between input (molecular structure descriptors) and output (melting properties), that could be described by XAI evaluation. This is an important advantage considering the improvement of the performance of process and products design including TAG molecules.

Pressure control of tritiated hydrogen isotopologues in hermetically sealed vessels by non-evaporable getters for sub-Doppler-resolution spectroscopy

Small molecules serve as valuable benchmarks for testing quantum chemical theories. Ultra-high-resolution spectroscopy currently offers the capability of measuring molecular hydrogen energy levels with a relative accuracy on the order of 10-10. Expanding such investigations to encompass different isotopologues of molecular hydrogen has emerged as a promising avenue for examining mass-dependent contributions to the full description of molecular structure in the framework of relativistic quantum electrodynamics. However, the delicate nature of handling radioactive tritium in a high-resolution spectroscopy environment poses significant technological challenges, thereby limiting the extension of these studies to include T2, DT and HT isotopologues. In this work, we present the experimental setup of the very sensitive, Doppler-free technique of Noise-Immune Cavity-Enhanced Optical Heterodyne Molecular Spectroscopy (NICE-OHMS), used to measure rovibrational transitions in the HT molecule. The NICE-OHMS measurements were performed in a closed cavity system without connection to an actively pumped vacuum system. For this reason, a new method for tritium storage and pressure regulation within 0.05–1Pa based on a temperature-controlled mini-getter system is employed using less activity than the tritium exemption limit (1GBq). Non-Evaporable Getters of the type SAES St171 were used for this purpose exploiting their property that hydrogen is released upon heating, while other gases remain being pumped. Prior to the NICE-OHMS experiment, the reversible sorption properties of the getter for hydrogen isotopes were investigated. We show measurements of the equilibrium (hydrogen) pressure for all three pure isotopes and for a H2:HT:T2 mixture (with H:T = 1:1) as a function of temperature for a system of defined volume and amount of gas. For the read-out of the temperature, a method using the resistance of the getter in combination with a pyrometric calibration has been implemented. We discuss the experiences from practical use of the tritium getter and show results obtained with the NICE-OHMS setup leading to frequency calibration of near-infrared transitions in HT at an accuracy, surpassing previous studies by nearly three orders of magnitude.

Understanding the mechanism of microplastic-associated antibiotic resistance genes in aquatic ecosystems: Insights from metagenomic analyses and machine learning

The pervasive presence of microplastics (MPs) in aquatic systems facilitates the transmission of antibiotic resistance genes (ARGs), thereby posing risks to ecosystems and human well-being. However, owing to variations in environmental backgrounds and the limited scope of research subjects, studies on ARGs in MPs lack unified conclusions, particularly regarding whether different types of MPs selectively promote ARG enrichment. Analysing large-scale datasets can better encompass broad spatiotemporal scales and diverse samples, facilitating a more extensive exploration of the complex ecological relationships between MPs and ARGs. The present study integrated existing metagenomic datasets to conduct a comprehensive risk assessment and comparative analysis of resistance groups across various MPs. In addition, we endeavoured to elucidate potential associations between ARGs and bacterial taxa, as well as MP structural features, using machine learning (ML) methods. The findings of our research highlight the pivotal role of MP type in shaping plastispheres, accounting for 9.56 % of the biotic variation (Adonis index) and explaining 18.59 % of the ARG variance. Compared to conventional MPs, biodegradable MPs, such as polyhydroxyalkanoates (PHA) and polylactic acid (PLA), exhibit lower species uniformity and diversity but pose a higher risk of ARG occurrence. These ML approaches effectively forecasted ARG abundance by using the bacterial taxa and molecular structure descriptors (MDs) of MPs (average R2tra = 0.882, R2test = 0.759). Feature analysis showed that MDs associated with lipophilicity, solubility, toxicity, and surface potential significantly influenced the relative abundance of ARGs in the plastispheres. The interpretable multiple linear regression (MLR) model, particularly notable, elucidated a linear relationship between bacterial genera and ARGs, offering promise for identifying potential ARG hosts. This study offers novel insights into ARG dynamics and ecological risks within aquatic plastispheres, highlighting the importance of comprehensive MP monitoring initiatives.

First Principle Studies of Electronic Properties, Global Reactivity Descriptors, and Molecular Docking of Olivacine Drug

AbstractOlivacine, a semisynthetic isomer of ellipticine, belongs to the family of natural alkaloids; which possess analgesic, antibacterial, and antipyretic properties. It is a model anticancer drug acting as topoisomerase II inhibitor. The mechanism of action and antineoplastic properties of olivacine are ascribed to its intercalative binding into DNA helices. The present paper reports DFT investigation of the molecular structure, electronic properties, and global reactivity descriptors of the drug. Frontier orbitals (HOMO and LUMO) and MEP surface of the olivacine molecule have been examined. Furthermore, inhibition activity and binding sites of olivacine with kinase protein (PDB Id: 3OG7) have been explored by molecular docking technique. Results have been used to elucidate physico‐chemical aspects and preferred binding patterns of the olivacine drug.

Single and mixed dithiocarbamato metal(III) complexes (Co, Rh, and Ir): Crystal and molecular structure description and interplay

This review focuses on the crystal and molecular structures of single and mixed dithiocarbamate ligands of cobalt, rhodium, and iridium in the +3 oxidation state. The complexities of their chelating and bridging modes come into play through modification of the substituents on the carbamate nitrogen atoms of the ligands and additional coordination of secondary phosphino-containing ligands, culminating in various applications such as biological, analytical, medicine, and catalysis. Other considerations include the geometrical coordination environments around the metal centres and their comparison with isostructural congeners. The distortions around the metal centres and their subsequent effects on the symmetries of bonds in the primary and secondary coordination spheres are discussed. The trans-effects of secondary P-ligands and their effects on geometrical alignment and structural stability have become valuable yardsticks in analyzing structural modifications and stabilities.

Molecular Design and High‐Throughput Virtual Screening of Electron Donor and Non‐fullerene Acceptors for Organic Solar Cells

The complicated trilateral relationships among molecular structures, properties, and photovoltaic performances of electron donor and acceptor materials hinder the rapid improvement of power conversion efficiency (PCE) of organic solar cells (OSCs). Herein, the database of 310 donor and non‐fullerene acceptor pairs is constructed and 39 molecular structure descriptors are selected. Four kinds of machine learning (ML) algorithms random forest (RF), extra trees regression, gradient boosting regression trees, and adaptive boosting are applied to predict photovoltaic parameters. The coefficient of determination, Pearson correlation coefficient, mean absolute error, and root mean square error are adopted to evaluate ML performance. The results show that the RF model exhibits the best prediction accuracy. The Gini important analysis suggests the fused ring and aromatic heterocycles are critical fragments in determining PCE. The molecular unit sets are constructed by cutting each donor and acceptor molecules in database. The 31 752 D‐π‐A‐π type donor molecules and 5 455 164 A‐π‐D‐π‐A type acceptor molecules are designed by recombination of molecular units, and 173 212 367 328 donor–acceptor pairs are generated by combining the newly designed donor and acceptor molecules. Based on the predicted PCE using the trained RF model, 42 donor–acceptor pairs exhibit the predicted PCE > 16%, in which the highest PCE is 16.24%.

Ultrasound-assisted ring opening of epoxides in HFIP: THF: Synthesis, characterization, computational studies and molecular docking of novel 2‑hydroxy dithiocarbamates

Under the influence of ultrasonic irradiation, pyridazinone, triazinone, or phthalimide containing 2‑hydroxy dithiocarbamates, a biologically relevant novel organo-sulfur compound, was synthesized. Detailed characterization, computational, and molecular docking studies are being investigated. Molecular interactions were studied using 3D Hirshfeld surfaces and corresponding 2D fingerprint plots. Theoretical (DFT) studies on the molecular structure, HOMO, LUMO, and quantum chemical descriptors were performed at the B3LYP/6–311++G(d,p) level of theory. At the same time, the interaction energy was computed using the B3LYP/6–31G(d,p) level of theory. The FMO study revealed that molecules 4a and 4p in the gas phase have 3.545 eV and 3.263 eV HOMO-LUMO energy gaps, respectively, and they are hence kinetically stable. Quantum chemical calculations confirm the electrophilic character of compounds 4a and 4p, as the molecule is stable and highly electrophilic. The interactions of 2‑hydroxy dithiocarbamate derivatives (4a-4t) with the ligand-binding site of the target COX-2 (cyclooxygenase-2) enzyme were investigated using in-silico molecular docking experiments. Compared to the standard medicine celecoxib, the results showed that most synthesized derivatives had better glide scores and interaction. The docking study of all the synthesized compounds revealed that compounds 4a, 4e, and 4o interact well with the COX-2 enzyme as anti-inflammatory drugs. Molecular dynamic simulation was utilized to validate the docking study and explore the stable binding site and interaction of compound 4o, which is the most potent. The findings indicated that compound 4o exhibited better stability and interaction when compared to the reference drug.

The prediction of donor number and acceptor number of electrolyte solvent molecules based on machine learning

Electrolyte solvents have a critical impact on the design of high performance and safe batteries. Gutmann’s donor number (DN) and acceptor number (AN) values are two important parameters to screen and design superior electrolyte solvents. However, it is more time-consuming and expensive to obtain DN and AN values through experimental measurements. Therefore, it is essential to develop a method to predict DN and AN values. This paper presented the prediction models for DN and AN based on molecular structure descriptors of solvents, using four machine learning algorithms such as CatBoost (Categorical Boosting), GBRT (Gradient Boosting Regression Tree), RF (Random Forest) and RR (Ridge Regression). The results showed that the DN and AN prediction models based on CatBoost algorithm possesses satisfactory prediction ability, with R2 values of the testing set are 0.860 and 0.96. Moreover, the study analyzed the molecular structure parameters that impact DN and AN. The results indicated that TDB02m (3D Topological distance based descriptors−lag 2 weighted by mass) had a significant effect on DN, while HATS1s (leverage-weighted autocorrelation of lag 1/weighted by I-state) plays an important role in AN. The work provided an efficient approach for accurately predicting DN and AN values, which is useful for screening and designing electrolyte solvents.

Insight to the prediction of CO2 solubility in ionic liquids based on the interpretable machine learning model

In this work, we investigated three different machine learning (ML)-based models, i.e., gaussian process regression (GPR), LightGBM, and CatBoost, for predicting the solubility of CO2 in various ionic liquids (ILs). Three molecular descriptors, i.e., group contribution (GC), molecular structure descriptors (MSD), and hybrid GC-MSD are used in our three models. The performance of our developed models were rigorously evaluated using mean absolute error (MAE), coefficient of determination (R2), and mean relative error (MRE) (i.e., relative deviation in percentage), with each model subjected to multiple tests employing different random state parameters. The dataset underwent partitioning into training and testing sets at an 80:20 ratio, with additional splits at various ratios to assess prediction performance sensitivity. Overall, all models exhibited proficient CO2 solubility prediction in ILs, with performance varying based on descriptor type. Notably, the hybrid GC-MSD consistently outperformed others, attributed to GC-MSD incorporates a broader array of molecular feature information. Particularly, the CatBoost-GC-MSD model excelled, achieving an impressive R2 of 0.9925, MAE of 0.0122, and MRE of 11.1550%. Comparing our models to previous studies revealed the superior performance of CatBoost-GC-MSD across all descriptor types. Furthermore, our model interpretation, employing shapley additive explanation (SHAP) analysis, identified pressure, temperature, Chi0, Kappa2, and EState_VSA10 as the top five influential input features. These findings provide valuable insights into the underlying molecular features affecting CO2 solubility in ILs and lay the foundation for future research in this field.

The Euler Sombor index of a graph

AbstractA novel geometric method is proposed for constructing vertex‐degree‐based molecular structure descriptors, which is the perimeter of an ellipse whose focal points represent the degree‐point and its dual‐point of a pair of adjacent vertices in a graph . We first analyze the chemical applicability of this elliptic Sombor index, and then establish its mathematical properties and determine the extremal values for this elliptic Sombor index among all (molecular) trees and characterize the corresponding extremal graphs.

Unveiling the electronic and molecular structure of a trinuclear ruthenium cluster containing one nitrosyl ligand

The understanding of the Ru-NO bond in Ru nitrosyl systems is of great interest due to the non-innocent nature of the NO ligand, and because of the ability of such compounds to release nitric oxide, an essential physiological regulator. The Ru-NO bond description can be even more complicated when it comes to polynuclear systems such as the μ-oxo clusters of general formula [Ru3O(CH3COO)6(L)3]n, which can be electronically localized or delocalized themselves depending on the nature of the L ligands, or present unpaired electrons depending on the Ru ions oxidation state. Herein, we present a detailed electronic- and molecular-structure description of the [Ru3O(CH3COO)6(py)2NO]PF6 (py = pyridine) cluster using multiconfigurational approaches and X-ray diffraction analysis. The X-ray data unveil a linear Ru–NO moiety with a Ru-NO angle of 180°. Although most linear {RuNO}6 complexes have been largely described as RuII–NO+, our valence bond-type analysis based on a CASSCF ground state wavefunction, with an active space comprised of 18 electrons and 16 orbitals, showed a predominance of the RuIII–NO° configuration, with minor contributions from RuIV–NO– and RuII–NO+. These findings provide a more precise framework to rationalize the electronic properties of trinuclear ruthenium nitrosyls, aiding the planning of new NO releasers based on those clusters.

EKGDR: An End-to-End Knowledge Graph-Based Method for Computational Drug Repurposing.

The lengthy and expensive process of developing new drugs from scratch, coupled with a high failure rate, has prompted the emergence of drug repurposing/repositioning as a more efficient and cost-effective approach. This approach involves identifying new therapeutic applications for existing approved drugs, leveraging the extensive drug-related data already gathered. However, the diversity and heterogeneity of data, along with the limited availability of known drug-disease interactions, pose significant challenges to computational drug design. To address these challenges, this study introduces EKGDR, an end-to-end knowledge graph-based approach for computational drug repurposing. EKGDR utilizes the power of a drug knowledge graph, a comprehensive repository of drug-related information that encompasses known drug interactions and various categorization information, as well as structural molecular descriptors of drugs. EKGDR employs graph neural networks, a cutting-edge graph representation learning technique, to embed the drug knowledge graph (nodes and relations) in an end-to-end manner. By doing so, EKGDR can effectively learn the underlying causes (intents) behind drug-disease interactions and recursively aggregate and combine relational messages between nodes along different multihop neighborhood paths (relational paths). This process generates representations of disease and drug nodes, enabling EKGDR to predict the interaction probability for each drug-disease pair in an end-to-end manner. The obtained results demonstrate that EKGDR outperforms previous models in all three evaluation metrics: area under the receiver operating characteristic curve (AUROC = 0.9475), area under the precision-recall curve (AUPRC = 0.9490), and recall at the top-200 recommendations (Recall@200 = 0.8315). To further validate EKGDR's effectiveness, we evaluated the top-20 candidate drugs suggested for each of Alzheimer's and Parkinson's diseases.

Fe2+-NTA synergized UV254 photolytic defluorination of perfluorooctane sulfonate (PFOS): Enhancing through intramolecular electron density perturbation via electron acquisition

Perfluorooctane sulfonate (PFOS) is a persistent organic pollutant posing a risk in environmental persistence, bioaccumulation and biotoxicity. This study was to reach a comprehensive and deeper understanding of PFOS elimination in a UV254 photolytic treatment with the co-presence of Fe2+ and nitrilotriacetic acid trisodium salt (NTA). PFOS defluorination was noticeably enhanced in the UV/Fe2+-NTA treatment compared with UV/NTA, UV/Fe2+ and our previously studied UV/Fe3+ treatments. UV–vis, FTIR, and UPLC/MS-MS results indicated the formation of PFOS-Fe2+-NTA complex in PFOS, Fe2+ and NTA mixture. The transition energy gap of PFOS-Fe2+-NTA decreased below the excitation energy supplied by UV254 irradiation, corresponding with red shift appearing in UV–vis scanning spectrum. This favored intramolecular electron transfer from Fe2+-NTA to PFOS under UV254 irradiation to form electron-accepting PFOS. Molecular electrostatic potential and atom charge distribution analyses suggested electron density rearrangement and perturbation in the perfluorinated carbon chain of electron-accepting PFOS, leading to the decrease in bond dissociation energies. Intermediate products detection suggested the parallel defluorination pathways of PFOS desulfonation, middle carbon chain scission and direct C-F cleavage. NTA exhibited crucial functions in the UV/Fe2+-NTA treatment by holding Fe2+/Fe3+ in soluble form as a chelant and favoring water activation to generate hydrated electrons (eaq−) under UV irradiation as a photosensitizer. Fe2+ acting as the conduit for electron transfer and the bridge of PFOS anion and NTA was thought functioning best at 200 µM in this study. The degree of UV/Fe2+-NTA -synergized PFOS defluorination also depended on eaq− yield and UV254 photon flux. The structure dependence on the electron transfer process of PFOS and PFOA was explored incorporating molecular structure descriptors. Because of possessing greater potential to acquire electrons or less likeliness to donate its electrons than PFOA, PFOS exhibited faster defluorination kinetics in the published “reduction treatments” than “oxidation” ones. Whereas, PFOA defluorination kinetics were at similar level in both “reduction” and “oxidation” treatments.

Study for Some Eccentricity-based Topological Indices of Second Type of Dominating David-derived Network.

Dominating David-derived networks are widely studied due to their fractal nature, with applications in topology, chemistry, and computer sciences. The use of molecular structure descriptors is a standard procedure that is used to correlate the biological activity of molecules with their chemical structures, which can be useful in the field of pharmacology. This article's goal is to develop analytically closed computing formulas for eccentricitybased descriptors of the second type of dominating David-derived network. Thermodynamic characteristics, physicochemical properties, and chemical and biological activities of chemical graphs are just a few of the many properties that may be determined using these computation formulas. Vertex sets were initially divided according to their degrees, eccentricities, and cardinalities of occurrence. The eccentricity-based indices are then computed using some combinatorics and these partitions. Total eccentricity, average eccentricity, and the Zagreb index are distance-based topological indices utilized in this study for the second type of dominating David-derived network, denoted as D2(m). These calculations will assist the readers in estimating the fractal and difficult-tohandle thermodynamic and physicochemical aspects of chemical structure. Apart from configuration and impact resistance, the D2(m) design has been used for fundamental reasons in a variety of technical and scientific advancements.

On the Entire Harmonic Index and Entire Harmonic Polynomial of Graphs

A topological descriptor is a numerical parameter that describes a chemical structure using the related molecular graph. Topological descriptors have significance in mathematical chemistry, particularly for studying QSPR and QSAR. In addition, if a topological descriptor has a reciprocal link with a molecular attribute, it is referred to as a topological index. The use of topological indices can help to examine the physicochemical features of chemical compounds because they encode certain attributes of a molecule. The Randić index is a molecular structure descriptor that has several applications in chemistry and medicine. In this paper, we introduce a new version of the Randić index to the inclusion of the intermolecular forces between bonds with atoms, referred to as an entire Harmonic index (EHI), and we present the entire Harmonic polynomial (EHP) of a graph. Specific formulas have been obtained for certain graph classes, and graph operations have been obtained. Bounds and some important results have been found. Furthermore, we demonstrate that the correlation coefficients for the new index lie between 0.909 and 1. In the context of enthalpy of formation and π-electronic energy, the acquired values are significantly higher than those observed for the Harmonic index and the Randić index.

Geometric approach to vertex‐degree‐based topological indices–Elliptic Sombor index, theory and application

AbstractA novel geometric method is proposed for constructing vertex‐degree‐based molecular structure descriptors (topological indices). The model is based on an ellipse whose focal points represent the degrees of a pair of adjacent vertices. This approach enables a geometric interpretation of several previously known topological indices, and lead to design of a few new. The area of the ellipse induces a vertex‐degree‐based topological index of remarkable simplicity, which we call elliptic Sombor index(). The main mathematical properties of are established, especially its relations to other, earlier known, indices. Then the applicative potential of is analyzed.

The minimal chemical tree for the difference between geometric–arithmetic and Randić indices

AbstractTopological indices are numerical parameters derived from the structural information of chemical compounds. By providing a quantitative description of molecular structures, topological indices enable researchers to predict various properties and behaviors of molecules. The Randić index () and the geometric–arithmetic index () are widely recognized topological indices. It is observed that, for any given graph . We aim to investigate the gap between and for chemical tree. The complete characterization of minimal chemical tree for is carried out here. This article offers an interesting finding that, whereas and provide same minimal chemical trees, yields minimal tree structures that are totally different from and . Moreover is observed to correlate well with physico‐chemical properties of octanes.

On Relations between Distance-Based Topological Indices

Motivated by the recent paper On topological indices and their reciprocals, MATCH Commun. Math. Comput. Chem. 91 (2024) 287, we establish additional relations between distance- and degree-and-distance-based molecular structure descriptors: Wiener, hyper-Wiener, Harary, connective eccentricity, eccentric connectivity, degree distance, Gutman, additively weighted Harary, and multiplicatively weighted Harary indices, especially for their products.

Molecules structure and viscosity relationship of nematic liquid crystal and BPNN-QSAR model

Nematic liquid crystal materials designed for optics, microwave communication tuning, etc. need high response speed, which is related to the rotational viscosity and the birefringent index of the liquid crystal. In order to achieve a wide tuning range of phase modulation, the nematic liquid crystals often employ large π-electron conjugated systems and large polar groups to enhance the birefringence and dielectric anisotropy of the liquid crystal molecule, which, however, increases the viscosity of the liquid crystal material, deteriorating the response speed of the microwave device. Herein, we explore the viscosity of the nematic liquid crystal from the perspective of liquid crystal compound structure by testing the viscosity of our designed and synthesized forty-two different nematic liquid crystals by using a rotating rheometer at 25 ℃. To the best of our knowledge, the BPNN-QSAR quantitative structure-activity model between nematic liquid crystal molecular structure and viscosity is established for the first time. The correlation coefficient between the predicted value and the experimental value is <i>q</i><sup>2</sup> = 0.607 > 0.5, indicating that the model can be used to predict the viscosity performances of liquid crystal compounds. Besides, the molecular structure descriptors affecting the viscosity properties are explored. Based on the practical application and this model, seven liquid crystal molecules of two series with large birefringent index are designed and tested. The viscosity predicted by the BPNN model is smaller than that of the molecules of the same type and matches with the measured viscosity.