% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Sitani:890265,
author = {Sitani, Divya and Giorgetti, Alejandro and
Alfonso‐Prieto, Mercedes and Carloni, Paolo},
title = {{R}obust {P}rincipal {C}omponent {A}nalysis‐based
{P}rediction of {P}rotein‐{P}rotein {I}nteraction {H}ot
spots ( {RBHS} )},
journal = {Proteins},
volume = {89},
number = {6},
issn = {1097-0134},
address = {New York, NY},
publisher = {Wiley-Liss},
reportid = {FZJ-2021-00849},
pages = {639-647},
year = {2021},
abstract = {Proteins often exert their function by binding to other
cellular partners. The hot spots are key residues for
protein-protein binding. Their identification may shed light
on the impact of disease associated mutations on protein
complexes and help design protein-protein interaction
inhibitors for therapy. Unfortunately, current machine
learning methods to predict hot spots, suffer from
limitations caused by gross errors in the data matrices.
Here, we present a novel data pre-processing pipeline that
overcomes this problem by recovering a low rank matrix with
reduced noise using Robust Principal Component Analysis.
Application to existing databases shows the predictive power
of the method.},
cin = {IAS-5 / INM-9},
ddc = {570},
cid = {I:(DE-Juel1)IAS-5-20120330 / I:(DE-Juel1)INM-9-20140121},
pnm = {525 - Decoding Brain Organization and Dysfunction
(POF4-525) / 5241 - Molecular Information Processing in
Cellular Systems (POF4-524)},
pid = {G:(DE-HGF)POF4-525 / G:(DE-HGF)POF4-5241},
typ = {PUB:(DE-HGF)16},
pubmed = {33458895},
UT = {WOS:000613869900001},
doi = {10.1002/prot.26047},
url = {https://juser.fz-juelich.de/record/890265},
}