High precision deep-learning model combined with high-throughput screening to discover fused [5,5] biheterocyclic energetic materials with excellent comprehensive properties

Finding novel energetic materials with good comprehensive performance has always been challenging because of the low efficiency in conventional trial and error experimental procedure. In this paper, we established a deep learning model with high prediction accuracy using embedded features in Directed Message Passing Neural Networks. The model combined with high-throughput screening was shown to facilitate rapid discovery of fused [5,5] biheterocyclic energetic materials with high energy and excellent thermal stability. Density Functional Theory (DFT) calculations proved that the performances of the targeting molecules are consistent with the predicted results from the deep learning model. Furthermore, 6,7-trinitro-3 H -pyrrolo[1,2- b ][1,2,4]triazo-5-amine with both good detonation properties and thermal stability was screened out, whose crystal structure and intermolecular interactions were also analyzed. In this study, we used D-MPNN embedded with features to rapid discovery of 6,7-trinitro-3 H -pyrrolo[1,2- b ][1,2,4]triazo-5-amine with high energy and excellent thermal stability. DFT calculations prove the performances of the targeting molecule.