From: Contact prediction in protein modeling: Scoring, folding and refinement of coarse-grained models
Contact predictors | Method | Input data | Accuracy [%] | Coverage [%] |
---|---|---|---|---|
Baker | Neural network | Contact predictions from 24 servers, predicted by JUFO secondary structure, amino acid properties, PSI-BLAST generated PSSM matrix, length of a protein sequence | 25.5 | 3.7 |
PROFcon | Feed-forward neural network with back-propagation | evolutionary profiles obtained using PSI-BLAST, predicted secondary structure and solvent accessibility, sequence conservation, biophysical features and "complexity" of residues | 24.2 | 3.6 |
Baldi-group-server | RNN – Recursive neural network | PSI-BLAST generated sequence profiles, correlated mutations, predicted secondary structure, solvent accessibility | 21.9 | 2.9 |
GPCPRED | Genetic programming with self-organizing maps | PSI-BLAST generated sequence profiles, sequence separation | 17.4 | 2.7 |
Karypis | Support Vector Machines | Sequence profiles, correlated mutations from multiple sequence alignment analysis, sequence conservation, sequence separation, predicted secondary structure | 11.0 | 1.5 |
KIAS | CMA analysis | Multiple sequence alignment, hydrophobic packing of residues (data obtained from sequence conservation and hydrophobicity) | 11.0 | 1.7 |
SAM-T04 | Neural network | Alignments, predicted secondary structure and propensities of residues in contact | 9.6 | 1.43 |
Hamilton-Huber-Torda | Feed-forward neural network | Mutational correlations from multiple sequence alignments, biophysical class of contacting pair of residues, predicted secondary structure, sequence separation, length of protein sequence | 9.1 | 1.3 |
CORNET | Neural network | PSI-BLAST generated sequence profiles, correlated mutations and sequence conservation, sequence separation | 2.5 | 0.34 |