TY  - JOUR
AU  - Sitani, Divya
AU  - Giorgetti, Alejandro
AU  - Alfonso‐Prieto, Mercedes
AU  - Carloni, Paolo
TI  - Robust Principal Component Analysis‐based Prediction of Protein‐Protein Interaction Hot spots ( RBHS )
JO  - Proteins
VL  - 89
IS  - 6
SN  - 1097-0134
CY  - New York, NY
PB  - Wiley-Liss
M1  - FZJ-2021-00849
SP  - 639-647
PY  - 2021
AB  - 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.
LB  - PUB:(DE-HGF)16
C6  - 33458895
UR  - <Go to ISI:>//WOS:000613869900001
DO  - DOI:10.1002/prot.26047
UR  - https://juser.fz-juelich.de/record/890265
ER  -