8:00 am Registration and Welcome Coffee
8:50 am Chair’s Opening Remarks
9:00 am Panel: The Good, the Bad and the Ugly
A Reflection of the Previous Year: Implementation and Utilization of Machine Learning in R&D Processes
9:30 am Panel: Big Data, Big Deal?
10:00 am Recent Innovation in Deep Learning for Drug Discovery and Development
10:30 am Speed Networking – Establish meaningful business connections at a rapid rate
11:00 am Morning Networking Break
11:30 am Speed Learning: Roundtable discussions like you’ve never seen them before
Synopsis
Uncover the story behind four technological advancements from target discovery to phase II clinical trials in one quick-fire session. Each table will be hosted by leading specialist who will share the secrets of their most high-impact strategy; you then get the opportunity to question the host before moving on to your next table.
12:00 pm Unconventional Machine Learning for the Biomedical Sciences
Synopsis
• We evaluated several unconventional machine learning (ML) strategies on actual human tumor data and showed for the first time the efficacy of multiple annealing-based ML algorithms for classification of high-dimensional, multi-omics human cancer data from the Cancer Genome Atlas.
• To assess algorithm performance, we compared these classifiers to a variety of standard ML methods and results indicate the feasibility of using annealing-based ML to provide comparable classification of human cancer types and associated molecular subtypes and superior performance with smaller training datasets.
• Our results provide compelling empirical evidence for the potential future application of unconventional computing architectures in the biomedical sciences.
12:30 pm Lunch Networking Break
Augmentation of Early Stage R&D for Increased Efficiency and Accuracy
1:30 pm Are we there yet? The Use of AI in Target and Drug Discovery
Synopsis
• Addressing the hype cycle, and current expectations related to deployment of AI/ ML in early drug discovery
• How knowledge-based classification of proteins, combined with exhaustive annotations of drug-target-disease associations can inform and contextualize the decision-making process with respect to target selection
• The importance of in-depth domain expertise with respect to the development, interpretation and deployment of AI/ML models (XGBoost, MetaPath and 17 different types of “big” data) in target discovery for Type 2 Diabetes, Alzheimer’s disease and Autophagy
2:00 pm Discovery Without Data: Novel Target Selection
Synopsis
• Deep learning in pharmacogenomics for novel drug discovery and patient stratification
• How to overcome the data gap and provide the ML programming with the knowledge necessary to make new discoveries
2:30 pm Themed Networking Afternoon Break
Synopsis
Finding the right solution for your specific challenge can be like finding a needle in a haystack – especially when there are a wealth of options available. AI-ML 2020 is the forum to facilitate these conversations and marry problems with solutions. Our themed networking meetings will allow industry and solution providers to find
matches made in heaven.
2:30 pm Poster Session
Synopsis
Join us in the exhibition hall for a browse of our poster submissions – ranging from early stage target discovery to clinical trial design. Don’t forget to grab a coffee and discuss with your colleagues!
3:30 pm Case Study: Cell Line Development and Bioreactor Prediction
Synopsis
• Establish which vectors impact anti-bodies and predict how they will affect the final product
• Generate the right biologics at an early stage to scale up to the right protein or antibody for specific patients
4:00 pm Strategies for Building AI-ready Data Sources and (semi)autonomous Reasoning Agents Operating on top of them
Synopsis
Here, we present a prototype Translator framework and architecture, which we have developed for integrating semantically, annotated Knowledge Sources (over 40) and for creating a data platform to support automated reasoning and serendipitous discovery of new ‘facts’ or interesting and testable hypotheses. We also discuss the strategies of how to integrate and provide high-value AI-ready data sources as well as how to develop (semi) autonomous reasoning agents that would advance reasoning through innovative uses of these knowledge sources.