Improved prediction of protein-protein binding sites using a support vector machines approach.

By James R. Bradford, David R. Westhead. Bioinformatics, 2005

354 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c65c37e59bcacb615a117e03bb689da3ddc93429

How researchers see this paper

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

In Molecular Biology

Citations in the corpus

Deciphering Protein–Protein Interactions. Part II. Computational Methods to Predict Protein and Domain Interaction Partners (2007, positive): “Different classification methods have been successfully applied to the prediction of protein and domain interactions [41–54].”
ElliPro: a new structure-based tool for the prediction of antibody epitopes (2008, methodology): “ElliPro has been tested on a benchmark dataset of epitopes inferred from 3D structures of antibody-protein complexes [11] and compared with six structure-based methods, including the only two existing methods developed specifically for epitope prediction, CEP [12] and DiscoTope [13]; two protein-pro”
CPORT: A Consensus Interface Predictor and Its Performance in Prediction-Driven Docking with HADDOCK (2011, neutral): “Second, the predictors used by Huang and Schroeder do not include PIER and WHISCY, but do include a patch predictor, PPI-PRED [22].”
Predicting protein function from sequence and structural data. (2005, methodology): “These include statistical methods, data-mining approaches [49] and machine learning techniques (support vector machines and neural networks) to try to predict catalytic residues [50], protein–protein binding sites [51] and enzyme family classification [52,53].”
Prediction‐based fingerprints of protein–protein interactions (2006, methodology): “46”
Recent progress and future directions in protein-protein docking. (2008, neutral): “Instead, the focus is on the salient or promising features of new approaches , several of which are data-based or data-driven, and many of which have not yet been tested in CAPRI.”
LIGSITEcsc: predicting ligand binding sites using the Connolly surface and degree of conservation (2006, methodology): “Conservation has been widely used for function site prediction [26-28] and protein-protein interaction interface prediction [29-32], combined with other physiochemical properties.”