School of CS newsletter

Welcome to the Research Office, which is back in the Kilburn Building.  On Monday this week Anna Humble, Natalia Stefanovic, Manny Singh and Terry Williams moved into KB 2.126, which is next to ACSO in the Kilburn building.  For the very short term, we hope, telephone numbers do not yet work; so please have patience.  As normal, emails should be sent to  researchsupportcsm@manchester.ac.uk.

The next meeting of the School Leadership Team will be on Monday 13 march 2017 between 12 pm and 2 pm.  The agenda for this meeting, together with previous agenda and minutes can be seen via http://staffnet.cs.manchester.ac.uk/committees/slt/. Please send items for discussion and comments to me using Robert.Stevens@Manchester.ac.uk.

Professor Robert Stevens

All staff will receive an email when the University Staff Survey launches on Monday 6th March. The survey will be open until 18th April. It is really important that your views are heard so please do take the time to complete the survey. It should only take around 15 minutes.

The aim of the survey is to find out staff feel about various issues and this feedback is used to inform actions plans. Within the School, feedback from the last survey was considered by the Staff Development Committee (SDC) and translated into a number of actions, which included:

• Improved transparency by circulating SLT agendas and minutes
• Undertaking review of duties, with the aim of reducing academic workload
• Subsequent surveys undertaken by SDC to better understand staff morale and wellbeing
• Establishment of the Early Career Researcher network – regular informal lunches and team activities to create a cohort effect and encourage mutual support
• Local small-scale best practice sharing and training on Blackboard, with an emphasis on using it for exams
• ​Improved induction procedure for new members of staff
• ​Investigations into bullying & harassment, close collaboration with the University’s equality and diversity group to improve understanding of these and related issues
• Increased collaboration with Estates to improve temperature regulations in offices and labs
• Changes to the school’s workload model
• Improved processes to ensure that PDRAs receive suitable career development support and have the opportunity to gain teaching experience

We do genuinely want to hear feedback from staff, so would encourage everyone to complete the survey. As added incentives staff will be able to choose a charity to receive a donation from the University on their behalf, and there is also a prize draw for a £250 voucher towards a mini-break.

Predicting Drug-Drug Interactions Through Similarity-Based Link Prediction Over Web Data by Achille Fokoue in KB L.T. 1.5 on Friday 10th March at 12pm

Drug-Drug Interactions (DDIs) are a major cause of preventable adverse drug reactions (ADRs), causing a significant burden on the patients’ health and the healthcare system. It is widely known that clinical studies cannot sufficiently and accurately identify DDIs for new drugs before they are made available on the market. In addition, existing public and proprietary sources of DDI information are known to be incomplete and/or inaccurate and so not reliable. As a result, there is an emerging body of research on in-silico prediction of drug-drug interactions. We present Tiresias, a framework that takes in various sources of drug-related data and knowledge as inputs, and provides DDI predictions as outputs. The process starts with semantic integration of the input data that results in a knowledge graph describing drug attributes and relationships with various related entities such as enzymes, chemical structures, and pathways. The knowledge graph is then used to compute several similarity measures (including semantic-based and neural network based measures) between all the drugs in a scalable and distributed framework. The resulting similarity metrics are used to build features for a large-scale logistic regression model to predict potential DDIs. We highlight the novelty of our proposed approach and perform thorough evaluation of the quality of the predictions. The results show the effectiveness of Tiresias in both predicting new interactions among existing drugs and among newly developed and existing drugs.

UCL and BCS Academy will be presenting the 13th London Hopper Colloquium on Thursday, 25 May 2017 at the BCS headquarters in London. This 1-day event will feature women speakers talking about their research, a spotlight competition open to postgraduate students, and lots of opportunities to network with other new researchers in computing.

The speakers are:

•   Dr. Lynne Baillie, Heriot-Watt University - Building User Centered Rehabilitation Technologies

•   Juliet Grout, IBM - Cybersecurity the billion pound problem

•   Dr Anna Muszkiewicz, University of Oxford - Simulations of the human heart shed light on mechanisms underpinning atrial fibrillation

•   Dr. Larissa Romualdo-Suzuki, Greater London Authority - Data as Infrastructure for Smart Cities

We are also pleased to announce that Maja Mataric', Professor and Chan Soon-Shiong Chair of Computer Science, Neuroscience, and Pediatrics at the University of Southern California (USC) will be presenting the 7th Karen Spärck Jones Lecture, an evening event, honouring women in computing research, that will follow the London Hopper at the BCS Headquarters. Professor Mataric' is also the Founding Director of the USC Robotics and Autonomous Systems Center, and a director of the USC Robotics Research Lab.

Both of these events are free. Please check http://academy.bcs.org/content/london-hopper-colloquium-2017 mid-March, 2017 for details on the programmes, venue and registration.

The London Hopper and Karen Spärck Jones Lecture take place at the BCS headquarters in Central London, with support from University College London, the BCS Academy and IBM.

Following requests, you can now make a slide for the Big TV on the lower first and the foyer back projector as a single image file. Details are here:

https://wiki.cs.manchester.ac.uk/index.php/BigScreen#Creating_.27Image_only.27_sides_in_Newsagent

Thanks to Chris.