Conservation and prediction of solvent accessibility in protein families

By Burkhard Rost, Christopher Sander. 1994

How researchers see this paper

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

Citations in the corpus

Modeling aspects of the language of life through transfer-learning protein sequences (2019, methodology): “The idea was applied to other tasks, including the prediction of transmembrane regions [11 – 13], solvent accessibility [14], residue flexibility (B-values) [15, 16], inter-residue contacts [17] and protein disorder [15, 18 – 20].”
Better prediction of functional effects for sequence variants (2015, neutral): “We compiled the original SNAP features: biophysical amino acid properties, explicit sequence, PSIC profiles [37], secondary structure and solvent accessibility [38-40], residue flexibility [41], and SWISS-PROT annotations.”
Improved Disorder Prediction by Combination of Orthogonal Approaches (2009, methodology): “PROFacc [72] is a method that predicts residue solvent accessibility.”
A Unified Multitask Architecture for Predicting Local Protein Properties (2012, unknown): “15 [34].”
MDockPP: A hierarchical approach for protein-protein docking and its application to CAPRI rounds 15–19 (2010, methodology): “Biological information about the binding site is valuable for improving the selection of correct modes (Targets 32, 33, 34, 37, 40, and 41), despite that some experimental information may be misleading (Targets 38 and 39).”
Protein flexibility and rigidity predicted from sequence (2005, background): “Local information: for a window of w sequence-consecutive residues, we used the evolutionary proﬁle (below) for each residue ( w + 9, i.e., 9 , 21 input units), the 3-state secondary structure predicted by PROFsec 55,60,61 ( w + 5, i.e., 5 , 3 units), and the 2-state solvent accessibility predicted ”
Evaluation of structural and evolutionary contributions to deleterious mutation prediction. (2002, methodology): “The Cb density feature is a count of the number of Cb atoms within 10 Å of the Cb of the mutated residue and the relative solvent-accessibility is the solvent-accessible surface area of the native residue at the mutation site as calculated by DSSP12 and normalized by the maximum value for each resi”
Prediction of protein B‐factor profiles (2005, unknown): “25,44,45”
Maximum Allowed Solvent Accessibilites of Residues in Proteins (2012, methodology): “[14] used the Rose scale, which differs quite substantially from the scale we propose here.”
Accurate prediction of solvent accessibility using neural networks–based regression (2004, methodology): “the PHDacc method achieved a cross-validated accuracy of about 75% for the two-state problem with 25% threshold.(9) The Jnet prediction method is based on feed-forward NN and combines into a consensus prediction classifier trained with Psi-BLAST PSSM and HMMER profile Hidden Markov Model (HMM) repre”
SNAP: predict effect of non-synonymous polymorphisms on function (2007, methodology): “The final SNAP network architecture included the following input features: explicit PSI-BLAST frequency profile, relative solvent accessibility predictions (PROFacc), secondary structure predictions (PROFsec), sequence-only predictions of 1D structure (PROFsec/ PROFacc), Pfam information, PSIC score”
A critical view on conservative mutations. (2001, background): “These differences in the solvent accessibility profile have found wide applications in various structure prediction methods (Holbrook et al., 1990; Rost and Sander, 1994; Thompson and Goldstein, 1996).”
Combining prediction of secondary structure and solvent accessibility in proteins (2005, methodology): “15,18 Of course, in real applications, the actual solvent accessibility is not known, and its predicted value has to be used instead.”