February 26-28, 2019
San Francisco

Day One
Tuesday 27th February, 2018

Day Two
Wednesday 28th February, 2018

08.00
Registration & Breakfast

08.50
Chair’s Opening Remarks

  • Enrico Ferrero Scientific Leader-Computational Biologist, GSK
  • Gerald A. Higgins Research Professor, Computational Medicine and Bioinformatics, University of Michigan Medical School

The Fundamentals of Setting Up a Successful AI & Machine Learning Approach in Drug Discovery

09.00
Case Study: Deploying an AI-driven Drug Discovery Platform

Synopsis

  • How AI is disrupting the current drug discovery status quo?
  • What are the policies & approaches necessary to deploy a successful AI based drug discovery pipeline?
  • Which actionable outcomes AI has already delivered in the drug discovery field?

09.30
Case Study: Big Pharma Perspective on the Use of AI & Machine Learning

Synopsis

  • Potential ways to use AI & machine learning in drug discovery/development
  • Considerations when thinking of using AI & machine learning
  • A perspective on “black box” AI

10.00
Discuss: Evolution of Machine Learning Approaches into Deep Learning Approaches for Drug Discovery: Unlocking the Potential While Avoiding the Hype

Synopsis

  • Is big data a big failure?
  • What lessons have been learned that are applicable to “AI”?
  • Is AI just a hype?

10.35
Case Study: Reinventing Drug Discovery with AI

  • Robin McEntire Emerging Technologies Solutions Specialist, Data2Discovery Inc

Synopsis

  • Traditional paradigms have mostly failed to bring successful new treatments out of clinical trials
  • Preclinical drug discovery is ripe for disruptive innovation
  • Data2Discovery demonstrates how AI, Machine Learning, Graph Analytic technologies, and linked data will break down historical silos and paradigms, providing promising new transformative opportunities for successful drug discovery

10.45
Speed Networking & Morning Refreshments

Matching AI & Machine Learning to Pharma Challenges

11.45
Case Study: Preparation of Chemical Data Sets for Machine Learning Analysis

  • Ben Allen Senior Computational Research Scientist, e-Therapeutics

Synopsis

  • How to turn chemicals into data?
  • How to deal with spare, noisy data?
  • How e-therapeutics uses this data?

12.15
Case Study: Improving Bio-therapeutic Development Through AI Technologies

Synopsis

  • Large scale, curated, data collection across therapeutic development pipeline to enable predictive modeling and automated decision making
  • Predicting molecular properties from sequence to allow exploration of design space in silico in search of optimal therapeutic molecules
  • Predictive models to incorporate both the complexity of biology and therapeutic development behavior

12.45
Case Study: Predicting Novel Drug Targets Using Machine Learning and the Open Targets Data

Synopsis

  • Challenges in target identification & validation due to poor association between drug targets & the disease
  • Use of semi-supervised classification approach to explore gene-disease associate data from the Open Targets platform
  • Application of neural network in predicting accurate genes or proteins as drug targets

13.15
Case Study: How Drugs or Patients Can Be Represented to Infer Therapeutic Insights

Synopsis

  • Deep learned representations of drug responses improve drug indication and target predictions
  • Representation learning of electronic medical records gives insights into drug discovery
  • Showcases of Standigm applicable artificial intelligence

13.30
Networking Lunch

Zooming the Spot Light on the Critical Issues: Voice, Exchange & Evaluate Ideas

14.30
Discuss: If the Strength of AI Is in Translation How to Make Smart/Strategic Decisions in Early Phases of Drug Discovery Based on the Lessons Learned from Failed Clinical Trials?

Synopsis

  • Most of the money is spent in clinical development but most of the decisions are made in drug discovery! How feasible this model is?
  • Short term versus long terms goals/milestones of AI-driven projects
  • Target Prioritization
  • Development of similarity based drug repurposing models

15.15
Discuss: The Big Pharma Perspective Around Data Partnership with Smaller Pharma Companies, Biotech Companies and Solution Providers

Synopsis

  • What is the best model of collaboration/partnership?
  • Are AI-driven biotech companies leading the way?
  • Are the solution providers trying to solve the right problem?

16.00
Afternoon Refreshments & Networking

Matching AI & Machine Learning to Pharma Challenges

16.30
Roundtable Discussions

Synopsis

Our breakout roundtables will allow you to have more intimate discussions with AI and pharma leaders around some of the hottest topics in the field. Discover multiple perspectives on these key issues, so that you can learn from your fellow experts in the audience. Drive your own learning, crowd-source ideas and get inspired. Immerse yourself in the following discussions:

  • How to industrialize AI & machine learning from theory into practice?

          Moderator: Mark Hallen: Research Assistant Professor- Toyota Technological Institute at Chicago

  • How to best change cultural influences to expedite the adoption & application of AI in pharma?

          Moderator: TBC

  • What are the bottlenecks to innovation: Discussing the regulatory acceptance for AI technology in pharma?

          Moderator: Michael Kremliovsky: Director- Medical Devices & eHealth- Bayer

17.00
Chair’s Closing Remarks & End of Day One