The benefits of Machine Learning are clear; accelerated product discovery and research targeting are rapidly transforming company workflows and increasing the speed of work. Many large biopharma’s have already leveraged ML to accelerate drug discovery processes and increase the accuracy of patient risk prevention. However, these processes are not just for biopharma companies: Machine Learning and Deep Learning can revolutionise product design by quickly uncovering potential new areas of research or finding more efficient solutions to quality and workflow challenges. With this industry first panel, join ML and AI leaders as they discuss their successful implementations, how they identify external partners, and outline how ML could revolutionise the workflows of your lab.

The discussion will consider:

•     taking the first steps in ML utilisation and establishing use cases appropriate for your specific needs

•     Establishing infrastructure and scaling ML from a part of a lab to an entire process

•     Identifying blind-spots, navigating ML governance and harmonising ML strategies with senior leadership

•     Discussing lessons learned, and looking to the future of automation

Artificial intelligence is going to remain a cornerstone of lab automation until labs are being operated with the lights off. However, for many, use cases and system wide adoption take time to build so the idea of an automated lab lies far in the future. This is a future that will only be reached if the foundations can be laid early. If the high volume of data labs collect can be standardized and annotated correctly. If reasonable explanations can be rolled out so that modular A.I adoption can spread across the industry. If methodology between experimental and computational teams can be standardised. Join this plenary to learn:

·       Sharing methods between different teams to allow for adoption of modular A.I. methods

·       Coordinating collaboration between experimental and computational teams that standardize workflows and unite teams implementing A.I.

·       Annotating and cleaning data so that future A.I. models can be easily scaled and tested

·       Spreading successful cases between research and lab teams to test upcoming models in differing environments