Chem-Bioinformatics using Machine Learning Techniques

      Identification of potential drug molecules (known as lead discovery and optimization) accounts for about one-third of the drug development cost and considerable amount of time. Pharmaceutical companies are therefore investing significant resources in developing novel computational techniques to reduce the time and cost early in the drug development process. The objective of my research is to develop novel computational models and software for bioactivity prediction and data mining of drug molecules from large databases. Using supervised machine learning techniques (i.e., GA and PCA for classification and feature selection followed by ANN or SVM techniques for pattern recognition), in combination with statistical regression analysis, we are currently developing robust computational models for rapid and reliable prediction of biologicalactivity of HIV protease inhibitors (i.e., potential HIV drug compounds). This research is being carried out in collaboration with Prof. R. Garg who has research grants from NIH and industry. 

Projects:

  • Hybrid GA-ANN based Computational Prediction Tools for Drug Design
  • Shape Analysis Techniques for HIV Protein -Ligand Interactions

Chem-Bioinformatics - Publications

2012

G.M. Ko, A.S. Reddy, R. Garg, and S. Kumar, Computational Modeling Methods for QSAR Studies on HIV-1 Integrase Inhibitors (2005-2010), Current Computer-Aided Drug Design (Bentham Science), Vol. 8(4), pp. 255-70. Dec. 2012.
  1. G.M. Ko, A.S. Reddy, S. Kumar, R. Garg, B.A. Bailey, and A.R. Hadaegh, Differential Evolution-Binary Particle Swarm Optimization Algorithm for the Analysis of Aryl β-Diketo Acids for HIV-1 Integrase Inhibition, IEEE World Congress on Computational Intelligence, Brisbane, Australia, 2012, pp. 1849-1855.
  1. S. Alla, H. Desai, S. Kumar, and R. Garg, Comparison of RSH with Shape Signatures and MACT Technique for Shape Analysis of HIV-1 Protein, IEEE Symp. Computational Intelligence in Bioinformatics and Computational Biology (IEEE CIBCB), San Diego, May 2012.
2011

A. S. Reddy, V. Jallahalli, S. Kumar, R. Garg, X. Zhang, and G. N. Sastry, Analysis of HIV Protease Binding Pockets based on 3D-Shape and Electrostatic Potential Descriptors, Chem. Biol. Drug. Design, Vol. 77, 2011, pp. 137–151.

PDF
2010

A. S. Reddy, S. Kumar and R. Garg, Hybrid-Genetic Algorithm based Descriptor Optimization and QSAR Models for Predicting the Biological Activity of Tipranavir Analogs for HIV Protease Inhibition, Elsevier J. Molecular Graphics and Modeling, Vol. 28, 2010, pp. 852–862.

PDF

G. M. Ko, A. S. Reddy, S. Kumar, B. A. Bailey and R. Garg, Computational Analysis of HIV-1 Protease Protein Binding Pockets, J. Chem. Information and Modeling, Vol. 50, 2010, pp. 1759–1771.

PDF

G. Ko, S. Alla, S. Kumar and R. Garg, Classification of HIV-1 Protease Crystal Structures Using Random Forest, Linear Discriminant Analysis and Logistic Regression, IEEE Symp. Computational Intelligence in Bioinformatics and Computational Biology, May 2-5, 2010, Montreal, Canada.

PDF
2008

S. Kumar, R. Garg, S. Alla, X. Zhang, V. Jallahalli and M. Jahagirdar, 3D-Shape Analysis of the HIV-1 Protease Ligand Binding Site, IEEE Symp. Computational Intelligence in Bioinformatics and Computational Biology, Sun Valley, Idaho, Sept. 15-17, 2008

PDF

S. Alla, A. Aulia, S. Kumar and R. Garg, Using Hybrid GA-ANN to Predict Biological Activity of HIV Protease Inhibitors, IEEE Symp. Computational Intelligence in Bioinformatics and Computational Biology, Sun Valley, Idaho, Sept. 15-17, 2008.

PDF

Gene M. Ko, S. Alla, S. Kumar and R. Garg, Cheminformatics Analysis of HIV-1 Protease Mutations, 236th Fall ACS National Meeting, Aug. 17-21, 2008, Philadelphia, PA (received the ACS CINF Scholarship for Scientific Excellence award).
2007

J. Woo, B.-W. Hong, S. Kumar, I. B. Ray, C.-C. Jay Kuo, Joint Reconstruction and Registration using Level Sets: Application to Computer-Aided Ablation of Atrial Fibrillation, IEEE Int. Conf. Frontiers in Convergence of Bioscience and Information Technologies, Jeju-Do, Korea, Oct. 11-13, 2007.

B. Bhhatarai, S. Alla, S. Kumar and R. Garg, Novel Cheminformatics Study of Non-Peptidic HIV Protease Inhibitors using Machine Learning and Statistical Tools, 233rd National ACS Meeting, 23-29 March 2007, Chicago. (received the ACS CINF Scholarship for Scientific Excellence award)

V. K. Jalahalli, X. Zhang, S. Kumar and R. Garg, Novel Fast Adaptive Algorithm for 3D-Shape Analysis of Protein (HIV Protease)-Ligand Interactions, 234th ACS National Meeting, Boston, MA, August 19-23, 2007.

Gene M. Ko, A. S. Reddy, S. Kumar, R. Garg, Probing the PDB: Mutational Mapping Analysis of HIV-IP protease, ACS West Coast Regional Meeting, San Diego, Oct. 10-12, 2007.