Improving the prediction accuracy of residue solvent accessibility and real‐value backbone torsion angles of proteins by guided‐learning through a two‐layer neural network

By Eshel Faraggi, Bin Xue, Yaoqi Zhou. 2009

135 citations recorded by the source corpus.

Subfields: Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Protein Homology Detection Through Alignment of Markov Random Fields (2015, methodology): “Meanwhile, homology detection and fold recognition are two essential techniques used to detect if two proteins are homologous or share similar folds [5, 6].”
Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions (2017, methodology): “Output : Predicted propensities and binary scores for each residue in the input sequence from MFDp2 and MFDp; disorder content predicted with DisCon; evolutionary conservation, secondary structure predicted with PSIPRED [97], and solvent accessibility predicted with Real-SPINE3[98] for each residue ”
Improved de novo structure prediction in CASP11 by incorporating coevolution information into Rosetta (2016, methodology): “19 Previously described sequence profile, secondary structure (SS), and Ramachandran-based score terms were used for fragment selection, in addition to depth dependent structure profile,20 phi and psi torsion,21 and solvent accessibil-ity21 score terms.”
Computational identification of MoRFs in protein sequences (2015, methodology): “…Scoring Matrices (PSSM) generated with PSI_BLAST (Altschul et al., 1997), relative solvent accessibility estimated by the Real-SPINE3 predictor (Faraggi et al., 2009), flexibility (B-factor) predicted by PROFbval (Schlessinger et al., 2006), and the results of five different intrinsic disorder…”
AUC-Maximized Deep Convolutional Neural Fields for Protein Sequence Labeling (2016, methodology): “Instead, we compare our method with the following ab initio predictors: (i) for ACC prediction, we compare to SPINE-X [14] and ACCpro5-ab [34].”
Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto‐encoder deep neural network (2014, background): “Unlike secondary structures, these dihedral angles (φ and ψ) can be predicted as continuous variables and their predicted accuracy has been improved over the years [6-8] so that it is closer to dihedral angles estimated according to NMR chemical shifts [9].”
iFC2: an integrated web-server for improved prediction of protein structural class, fold type, and secondary structure content (2010, methodology): “The integrated servers include PredictProtein (Rost et al. 2004), which predicts two residue-level descriptors, secondary structure and solvent accessibility, Real-SPINE (Dor and Zhou 2007; Faraggi et al. 2009 ) that also predicts two residue-level descriptors, solvent accessibility and backbone an”
MoRFpred, a computational tool for sequence-based prediction and characterization of short disorder-to-order transitioning binding regions in proteins (2012, methodology): “Real-SPINE3 (Faraggi et al., 2009) and PROFbval (Schlessinger et al., 2006) are used to predict relative solvent accessibility and B-factors, respectively.”
Chemical shift-based methods in NMR structure determination (2018, unknown): “As expected, the accuracy of these chemical shiftbased methods is higher (>73% of the torsion angle predictions lie within 30° from corresponding angles in the reference structures) compared to approaches that exclusively use sequence information (>65% of the predictions lie within 36° from the refe”
A generic method for assignment of reliability scores applied to solvent accessibility predictions (2009, unknown): “The current best method available for real value surface exposure prediction is Real-SPINE [22, 23 ].”
RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning (2018, background): “Otherwise the effect of predicted dihedral angles as restraints for three dimensional structure prediction would be limited [34].”