What would have taken 4,000 years of computations in specific cancer therapy research can now be done in a day.

In cancer therapy today, even if a patient receives a targeted drug, some cancer cells may develop a resistance to the drug and prevent full remission.

The mechanism for how certain cancers become drug resistant remains unclear. Since the effectiveness of cancer drugs may vary depending on the individual’s physical makeup and the variations in gene expression, a comprehensive search of all 20,000 genes in the human genome to understand how drug resistance occurs could take more than 4,000 years using a conventional computer.

Now, with the use of one of the world’s fastest supercomputers and AI algorithms, specific comprehensive search could be conducted within a day. This achievement was announced by Fujitsu and the Tokyo Medical and Dental University (TMDU) on 7 March.

This approach to problem solving involves the use of Fujitsu supercomputer named “Fugaku”, the use of “parallel conditional and causal algorithms” to maximize computational performance, and a genetic database of drug sensitivity and resistance data.

In future, the two institutions plan to conduct multilayered and comprehensive analyses the aim of accelerating medical research in the fields of drug efficacy, drug discovery and other medical strategies such as using advanced biomarkers to improve targeting of cancer therapies for individual genetic profiles. This can radically boost clinical research in terms of cost and efficiencies.

According to Prof Seiji Ogawa, Graduate School of Medicine, Kyoto University: “If the (bio)marker that predicts who will benefit from the drug is known, the cost of clinical trials can significantly be reduced and the probability of success of clinical trials can be increased.”

In addition to improving medical care, the new technology can be used to resolve challenges in a variety of fields, including marketing, system operations and manufacturing.