In-silico drug discovery is pivotal in modern pharmaceutical research to expedite drug discovery or repurposing. This approach reduces reliance on animal testing, aids in personalized medicine, and facilitates drug repurposing, making it an indispensable tool for accelerating the discovery and optimization of novel therapeutics. However, discovering a new drug from scratch is costly as well as time consuming therefore finding new uses for FDA-approved drugs has become a primary alternative strategy for the pharmaceutical industry. This practice, usually referred to as drug repurposing, is highly attractive because of its potential to speed up the process of drug development, reduce costs, and provide treatments for unmet medical needs.
Our group is developing transformer based methods, web tools, and databases for different drug discovery and repurposing applications. Currently, we are developing transformer-based models for target based and phenotypic drug repurposing applications. Furthermore, we are also developing transformers-based method to predict adverse drug reactions. Using natural language processing-based models, we are predicting the outcomes of clinical trials and to mine/extract drug-target interactions from whole PubMed. In near future, we plan to extend language processing-based models for other applications such as to mine gene-disease associations and adverse drug reactions.