Machine learning algorithm used to build a QSAR model for pyrazoline scaffold as anti-tubercular agent

T Prabha*, C Selvinthanuja, S Hemalatha, S Sengottuvelu, J Senthil

Department of Pharmaceutical Chemistry, Nandha College of Pharmacy, Tamilnadu, India

ABSTRACT

Machine learning has become an essential tool for drug research to generate pertinent structural information to design drugs with higher biological activities. In this paper, we used python program language on pyrazoline scaffold, which is collected from diverse literature for the inhibition of Mycobacterium tuberculosis. Pyrazoline, a small molecule scaffold could block the biosynthesis of mycolic acids, resulting in mycobacteria death and leading to anti-tubercular drug discovery. The generated QSAR model afforded the ordinary least squares (OLS) regression as R2 = 0.380, F=4.909, and Q2 =0.303, reg. coef_ developed were of 0.00651593 (molecular weight), -0.0069445 (hydrogen bond acceptor), -0.07576775 (hydrogen bond donor), -0.239021 (LogP) and reg. intercept of 3.10331589018553 developed through statsmodels.formula module. The support vector machine of the sklearn module generated the model score of 0.6294242262068762, the developed model was cross-validated by using the test set compounds and plotting the linear curve between the predicted and actual pMIC50 value. We have found that the values obtained using this script correlated well and may be useful in the design of a similar group of pyrazoline analogs as anti-tubercular agents.

Keywords:

Machine Learning, QSAR, Python, Mycobacterium tuberculosis, Pyrazoline scaffold.