Optimization of Gaussian Kernel Function in Support Vector Machine aided QSAR studies of C-aryl glucoside SGLT2 inhibitors

The present investigations include utility of latest statistical algorithm Support Vector Machine (SVM) to identify non-linear structure activity relationship between IC 50 values and structures of C-aryl glucoside SGLT2 inhibitors. Training dataset consisted of forty molecules and the remaining six...

Full description

Saved in:
Bibliographic Details
Published in:Interdisciplinary sciences : computational life sciences 2013-03, Vol.5 (1), p.45-52
Main Authors: Prasoona, Rebekah K., Jyoti, A., Mukesh, Yadav, Nishant, Sharma, Anuraj, Nayarisseri S., Shobha, Joshi
Format: Article
Language:English
Subjects:
Algorithms
Benzhydryl Compounds
Biomedical and Life Sciences
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Appl. in Life Sciences
Diabetes Mellitus, Type 2 - drug therapy
Gaussian
Glucosides
Glucosides - chemistry
Health Sciences
Humans
Inhibitors
Inhibitory Concentration 50
Kernel functions
Life Sciences
Mathematical and Computational Physics
Medicine
Molecular structure
Nonlinearity
Quantitative Structure-Activity Relationship
Sodium-Glucose Transporter 2 Inhibitors
Statistics for Life Sciences
Support vector machines
Theoretical
Theoretical and Computational Chemistry
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The present investigations include utility of latest statistical algorithm Support Vector Machine (SVM) to identify non-linear structure activity relationship between IC 50 values and structures of C-aryl glucoside SGLT2 inhibitors. Training dataset consisted of forty molecules and the remaining six molecules were chosen for test set validation. SVM under Gaussian Kernel Function yielded non-linear QSAR models. Forward selection algorithm was applied after pruning and redundancy check on molecular descriptors. Internal validations of QSAR models have been achieved using R CV 2 (LOO), PRESS, SDEP and Y-Scrambling. SVM aided non-linear models are more efficient when optimization of Gaussian Kernel Function was introduced. Non-linear QSAR studies further identified atomic van der Waals volumes, atomic masses, sum of geometrical distances between O..S and degree of unsaturation as molecular descriptors and crucial structural requirements to model IC 50 of C-aryl glucoside derivatives.
ISSN:1913-2751
1867-1462
DOI:10.1007/s12539-013-0156-y