From data to discovery: The rise of information-theoretic predictive models in drug development

Accelerating drug design and development is crucial for improving patient outcomes and addressing health concerns. Faster procedures for the drug development process lower costs, speed up the discovery of cures, and provide faster access to life-saving medications. Unlike existing tools that primarily provide probabilistic biological activity spectra from SMILES input, the proposed system incorporates a hybrid neural network integrated with an information-theoretic predictive models to dynamically simulate pharmacokinetic and pharmacodynamic processes using structure-based and biological sample data. This allows for a more robust prediction across various targets and physiological contexts. This paper analyzes information-theoretic predictive models on a set of biological sample screening results for drug design. Based on the formal peptide receptor, the ASC analysis of the data set was used to generate, adapt, and configure ten mathematical models of the research subject, ensuring reliable modeling results. Based on the set of features of biological samples, two active samples were selected, which, with a high degree of reliability, are also suitable for creating drugs based on the formyl peptide receptor. Researchers can choose the most important characteristics of biosamples with the use of class information portraits, which lowers the effort required for drug development and improves forecast accuracy.As a result of the Feature contribution analysis, features that positively affect the active state of bio samples were identified, and the strength of their influence was also determined.