Predicting structure‐dependent properties directly from the three dimensional molecular images via convolutional neural networks

Abstract

Machine learning (ML) provides an efficient method to predict the unknown properties during the exploration of new materials, but how to efficiently represent the molecules as input is still not fully solved. Inspired by image processing, one of the classical ML tasks, this work developed a method to predict the structure-dependent properties by converting the atom position into a three-dimensional (3D) molecular image and learning the structure features from the image via a classical convolutional neural networks. After trained with datasets larger than 12,000 species, a very high accuracy is obtained in predicting both theoretical molecular energy and experimental properties including melting points, boiling points, and flash points. Since stereoscopic information is explicitly and accurately represented by the molecular images, our model successfully distinguish the melting points and boiling points of molecules with similar structure, including those of trans-cis isomers.

AI-assisted chemistry research: a comprehensive analysis of evolutionary paths and hotspots through knowledge graphs

“…Bigdata-based artificial intelligence (AI) excels at automating and intelligently completing tedious, repetitive tasks, reducing the waste of resources and environmental pollution. [5][6][7][8][9][10][11] Although the chemical industry has not been at the forefront of adopting new digital technologies, chemical scientists have begun recognizing the potential and necessity of digital transformation in the field. 12 The integration of chemistry and digitization has attracted wide attention in the scientific community.…”