News‎ > ‎


19/03/2019 - AI3SD AI for Materials Discovery Workshop

posted by Samantha Kanza   [ updated ]

On the 19th March AI3SD hosted an AI for Materials Discovery Workshop at the University of Southampton. This was a very well attended workshop, with over 60 participants attending across the University of Southampton and representatives from many other Universities and Research Institutes, with some industry attendees also. This workshop ran across an afternoon and was made up of five keynote talks which generated a lot of questions and discussions! This was a great workshop for AI3SD as it brought in many new members and raised awareness of the Network+ across different research groups. 

13/03/2019 - AI3SD Attends Pistoia Annual Conference & SES Data Cafe

posted by Samantha Kanza   [ updated ]

On the 13th March Dr Samantha Kanza and Dr Nicola Knight divided and conquered to attend both the Pistoia Alliance Annual Conference (specifically their Lab of the Future session) and the SES Data Cafe which ran simultaneously to each other in different parts of London.

Nicola attended the Lab of the Future session to see how Pistoia is progressing in this area, as AI3SD is looking to run an Intelligent Lab Workshop in 2020, and Nicola, Samantha and Jeremy are all involved with a research project called Talk2Lab and have worked with Pistoia before (indeed Nicola and Samantha came 2nd in their Hack the Lab Hackathon last year) in these research areas, which led to an article in Scientific Computing World. More information about Pistoia's conference can be found here

Samantha meanwhile attended the SES Data Cafe to discuss Research Data Management. SES (the Science and Engineering South Consortium) brings together a number of Universities (Oxford, Cambridge, Southampton, Kings College London, Queen Mary University of London, UCL and Imperial College London). Samantha and Jeremy have extensively researched this area, and AI3SD is very interested in the management and preservation of scientific research and data. Quality and availability of data is an issue that arises at every single one of our workshops, and it is clear that until these issues are resolved, high barriers to utilising this data for AI/ML will remain. 

12/03/2019 - AI3SD Attends Pistoia Alliance Centre of Excellence for AI/ML in Life Sciences Workshop

posted by Samantha Kanza   [ updated ]

On the 12th March Dr Samantha Kanza attended the Pistoia Alliance Workshop on AI/ML in Life Sciences. This was a very interesting workshop comprising a combination of focused talks on applications of AI/ML to the life sciences in both academia and industry, and expert panel discussions; coupled with some detailed information about the virtual hackathon Pistoia ran over the last few months. This was a great place for us to promote AI3SD and gain some new contacts, and AI3SD will be hosting a joint hackathon with Pistoia later in the year. 

More information on this event can be found here

06/03/2019 - AI3SD & MDC AI in Drug Discovery & Drug Safety Workshop

posted 22 Mar 2019, 05:36 by Samantha Kanza   [ updated 22 Mar 2019, 05:38 ]

On the 6th March AI3SD teamed up with the Medicines Discovery catapult to run a workshop at Alderley Park Conference Centre on AI in Drug Discovery & Drug Safety. This was a very well received event, there was a strong industry presence among the attendees and several representatives from different Universities. There were four keynote talks and working group discussions on topics that were elicited from initial open discussions after the presentations.

The Keynote speakers were:
The key themes identified for working group topics were:
  • Skills and training 
  • Data Quality / Access / Collation / Reproducibility
  • Data Sharing / Interdisciplinary data - data interoperability 
  • Optimisation of Drug Discovery Process
  • Explainable AI / Models
  • Data Decisions & ML Trustworthiness 
We are currently formalising the report for this event and it will be posted here shortly. 

The original event page can be found here

06/02/2019 - AI3SD Molecules, Graphs & AI Workshop

posted 21 Mar 2019, 11:49 by Samantha Kanza   [ updated ]

On the 6th February AI3SD hosted a Molecules, Graphs & AI Workshop at the picturesque Ageas Bowl in Botley. This was a lively workshop with three keynote talks and working group discussions on topics that were elicited from initial open discussions after the presentations.

The Keynote speakers were: 
We are currently formalising the report for this event and it will be posted here shortly. 

The original event page can be found here

30/01/2019 - AI3SD Attends Recoding Black Mirror Workshop @ CPCD Conference

posted 21 Mar 2019, 10:09 by Samantha Kanza   [ updated ]

In late January 2019, your Network Co-ordinator Dr Samantha Kanza attended the Recoding Black Mirror Workshop, which was part of the CPCD Conference 2019. 

This was a one day workshop that focused on the ethical and societal challenges of digital technologies, with a look to considering technological approaches to preventing us ending up in a dystopian future (much like the ones depicted in Black Mirror!). This was a fascinating workshop that focused on the socio-technical issues of AI. This was a great place to promote AI3SD as we are very interested in the ethical and societal issues of AI for Scientific Discovery, and we made some useful contacts here. 

More information on this event can be found here.

We are in the process of finalising our report for this event which will be posted here shortly. 

24/01/2019 - AI3SD Gives Tech Talk at Syngenta

posted 21 Mar 2019, 09:55 by Samantha Kanza   [ updated ]

Professor Jeremy Frey, Dr Samantha Kanza and Dr Nicola Knight gave a Tech Talk at Syngenta about their work on the Talk2Lab project. This project is focused on bringing the laboratory into the 21st Century, through the use of Internet of Things devices such as sensors, Raspberry PI's and the Amazon Alexa. 

22/01/2019 - AI3SD Network+ Town Meeting

posted 21 Mar 2019, 09:36 by Samantha Kanza   [ updated 21 Mar 2019, 09:37 ]

On the 22nd January 2019 AI3SD Hosted a Network+ Town Meeting at the SCI in London. This purpose of this meeting was to give prospective applicants the opportunity to ask questions about our first funding call, and also to find other organisations to collaborate with. There was time set aside for specific networking to find collaborators, and upon request from our attendees we created a Collaborators Page on this website for members who are actively seeking collaborators in research areas linked to AI3SD (both for this funding call and in general). All questions and answers were written up and added to our funding call page as an FAQ. 

12/12/2018 - Faraday Division Chemistry Software Tools Meeting

posted 5 Mar 2019, 08:25 by Samantha Kanza   [ updated 5 Mar 2019, 08:26 ]

The Frey Group at University of Southampton (including Jeremy and Samantha) helped out at this event. It was designed to help physical chemists find the best software tools for their research, and Jeremy and Samantha presented talks on Responsible, Reproducible Research & FAIR Data, and Collaborative Paper Writing: Google Docs, Word and Office 365, TeX and Overleaf. There were also other talks on using GitHub, using Electronic Lab Notebooks, how to give presentations, and about joining the Royal Society of Chemistry. This was a very informative events, and a great opportunity for us to connect with researchers in this field and promote the Network+ to them as a place for them to make new contacts and see what relevant events and funding calls we had in place that were applicable to their research.

More information on this event can be found here

05/12/2018 - AI3SD Launch

posted 5 Mar 2019, 08:20 by Samantha Kanza   [ updated 5 Mar 2019, 08:25 ]

On the 5th December 2018 we launched AI3SD officially! Here is a blog post written by Michelle Pauli about the event. You can find full coverage of all the presentations in the main report which can be found here.

Will AI save the NHS?
Michelle Pauli

The pace of progress in AI has been picking up dramatically. The recent launch meeting of the EPSRC-funded AI3SD Network+ brought together experts in the field to explore new developments in machine learning and drug discovery and set the scene for the next three years of innovation and collaboration.

Will artificial intelligence (AI) be the saviour of the NHS? It might sound far-fetched but it was one of the most compelling assertions offered at the launch meeting of AI3SD Network+ (Artificial Intelligence and Augmented Intelligence for Automated Investigations for Scientific Discovery) in London earlier this month.

The claim was made by Professor Jackie Hunter, director of BenevolentAI, who kicked off the meeting by highlighting the sheer unsustainable inefficiency of the drug discovery industry. With only 6% of molecules currently reaching market, what other sector would tolerate a failure rate of 94%? It takes 12-15 years to get a drug to market and most people in the industry never work on something that makes it through to clinical trials, let alone patients. She outlined how AI will reduce costs and improve success rates, describing the “tsunami of evidence” of the last few years, and the inability to harness such data at scale until AI is applied to that space. Using machine learning will reduce timelines in all phases of drug discovery: hypothesis generation, drug target validation, lead discovery and lead optimisation. In drug development it will have equally powerful effects, from rapid interrogation of study data, identification of novel biomarkers and enhanced mining of clinical data for patterns of response to better real-world outcomes monitoring. AI is, she says, “already transforming R+D and the pace will only accelerate. It will require cultural change, different ways of working, different ways of funding and new business models.”

Professor Hunter was talking to more than 100 delegates from a wide mix of universities, commercial companies, government agencies and research organisations.  They had come to hear a range of perspectives on the topic of AI and chemical synthesis, and to participate in an exciting new ESPRC-funded network which will demonstrate how cutting-edge artificial and augmented intelligence technologies can be used to push the boundaries of scientific discovery.

The launch took place in the month when DeepMind announced that its latest AI program, AlphaFold, had taken a significant first step in solving the ‘protein folding’ problem, coming top of a competition to predict the 3D shapes of proteins. Professor Adam Prugel-Bennett touched on these developments in his fascinating overview of machine learning, particularly the progress DeepMind’s programs AlphaGo and AlphaGo Zero have made in the Chinese board game Go in the last three years and how it exemplifies the field’s sudden, recent change in pace. The ImageNet large scale visual recognition challenge also gives a clear indication of progress with image classification: in the competition’s first year in 2010 every team got at least 25% wrong; by 2017, 29 out of 38 teams got less than 5% wrong – a “super human performance”.

Professor Prugel-Bennett was keen to explode the myth that AI is some kind of machine that does impeccable logic. He emphasised instead that it is “just reducing errors”, recognising pattern sets very well and using those to make judgement, reducing errors on some sets. There are certain areas where making fewer errors is clearly of benefit, such as fraud and spam detection, self-driving cars and, of course, medical diagnosis. However, the training data needs to be there.

Early work in deep learning used supervised learning where there were labels for the data. In the last three years the excitement has been around unsupervised learning, working with the data alone and learning patterns in data. One of the techniques for doing this is Generative Adversarial Networks (GANs), the other is Variational Auto-Encoders (VAEs). With object recognition now mainstream, the machine learning community is looking at more demanding tasks, including visual question answering, which involves understanding both natural language and images.

The question of strategies for collating the colossal amounts of data needed for AI was picked up by Professor John Overington, from the Medicines Discovery Catapult (MDC), a national facility connecting the UK community to accelerate innovative drug discovery. He used his experience with ChEMBL, the world’s largest public primary database of medical chemistry data, to delve into the challenges and opportunities of using free, large-scale datasets for AI training and application data, touching on the ‘reproducibility reproducibility problem’ along the way.

He was frank about the level of errors in the public datasets he has been involved with – ChEMBL (2.3m compounds, an open-data API is available), SureChEMBL (the public chemical patent resource with 18m structures generated via name-recognition, and available as a client feed) and Unichem (a single chemical integration source). For instance, errors run to 5% of structures; 2-3% of targets; 1% of activity values. There is also variability in the data (the underlying ‘reproducibility problem’) – about the same 10-fold difference for different orthologues as for different labs, a five to 10-fold variance in cell line data, and about 1-2% of compounds from suppliers may not be correct. However, he was clear that, nine years ago when ChEMBL was set up, it was a good design decision to focus on collecting all the data in case it would have a use in the future and could be cleaned up accordingly.

In describing Crispy, a live knowledge graph of UK drug discovery assets and capability, Professor Overington emphasised the need for collaborative and competitive intelligence, the current difficulty of discovering the best collaborators and the need to join up people with assets and skills to work together. This renewed imperative for collaboration for successful AI discoveries is also an area Professor Hunter touched on in her presentation, highlighting the way that AI is changing ways of working, creating more integrated environments and cross-functional teams.

Creating an environment for collaboration and bringing people – from both diverse organisations and disciplines – together is one of the key aims of the Network, with funding calls focusing on interdisciplinary applications between AI and chemistry. This launch meeting is just the beginning, urged the network’s principal investigator Professor Jeremy Frey and coordinator Dr Samantha Kanza. The first funding call will be early next year and future events, which will all be listed on the website include conferences, workshops and hackathons.  

To join the mailing list send an email to with the following details: 

The AI3SD Network+ has been funded by the Engineering and Physical Sciences Research Council (EPSRC) under grant number EP/s000356/1

Presenting at the launch event were:

1-10 of 15