Blog
We provide easy-to-understand explanations of Matlantis terminology and the latest technology trends from an expert's perspective. We deliver information that will help you solve your problems and make new discoveries.
Editor’s PICK
Explainer : Why Did the AI Predict That ? Uncovering Atomic-Level Interpretability through PFP Descriptors and Shapley Values
The online proceedings for the Spring Meeting of the Japan Society of Applied Physics have been published, and it feels like the academic conference season has finally arrived. I'm sure there are many people who have submitted their proceedings and are busy preparing their presentations, and many others who are looking at the published proceedings and planning to attend. At the 86th Autumn Meeting of the Japan Society of Applied Physics last year, I gave a presentation entitled "Interpretation of predictions at the atomic level by combining PFP descriptors and Shapley values."
Materials Informatics Explainer computational chemistry
Writing SMILES from scratch
With the spread of materials informatics (MI), DFT calculations, and molecular dynamics simulations, the number of opportunities to input molecular structures on computers is rapidly increasing. In these cases, the SMILES (Simplified Molecular Input Line Entry System) notation, which treats molecular structures as character strings, is often used. Many chemical software programs allow you to input molecular structures and SMILES.
Explainer computational chemistry
Nagoya University × Matlantis Case Study:“Advanced Experiments for Frontier Technologies and Sciences” —A Four-Day Intensive Course That Sparked Experimental Students’ Curiosity Through AI Simulation
Nagoya University's Graduate School of Engineering's "Cutting-Edge Science and Engineering Experiments" for the second half of the 2025 academic year included a chemical simulation experiment class incorporating the AI atomic-level simulator "Matlantis." By utilizing the power of AI simulation, the quality and speed of research can be dramatically improved. Experimental students who are not experts in computational chemistry experienced this potential with their own hands.
Interview computational chemistry
Introduction to Machine Learning Interatomic Potentials (MLIPs): A Game Changer in Materials Simulation
Introduction In the fields of materials science, chemistry, and drug discovery R&D, atomic and molecular level simulations have become established as a fundamental technology for elucidating the properties and reaction mechanisms of materials from a microscopic perspective. However, full-scale application in R&D has always been hindered by the trade-off between "accuracy," "computational cost," and "versatility." For example, first-principles calculations are quantum
Machine learning force field Explainer
High-Accuracy and High-Speed MOF Calculations with Matlantis - Benchmark Results of Machine Learning Interatomic Potentials -
Matlantis can calculate a wide range of materials, but among them, metal-organic frameworks (MOFs) are important materials with a wide range of applications, including catalysts and CO2 storage. This material, discovered in the 1990s, has already been industrialized and is attracting attention worldwide as an essential material for maintaining a sustainable society. In fact, the 2025 Nobel Prize
Explainer computational chemistry
Featured Tags
Blog article list
Generalization evaluation of machine learning scoring functions for structure-based virtual screening
Materials Informatics computational chemistry
Compound design using deep reinforcement learning
Chemoinformatics Bioinformatics
Universal Neural Network Potential for Materials Discovery
Materials Informatics Machine Learning Force Fields
Accelerating protein-compound docking simulations using GPUs
Cheminformatics Bioinformatics Drug Discovery
Neural Network Potential Considering Charge Transfer
computational chemistry
Searching for SARS-CoV-2 protease inhibitors using AI drug discovery technology
Cheminformatics Bioinformatics Drug Discovery
We are releasing the open source Pytorch implementation of DFT Dispersion.
computational chemistry
Improving Protein-Drug Binding Free Energy Calculations Using Neural Network Potential
Cheminformatics Bioinformatics Drug Discovery
Crystal structure prediction using PFP
Materials informatics crystal structure prediction
Surface energy benchmark using PFP
PFP benchmark
Lattice thermal conductivity calculation using PFP
PFP benchmark thermophysical properties
Application of LightPFP to enzyme reactions
Bioinformatics Drug Discovery Enzymes
-
URL
Copied
