Density Prediction Models for Energetic Compounds Merely Using Molecular Topology

Abstract

Newly developed high-throughput methods for property predictions make the process of materials design faster and more efficient. Density is an important physical property for energetic compounds to assess detonation velocity and detonation pressure, but the time cost of recent density prediction models is still high owing to the time-consuming processes to calculate molecular descriptors. To improve the screening efficiency of potential energetic compounds, new methods for density prediction with more accuracy and less time cost are urgently needed, and a possible solution is to establish direct mappings between the molecular structure and density. We propose three machine learning (ML) models, support vector machine (SVM), random forest (RF), and Graph neural network (GNN), using molecular topology as the only known input. The widely applied quantitative structure–property relationship based on the density functional theory (DFT–QSPR) is adopted as the benchmark to evaluate the accuracies of the models. All these four models are trained and tested by using the same data set enclosing over 2000 reported nitro compounds searched out from the Cambridge Structural Database. The proportions of compounds with prediction error less than 5% are evaluated by using the independent test set, and the values for the models of SVM, RF, DFT–QSPR, and GNN are 48, 63, 85, and 88%, respectively. The results show that, for the models of SVM and RF, fingerprint bit vectors alone are not facilitated to obtain good QSPRs. Mapping between the molecular structure and density can be well established by using GNN and molecular topology, and its accuracy is slightly better than that of the time-consuming DFT–QSPR method. The GNN-based model has higher accuracy and lower computational resource cost than the widely accepted DFT–QSPR model, so it is more suitable for high-throughput screening of energetic compounds.

Decoding hexanitrobenzene (HNB) and 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) as two distinctive energetic nitrobenzene compounds by machine learning

“…These algorithms were successfully applied in previous studies. 27,32,40,41 Then, the best model with the lowest root mean squared error (RMSE) and mean absolute error (MAE), and the highest coefficient of determination (R 2 ) was adopted for subsequent application. As for the molecular flatness, LR, Linear SVC, SVC, RFC, GBC, and MLP Classifier algorithms were applied, as T4.…”

“…26 In comparison, there have been much fewer attempts of using ML in the investigation of EMs. Recently, the main focus has been upon the prediction models of some main properties of EMs, such as density, energetics and detonation properties, as well as the screening of potential energetic compounds, [22][23][24][27][28][29][30][31][32] far from the power of ML itself. This is mainly ascribed to the limitation of available data and fewer attempts of applying ML.…”

Deep learning modeling strategy for material science: from natural materials to metamaterials

“…The GNN model can also predict the crystal density of high-energy compounds [105] and the performance of inorganic materials [37]. In order to fully understand the relationship between atoms in materials and the effects of atoms on material properties, researchers [37] proposed a GNN model global attention GNN (GATGNN).…”

Crystal Structure and Noncovalent Interactions of Heterocyclic Energetic Molecules

“…Energetic materials (EMs), mainly including explosives, propellants and pyrotechnics are a class of important metastable compounds that involve explosive groups, or oxidants and reducers, that can transiently release considerable energy through their self-redox reactions after sufficient stimulation and have occupied an important place in mining, military equipment, space exploration and fireworks [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 ]. Regarding an EM, energy and safety, which significantly depend on the crystal packing, are two of the most important concerns and attract the most attention, as the energy represents their efficiency and the safety guarantees their applicability.…”