About this course
Disease modeling and target discovery are critical areas in biomedical research that involve using computational and experimental approaches to gain insights into the causes of diseases and identify potential targets for drug development. With the increasing prevalence of complex diseases such as cancer, Alzheimer's, and diabetes, there is a growing need for researchers and healthcare professionals with expertise in these areas.
The course content is composed of seven lectures covering key topics such as target selection criteria, the use of computational approaches, and emerging trends. A special emphasis is placed on case studies to illustrate the practical application of the concepts covered. In particular, course participants have the opportunity to freely explore a demo edition of PandaOmics, a popular commercial tool for target discovery and omics data analysis.
Upon completion of the program you will gain:
In-depth knowledge of the challenges and opportunities in drug target discovery, including the emerging role of AI, achievements, and failures of pharma companies in recent years and the most promising therapeutic areas
Practical skills in identifying and evaluating potential drug targets, including familiarity with several popular tools and resources
Knowledge of the latest trends and emerging topics in target discovery, such as the use of large language models and the evolution of the druggable genome concept.
Exposure to several case studies that illustrate the practical application of the concepts covered, and the ability to critically evaluate and compare different target discovery strategies.
Who is the course for?
The target audience for this course is individuals interested in drug discovery, biomedical research, and healthcare innovation such as researchers, scientists, and professionals in the pharmaceutical industry. The course is especially suitable for students pursuing a degree in molecular biology, chemistry, or related fields who want to understand the aspects of initial but key steps in drug development. They will see how fundamental science can be applied to the development of novel therapeutics. Specialists in data analysis, machine learning, and natural language processing may also be interested in this course, since these areas are actively used in drug development. The course will provide them with knowledge about problem setting and potential applications as well as give an intro to the underlying biology. Overall, our course can initiate or boost your career in big pharma or small biotech companies. Join us today and take the first step toward making a positive impact on human health!
Introduction to drug discovery and the role of target discovery in the process.
Factors to consider when selecting a target for drug development.
Overview of the current target discovery landscape and challenges facing the industry.
Computational approaches and AI in target discovery demonstrated via case studies.
The advantages and challenges of targeting multiple proteins simultaneously.
Current and emerging trends in target discovery.
About Insilico Medicine
This course is presented to you by Insilico Medicine, an artificial intelligence-driven pharma-technology company that focuses on accelerating drug discovery and development. Insilico Medicine develops the PHARMA.AI platform to discover novel targets, design novel molecules and maximize chances of successfully conducting clinical trials. Currently Insilico Medicine has 29 targets participating in 31 programs in a diversified pipeline covering fibrosis, oncology, COVID-19, aging and other indications.
PandaOmics is a SaaS software platform developed by Insilico Medicine that leverages the power of deep learning AI algorithms to discover therapeutic targets associated with a specific disease. The platform analyzes omics data and combines it with prior information from various sources such as publications, clinical trials, and grant applications. The algorithms used by PandaOmics consider multiple factors, including novelty, confidence, commercial tractability, druggability, safety, and other essential properties that influence the selection of therapeutic targets. PandaOmics has been instrumental in identifying new targets for various diseases, including cancer, Amyotrophic Lateral Sclerosis (ALS), COVID-19, and related variants. Its discovery of a novel target for idiopathic pulmonary fibrosis has led to the development of a lead drug candidate designed through Insilico Medicine's Chemistry42 platform, which has successfully completed Phase 1 clinical trials. This achievement marks the first AI-designed and AI-discovered drug to reach this milestone.
Course attendees are provided with free access to the demo version of PandaOmics. Do not miss your chance to try the best software for cutting-edge research in drug development!
Meet Your Instructors
- Ivan Ozerov, PhD, Senior Director, Target Discovery and Omics Research
- Mikhail Pyatnitskiy, PhD, Senior Software Analyst
- Alex Zhavoronkov, PhD, founder and CEO of Insilico Medicine
- Kyle Tretina, PhD, Alliance Manager, AI Platform
- Frank W. Pun, PhD, MBA, Head of Hong Kong Office, Application Science Lead
- Alexander Veviorskiy, Sr. Bioinformatician, Target Discovery
- Anna Gaponova, PhD, Research Biologist
- Shan Chen, PhD, Associate Director of Bioinformatics
- Anastasia Shneyderman, PhD, Data Curation Team Lead
- Vladimir Naumov, MD, Bioinformatics Team Lead
- Chun Wai Wong, Application Scientist
- Bonnie Hei Man Liu, PhD, Sr. Biologist
- Hoi Wing Leung, PhD, Sr. Biologist
- Xi Long, PhD, Sr. Bioinformatician, Application Scientist Manager
- Geoffrey Ho Duen Leung, Sr. Bioinformatician
- Nina Tikhonova, Research Biologist
- Viktoria Sarkisova, Research Biologist
Ruslan Gumerov, Bioinformatician
- Introductory Lecture by Alex Zhavoronkov, PhD, founder and CEO of Insilico Medicine (31:24)
- Drug Target Discovery - Definitions (8:15)
- Brief History of Drug Target Discovery (8:33)
- Target-centric Approach In Drug Discovery (8:55)
- Drug Development Funnel (6:01)
- Importance of the Target Selection: Phase 2 Failures (3:41)
- Proteins and Other Types of Biological Molecules as Targets (11:51)
- Who Discovers Targets in the Modern World (7:00)
- Complexity and Diversity of the Target Discovery Tasks (8:32)
- Major achievements and failures of the pharma companies in the last 20 years (6:35)
- Top pharma companies and their pipelines nowadays (6:00)
- The most crowded and abandoned therapeutic areas, Phase Transition Success and Likelihood of Approval (8:22)
- Innovation at big pharma vs small biotech (4:44)
- Successful repurposing within and across disease areas (4:52)
- Why Use AI for Target Selection? (7:09)
- Omics Data Types - Advantages and Downsides (7:30)
- Use of Biological Graphs (11:33)
- Text Data and Prior Knowledge (13:08)
- Examples of the Tools for Drug Target Discovery (11:53)
- Applications of Single Cell Data in Drug Discovery (9:55)
- Omics Data Analysis Put in the Context of Prior Knowledge (5:03)
- Challenges in Multi-Omics Computational Approaches to Target Selection (6:18)
- Validation of Computational Approaches to Target Selection (9:06)
- Previous Attempts and Growing Role of Computational Methods to Meet Target Selection Criteria (14:16)
- AI for Target Discovery (14:07)
- AI for Target Discovery: Case Studies (25:57)
- PandaOmics Target ID Page (3:52)
- Exercise: Novel Small Molecules Targets for Liver Cirrhosis
- Exercise: Novel Antibody Targets for Sarcoma
- Exercise: Common Targets for Familial and Sporadic Amyotrophic Lateral Sclerosis
- New Therapeutic Modalities (20:27)
- Evolution of the Druggable Genome Concept (10:49)
- Untargeted to Targeted - Re-Evaluation of the Mechanism of Action and Toxicity for Old Drugs (5:02)
- Indication Expansion and Prioritization (8:27)
- Target Discovery and Senolytics (7:38)
- Large Language Models in Drug Discovery (2:41)
Identification of Therapeutic Targets for Amyotrophic Lateral Sclerosis Using PandaOmics – An AI-Enabled Biological Target Discovery Platform
Frontiers in Aging Neuroscience, 2022
In silico Pathway Activation Network Decomposition Analysis (iPANDA) as a method for biomarker development
Nature Communications, 2016
Hallmarks of aging-based dual-purpose disease and age-associated targets predicted using PandaOmics AI-powered discovery engine
AlphaFold accelerates artificial intelligence powered drug discovery: efficient discovery of a novel CDK20 small molecule inhibitor
Chemical Science, 2023
High-confidence cancer patient stratification through multiomics investigation of DNA repair disorders
Cell Death & Disease, 2022