Title :
Using Neural Network classifier Support Vector Machine Regression for the prediction of Melting Point of Drug - like compounds
Author :
Rafidha Rahiman, K.A. ; Balakrishnan, Kannan ; Sherly, K.B.
Author_Institution :
Dept. of Comput. Applic., Cochin Univ. of Sci. & Technol., Kochi, India
Abstract :
In our study we use a kernel based classification technique, Support Vector Machine Regression for predicting the Melting Point of Drug - like compounds in terms of Topological Descriptors, Topological Charge Indices, Connectivity Indices and 2D Auto Correlations. The Machine Learning model was designed, trained and tested using a dataset of 100 compounds and it was found that an SVMReg model with RBF Kernel could predict the Melting Point with a mean absolute error 15.5854 and Root Mean Squared Error 19.7576.
Keywords :
design engineering; drugs; learning (artificial intelligence); pattern classification; pharmaceutical industry; radial basis function networks; support vector machines; 2D autocorrelation; SVMReg model; connectivity index; drug-like compounds; kernel based classification technique; machine learning model; mean absolute error; melting point prediction; neural network classifier; radial basis function kernel; root mean squared error; support vector machine regression; topological charge index; topological descriptors; Compounds; Computational modeling; Data mining; Drugs; Kernel; Predictive models; Support vector machines; Data Mining; Machine Learning; Melting Point; QSA; Support Vector Machine;
Conference_Titel :
Emerging Trends in Electrical and Computer Technology (ICETECT), 2011 International Conference on
Conference_Location :
Tamil Nadu
Print_ISBN :
978-1-4244-7923-8
DOI :
10.1109/ICETECT.2011.5760195
