Applying artificial intelligence and machine learning framework for de novo design of pyrazole-based VEGFR-2 inhibitors.

VEGFR-2 is an important target for oncological interventions due to its key role in angiogenesis, a biological process vital for tumour expansion and metastasis. The targeted blockade of VEGFR-2 has emerged as a promising treatment approach across a diverse range of cancers. Pyrazole derivatives extensively studied in this setting have exhibited considerable promise as inhibitors and modulators of VEGFR-2, attributable to their structural diversity and associated biological activities, thereby rendering them compelling candidates for pharmacological development. This study has employed artificial intelligence and machine learning (AI-ML) frameworks to develop groundbreaking pyrazole derivatives designed as anticancer agents specifically targeting the VEGFR-2 kinase. Specifically, this research investigates VEGFR-2 kinase inhibitors and modulators using methodologies and tools such as Reinvent4, ADMET-AI, SwissADME, AutoDock Vina, molecular dynamics (MD) simulations via Gromacs, and MM-GBSA for an exhaustive assessment of their molecular properties and interaction analyses relevant to VEGFR-2 kinase inhibition. The amalgamation of these methodologies furnishes a robust framework for modern drug discovery, wherein chemical space is systematically refined. Ultimately, five lead VEGFR-2 inhibitors-modulators were identified for subsequent development as potential therapeutics targeting VEGFR-2; however, they still require biological efficacy assessment to further optimise and progress toward preclinical evaluation.