Ground-breaking project could lead to new targeted therapies for cancer
Recent biomedical research shows that many serious diseases, in particular cancer, are caused by persistent disruptions of cellular communication processes. These processes use a biochemical reaction called phosphorylation to control the information flow.
This biochemical computer is faulty in cancer, and drugs that block rogue phosphorylation reactions have proven effective cancer treatments. However, despite half a century of intense research, discovering these critical phosphorylation reactions is still slow due to the extensive manual effort required.
Automated, highly-confident prediction of previously unknown phosphorylation reactions is therefore much desired. This can lead to substantially increased rates of discoveries in cellular computing, which can in turn deliver the targets for more efficient cancer drugs.
Fujitsu Laboratories Ltd, Fujitsu Ireland and Insight Centre for Data Analytics at NUI Galway have worked since 2015 on TOMOE, a novel discovery informatics platform based on knowledge graphs and statistical relational learning.
The Irish part of the TOMOE team, led by Dr Pierre-Yves Vandenbussche and Dr Vit Novacek, has recently initiated a proof-of-concept collaboration with Systems Biology Ireland at University College Dublin led by Professor Walter Kolch.
The team has applied the automated discovery technology to the use case of phosphorylation prediction. The project focuses on phosphorylation reactions that could be cancer therapy targets, but the engine can also automatically generate predictions for types of phosphorylation reactions that have gone awry in other diseases.
This will make it a powerful tool for discovering the next generation of drug targets by computation guided experiments that will allow us to systematically analyse and understand the role of phosphorylation in living organisms.
Professor Walter Kolch, Director, Systems Biology Ireland and Fellow, UCD Conway Institute said, “This work with Fujitsu is an exciting glimpse into the future of drug target discovery in which computational modelling will shortcut a laborious experimental process.”
As of March, 2017, the team has finished working on the first functioning prototype of the prediction engine. The prototype is currently being tested on a comprehensive knowledge graph covering known phosphorylation reactions and related protein interactions in humans that are available in machine-readable format.
Further implementation details and preliminary results will be released later this year.
2 March 2017
For further information contact, Micéal Whelan, Communications Manager (Innovation), University College Dublin, e: email@example.com or t: +353 (0)1 716 3712,
Phosphorylation is a biochemical reaction where a phosphate residue is transferred by a kinase to a substrate, often causing a change in function in the substrate. Phosphorylation involves direct physical interactions between kinases and their substrates as well as indirect functional associations that result from the changes in activity of the substrates. These types of interactions are often represented as directed graphs with labelled edges corresponding to different interaction types.
Role of phosphorylation in diseases can be significant as it regulates for instance cell growth, cell differentiation, and cell death. Disruptions of these regulatory processes are the main culprit of many serious diseases such as cancer. Therefore, phosphorylation is one of the key topics studied in system and molecular biology, as well as in pharmacology. The majority of targeted cancer therapies rely on drugs that block certain phosphorylation reactions that have gone rogue in cancer cells.
Thus, phosphorylation is a major area for finding new drug targets. However, the research still faces substantial challenges in finding new phosphorylations and their functions. One of the reasons is the large number of possible phosphorylations - exploring this vast space is hard even with modern high-throughput technologies. Another reason is the tedious experimental work required to identify the key phosphorylation reactions that are involved in diseases.
Knowledge graphs are graph-structured knowledge bases that allow for large-scale and robust representation, integration, analysis and completion of real world knowledge. This framework has become increasingly popular in AI research in the last few years and has already been heavily used in many industrial AI products.
Statistical relational learning is a sub-discipline of AI and machine learning that is concerned with domain models that exhibit both uncertainty (which can be dealt with using statistical methods) and complex, relational structure. This makes it a perfect vehicle for reasoning with knowledge graphs.
Systems Biology Ireland (SBI) is an Institute based at University College Dublin. It specialises in cellular signal transduction investigation with a particular focus on development of new treatment strategies in cancer. The centre has expertise in phosphorylation network mapping, drug target and biomarker discovery; patient stratification and sub-population characterisation; combination therapy prediction and screening; drug target validation; and protein-protein interaction profiling. The experimental approach of the group combines traditional biological experimentation with advanced omics profiling technologies, and computational modelling and simulation. This combined approach allows important nodes in signalling networks to be identified quickly and at a lower cost than might otherwise be possible. www.ucd.ie/sbi/
The Insight Centre for Data Analytics is the largest of Science Foundation Ireland's research centres, with 400 researchers working across Ireland in areas including connected health, decisions analytics, media analytics, internet of things and recommender systems. The Centre also has more than forty commercial partners working with them on a range of industry projects. Insight is made up of four main centres: Insight at DCU, Insight at NUI Galway, Insight at UCC and Insight at UCD. The research reported in this press release has been coordinated by the branch of Insight based at NUI Galway. www.insight-centre.org/
Fujitsu Ireland is part of the global Fujitsu Group, delivering IT-based business solutions to customers in 70 countries through a workforce of 170,000 employees. Our regional structure enables customers to share in best-practice approaches, knowledge and re-use from around the world whilst local operations ensure that solutions are delivered in line with local customer requirements. With some 800 people employed throughout the island of Ireland, we concentrate on our core strengths, delivering customer focused solutions. From keeping tills ringing, protecting our borders through to building mobile phone networks Fujitsu touches the lives of millions of people in Ireland every day. Fujitsu’s existing customer base includes some of the leading organisations in the public and private sector in Ireland, including Aer Lingus, Airtricity, Dublin Airport Authority, ESB, Road Safety Authority, Telefonica, The Courts Service and Institute of Art and Design Dun Laoghaire, and Topaz. www.fujitsu.com/ie/
Fujitsu Laboratories Ltd is the main global research division of Fujitsu Limited. The laboratories have a mission to contribute to the social innovation and the growth of Fujitsu Group. We are working on emerging technologies related to ICT from advanced materials, next-generation devices, networks and cloud systems to the creation of next-generation solutions and services. The AI branch of Fujitsu Laboratories involved in this project engages in R&D on the human-centric AI technology that provides the services based on the intelligent ICT system and that can understand the human emotions and affections. www.fujitsu.com/jp/group/labs/en/