Reverse pharmacology approach to validate the diabetic wound-healing activity of Jatyadi thailam formulations in vitro on diabetic mimic environment.

Objective: Jatyadi thailam, an Ayurvedic preparation, is renowned for its efficacy in diabetic wound healing and inflammation. This study aimed to validate and compare the diabetic wound-healing potential of two Jatyadi thailam formulations - Ayurvedic formulary of India Jatyadi thailam (JT-AFI) and Yogagrantha formulation of Jatyadi thailam (JT-YG), in a diabetic environment using L929 fibroblast cells in vitro. Methodology: The effects on cell survival, proliferation, migration, angiogenesis, cell cycle progression, apoptosis, ROS generation, and mitochondrial function were evaluated.Results: The formulations promoted cell proliferation, migration, angiogenesis, while also regulating cell cycle and apoptosis. They effectively suppressed ROS generation and modulated mitochondrial function. JT-AFI exhibited superior efficacy in accelerating diabetic wound healing compared to JT-YG.Conclusion: These findings provide substantial support for the mechanistic role of Jatyadi thailam in diabetic wound healing.

A Review on Deep Learning-driven Drug Discovery: Strategies, Tools and Applications.

It takes an average of 10-15 years to uncover and develop a new drug, and the process is incredibly time-consuming, expensive, difficult, and ineffective. In recent years the dramatic changes in the field of artificial intelligence (AI) have helped to overcome the challenges in the drug discovery pipeline. Artificial intelligence (AI) has taken root in various pharmaceutical sectors, from lead compound identification to clinical trials. Deep learning (DL) is a component of artificial intelligence (AI) that has excelled in many fields of Artificial intelligence (AI) research over the past decades. Its numerous applications in the realms of science and technology, especially in biomedicine and bioinformatics, are witnessed deep learning (DL) applications significantly accelerate drug discovery and pharmaceutical research in recent years, and their usefulness has exceeded expectations and shown good promise in tackling a range of issues with drug discovery. Deep learning (DL) holds great potential for drug development since it allows for sophisticated image interpretation, molecular structure and function prediction, and the automated creation of novel chemical entities with specific features. In the process of drug discovery, deep learning (DL) can be incorporated at all stages like identification of targets, prognostic biomarkers, drug designing and development, synergism and antagonism prediction, etc. This review summarizes various approaches of deep learning (DL) in drug discovery like deep generative models for drug discovery, deep learning (DL) tools for drug discovery, synergy prediction, and precision medicine.