Machine learning-based predictive modeling, virtual screening and biological evaluation studies for identification of potential inhibitors of MMP-13

Abstract

Matrix Metalloproteinase-13 (MMP-13) is a collagenase that regulates the homeostasis of the extracellular matrix (ECM) and basement membrane, as well as the breakdown of type II collagen. Recent research studies on the molecular and cellular mechanisms of cartilage degradation suggest that MMP-13 overexpression triggers osteoarthritis and is considered a promising target for osteoarthritis treatment. The present work employs machine learning-based virtual screening and structure-based rational drug design approaches to identify potential inhibitors of MMP-13 with diverse chemical scaffolds. The twelve top-scoring screened compounds were subjected to biological evaluation to validate the robustness and predictive modeling of ML-based Virtual Screening. It was observed that eight compounds exhibited approximately 44%–60% inhibition at 0.1 µM concentration, and the IC50 lies in the range of 1.9–2.3 µM against MMP-13. Interestingly, two of the compounds, DP01473 and RH01617, showed potent dose-dependent inhibitory activity. Compound DP01473 inhibited MMP-13 by 44%, 50%, and 70%, while compound RH01617 inhibited MMP-13 by 54%, 55%, and 57% at 0.1 μM, 1 μM, and 10 μM concentrations, respectively, and can be further optimized for the design and development of more potent MMP-13 inhibitors.

Communicated by Ramaswamy H. Sarma

Keywords:

• MMP-13
• cartilage degradation
• machine learning (ML)
• virtual screening
• molecular docking
• osteoarthritis

Acknowledgment

SP acknowledges CSIR, Govt. of India, for Senior Research Fellowship. LP acknowledges University Grant Commission (UGC), New Delhi, India, for providing fellowship, Grant from DBT, Govt of India (Project Number GAP0384) is gratefully acknowledged. Authors are grateful to CSIR-CDRI chemical repository for providing compounds for biological evaluation from Maybridge library. This manuscript is a CSIR-CDRI communication number 10450.

Disclosure statement

The authors declare that they have no competing interests.

Additional information

Funding

This work was supported by the Department of Biotechnology, Ministry of Science and Technology, Government of India.