AlphaFold2 examples from CASP 14: Difference between revisions
From Proteopedia
Jump to navigationJump to search
Eric Martz (talk | contribs) No edit summary |
Eric Martz (talk | contribs) No edit summary |
||
| Line 19: | Line 19: | ||
The quality of a prediction in CASP is judged, in large part, by the [[Theoretical_models#CASP_14_Global_Distance_Test_Results|Global Distance Test Total Score, GDT_TS]]. AlphaFold2's predicted structure<ref>Download AlphaFold2's predicted structure for ORF8 from [https://predictioncenter.org/casp14/MODELS_PDB/T1064-D1/T1064TS427_1-D1.pdb T1064TS427_1-D1.pdb].</ref> has a '''GDT_TS score of 87'''. (A score of 0 is meaningless, and a score of 100 means perfect agreement with an X-ray crystal structure.) 87 means the model is close to the accuracy of an X-ray crystal structure. The structure predicted by AlphaFold2 is almost as close to the X-ray crystallographic model [[7jx6]] as is the independently-determined X-ray structure [[7jtl]]. AlphaFold2 predicted the positions of 92 amino acids. (CASP 14 excluded residues 48-59, a 12-residue surface loop, from the target residues<ref name="casp14domains" />.) 83 amino acid alpha carbons in the prediction aligned with those in [[7jx6]] with an RMSD of 1.25 Å<ref name="imf" />. When sidechains are included, | The quality of a prediction in CASP is judged, in large part, by the [[Theoretical_models#CASP_14_Global_Distance_Test_Results|Global Distance Test Total Score, GDT_TS]]. AlphaFold2's predicted structure<ref>Download AlphaFold2's predicted structure for ORF8 from [https://predictioncenter.org/casp14/MODELS_PDB/T1064-D1/T1064TS427_1-D1.pdb T1064TS427_1-D1.pdb].</ref> has a '''GDT_TS score of 87'''. (A score of 0 is meaningless, and a score of 100 means perfect agreement with an X-ray crystal structure.) 87 means the model is close to the accuracy of an X-ray crystal structure. The structure predicted by AlphaFold2 is almost as close to the X-ray crystallographic model [[7jx6]] as is the independently-determined X-ray structure [[7jtl]]. AlphaFold2 predicted the positions of 92 amino acids. (CASP 14 excluded residues 48-59, a 12-residue surface loop, from the target residues<ref name="casp14domains" />.) 83 amino acid alpha carbons in the prediction aligned with those in [[7jx6]] with an RMSD of 1.25 Å<ref name="imf" />. When sidechains are included, | ||
{| class="wikitable" | {| style="text-align:center;" class="wikitable" | ||
|+ ORF8 Alignments With Chain A of [[7jx6]] | |+ ORF8 Alignments With Chain A of [[7jx6]] | ||
|- | |- | ||
! Model || Cα RMSD || Cα Aligned || RMSD Including Sidechains || Atoms Aligned | ! Model || Cα RMSD, Å || Cα Aligned || RMSD Including<br>Sidechains || Atoms Aligned | ||
|- | |||
| [[7jtl]]:A || 0.66 || 87/102 (85%) || 4.3 || 829/918 (90%) | |||
|} | |} | ||
Revision as of 20:25, 23 February 2021
This page is under construction. Eric Martz 01:03, 22 February 2021 (UTC)
Prediction of protein structures from amino acid sequences, homology modeling, has been extremely challenging. In 2020, breakthrough success was achieved by AlphaFold2[1], a project of DeepMind. For an overview of this breakthrough, verified by the bi-annual prediction competition empirical models, please see 7jtl. Below are illustrated some examples of predictions from that competition.
| |||||||||||
References
- ↑ Senior AW, Evans R, Jumper J, Kirkpatrick J, Sifre L, Green T, Qin C, Zidek A, Nelson AWR, Bridgland A, Penedones H, Petersen S, Simonyan K, Crossan S, Kohli P, Jones DT, Silver D, Kavukcuoglu K, Hassabis D. Improved protein structure prediction using potentials from deep learning. Nature. 2020 Jan;577(7792):706-710. doi: 10.1038/s41586-019-1923-7. Epub 2020 Jan, 15. PMID:31942072 doi:https://dx.doi.org/10.1038/s41586-019-1923-7
