Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/14200
Title: Quasi-supervised Strategies for Compound-protein Interaction Prediction
Authors: Çakı, O.
Karaçalı, B.
Keywords: Chemoinformatics
Compound Similarity
Compound-Protein Interactions
Drug Discovery
Machine Learning
Cost functions
Drug interactions
Learning algorithms
Learning systems
Supervised learning
Chemoinformatics
Compound similarity
Compound-protein interaction
Drug discovery
In-silico
Interaction prediction
Machine-learning
Protein interaction
Quasi-supervised learning
True positive
Proteins
alpha 2C adrenergic receptor
amcinonide
beta 1 adrenergic receptor
beta 2 adrenergic receptor
betaxolol
bisoprolol
cell nucleus receptor
chenodeoxycholic acid
chlorpromazine
chlorpromazine derivative
chlorpromazine hibenzate
chlorpromazine phenolphthalinate
cholesterol
cicloprolol
clozapine
denopamine
dipivefrine
dopamine 2 receptor
dopamine 3 receptor
dydrogesterone
epinephrine
eplerenone
estrogen receptor alpha
ethinylestradiol
etretinate
fenoldopam mesilate
fluoxymesterone
G protein coupled receptor
histamine H1 receptor
hydrocortisone
isoetarine
isotretinoin
levodopa
loteprednol etabonate
methoxamine
metixene
metoprolol
mifepristone
muscarinic M3 receptor
nandrolone phenpropionate
norethisterone
oxandrolone
oxymetazoline
perphenazine
pregnenolone
progesterone receptor
retinoic acid receptor beta
retinoic acid receptor gamma
retinoid X receptor alpha
retinoid X receptor gamma
ritodrine
salbutamol
salbutamol sulfate
spironolactone
tazarotene
terbutaline sulfate
testosterone
unclassified drug
protein
Article
chemical interaction
compound protein interaction
genome analysis
intermethod comparison
kernel method
Kolmogorov Smirnov test
learning algorithm
machine learning
molecular fingerprinting
pairwise kernel method
prediction
protein interaction
quasi supervised learning algorithm
semi supervised machine learning
algorithm
chemistry
Algorithms
Machine Learning
Proteins
Publisher: John Wiley and Sons Inc
Abstract: In-silico compound-protein interaction prediction addresses prioritization of drug candidates for experimental biochemical validation because the wet-lab experiments are time-consuming, laborious and costly. Most machine learning methods proposed to that end approach this problem with supervised learning strategies in which known interactions are labeled as positive and the rest are labeled as negative. However, treating all unknown interactions as negative instances may lead to inaccuracies in real practice since some of the unknown interactions are bound to be positive interactions waiting to be identified as such. In this study, we propose to address this problem using the Quasi-Supervised Learning (QSL) algorithm. In this framework, potential interactions are predicted by estimating the overlap between a true positive dataset of compound-protein pairs with known interactions and an unknown dataset of all the remaining compound-protein pairs. The potential interactions are then identified as those in the unknown dataset that overlap with the interacting pairs in the true positive dataset in terms of the associated similarity structure. We also address the class-imbalance problem by modifying the conventional cost function of the QSL algorithm. Experimental results on GPCR and Nuclear Receptor datasets show that the proposed method can identify actual interactions from all possible combinations. © 2021 Wiley-VCH GmbH.
URI: https://doi.org/10.1002/minf.202100118
https://hdl.handle.net/11147/14200
ISSN: 1868-1743
Appears in Collections:PubMed İndeksli Yayınlar Koleksiyonu / PubMed Indexed Publications Collection
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Show full item record



CORE Recommender

SCOPUSTM   
Citations

3
checked on Jul 13, 2024

Page view(s)

78
checked on Jul 15, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.