Assessment of domain boundary predictions and the prediction of intramolecular contacts in CASP8

By Iakes Ezkurdia, O. Graña, J. Izarzugaza, Michael L. Tress. 2009

76 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): “46,48 In the table, distance profile-based method outperforms the machine-learning-based methods for short and medium-range contacts and has a similar performance for the long-range contact prediction.”
Protein structure prediction from sequence variation (2012, neutral): “…contacts using three-dimensional information with machine-learning techniques, such as support vector machines, random forests and neural networks, but contact prediction accuracy remained “still quite low” 10 with substantial improvements to models achieved only for some small proteins 11,12 .”
Improved Contact Predictions Using the Recognition of Protein Like Contact Patterns (2014, background): “Structure Prediction), that is Cb-Cb, Ca for Glycine, distance between the amino-acids #8Å [42].”
Evaluation of residue-residue contact predictions in CASP9 (2011, methodology): “For comparison, in CASP8,42 the average Acc and X d values were 21.1% and 10.1%, respectively.”
Improving protein structure prediction using multiple sequence-based contact predictions. (2011, methodology): “For the hard free-modeling (FM) protein targets, it has been shown in the CASP experiments that the purely ab initio sequence-based contact predictions have a higher accuracy than those collected from the best template-based models (Ezkurdia et al., 2009).”
Critical assessment of methods of protein structure prediction—Round VIII (2009, unknown): “13 There are four papers assessing other aspects of structure modeling: domain and three-dimensional (3D) contact identification,14 assessment of disorder,15 prediction of model quality,16 and prediction of ligands binding sites.”
Assessing the accuracy of contact predictions in CASP13 (2019, background): “As early as the second CASP meeting in 1996,(2,3) contact predictions were made and assessed.(4-13) In general, protein structures are very well packed,(14) with densities comparable”
Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks (2014, background): “Therefore, it is not surprising that the prediction accuracy of contact maps is still low despite years of attempts [29].”
Deep Spatio-Temporal Architectures and Learning for Protein Structure Prediction (2012, methodology): “As a final consideration, from Table 2, the NN and RNN best performance on L/5 long range contacts reflect quite well the state-of-the-art in contact prediction [9, 15] with an accuracy in the 21-23% range.”
Accurate de novo structure prediction of large transmembrane protein domains using fragment-assembly and correlated mutation analysis (2012, background): “Although many different approaches have been proposed for predicting contacts from sequence data (19 – 31), success has remained relatively modest (32).”
IntFOLD: an integrated server for modelling protein structures and functions from amino acid sequences (2015, methodology): “This approach has been benchmarked in previous CASP experiments (15,16); however the category of domain prediction has since been removed by the CASP organizers.”
Deep architectures for protein contact map prediction (2012, methodology): “We train the archi- tecture on a large set of non-redundant proteins and test it on a large set of non-homologous domains, as well as on the set of protein do- mains used for contact prediction in the two most recent CASP8 and CASP9 experiments.”