Cambridge Healthtech Institute’s Inaugural
Artificial Intelligence for Drug Discovery & Development
Applications From Drug Design to Clinical Trials
March 19, 2020
This focused one-day symposium on Artificial Intelligence for Drug Discovery & Development will bring together scientists, clinicians and executives from early discovery, DMPK/toxicology, clinical trial management and other parts of the drug pipeline
to talk about the increasing use of analytics including AI, machine learning (ML) and data mining. The symposium will introduce attendees to how AI is being applied in drug discovery and development and highlight the application of advanced concepts
with relevant case studies and research findings.
Final Agenda
Download Brochure
WEDNESDAY, MARCH 18
Recommended Short Course
4:40 pm Dinner Short Course Registration*
5:00 - 8:00 SC4: Gene Editing for Targeted Therapies
Instructors:
Clifford Steer, M.D., Professor of Medicine and, Genetics, Cell Biology, and Development, University of Minnesota Medical School
Branden Moriarity, PhD, Assistant Professor, Department of Pediatrics, University of Minnesota Medical School
Khalid Shah, MS, PhD, Director, Center for Stem Cell Therapies and Imaging, Harvard Medical School; Vice Chair of Research, Brigham and Women’s Hospital
Jonathan Gootenberg, PhD, McGovern Fellow, McGovern Institute for Brain Research, MIT
Omar Abudayyeh, PhD, McGovern Fellow, McGovern Institute for Brain Research, MIT
*Separate registration required.
THURSDAY, MARCH 19
7:30 am Registration and Morning Coffee
8:15 Welcome Remarks from Conference Director
Tanuja Koppal, PhD, Senior Conference Director, Cambridge Healthtech Institute
8:25 Chairperson’s Opening Remarks
Shruthi Bharadwaj, PhD, Senior Scientist, Novartis Oncology Precision Medicine
8:30 Bringing Precision Drugs to the Clinic Faster Using Artificial Intelligence and Data Science
Olivier Elemento, PhD, Director, The Caryl and Israel Englander Institute for Precision Medicine; Associate Director, Institute for Computational Biomedicine, Weill Cornell Medicine
We have developed novel genomic assays and analytical tools for precision medicine that are being used routinely for personalized medicine for a variety of Weill Cornell patients. We also have developed AI predictive models for improving how drugs
are developed, from prediction of mechanisms-of-action to prediction of drug safety, prediction of indication for drug repositioning and predicting effective drug combinations.
9:00 Explainable AI for Data-Driven Medicine: From Data to Models and Treatments
Igor Jurisica, PhD, DrSc, Senior Scientist, Krembil Research Institute; Professor, Medical Biophysics, University of Toronto
To fathom complex diseases, we need to systematically integrate diverse data and link them using relevant annotations and relationships. Graph theory, data mining, machine learning and visualization enables data-driven modeling and precision medicine.
Here, we highlight integrative computational biology and AI that help building explainable models, identifying prognostic and predictive signatures, re-positioning existing drugs for novel use, unraveling mechanism of action for therapeutics,
and prioritizing them based on predicted toxicity.
9:30 Leveraging Image-Derived Phenotypic Measurements for Drug-Target Interaction Predictions
Arvind Rao, PhD, Associate Professor, Department of Computational Medicine and Bioinformatics, University of Michigan
We propose a novel in silico drug discovery approach to identify kinase targets that impinge on nuclear receptor signaling with data generated using high-content analysis (HCA). Using imaging-derived descriptors,
we provide prediction results of drug-kinase-target interactions based on single-task learning, multi-task learning, and collaborative filtering methods. Our promising results suggest that imaging-based information can be used as an additional
source of information to existing virtual screening methods, thereby making the drug discovery process more time and cost efficient.
10:00 Networking Coffee Break
10:30 Key Elements of a Digital Strategy for Nucleic Acid-based Medicines
Peter Hagedorn, PhD, Senior Principal Scientist and Team Leader of Bioinformatics and RNA Biology, Roche Innovation Center Copenhagen
For drug discovery of small molecule compounds, examples leveraging AI methods have started to appear, although major breakthroughs have yet to be seen. For nucleic-acid based medicines that target RNA, an analysis of the opportunities and pitfalls
for using AI methods will be presented. For this modality, there is a high pace of technology innovations and new fundamental insights, and key elements of a general digital strategy that takes this into account will be discussed.
11:00 AI and ML Approaches for Clinical Trials
Shruthi Bharadwaj, PhD, Senior Scientist, Novartis Oncology Precision Medicine
With the increase in availability of clinical trial data, AI and machine learning approaches are becoming imperative in mining and finding clinically significant insights. In this talk, I will provide an overview of the various approaches currently
used to tackle the big-data problem in pharma.
11:30 Luncheon Presentation (Sponsorship Opportunity Available) or Enjoy Lunch on Your Own
1:20 PANEL DISCUSSION: How Is AI/ML Addressing Real-World Healthcare Problems?
Moderator: Michael Liebman, PhD, Managing Director, IPQ Analytics, LLC
Panelists:
Mary Jo Lamberti, PhD, Research Assistant Professor; Associate Director of Sponsored Research, Tufts Center for the Study of Drug Development
Debbie Lin, PhD, Executive Director, Venture Fund Digital Health, Boehringer-Ingelheim
The methodologies of AI (e.g., machine learning, deep learning) are increasingly focused on healthcare to provide analysis with the goal of identifying critical relationships that can enhance clinical decision-making (e.g., diagnosis and treatment)
and drug development. The availability of big data, however, may enable the application of these methods, but we must evaluate if the results actually address the clinical questions that exist in real-world medicine and in real-world patients.
2:20 Networking Refreshment Break
2:40 Chairperson’s Remarks
Barun Bhhatarai, PhD, Investigator, Novartis Institute for Biomedical Research
2:45 ML and AI on ADME/Tox-Accelerating Drug Discovery
Barun Bhhatarai, PhD, Investigator, Novartis Institute for Biomedical Research
This talk will focus on the application of ML and AI approaches to accelerate drug discovery in ADME/Tox with some case studies and the spirited path traditional pharma has to navigate aiming towards the end goal.
3:15 Low-N Protein Engineering with Data-Efficient Deep Learning
Surge Biswas, Graduate Student, Laboratory of Dr. George Church, Wyss Institute for Biologically Inspired Engineering
Engineering proteins with desired functions holds great promise for the design of biologics. In this talk, I’ll describe how machine learning can be used to accelerate protein design in extremely low data (“low-N”) settings.
These scenarios are typical in the later stage development of a biologic when assays are more reflective of real-world use and costs are high. Our findings have implications for improving late stage R&D and addressing the declining ROI
in drug development.
3:45 Reversing Unhealthy Cell Behavior Using a Cellular Time Machine
Milind Kamkolkar, Chief Data Officer, Cellarity
Cellarity is the only therapeutics company designing and developing medicines that targets cell behavior. This talk will focus on how the convergence of single cell data, sophisticated machine learning approaches targeting an emergent view of cells in their perturbational state, allowed for the creation of a new biological field, cell behavior. This new field of biology study is incredibly useful for creating medicines with more predictable clinical outcomes. The discussion will also cover what it took to re-architect R&D processes and to develop a true interdisciplinary team to uncover unappreciated biological phenomena in the context of drug design and development, and how with examples, using this approach, can reverse disease states to healthy ones.
4:15 Close of Symposium
Download Brochure