-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
- Cosmetic Ingredient
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
Today, Google’s DeepMind team and the European Institute of Bioinformatics (EMBL-EBI) have collaborated to release the AlphaFold Protein Structure Database predicted by the artificial intelligence system AlphaFold
.
This database will be freely available to scientific researchers around the world for open use
A week ago, the DeepMind team just published a paper in the journal Nature, and disclosed the source code of the optimized AlphaFold artificial intelligence system and described its design framework and training methods in detail
.
This system performed amazingly in the 2020 International Protein Structure Prediction Competition (CASP).
The protein 3D structure database released today 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.
In a paper published in Nature today, researchers pointed out that AlphaFold can make a reliable prediction of the structure position of 58% of the amino acids in the human proteome (confident prediction), and the structure prediction of 36% of the amino acids has reached a high level.
Confidence (very high confidence)
.
DeepMind and EMBL-EBI also stated that they will continue to add new protein 3D prediction structures to this database
.
By the end of this year, the database may contain 130 million protein structures
The structure predicted by AlphaFold still has many limitations
.
The researchers pointed out that many proteins function by binding to other proteins, nucleotides or ligands, and AlphaFold cannot yet predict the 3D structure of complex complexes
Even so, large-scale accurate structural predictions will provide scientists with an important tool
.
A review article published by EMBL-EBI pointed out that this database will have an "immediate" impact on molecular structural biology research, launching previously considered impossible or impractical research projects, and speeding up the establishment of models of complex protein complexes
Note: The original text has been deleted
Reference materials:
[1] Putting the power of AlphaFold into the world's hands.
[2] DeepMind and EMBL release the most complete database of predicted 3D structures of human proteins.
