ICIC 2017: The Next Era: Deep Learning for Biomedical Research
8 likes•2,759 views
The document discusses the impact of deep learning and artificial intelligence on biomedical research, particularly in the pharmaceutical industry, highlighting the growing costs of drug development and the potential for AI to drive breakthroughs. It outlines various AI methodologies, data repositories, and their applications in drug discovery and healthcare. The author emphasizes the urgency for the industry to adapt to these technological advancements as the landscape of medicine is poised for significant transformation.
ICIC 2017: The Next Era: Deep Learning for Biomedical Research
- 1. `The Next Era: Deep Learning for Biomedical Research Srinivasan Parthiban ICIC 2017, Heidelberg, Germany October 23-24, 2017
- 2. Mastering the Game of Go 2016 2017
- 3. Pharma Industry has a problem: Cost to develop a New Drug > $ 2.6 B and Growing
- 4. Big breakthroughs happen when what is suddenly possible meets what is desperately needed Thomas L. Friedman
- 5. The Beginning of the AI Revolution in Pharma Fierce Biopharma 2016 BBC, August 2017 Nature, July 2017 DDD 2017 August, 2017
- 6. AI Annual Global Financing History Healthcare emerges as hottest area of investment
- 8. The Deep Learning Recipe Algorithms ComputeBig Data
- 9. Neurons and the Brain neuron cell body synapse axon nucleus dendrites of next neuron axon tips neuron cell body nucleus synapse dendrites axon of previous neuron
- 10. Deep Learning Primitives Fully Connected Layer Convolutional Layer Recurrent Neural Network Layers Long Short Term Memory (LSTM) Cells
- 11. Dog
- 13. AI and Your Skin Source: Nature 542, 115–118 (02 February 2017)
- 16. Biopharmaceutical Research and Development Process
- 17. Biomedical Literature is filled with Billions of pages of useful information
- 19. Causes of Clinical Failure
- 20. Data Repositories Database Unique Compounds Experimental facts Main data types ChEMBL v.21 1,592,191 13,968,617 PubChem HTS assays and data mined from literature BindingDB 529,618 1,207,821 Experimental protein-small molecule interaction data PubChem >60M >157M Bioactivity data from HTS assays Reaxys >74M >500M Literature mined property, activity and reaction data SciFinder (CAS) >111M >80M Experimental properties 13C and 1H NMR spectra, reaction data GOSTAR >3M >24M Target-linked data from parents and articles AZ IBIS - >150M AZ in-house SAR data points OCHEM >600k >1.2M Mainly ADMET data collected from literature
- 21. +1 -2 -5 +1 +3 +5 Experiment with Different Moves Receive a Score for Each Move Interacting with the Environment Use Math to Represent the Goal of Walking Reinforcement Learning
- 22. The Dawn of a New Era for Data Driven Medicine? Multitask Learning
- 24. Neural Networks for Meaningful Leads Drug Database
- 25. One-Shot Learning You show Giraffe once to a 3 year old kid, you do not need to teach the kid again
- 26. Deep Learning in Drug Discovery
- 27. HIV Protease Inhibitors are Powerful anti-AIDS drugs Inhibitor Protease Quality Inhibitors for Quality Results
- 28. New Players are Entering the Healthcare Space
- 29. How to think about AI… Today 2040 2060 Artificial Narrow Intelligence Artificial General Intelligence Artificial Super Intelligence Less than human intelligence Equal to human intelligence Far Greater than human intelligence
- 30. [email protected] Thank You Chennai, Tamil Nadu, Indiawww.vingyani.com The World is Going to Change With or Without You… Get Ready!