An AI system for predicting protein conformation. It is possible to predict the three-dimensional structure (folding structure) of a protein from its primary sequence (amino acid sequence). It learns hundreds of thousands of protein structure databases and uses DeepMind-based deep learning techniques to predict the conformation of new proteins from their amino acid sequences.
A tool for generating wavevector paths in band calculations of solids. It identifies high-symmetry points in reciprocal space based on the symmetry of the crystal and provides a standardized “path” connecting them. It supports various crystal structure formats (such as POSCAR and CIF) and is compatible with many electronic structure calculation software (e.g., VASP, Quantum ESPRESSO, ABINIT). A web-based interface is also available.
A Python package for extracting structural features from point cloud and image data using the mathematical framework of persistent homology. In the field of materials science, it is used to characterize structural differences between liquids and glasses, as well as for dimensionality reduction of microscope images. It is also useful for obtaining structural descriptors for machine learning.