News‎ > ‎

EventCoverageItems

12-13/09/2019 - AI3SD Machine Learning for Chemistry Training Workshop & Hackathon - Wide Lane Southampton

posted 19 Sep 2019, 02:32 by Samantha Kanza   [ updated 19 Sep 2019, 02:49 ]

On the 12th and 13th September 2019 AI3SD hosted a training workshop and hackathon, intended to help upskill scientists in Data Science, AI and Machine Learning techniques for Chemistry and provide some challenges to test out their new skills. 



Day 1 began with some informative presentations: 
The Challenges presented to the teams are detailed below. Full details of each challenge and the datasets provided can be found here
  • Solubility Challenge: This was a model building challenge to predict intrinsic aqueous solubilities using the available solubility datasets enhanced by other datasets
  • Data Mashup Challenge: A challenge to combine data from multiple different sources 
  • Chemical Safety Library Challenge: A challenge to work with the Pistoia Alliance's Chemical Safety Library Dataset and enhance it with other data sources. 
After this teams were formed and challenges were chosen! We had four teams, three of whom chose to do the solubility challenge and one who chose to do the data mashup challenge.

For the solubility challenge the different teams used a variety of methods to address this challenge. One team focused on using dimensionality reduction to select features that are good predictors of solubility. They used NCA to construct a pipeline and plan to evaluate a variety of methods from sklearn. The two others both used PCA, one initially using decision tree analysis, then variance analysis and PCA for feature extraction, followed by using AdaBoost Regression pipelined with anova analysis and PCA feature analysis; the other used scikit-learn and rdkit to work out fingerprints to do some initial machine learning, random forest and PCA. For the data mashup challenge the fourth team worked on a Jupyter notebook to pull spectra and physical data from a variety of different data sources to describe a list of common impurities (like solvents), with the look to facilitating a user importing their own dataset and viewing it alongside the provided spectra. 

Each of the teams were very energetic and enthusiastic and put together some very interesting work in a short space of time, and we were very impressed with all of their work. There had to be some winners however! And two teams did stand out for their innovative work, and the results were: 
  • 1st Place: Team Underachievers who undertook the data mashup challenge! 
  • 2nd Place: The Insolubles who undertook the solubility challenge! 






11/09/2019 - AI3SD Network+ Town Meeting & Funding Workshop - Wide Lane, Southampton

posted 11 Sep 2019, 04:44 by Samantha Kanza   [ updated 17 Sep 2019, 02:12 ]

On the 11th September 2019 AI3SD Hosted a Network+ Town Meeting and Funding Workshop at the University of Southampton Wide Lane Sports Ground in Eastleigh. This purpose of this meeting was to provide some useful talks around the different aspects of creating research projects including developing sustainable research software and impact and Intellectual Property in research projects, and also to give prospective applicants the opportunity to ask questions about our second funding call, and also to find other organisations to collaborate with. There was a presentation on tips for writing your funding application, and time set aside for specific networking to find collaborators. All questions and answers were written up and added to our Funding FAQ Page

18/07/2019 - AI3SD, Dial-a-Molecule, Directed Assembly & University of Leeds AI & ML in Chemical Discovery & Development

posted 11 Sep 2019, 04:38 by Samantha Kanza   [ updated 23 Sep 2019, 02:20 ]

On the 18th and 19th July 2019 AI3SD teamed up with the Dial-a-Molecule Network, Directed Assembly Network and the University of Leeds to run a meeting for AI/Machine Learning for Chemical Discovery & Development. 

This was a two day residential event aiming to bring together stakeholders with different backgrounds including academic/industry, researchers/data owners, and chemists/engineers/computer scientists, to discuss applications of AI and Machine Learning in Chemical Discovery and Development. Over the two days a series of structured discussion sessions were held to form a general consensus on some key objectives and milestones to deliver the promised impacts of these important tools within the remit of the three networks.  

These discussions have been captured in the Event Summary written by Dr Bao Nguyen which can be found here

Additionally, Professor Jonathan Goodman, who is a member of our advisory board also presented on AI3SD. His presentation can be found here

11/07/2019 - AI3SD Funds ECR to attend ISTCP: 10th Triennial Congress of the International Society for Theoretical Chemical Physics

posted 5 Sep 2019, 08:18 by Samantha Kanza   [ updated 18 Sep 2019, 03:48 ]

AI3SD offers funding for ECR members of AI3SD looking to attend conferences that are relevant to the Network+.

On the 11th July, Dr Grant Hill from the University of Sheffield attended the  ISTCP: 10th Triennial Congress of the International Society for Theoretical Chemical Physics. This was a seven day conference held in Norway with the aim of showcasing the achievement and advances of all areas of theoretical chemical physics. The conference had several areas that are of high interest to AI3SD including the sessions on Machine Learning and some of the talks in the Physical Organic Chemistry and Catalysis Sessions.

The full report written by Dr Grant Hill can be found here

03/07/2019 - AI3SD Presents at Dial-a-Molecule Annual Meeting

posted 5 Sep 2019, 03:50 by Samantha Kanza   [ updated 19 Sep 2019, 02:12 ]

In early July 2019 Dr Samantha Kanza attended the Dial-a-Molecule Annual Meeting to present about AI3SD. 

The Dial-a-Molecule EPSRC Grand Challenge Network was funded from 2010-2015 and was re-funded for it's third phase from October 2016 to March 2020. Dial-a-Molecule and AI3SD have worked closely together on a number of joint events and there are some overlaps in themes and areas of research interest. Given that Dial-a-Molecule will be finishing in 2020, in their annual meeting they invited several networks with related themes to present to the Dial-a-Molecule members about their own networks and where there were relevant themes and opportunities for Dial-a-Molecule members to get involved. 

Samantha presented on AI3SD, outlining where our main research themes overlap with Dial-a-Molecule, and noted where there are relevant events and funding opportunities for Dial-a-Molecule members to get involved with. The full presentation can be downloaded from here

The full event information for this meeting can be found here

10/06/2019 - AI3SD Attends CogX

posted 5 Sep 2019, 03:44 by Samantha Kanza

In mid June 2019, Dr Samantha Kanza and Dr Nicola Knight attended CogX: The Festival of AI and Emerging Technology in the scenic Coal Drops Yard near Kings Cross. This event had the real festival feel with outdoor stages and on the first day typical British weather that had us all hiding indoors where possible. Despite the rain however it was a great event. 

This festival boasted a packed expo with a range of cool new machine learning demonstrations and products, including the chance to drive in a Red Bull Formula One car, and enjoy Virtual Reality fun with IBM using an Oculus Rift.

There were also 10 different stages:
  • Impact Stage
  • Ethics Stage
  • Future of Work and Education Stage
  • Innovation, Investment and the Economy Stage
  • Cutting Edge Stage
  • Lab to Live Stage
  • Web 3.0 & Decentralised Future Stage
  • The Alan Turing Research Stage
  • Health Stage
  • Canal Stage
Overall it was a very interesting event with many thought provoking talks demonstrating current advances in Artificial Intelligence and Machine Learning technologies with a heavy focus on cryptocurrencies and block chain. 

The original event information can be found here

06/05/2019 - AI3SD Funds ECR to attend Machine Learning for Materials Science Workshop

posted 26 Jun 2019, 08:27 by Samantha Kanza   [ updated 23 Jul 2019, 02:26 ]

AI3SD offers funding for ECR members of AI3SD looking to attend conferences that are relevant to the Network+.

On the 6th May, Dr James Cumby from the University of Edinburgh attended the Machine Learning for Materials Science Workshop. This was a five day workshop focused on applying machine learning to materials discovery or understanding, which is highly pertinent to AI3SD as AI for Materials Discovery is one of our main themes. 

James's report can be found here.

01/05/2019 - AI3SD Semantics and Knowledge Learning for Chemical Design Workshop

posted 9 May 2019, 06:13 by Nicola Knight   [ updated 23 Jul 2019, 02:30 by Samantha Kanza ]

On the 1st of May AI3SD hosted a Semantics and Knowledge Learning for Chemical Design workshop at the Solent Conference Centre, Southampton. This full day workshop had five keynote talks from experts both from the computer science and chemistry areas of research. These talks covered a wide range of topics and provided lots of inspiration for the lively question sessions following the talks. Following the talks an open discussion was held talking about how semantics can help, what are the areas where there are currently difficulties and what could be done to improve these. 



Keynote speakers:
The formal report for this event written by Dr Samantha Kanza can be found here

The original event page can be found here

08/04/2019 - AI3SD Attends Paperless Lab Academy

posted 16 Apr 2019, 04:09 by Samantha Kanza   [ updated 16 Apr 2019, 04:09 ]

In early April 2019, Dr Samantha Kanza and Dr Nicola Knight attended the Paperless Lab Academy. This was a fascinating conference with a strong focus on Research Data Management and different strategies to not only go paperless in the lab, but also how best to organise one's data. There were a range of talks and workshops/demos including some on FAIR data and the use of semantic web technologies both in conjunction with AI and for interoperability purposes.

We are currently formalising the report for this event and it will be posted here shortly. 

More information on the event can be found here.

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

posted 22 Mar 2019, 09:28 by Samantha Kanza   [ updated 15 Jul 2019, 04:20 ]

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. 

The Keynote speakers were: 
The formal report for this event written by Dr Nicola Knight and Dr Colin Bird can be found here

The original event page can be found here

1-10 of 24