Unicamp received this Monday morning (12) one of the most prominent researchers in creating a database of 3D protein structures through artificial intelligence algorithms, bioinformatician Dr. Sameer Velankar. He is currently director of the artificial intelligence database at European Bioinformatics Institute (EMBL-EBI), in Cambridge (UK). Velankar had a major influence on the development of the Protein Structure Database (Protein Data Base, EMBL-EBI PDB) and DeepMind's AlphaFold. This feat has generated an unprecedented number of reliable protein structure predictions, which are accessible to the scientific community at large.
Most proteins fold into 3D structures that determine their function and orchestrate the cell's biological processes. Knowing this structure helps to understand how they are shaped and how they interact with each other or with other molecules. By extension, we advance in understanding how life works at a biochemical level. This information is also valuable for accelerating the search for new medicines and treatments.
Currently, AlphaFold represents a major revolution in the area of structural biology. Over the last 50 years, 3D structures determined experimentally in the laboratory represent a set of approximately 100 proteins, a very small fraction of the size and diversity of the protein universe. Using AI, researchers had already built a database with around 1 million protein structures. Now, with the improvement of the program, this number has increased by 200 times, which covers almost all organisms on Earth whose genomes have already been sequenced.
The lecture "Enabling use of structural data: PDBe-Knowledge Base and its role in facilitating structural biology research” took place in the auditorium of the Unicamp Computing Institute.
The event was co-organized by Medicinal Chemistry Center (CQMED) of the Center for Molecular Biology and Genetic Engineering (CBMEG) and by Record.ai (Artificial Intelligence Lab), from the Computing Institute, both at Unicamp. The researcher's visit also has support from the Brazilian Association of Bioinformatics and Computational Biology (AB3C).
