Fig. 2: The folding process illustrated for CASP13 target T0986s2. | Nature

Fig. 2: The folding process illustrated for CASP13 target T0986s2.

From: Improved protein structure prediction using potentials from deep learning

Fig. 2

CASP target T0986s2, L = 155, PDB: 6N9V. a, Steps of structure prediction. b, The neural network predicts the entire L × L distogram based on MSA features, accumulating separate predictions for 64 × 64-residue regions. c, One iteration of gradient descent (1,200 steps) is shown, with the TM score and root mean square deviation (r.m.s.d.) plotted against step number with five snapshots of the structure. The secondary structure (from SST33) is also shown (helix in blue, strand in red) along with the native secondary structure (Nat.), the secondary structure prediction probabilities of the network and the uncertainty in torsion angle predictions (as κ−1 of the von Mises distributions fitted to the predictions for φ and ψ). While each step of gradient descent greedily lowers the potential, large global conformation changes are effected, resulting in a well-packed chain. d, The final first submission overlaid on the native structure (in grey). e, The average (across the test set, n = 377) TM score of the lowest-potential structure against the number of repeats of gradient descent per target (log scale).

Back to article page