Data driven drug discovery and application in malaria

Abstract

Traditional drug discovery and development processes are time-consuming and costly, with only a newlinefraction of compounds progressing to clinical testing and an even smaller percentage making it to market. newlineTo address these challenges, computer-aided drug discovery (CADD) methodologies have emerged newlineas efficient tools for designing and evaluating potential drug candidates. By utilizing computational algorithms newlineto model drug-receptor interactions, CADD significantly reduces costs and timeframes associated newlinewith lead identification and optimization while maintaining high quality. Integrating deep learning newlinealgorithms further enhances drug discovery pipelines by enabling the analysis of molecular structures, newlinegenetic data, and biochemical interactions to predict drug efficacy and toxicity, and optimize dosage newlineregimens. Deep learning helps to design new small molecule drugs and peptide drugs. Nowadays, newlinetarget-based drug design is giving promising results. We propose a novel computational pipeline that newlineleverages single-cell transcriptomic data to identify crucial proteins as drug targets for malaria, a disease newlinewith increasing resistance to conventional treatments. Through mutual-information-based feature newlinereduction and protein-protein interaction network analysis, key proteins vital for the survival of Plasmodium newlinefalciparum are identified, and potential drug molecules are computationally predicted using newlinedeep learning techniques. We can use this pipeline to select targets for any disease for developing drugs. newlineAdditionally, we explored peptides as promising therapeutic agents due to their targeted interactions newlinewith biological targets and reduced side effects compared to small-molecule drugs. We introduce HYDRA, newlinea hybrid diffusion model for designing therapeutic peptides tailored to specific target receptors, newlineexemplified by the design of peptides targeting Plasmodium falciparum Erythrocyte Membrane Protein newline1 (PfEMP1) genes. HYDRA generates highly stable and diverse peptides based on a protein target. newlineGene expression is a multiface