[Turing-Southampton] AI3SD Winter Seminar Series #2 - Robots, AI and NLP in Drug Discovery - 02122020

[Susan Davies]

***apologies if you receive this more than once***

Circulated on behalf of Samantha Kanza

Hi All,

We are delighted to announce the second event in our Winter Seminar Series:  Robots, AI and NLP in Drug Discovery on the 2nd December 2020 - 14:00-16:45

You can sign up for this event here: https://ai3sd-winter-series-021220.eventbrite.co.uk<https://ai3sd-winter-series-021220.eventbrite.co.uk/>

This event consists of three talks:

Natural Language Processing in AI-driven Drug Discovery: What it is, why it matters and how (not) to do it - Dr Sia Togia<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.linkedin.com%2Fin%2Ftheodosiatogia%2F&data=04%7C01%7C%7C394ec618c28547a68caf08d8908543e8%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637418249327288735%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=gyR5Kzbs5bMfnJE0iNtIsInGuq5PY4RBRTomT6qNeU4%3D&reserved=0> (Benevolent AI):
Natural Language Processing (NLP) has been used in drug discovery for decades. However, the emergence of AI-driven drug discovery coupled with recent advances in NLP have redefined the relationship between the two fields. This talk will focus on major classes of NLP techniques used in drug discovery as well as challenges arising when creating real-world biomedical NLP systems. The talk will cover topics such as dataset selection and construction, evaluation, models, methodology, research process and structure of NLP systems in AI-driven drug discovery.

New Trends in Drug Discovery - Robotics & AI - Dr Martin-Immanuel Bittner<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.linkedin.com%2Fin%2Fmartinimmanuelbittner&data=04%7C01%7C%7C394ec618c28547a68caf08d8908543e8%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637418249327298690%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=llHtkRc5UJcHfCgha1ywvivlg6wrO9LEHlC4JArI4gg%3D&reserved=0> (Arctoris)
The drug discovery ecosystem is undergoing transformational change. New technologies have an increasing impact on how drugs are being discovered and developed, including in particular Artificial Intelligence and robotics. A critical precondition for successful development of AI applications is having access to large amounts of structured, annotated, machine-learnable data. The talk will cover how recent advances in laboratory automation and robotics enable the generation of biomedical data at scale, providing the most critical input for AI systems. The talk will present real-world case studies, showing how leading AI drug discovery firms benefit from full automation of their discovery processes, delegating experiment execution to advanced robotics, and allowing for projects to move to the next stage faster and more efficiently.

An Open Competition of People and Machines to Develop Predictive Models for Antimalarial Drug Discovery - Professor Matthew Todd<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.ucl.ac.uk%2Fpharmacy%2Fpeople%2Fprofessor-matthew-todd&data=04%7C01%7C%7C394ec618c28547a68caf08d8908543e8%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637418249327298690%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=WLRyKrfk51C2l0sW45YH0crZ2LQggTVBqGDEVLhtBAQ%3D&reserved=0> (University College London)
One of the most promising series within the Open Source Malaria (OSM) consortium involves compounds that are active in the in vivo model of the disease. A molecular mechanism of action is strongly implicated, and is a mechanism shared with several leading antimalarials in the drug development pipeline, but no crystal structure has been obtained for the protein target. This OSM project is in the lead optimisation phase, with small changes being made to the structures synthesised. Yet even now many compounds designed by the human chemists are proving to be inactive, which can be wasteful of project resources. Over the last several years the consortium has run open competitions to see if the broader community can derive more predictive models for which molecules to synthesise. The most recent, funded by AI3SD, elicited high quality, open submissions from academia and several new companies specialising in artificial intelligence and machine learning. To close the loop, and examine the utility of these predictions, several of the novel structures proposed were synthesised and evaluated in a blood stage antimalarial assay. Were the machine-assisted predictions better than those derived from human intuition? An answer will be provided.

Further details of the rest of the seminar series can be found on our website: https://www.ai3sd.org/winter-seminar-series-2021<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.ai3sd.org%2Fwinter-seminar-series-2021&data=04%7C01%7C%7C394ec618c28547a68caf08d8908543e8%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637418249327308649%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=mNLOUlZF49D9rv99x41SMFLWagBIThvbtKPe2R%2BgFE8%3D&reserved=0>. We are still finalising the details of some of the seminars, and emails/eventbrites will be sent out as each seminar is finalised. If you are interested in getting involved with our seminar series then please get in touch with us on info at ai3sd.org<mailto:info at ai3sd.org>.

Best Wishes,

Dr Samantha Kanza
Research Fellow & Enterprise Fellow Network+ Coordinator of the AI3 Science Discovery Network+
Faculty of Engineering and Physical Sciences
University of Southampton

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.ecs.soton.ac.uk/pipermail/turing-southampton/attachments/20201124/54809230/attachment.html