...
| Avertissement |
|---|
As stated in the Colab notebook: "In comparison to AlphaFold v2.0, this Colab notebook uses no templates (homologous structures) and a selected portion of the BFD database. We have validated these changes on several thousand recent PDB structures. While accuracy will be near-identical to the full AlphaFold system on many targets, a small fraction have a large drop in accuracy due to the smaller MSA and lack of templates. For best reliability, we recommend instead using the full open source AlphaFold, or the AlphaFold Protein Structure Database." |
There is now a faster approach to multiple sequence alignment within AlphaFold developped by the group of Martin Steinegger (reference to the preprint paper). It has been implemented in a Google Colab notebook similarly to the above. The prediction should take about 10 minutes to run (vs. 60+ minutes with the DeepMind implementation above).
https://colab.research.google.com/github/sokrypton/ColabFold/blob/main/AlphaFold2.ipynb