Prediction‐based fingerprints of protein–protein interactions

By Aleksey A. Porollo, Jaroslaw Meller. Proteins: Structure, Function, and Bioinformatics, 2006

418 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/2f871fda8e3dd460a19f6e07f1f52ad8e9e34806

How researchers see this paper

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

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

Applying the Naïve Bayes classifier with kernel density estimation to the prediction of protein-protein interaction sites (2010, methodology): “…atoms of the target chain and any atoms of the interacting chains (Ofran and Rost, 2007), and SPPIDER defined the interface residues based on >4% rSA change and >5 Å2 SA change on complex formation of the exposed surface residues, which were defined if their rSA was >5% (Porollo and Meller, 2007).”
CPORT: A Consensus Interface Predictor and Its Performance in Prediction-Driven Docking with HADDOCK (2011, neutral): “For PIER, WHISCY, ProMate, SPPIDER and cons-PPISP these numbers were 71, 58, 56, 52 and 49, respectively.”
Recent progress and future directions in protein-protein docking. (2008, background): “…main challenges in protein docking today are to be able to generate reliably trial conformations which closely resemble those of the native complex, and to devise improved scoring functions which can correctly distinguish near-native docking orientations from a list of highly complementary decoys.”
End-to-End Learning on 3D Protein Structure for Interface Prediction (2018, background): “For the distinct task of single interface prediction, also known as binding site prediction, methods such as Jordan et al. [25], Porollo and Meller [26], Northey et al. [27], and Hwang et al. [28] also use high-level structural features to predict interfacial residues, but in a non-partner-speciﬁc m”
Protein interaction interface region prediction by geometric deep learning (2021, methodology): “The relatively better performance of PInet on geometry alone leads us to conjecture that PInet could benefit from a different encoding of physicochemical features or a more direct aggregation of the features (e.g. as convolution would do), In addition to the full dataset, the MaSIF paper also includ”