Nature: What's next for AlphaFold and the AI protein-folding revolution

Vectorspace AIVectorspace AI
$0.92159
‑8.52%
self.VectorspaceAI1m ago
"DeepMind software that can predict the 3D shape of proteins is already changing biology." "Even when the software gets it right, it cannot model how a protein would look when bound to a drug or other small molecule (ligand), which can substantially alter the structure. Such caveats make Roth wonder how useful AlphaFold will be for drug discovery." "AlphaFold deploys deep-learning neural networks: computational architectures inspired by the brain’s neural wiring to discern patterns in data. It has been trained on hundreds of thousands of experimentally determined protein structures and sequences in the PDB and other databases. Faced with a new sequence, it first looks for related sequences in databases, which can identify amino acids that have tended to evolve together, suggesting they’re close in 3D space. The structure of existing related proteins provides another way to estimate distances between amino-acid pairs in the new sequence. "AlphaFold iterates clues from these parallel tracks back and forth as it tries to model the 3D positions of amino acids, continually updating its estimate. Specialists say the software’s application of new ideas in machine learning research seems to be what makes AlphaFold so good — in particular, its use of an AI mechanism termed ‘attention’ to determine which amino-acid connections are most salient for its task at any moment." "Researchers at pharmaceutical companies and biotechnology firms are excited about AlphaFold’s potential to help with drug discovery, says Shoichet. “Critical optimism is how I’d describe it.” In November 2021, DeepMind launched its own spin-off, IsoMorphic Labs, which aims to apply AlphaFold and other AI tools to drug discovery." [https://www.nature.com/articles/d41586-022-00997-5](https://www.nature.com/articles/d41586-022-00997-5) AlphaFold2's breakthrough is based on advanced NLP/NLU language modeling as described in the paper titled, "Attention is all you need". Other famous current models that are emerging in NLP tasks consist of dozens of transformers or some of their variants, for example, GPT-2 or BERT. [https://fabianfuchsml.github.io/alphafold2/](https://fabianfuchsml.github.io/alphafold2/) Language models which result in feature vectors used to make predictions. The first language models widely used in industry included LBNL (Lawrence Berkeley National Lab) model [https://www.kaggle.com/genopharmix/discussion](https://www.kaggle.com/genopharmix/discussion) and after that, "word2vec" produced by Tomas Mikolov at Google in 2013, 5 years after LBNL [https://en.wikipedia.org/wiki/Word2vec](https://en.wikipedia.org/wiki/Word2vec).