Boosting productivity and performance in drug discovery with SEQUOIA - Semantic Query of Information Assets

Project Information

SEQUOIA-DD

Grant agreement ID: 736397

DOI

10.3030/736397

Project closed

EC signature date 25 July 2016

Start date 1 September 2016

End date 28 February 2017

Funded under

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Total cost

€ 71 429,00

EU contribution

€ 50 000,00

Coordinated by

SYNAPSE INFORMATION LIMITED
United Kingdom

Periodic Reporting for period 1 - SEQUOIA-DD (Boosting productivity and performance in drug discovery with SEQUOIA - Semantic Query of Information Assets)

Reporting period: 2016-09-01 to 2017-02-28

Summary of the context and overall objectives of the project

Synapse currently builds software for complex data integration so forensics experts can ask sophisticated queries that span multiple online financial repositories to discover the next Bernie Madoff, hidden amongst millions of online filed financial statements worldwide. This is now technically possible because regulators mandated that the millions of annual accounts filings must be carried out in XBRL – a precursor to semantic query. Unlike a Google search that returns thousands of records, semantic search returns just the handful that precisely match the query. Drug R&D data is now published in semantic format and so Synapse could potentially answer similarly complex, but high impact questions such as ‘will this candidate drug fail toxicity tests’? This report shows how Synapse will build a powerful software query platform for Drug Researchers worldwide.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

This Phase 1 (work package 2) required finding classes of high impact questions in the Drug R&D domain which we concluded had to be at the start of the Drug R&D process rather than towards the end, because for the latter, the confidentiality of data and regulatory hurdles are insurmountable for our short term goals. We needed to find an unmet (work packages 3, 4 & 5) need that was common across all Researchers in the domain whether they worked in Pharma, Biotech or Academic R&D. We needed a common process, which researchers know is incompletely thorough and where the consequences for lack of thoroughness are highly expensive. We needed to find a process which is all too frequently heavily manual but which would lend itself to new inexpensive technology – in this case 3-D printing of macrofluidics discovered with a local partner (work packages 6, 7 & 8) – such that the most budget pressed academic could use it. Assuming that we then bundled this inexpensive open source macrofluidics hardware platform with the semantic query system we will build, we had one final hurdle to overcome. For decades, data query companies have tried to sell business and scientific users graphical interfaces that sought to automate the work that programmers do but have failed to have great success. Researchers instead frequently choose to do all of their work ‘inside’ spreadsheets. In this Phase 1 we have discovered a method to overcome this market adoption problem.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

By giving researchers a powerful interrogation tool to access and investigate datasets from around the world to help focus their research, we will be improving the efficiency of drug discovery and potentially increase the number of successful drug candidates reaching patients and consequently lead to better prognosis for millions of patients worldwide. Synapse has created a system today where the ordinary spreadsheet ‘sits on top of’ financial data, and lets the user query millions of records as if they are locally present. This is well adopted in the financial world and we believe we can succeed in Drug R&D. We have found collaborators specialising in the ADMET (early stage R&D) with an important un-met need to act as a starting point for commercialisation and have a clear plan of action defined showing a path to wider adoption.

Synapse Logo