Drug Res (Stuttg) 2018; 68(04): 189-195
DOI: 10.1055/s-0043-119288
Original Article
© Georg Thieme Verlag KG Stuttgart · New York

Monte Carlo Method Based QSAR Studies of Mer Kinase Inhibitors in Compliance with OECD Principles

Parvin Kumar
1   Department of Chemistry, Kurukshetra University, Kurukshetra, Haryana, India
,
Ashwani Kumar
2   Department of Pharmaceutical Sciences, Guru Jambheshwar University of Science and Technology, Hisar, Haryana, India
› Institutsangaben
Weitere Informationen

Publikationsverlauf

received 14. Juni 2017

accepted 02. September 2017

Publikationsdatum:
09. Oktober 2017 (online)

Zoom Image

Abstract

Monte Carlo method based QSAR studies for inhibitors of Mer kinase, a potential novel target for cancer treatment, has been carried out using balance of correlation technique. The data was divided into three random and dissimilar splits and hybrid optimal descriptors derived from SMILES and hydrogen filled graphs based notations were used for construction of QSAR models. The generated models have good fitting ability, robustness, generalizability and internal predictive ability. The external predictive ability has been tested using multiple criteria and described models exhibited good performance in all of these tests. The values of R2, Q2, R2 test, Q2 test, R2 m and ∆R2 m for the best model are 0.9502, 0.9388, 0.9469, 0.9083, 0.7534 and 0.0894 respectively. Also, the structural characteristics responsible for enhancement and reduction of activity have been extracted. Further, the agreement with the OECD rules for QSAR model has been discussed.

Supporting Information