Prediction of contact maps with neural networks and correlated mutations.

By Piero Fariselli, O. Olmea, Alfonso Valencia, Rita Casadio. 2001

234 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 3D Structure Computed from Evolutionary Sequence Variation (2011, background): “This suggests that residue correlations could provide information about amino acid residues that are close in structure [4,5,6,7,8,9,10,11].”
Improved Contact Predictions Using the Recognition of Protein Like Contact Patterns (2014, methodology): “In addition to utilising correlated mutations, earlier contact prediction methods used various machine learning approaches to improve the predictions [21].”
EVA: evaluation of protein structure prediction servers (2003, background): “Superfamily http://supfam.mrc-lmb.cam.ac.uk/SUPERFAMILY/ J Gough (36) Inter-residue contacts CORNET http://prion.biocomp.unibo.it/cornet.html P Fariselli, O Olmea and A Valencia, R Casadio ( 10 ,37,38) PDGCON http://www.pdg.cnb.uam.es:8081/ F Pazos, O Olmea and A Valencia (13) CONcons/CONhydro http:”
Deep learning methods in protein structure prediction (2020, methodology): “Early methods often relied on simple linear combinations of features, though FFNN [111] and other Machine Learning algorithms such as Self-Organizing Maps [112] and SVM [113] quickly followed.”
Using inferred residue contacts to distinguish between correct and incorrect protein models (2008, background): “As such, when the full range of structural space cannot be adequately sampled, or when competing energy functions result in divergent predictions of 3D structure, additional information is necessary to aid in selecting the model closest to the native structure.”
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”
De Novo Structure Prediction of Globular Proteins Aided by Sequence Variation-Derived Contacts (2014, methodology): “Support Vector Machine and neural network based approaches) [10,11,12,13] to the ones based on.”
Predicting protein residue-residue contacts using deep networks and boosting (2012, methodology): “…based methods use various machine learning methods such as support vector machines (Cheng and Baldi, 2007; Wu and Zhang, 2008), neural networks (Fariselli, et al., 2001; Hamilton, et al., 2004; Pollastri and Baldi, 2002; Tegge, et al., 2009; Walsh, et al, 2009 Xue, et al., 2009), hidden Markov…”
3D Protein Structure Predicted from Sequence (2011, unknown): “This suggests that residue correlation can provide information about amino acid residues that are close in structure [4,5,6,7,8,9,10,11].”
Prediction of protein beta-residue contacts by Markov logic networks with grounding-specific weights (2009, background): “On the other hand, in the β-partners problem, as in several related applications of machine learning to prediction of protein structural properties, a non-linear combination of such features is paramount to obtain more accurate predictions (Cheng and Baldi, 2005; Fariselli et al., 2001).”