TOKYO – July 6, 2021 – Preferred Networks, Inc. (PFN), ENEOS Corporation (ENEOS) and their joint venture Preferred Computational Chemistry (PFCC) announced today that PFCC has launched Matlantis™, a cloud-based atomistic simulator that significantly accelerates discovery and development of new materials.

PFCC’s Matlantis supports large-scale materials discovery by quickly simulating the atomic-scale behavior of various materials. PFN and ENEOS have incorporated a deep learning model into a conventional physical simulator to increase the simulation speed by tens of thousands of times and to support a wide variety of materials. The deep learning model for Matlantis has been trained with a vast amount of atomic structure data generated by physical simulation on PFN’s supercomputers. 

Key Features of Matlantis 

1. Versatility
Matlantis can simulate properties of molecules and crystal systems, including unknown materials. Any combinations of 55 elements are currently supported, and more elements will be added.

2. High-speed performance
The atomistic simulation tasks that take hours to months using conventional DFT (density functional theory) methods on a high-performance computer can be finished in only a few seconds using Matlantis.

3. User-friendliness
Thanks to the pre-trained deep learning model, physical property calculation library and high-performance computing environment, no hardware or software installations are required for performing simulations.

Material simulation on Matlantis screen

The product name Matlantis is a combination of “material” and “Atlantis,” a mythical continent appearing in Plato’s works that inspired adventurers worldwide. Out of 10⁶⁰ theoretically possible functional molecules, mankind has discovered only a handful of useful materials. The name represents PFCC’s commitment to help companies discover innovative materials in the vast ocean of unknown molecules. 

Headed by PFN’s Chief Operating Officer Daisuke Okanohara, PFCC was established on June 1, 2021 in Tokyo with a paid-in capital of 310 million yen with 51% ownership by PFN and 49% ownership by ENEOS.

“PFCC’s mission is to contribute to a sustainable future by enabling companies to create innovative materials,” said Daisuke Okanohara, Chief Executive Officer of PFCC. “To achieve this, we have combined Preferred Networks’ artificial intelligence expertise and computing infrastructure with ENEOS’s expertise in chemistry to build Matlantis. We look forward to providing powerful tools to help researchers worldwide discover game-changing materials that give a positive impact on our future.”