 |
| Alphabet uses AI to discover drugs |
Alphabet, the parent company of Google, has announced the creation of a new company that uses artificial intelligence methods for drug discovery.
This new company is based on DeepMind, another Alphabet subsidiary that pioneered the use of artificial intelligence to predict the structure of proteins.
The new company, Isomorphic Laboratories, builds on this success to develop tools that can help identify new drugs.
Demis Hassabis, CEO of DeepMind, is also CEO of Isomorphic Laboratories. However, the two companies remain independent and sometimes cooperate.
Over the years, experts have suggested that artificial intelligence is a faster and cheaper way to find new drugs for various diseases.
AI can help analyze a database of potential molecules, for example to find suitable molecules for specific biological targets or to adapt proposed compounds.
Hundreds of millions of dollars have been invested in companies developing artificial intelligence tools over the past two years.
Similar labs are trying to develop models that can predict how drugs will interact with the body. He can take advantage of DeepMind's work on protein structure to understand how multiple proteins interact.
A company does not have to develop its own medicines. Instead, sell his models. A company spokesman said in a statement: It is focused on developing partnerships with pharmaceutical companies.
However, drug development and testing can be more challenging than finding protein structures. For example, although the structures of the two proteins are physically related, it is difficult to tell how closely related they are.
Based on DeepMind's work on protein folding
A drug filter that appears promising due to its chemical effect may not work when applied to animals or humans.
More than 90% of drugs enter clinical trials and fail. Most problems have nothing to do with errors at the molecular level.
Work at DeepMind and proposed work in the Isomorphic lab could help overcome some of the research problems. However, due to the many challenges faced by drug development, they are not resolved any time soon.