It is widely known that the traditional drug discovery and development process is extremely time-consuming, expensive and challenging; taking an average of 10 – 15 years to bring a new drug to market. This has caused researchers to turn to artificial intelligence as a means to accelerate and reduce the cost of drug discovery. However, despite the wealth of information available on the potential of AI for the pharmaceutical industry, there is a real lack of case studies presenting data on precisely how AI can help revolutionise drug discovery.
‘Emerging AI/ML Technologies for Drug Discovery’ is a free to attend, 3-part interactive webinar series where we will share case studies, from leading academics and pharma professionals, on exactly how AI can be applied to the different stages of the drug discovery pipeline.
From this series, you will hear detailed case studies on how AI can be applied for target identification, validation and prioritisation, the ways in which AI can be used to screen small molecule libraries to identify drug candidates, as well as applications of computational approaches for the design of new molecules and drug repurposing.
By signing up for the first webinar, you will receive access to the rest of the webinar series.
Wednesday 2nd June – 3pm BST / 4pm CEST / 10am EDT
Identifying novel, druggable targets for therapeutic intervention remains a priority for the pharma industry since this process, as well as, validating, and prioritising identified targets remains an important bottleneck in drug discovery.
In this webinar, we will discuss innovations in AI/ML for target discovery and what is being done to validate targets once identified. We will also cover the novel computational approaches that are aiding the selection and prioritisation of drug targets for future drug development.
- AI applied to MRI data reveals new drug targets for liver disease
- Paul Nioi, Senior Director, Research, Alnylam Pharmaceuticals
- Predicting Mechanisms of Action, Human Toxicity and Optimizing Indication using Biology-driven AI
- Olivier Elemento, Professor of Physiology and Biophysics, Weill Cornell Medicine
- Using machine learning to increase experimental success
- Victoria Hipolito, Scientific Liaison Manager, BenchSci
Wednesday 9th June – 3pm BST / 4pm CEST / 10am EDT
Data from libraries of small molecules is driving new compound selection. The sheer size of libraries used to screen for new drug candidates means it is extremely size and resource consuming for researchers to review the data themselves – this is where AI and machine learning can help. These technologies allow researchers to extract insights from huge datasets, which had previously been largely inaccessible.
This webinar will cover the use of different AI and machine learning tools used to predict the properties of potential compounds and identify lead compounds from extensive small molecule libraries.
- From Metrics to a Holistic Understanding of Models: Aligning Deep Learning with Virtual Ligand Screening
- Austin Clyde, Computational Scientist, Argonne National Laboratory
- Drug and Target Predictions via Omics Data Integration
- Avi Ma’ayan, Professor in the Department of Pharmacological Sciences and Director of the Mount Sinai Centre for Bioinformatics, Mount Sinai Icahn School of Medicine
Wednesday 16th June – 3pm BST / 4pm CEST / 10am EDT
Despite advances in technology, de novo drug design has been a costly and time-consuming process for decades. AI technologies have been developed, which can design new compounds that precisely fit the structural criteria required to bind specific targets. Drug repositioning and repurposing has also peaked in interest as an alternative tool to accelerate drug discovery, it can be used to quickly detect existing drugs that can be utilised to fight against emerging diseases such as COVID-19, as well as existing diseases.
In this webinar we will discuss the applications of different AI technologies and explore lessons learned in the use of AI for de novo drug design and drug repurposing. We will also discuss whether the best approach to revolutionise the drug discovery pipeline in the future lies within AI led de novo drug design or drug repurposing.
- Deep learning approaches for neoantigen prediction in cancer immunology
- Kai Liu, Prinicpal AI Scientist, Head of Medical Language Processing, Genentech
- Real-World-Data for drug design and drug development
- Elise Bordet, Real-world Data and Analytics, Sanofi
- The future of drug discovery – de novo drug design vs drug repurposing
- Shameer Khader, Senior Director (Advanced Analytics, Data Science, Bioinformatics), AstraZeneca