©2025-2036 All Rights Reserved. Online Journal of Bioinformatics. You may not
store these pages in any form except for your own personal use. All other usage
or distribution is illegal under international copyright treaties. Permission to use any of these pages in any other way besides the
before mentioned must be gained in writing from the publisher. This
article is exclusively copyrighted in its entirety to OJB publications. This
article may be copied once but may not be reproduced or re-transmitted without
the express permission of the editors.
OJB©
Online Journal of Bioinformatics©
Onl J Bioinform©
Established 1995
ISSN 1443-2250
Volume
26 (1) : 37-46, 2025
Model to recognize drug from
non-drug like molecules.
Kailash Adhikari,
Tapobrata Lahiri, Hrishikesh Mishra, Kalpana Singh,
Arun Kumar CN.
Indian Institute of Information Technology, Jhalwa Campus, Allahabad, IBM India Pvt
Ltd., Bangalore, India
ABSTRACT
Adhikari K, Lahiri T,
Mishra H, Kalpana Singh, Kumar CN., Model to
recognize drug from non-drug like molecules, Onl J Bioinfo., 26 (1) :37-46, 2025. A model to identify drug like characteristics of any small molecule from any
database is described. Algorithms were used extract 15 of 785 sets of features
found to be significant for discrimination between drug and non-drug like
molecules. These features were fed into a neural network classifier and weights
and biases optimized through a Neuro-GA module. Drug molecules (409) were extracted
from chEMBL and Non-drug (735) from ZINC database SMILES
representation. For selection of best features of 785 with filter 23% using P
> 1 while 73.76% features with P < 0.05, yielded 580 with strong
discriminating power. For classification of 600 molecules into drug and non-drug
like with 450 training 150 test sets. Accuracy was 88%
for training and test data 86%. With Neuro-GA, accuracy was enhanced to 91%.
Key words: Drug likeness, molecular descriptors,
data warehousing and mining, backpropagation network
FULL-TEXT (SUBSCRIBE OR PURCHASE TITLE)