Contact prediction using mutual information and neural nets

By George Shackelford, Kevin J. Karplus. 2007

129 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

Toward optimal fragment generations for ab initio protein structure assembly (2012, methodology): “39–41 For this purpose, we collect the residue contact predictions from the distance profiles, which have the peak corresponding to the distance bin 8 A˚, a distance cutoff most frequently used in the contact prediction assessments.”
Protein contact prediction by integrating joint evolutionary coupling analysis and supervised learning (2013, methodology): “Supervised machine learning methods (Cheng and Baldi, 2007; Shackelford and Karplus, 2007; Wang and Xu, 2013) make use of MI, sequence profile and other protein features, as opposed to EC analysis that makes use of only residue co-evolution.”
Deep Spatio-Temporal Architectures and Learning for Protein Structure Prediction (2012, methodology): “Rather, we focus on a minimal set of features commonly used in machine learning-based contact prediction [11, 2, 21, 7, 24, 5].”
Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks (2014, background): “Among protein structural features, contact maps have been proposed as an intermediate step in assembling the unknown protein 3D structure from its amino acid sequence [16-22].”
Deep architectures for protein contact map prediction (2012, methodology): “Machine learning approaches use methods such as neural networks (Fariselli et al., 2001; Punta and Rost, 2005; Shackelford and Karplus, 2007), recursive neural networks (Baldi and Pollastri, 2003; Vullo et al., 2006), support vector machines (Cheng and Baldi, 2007) and hidden Markov models…”
Machine Learning Methods for Protein Structure Prediction (2008, background): “neural networks [72], 2-D recursive neural networks [45], and”
Disentangling Direct from Indirect Co-Evolution of Residues in Protein Alignments (2010, methodology): “Not surprisingly, residues that are close in the primary sequence are much more likely to contact each other in the structure than distant pairs, see [20] and figure 11 below.”
SAM-T08, HMM-based protein structure prediction (2009, background): “We have two distinct ways of predicting what residues may be in contact: ab initio contact prediction using neural networks and information about correlated mutations in the MSAs ( 21 ), and distance constraints extracted from the best alignments, for use in constraining the tertiary structure predi”
Using inferred residue contacts to distinguish between correct and incorrect protein models (2008, background): “…for contact prediction (Cheng and Baldi, 2007; Fariselli et al., 2001; Hamilton et al., 2004; Pollastri and Baldi, 2002; Punta and Rost, 2005; Shackelford and Karplus, 2007; Vullo et al., 2006), and though meaningful comparisons are made difficult by varying definitions of the problem,…”
Assessing the accuracy of contact predictions in CASP13 (2019, background): “not address the problem of effectively separating the noise that is attributed to higher-order transitive correlations from indirectly interacting residues.(28-33) A significant advance took place when various approaches focused on addressing the transitivity problem in residue contact signals, such”
Improving protein structure prediction using multiple sequence-based contact predictions. (2011, methodology): “…and Alexov, 2006; Olmea and Valencia, 1997; Vicatos et al., 2005) or generated 2011 Elsevier Ltd All rights reserved 1189 by other machine learning methods such as neural networks (Shackelford and Karplus, 2007; Tegge et al., 2009) would probably further improve the performance of the method.”