In January 2019, Charles River Laboratories and Atomwise formed an alliance to provide integrated, AI-Driven drug discovery.
History and Approach
Atomwise’s technology was first developed by Dr. Wallach, a PhD student at the University of Toronto. The technology uses convolutional neural networks to predict the bioactivity of small molecules for drug discovery applications. It uses a statistical approach that extracts insights from experimental affinity measurements and protein structures to predict the binding of small molecules to proteins.
This tool allows chemists to pursue hit discovery, lead optimization and toxicity predictions. Atomwise analyzes billions of compounds to identify a small, specific subset for synthesis and testing.
AtomNet is Atomwise's deep convolutional network.
AtomNet represents a protein-ligand pair as a set of 3-dimensional volumetric pixels containing channels for carbon, oxygen, nitrogen, etc atom types. AtomNet applies local convolutional filters to structural target information to predict new active molecules for targets with no previously known modulators.
David E. Weekly
Atomwise- News and Publications
Documentaries, videos and podcasts
- Artificial intelligenceArtificial intelligence (AI) is intelligence exhibited by machines.
- CompanyA company, abbreviated 'co.', is a legal entity made up of an association of people, be they natural, legal, or a mixture of both, for carrying on a commercial or industrial enterprise.
- Cluster: Artificial intelligenceA cluster of topics related to artificial intelligence.
- Y CombinatorY Combinator (also known as YC) is a US based seed accelerator, which was started in March 2005.
- Convolutional neural networkA type of neural network which uses overlapping input neurons modeled on the behavior of human visual cortex. Convolutional neural networks are best known for their use in image analysis, specifically object recognition.