TeamDrive
RUS

EU supercomputing project will help to speed up drug discovery

28 August 2018

GMP News

The EU-funded ExCAPE project is devising ways to develop new medicines fast using high performance computing and machine learning.

In January 2018 the European Commission launched a major initiative on supercomputing – the EuroHPC Joint Undertaking – to create an integrated world-class supercomputing and data infrastructure and encourage European contribution to this field. It is expected to be operational before the end of 2018.

The project is combining high performance computing (HPC – also known as supercomputing) and machine learning to speed up the discovery of new drugs. Scientists developing medicines need to find out how different pharmaceutical compounds behave – their bioactivity. Testing each compound individually is time-consuming and expensive, so it is necessary to find more efficient ways of predicting which compounds are likely to be helpful.

Machine learning – ‘teaching’ computers to assess and improve their performance of a task – is already used for this, but the algorithms currently used do not work well with large amounts of very disparate data. The ExCAPE project is therefore developing more advanced algorithms and ways of implementing them to run on supercomputers, accelerating drug discovery and reducing costs.

Currently, the average cost of developing a drug is €930 million and it takes 9 to 13 yearsfor a compound to reach the patient. The failure rates of pharmaceutical compounds in clinical trials are 54% due to a lack of efficiency and 9% due to toxicity. The EU pharmaceutical market is worth around €260 billion annually.

While HPC systems were originally designed and used mainly for carrying out physics simulations, in the last ten years a new type of use has emerged: handling and analysing big datasets. When that data is expensive to generate, it is important to make the most of it, not just by analysis but also carrying out calculations to make new predictions. This is the case with chemogenomics (predicting the activity of compounds in the drug discovery phase of the pharmaceutical industry), and so the ExCAPE project has brought together researchers from nine institutions to create sophisticated computational models to be used with this information.

The project is focused on developing algorithms, writing software that can be used on large HPC machines, and preparing datasets that can be used to test them. Some of the software and datasets have been released publicly as Open Source and Open Data. The project’s work should result in cheaper drug development, but also has possible applications in in e-commerce, fraud detection and manufacturing.

The project involves such EU countries as: Belgium (coordinator), Austria, Bulgaria, Czech Republic, Finland, Sweden, Spain, United Kingdom. The total budget of the project is €3,9 million.


Previous publication Next publication

Media Center

  • 31 October 2018

    Scientists unveiled a more effective approach for assessing drug response

    Scientists from Eli Lilly and Company, the Icahn School of Medicine at Mount Sinai (New York, USA) and Sema4 (Stamford, USA) released results from a proof-of-concept study demonstrating that patient-derived cells offer a more effective approach for assessing drug response than conventional methods.

  • 30 October 2018

    Researchers developed an AI approach to identify antibiotic resistance genes

    Researchers at the University of California San Diego (USA) have developed an approach that uses machine learning to identify and predict which genes make infectious bacteria resistant to antibiotics. The approach was tested on strains of Mycobacterium tuberculosis – the bacteria that cause tuberculosis (TB) in humans. It identified 33 known and 24 new antibiotic resistance genes in these bacteria.

  • 29 October 2018

    Expanding the reach of gene editing with a new CRISPR enzyme

    The CRISPR-Cas9 gene editing system has been widely studied because of its potential therapeutic applications, but limitations in the number of locations on the genome it can target remain a major drawback. Now scientists at the Massachusetts Institute of Technology have identified a new Cas9 enzyme that they say can help CRISPR reach more gene mutations.

  • 26 October 2018

    Biotech Backed by Bain, Pfizer loads prime CNS assets into new biotech

    Pfizer has followed through on its pledge to divest a hunk of its neuroscience R&D, spinning several programs into a new company called Cerevel Therapeutics backed by $350 million in venture funding. Pfizer is contributing a trio of clinical-stage drug candidates—including a Parkinson’s therapy due to start phase 3 testing next year—plus a clutch of earlier-stage programs, while Bain Capital and affiliates stumped up the initial funding.

Read more