“…For example, recurrent neural networks are designed to work with sequence data (also known as temporal or time-series data) of varying lengths, with most popular applications in speech recognition [89] natural language processing, [90] as well as some recent applications in materials informatics. [91,92] A relatively new class of deep learning is called geometric deep learning which is capable of dealing with non-Euclidean data, such as graphs with nodes and edges, where standard deep learning kernels like convolution are not well-defined. Due to its ability to work with graph data, it has found applications in quantum chemistry, [93,94] in particular for analyzing data from molecular dynamics simulations.…”