ABSTRACT
Phosphodiesterase 5 (PDE5) falls under a broad category of metallohydrolase enzymes responsible for the catalysis of the phosphodiesterase bond, and thus it can terminate the action of cyclic guanosine monophosphate (cGMP). Overexpression of this enzyme leads to development of a number of pathological conditions. Thus, targeting the enzyme to develop inhibitors could be useful for the treatment of erectile dysfunction as well as pulmonary hypertension. In the current study, several molecular modelling techniques were utilized including Bayesian classification, single tree and forest tree recursive partitioning, and genetic function approximation to identify crucial structural fingerprints important for optimization of tri-substituted pyrazoline derivatives as PDE5 inhibitors. Later, various machine learning models were also developed that could be utilized to predict and screen PDE5 inhibitors in the future.
Acknowledgements
Sk. Abdul Amin sincerely acknowledges Council of Scientific and Industrial Research (CSIR), New Delhi, India for awarding the Senior Research Fellowship (SRF) [FILE NO.: 09/096(0967)/2019-EMR-I, Dated: 01-04-2019]. Tarun Jha is also thankful for the financial support from RUSA 2.0 of UGC, New Delhi, India to Jadavpur University, Kolkata, India. We are very much thankful to the Department of Pharmaceutical Sciences, Dr. Harisingh Gour University, Sagar, India and Department of Pharmaceutical Technology, Jadavpur University, Kolkata, India for providing the research facilities.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Supplementary material
Supplemental data for this article can be accessed at: https://doi.org/10.1080/1062936X.2021.1989721