AlphaFold2 examples from CASP 14: Difference between revisions

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 <scene name='87/875686/Af2_vs_7jx6_chain_a/1'>the model is close to the accuracy of an X-ray crystal structure</scene><ref name="imf" />. 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" />.) See Table I below for [https://en.wikipedia.org/wiki/Root-mean-square_deviation_of_atomic_positions RMSD] values. The only intra-chain '''salt bridge''' (4.0 Å cutoff) that occurred in all 4 chains of the two X-ray structures was Arg101:Asp113. It also occurred in the AlphaFold2 prediction (Arg86:Asp98).

In CASP 14, 70 research groups and 42 automated servers predicted structures for ORF8. The median GDT_TS score for all 112 predictions was 26. AlphaFold2 made the best prediction (GDT_TS 87). <scene name='87/875686/Second_best_orf8_imf/1'>The second best prediction was by the group of Xian Ming Pan</scene>, with GDT_TS 43 (see Table I above). The fold and topology were predicted correctly, but the '''details are far less accurate''' than those in AlphaFold2's prediction. The 2nd best prediction has '''no disulfide bonds'''. The '''salt bridge''' Arg86:Asp98 is correctly predicted, along with two incorrectly predicted salt bridges.

Among predictions by automated servers for all ~100 CASP 14 targets, the top ranking server was QUARK from the Yang Zhang group (Univ. Michigan). For ORF8, the Zhang-TBM server made the best server prediction with a '''GDT_TS of 27'''. (The prediction by QUARK was almost as good, GDT_TS 26.) The prediction has the '''two chain termini not parallel, and the amino terminus is not a beta strand''', differing in both respects from the X-ray model. Also, '''no disulfide bonds''' are predicted. The '''salt bridge''' Arg86:Asp98 is correctly predicted, along with two incorrectly predicted salt bridges. The structural alignment is very poor and is not shown.