AI and ML in Drug Discovery: Predicting Bioactive Molecules when there is N...
Event Information
Description
Description
This one-day meeting concerns the application of machine learning/artificial intelligence (ML/AI) approaches to the discovery of new drug leads. Specifically the meeting is about cases where the biological target is not clearly established - so-called phenotypic drug discovery.
The meeting centers on a real example - a competition run by Open Source Malaria (OSM), funded by a grant from the EPSRC/AI3SD+ Network. Data on active and inactive compounds in one OSM antimalarial series were published online, and anyone was able to submit a model able to predict the actives. The models were judged against a dataset that was kept private, and the winners were asked to use their models to predict novel molecules. These are currently being made in the lab and biologically evaluated, and the results will be reported at the meeting, providing a real-world test, and a complete case study, of the capabilities of ML/AI approaches to accelerate modern drug discovery.
We will hear from some of the eleven competition entrants about how their models were constructed, and will have other presentations on related developments. We hope during this meeting to establish which approaches worked well, which did not, and why. All those interested in the application of ML/AI methods to drug discovery are encouraged to attend.
The meeting is free, but there will be a cap on numbers, meaning first come first served, meaning registration is essential. Lunch will be provided as part of this event.
GitHub Repository: https://github.com/OpenSourceMalaria/Series4_PredictiveModel
Programme
The draft agenda for the day is as follows:
-
10:00 - 10:25: Introduction about Open Source Malaria and this competition - Mat Todd & Ed Tse
-
10:25 - 10:50: Talk from Competition Entrant - Davy Guan (USyd)
-
10:50 - 11:15: Talk from Competition Entrant - Benedict Irwin (Optibrium)
-
11:15 - 11:40: Talk from Competition Entrant - Willem Van Hoorn (Exscientia)
-
11:40 - 12:05: Talk from Competition Entrant - Giovanni Cincilla (Molomics)
-
12:05 - 12:30: Talk from Competition Entrant - Ho-Leung Ng (KSU)
-
12:30 - 13:30: Lunch
-
13:30 - 14:00: DeeplyTough: Learning to structurally compare protein binding sites - Joshua Myers (Benevolent AI)
-
14:00 - 14:30: The AssayNet Project: A Directed Graph of Bioassays - Professor John Overington (Medicines Discovery Catapult)
-
14:30 - 15:00: Explainable AI for the Medicinal Chemist - Al Dossetter (MedChemica)
-
15:00 - 15:30: Multitask bioactivity prediction by comparing chemical and cell morphology information - Maria-Anna Trapotsi (University of Cambridge)
-
15:30 - 16:00: Concluding remarks and Possible Next Steps
-
16:00: End, with discussions to continue in local public house.
Mailing List
To become part of the AI3SD Network+, join our mailing list by sending an email to: listserv@jiscmail.ac.uk
Subject: Subscribe
Message: SUBSCRIBE AI3SD Firstname Lastname
Or go to https://www.jiscmail.ac.uk/AI3SD
Network Social Media
Email - info@ai3sd.org
Twitter - @AISciNet
LinkedIn - https://www.linkedin.com/in/ai3sd
LinkedIn Interest Group - AI3 Science Network Interest Group
FAQS
1. Who should attend?
All academic and industrial research scientists with an interest in the application of AI/ML approaches to drug discovery.
2. What will I get out of it?
We will discuss a real case study in which new AI/ML methods have been applied to a currently-active drug discovery project, and where the predictions made have been synthesised in the laboratory and biologically evaluated.
3. What are the aims of the event?
The meeting is a post-mortem of a real research competition carried out as part of a public domain drug discovery project, but we will also discuss the potential of AI/ML methods more generally. It is hoped that new collaborations may emerge between meeting attendees.
