Japan's Tokyo Medical and Dental University (TMDU) and Fujitsu Laboratories have jointly announced that using Fujitsu's Fugaku supercomputer has allowed them to achieve cancer gene analysis in less than a day, instead of months.
The study, according to Fujitsu, is aimed at improving the understanding of the relationship between cancer cells and cancer-related genes, which it hopes can eventually help establish new cancer therapies.
As part of this process, TMDU leveraged the Fugaku supercomputer and Fujitsu Laboratories' artificial intelligence "deep tensor" technology to analyse complex data sets about cancer genes and cells. The supercomputer then delivered this analysis in a format that could be easily understood.
"Harnessing the power of the world's fastest supercomputer, Fugaku, Fujitsu, and TMDU were able to extract a network representing the regulatory relationships among genes in epithelial cancer cells from the analysis of data with 20,000 genes, predict their relationship with infiltration and metastasis using deep tensor technology developed by Fujitsu Laboratories, and present prediction models," Fujitsu said.
See also: How the world's largest and fastest supercomputers are being used to understand the coronavirus[1]
Fugaku was jointly developed by Japanese scientific research institute RIKEN and Fujitsu, and has already been used by researchers in Japan for various matters, including helping the country fight COVID-19[2].
RIKEN Center for Computational Science director Satoshi Matsuoka recently said the program has been receiving "stellar results", mostly due to the computing resources available to scientists matching the entire high-performance compute capacity in Japan.
"For example, we're finding some existing drugs, drugs that have approved for other purposes like heart conditions or high blood pressure or parasites to be immensely useful against COVID-19," he said.
"So if these are proven to be effective, then we may have these