Supercomputers speed up the diagnosis of diseases

Supercomputers speed up the diagnosis of diseases

Personalized drug treatments are possible if enough data is available on the patient, and it has been stored and pre-processed correctly. Alongside eleven other academic and commercial players, the Finnish ELIXIR Center CSC and the   Barcelona supercomputing center (BSC)   kicked off the  European HPC Center of Excellence for Personalised Medicine (PerMedCoE) project in October 2020. The project will develop personalized medicine data analysis methods for supercomputers, also for pre-exascale supercomputers such as the future EuroHPC´s LUMI supercomputer for CSC.

Through the use of high-performance computing, data analysis can be accelerated, enabling the introduction of biological data such as genomics and proteomics as part of the diagnosis of diseases. The PerMedCoE project is developing algorithms that can significantly reduce the computing time required for analysis, facilitating and speeding up disease diagnosis and identification of the appropriate treatments. A genome analysis can take weeks or even months. Thanks to super computation and better software, diseases can be diagnosed in future within just hours or days.

Projects like this are important for research teams for example at Institute for Molecular Medicine Finland (FIMM), who are routinely working with massive amounts of data. The amount of data is increasing, there is a shortage of data storage space and data pre-processing takes time. Data processing can be alleviated by dividing work between CSC and FIMM. In the pilot stage, genomic data is transferred from FIMM to CSC. Data pre-processing and quality assurance of analysis are faster and in future, CSC will distribute data back to research teams on a national basis. CSC has also developed a new interface to its Allas -service for genomic data to be shared from FIMM.

Read more about the interview with Katja Kivinen, Director of the Technology Center of the Finnish Institute of Molecular Medicine (FIMM), on the ELIXIR-Finland website.