A Molecular Descriptor-Based Analysis of Organic Compounds and Designing New Promising Candidates by Machine Learning

High Resolution Image Download MS PowerPoint Slide A data-driven approach using Python has been employed to mine new energetic materials with higher heats of sublimation (Δ H ). A data set of 307 energetic compounds with experimental Δ H values was used to train machine learning models, including linear, random forest, gradient boosting, and extra trees, which yielded high R-squared values of 0.95–0.98. The descriptors ATS 1s and mZagreb1 are found to have a high Pearson correlation with the Δ H, while SHapley Additive exPlanations (SHAP) impact analysis reveals that ATS 1s and W path have a significant impact on model performance. Using these optimized models, 705 new organic compounds are designed with predicted Δ H as high as 170 kJ/mol. Notably, the results showed that the simplified molecular line entry system ( SMILES ) with a length of 500–700 has the highest synthetic accessibility (SA), suggesting that molecules with this range of complexity are more easily accessible than those with shorter or longer SMILES . This study demonstrates the potential of ML-assisted design of new organic materials and highlights the importance of considering SA in the design process. The predicted compounds with high Δ H and optimal SA hold promise for various applications, including propellants, explosives, and other high-energy materials.