Our Speakers

 

Hear from experts how the PercayAI suite is revolutionizing their omics and knowledge exploration workflows.

​

CompBio: An Augmented Intelligence System for Comprehensive Interpretation of Biological Data

​

Wednesday, Oct. 7

9:20 A.M. EST
Rich Head, MS; Associate Research Professor of Genetics and the Director of the Genome Technology Access Center, Washington University in St. Louis

​

Utilizing a revolutionary combination of contextual language processing and memory generation with components of artificial intelligence, the platform enables rapid human interpretation and hypothesis generation (Augmented Intelligence). Direct assessment of disease processes, target identification, drug mechanism of action, and the identification of translational mechanisms between animal models and human disease can occur in hours or days, instead of the weeks to months traditionally required to reach this depth of understanding.

​

 

Why Current Approaches Using AI in Drug Discovery Fail: How Can We Overcome?

​

Wednesday, Oct. 7
11:55 A.M. EST
Roundtable moderated by Joe Donahue, Managing Director, Life Sciences, Accenture

​

Participants include: 

Andreas Matern, Head of Digital Translational Medicine, Sanofi

John Quackenbush, Professor of Computational Biology and Bioinformatics; Chair, Department of Biostatistics; Harvard T.H. Chan School of Public Health

Seungtaek Lee, VP of Strategic Partnerships and AI RWE Head of CoE at ConcertAI

Preston Keller, PhD, MBA, President & CCO, PercayAI

Philip R.O. Payne, PhD, FACMI, FAMIA; Director, Institute for Informatics (I2) at Washington University School of Medicine in St. Louis

​

​

Accelerating Drug Discovery: In Silico Hypothesis Generation

​

Thursday, Oct. 8
10:40 A.M. EST
Philip R.O. Payne, PhD, FACMI, FAMIA; Director, Institute for Informatics (I2) at Washington University School of Medicine in St. Louis, Associate Dean for Health information and Data Science, Janet and Bernard Becker Professor and Chief Data Scientist

​

The contemporary drug discovery pipeline is challenged by a number of factors, including ongoing growth in terms of the cost of developing new molecules, increasing regulatory complexity, and barriers to participant recruitment and retention when conducting clinical trials.  All of these issues are further amplified by the demand for targeted and individualized therapeutics.  Such precision medicine paradigms are predicated on the availability of appropriate treatments, and further, the evidence-base needed to align those treatments with unique patient phenotypes.  As an alternative to traditional drug discovery approaches, in silico hypothesis generation has the potential to accelerate the timely, cost-efficient identification of new uses for existing therapies, in the form of either single or combination regimens.  In this presentation, we will explore the current-state-of-the-art in terms of mining extant data and knowledge resources, using artificial intelligence methods, in order to generate and validate hypotheses concerning such drug repositioning candidates.  Using examples from diverse application domains such as cancer, neurodegeneration, and infectious diseases, we will illustrate the potential benefits and pitfalls of such an accelerated drug discovery workflow.