Title:	Development of virtual screening strategies to accelerate drug discovery
DNr:	NAISS 2025/22-120
Project Type:	NAISS Small Compute
Principal Investigator:	Bruna Katiele de Paula Clemens <bruna.clemens@ki.se>
Affiliation:	Karolinska Institutet
Duration:	2025-01-31 – 2026-02-01
Classification:	10601
Keywords:

Abstract

The development of new drugs is a lengthy and costly process that can take over a decade and billions of dollars. It involves two primary stages: discovery and development. In the discovery phase, potential drug targets are identified, and compounds are screened and optimized using techniques like high-throughput screening and virtual screening. Preclinical trials in vitro and in animals evaluate the safety and efficacy of these compounds. The development phase includes human clinical trials to assess the drug's safety, efficacy, and pharmacokinetics. Regulatory agencies like the FDA (Food and Drug Administration) and EMA (European Medicines Agency) review the drug and monitor its safety post-approval. Computational techniques, such as Computer Aided Drug Design (CADD), have revolutionized drug discovery. By using computer approaches and more recently the incorporation of Artificial intelligence, researchers can accelerate the identification of promising drug candidates, optimize their properties, reduce development time, costs and impact of residual chemicals in the environment. This approach has led to the successful development of various drugs in the market. CADD has become an indispensable tool in the pharmaceutical industry, enabling faster and more efficient drug discovery and development. In this proposal we aim to develop an integrated computational pipeline that combines molecular docking for binding affinity estimation, AI-driven clustering for efficient prioritization of chemically diverse candidates, and molecular dynamics simulations to assess the stability and dynamics of drug-protein complexes. This approach accelerates the identification of promising drug candidates, enhance our ability to predict the stability and behavior of drug-protein interactions in biologically relevant environments, and reduce the time and cost associated with experimental screening. This multi-faceted strategy is designed to deliver promising drug candidates for experimental validation, paving the way for the development of innovative drugs.