- Why are vegetarians more likely to suffer from depression than meat eaters?
- Small wireless device implanted between skin and skull helps kill cancer cells
- Will the mRNA vaccine that can cure cancer come out near soon?
- Allogeneic T-cell therapy set for landmark first approval
- Boston University denies that the new COVID strain they made has 80% fatality rate
- A new generation of virus-free CAR-T cell therapy
Google establishes AI drug company Isomorphic Labs Headed by DeepMind CEO
- First human trial of HIV gene therapy: A one-time cure will be achieved if successful!
- New breakthrough in CAR-T cell therapy: Lupus erythematosus patients achieved treatment-free remission for up to 17 months
- How long can the patient live after heart stent surgery?
- First time: Systemic multi-organ recovery after death
- Where do the bacteria in the human gut come from?
Google establishes AI drug company Isomorphic Labs headed by DeepMind CEO
Recently, according to media reports such as THE VERGE, Google’s parent company Alphabet has established a new drug research and development company called Isomorphic Labs in the UK.
The company will use the research of Google’s artificial intelligence laboratory DeepMind to further explore the application of artificial intelligence (AI) in drug discovery. A spokesperson said that DeepMind CEO Demis Hassabis will also serve as CEO of Isomorphic Labs, but the two companies will remain independent and occasionally cooperate.
Isomorphic Labs: Building an artificial intelligence drug discovery model
Hassabis stated on his personal blog that Isomorphic Labs will try to build models that can predict how drugs interact with the body. It can use DeepMind’s work on protein structure to figure out how multiple proteins interact. The company may not develop its own drugs, but sell its models. A spokesperson said in a statement that it will focus on developing partnerships with pharmaceutical companies.
The work done at DeepMind and the work planned to be done at Isomorphic Labs can help new drugs find and solve some research bottlenecks, such as the problem of reasonable chemical level but not always effective when given to animals or humans, but it cannot quickly solve the numerous problems of drug development. challenge.
As Helen Walden, a professor of structural biology at the University of Glasgow, previously told The Verge, “the laborious and resource-intensive work of biochemical and biological evaluation of, for example, drug function” will continue.
Research progress of DeepMind under Google
There are several other companies dedicated to healthcare under Alphabet, including Verily, which develops software for the healthcare industry, and Calico, which is dedicated to aging and extending human life.
It is worth mentioning that DeepMind is also committed to healthcare. It used to have its own dedicated DeepMind health department.
However, after a controversial deal with the National Health Service of the United Kingdom, the department was merged into Google in 2018.
Since then, DeepMind has begun to conduct research in other fields of life sciences and has made breakthroughs in the field of protein folding.
In 2020, the company announced that it has developed a new generation of artificial intelligence system AlphaFold, which can accurately predict the structure of protein folding within a few days, solving a 50-year-old “major challenge”.
Specifically, AlphaFold2 accurately predicts the 3D structure of a protein based on the amino acid sequence in the International Protein Structure Prediction Competition (CASP).
Its accuracy is comparable to 3D structures resolved using experimental techniques such as cryo-electron microscopy (CryoEM), nuclear magnetic resonance, or X-ray crystallography.
Its processing speed is also faster. Depending on the size of the protein, it can generate an accurate protein structure within a few minutes to a few hours.
In July 2021, the DeepMind team under Google and the European Institute of Bioinformatics (EMBL-EBI) cooperated to release the AlphaFold Protein Structure Database predicted by the artificial intelligence system AlphaFold.
This database contains about 350,000 protein structures predicted by the AlphaFold artificial intelligence system, covering humans and 20 commonly used model organisms in biological research (E. coli, fruit flies, zebrafish, mice…). In terms of the human proteome, AI has made predictions about the structure of 98.5% of human proteins.
Previously, after decades of efforts by scientists, the analyzed protein structure only covered 17% of the amino acids in the human protein sequence.
Hassabis believes that artificial intelligence methods will be increasingly used not only to analyze data, but also to build powerful prediction and generative models of complex biological phenomena, helping scientists to take their work to a new level and greatly speed up drug discovery. process.
Just as mathematics proved to be the correct description language of physics, biology may be the perfect model for artificial intelligence applications.
(source:internet, reference only)