Advancing Precision Medicine: A Review of Innovative In Silico Approaches for Drug Development, Clinical Pharmacology and Personalized Healthcare

Machine Learning Techniques for Predicting Drug-Related Side Effects: A Scoping Review

BACKGROUND

Drug safety relies on advanced methods for timely and accurate prediction of side effects. To tackle this requirement, this scoping review examines machine-learning approaches for predicting drug-related side effects with a particular focus on chemical, biological, and phenotypical features.

METHODS

This was a scoping review in which a comprehensive search was conducted in various databases from 1 January 2013 to 31 December 2023.

RESULTS

The results showed the widespread use of Random Forest, k-nearest neighbor, and support vector machine algorithms. Ensemble methods, particularly random forest, emphasized the significance of integrating chemical and biological features in predicting drug-related side effects.

CONCLUSIONS

This review article emphasized the significance of considering a variety of features, datasets, and machine learning algorithms for predicting drug-related side effects. Ensemble methods and Random Forest showed the best performance and combining chemical and biological features improved prediction. The results suggested that machine learning techniques have some potential to improve drug development and trials. Future work should focus on specific feature types, selection techniques, and graph-based methods for even better prediction.

A Physiologically Based Pharmacokinetic (PBPK) Study to Assess the Adjuvanticity of Three Peptides in an Oral Vaccine

Following up on the first PBPK model for an oral vaccine built for alpha-tocopherol, three peptides are explored in this article to verify if they could support an oral vaccine formulation as adjuvants using the same PBPK modeling approach. A literature review was conducted to verify what peptides have been used as adjuvants in the last decades, and it was noticed that MDP derivatives have been used, with one of them even being commercially approved and used as an adjuvant when administered intravenously in oncology. The aim of this study was to build optimized models for three MDP peptides (MDP itself, MTP-PE, and murabutide) and to verify if they could act as adjuvants for an oral vaccine. Challenges faced by peptides in an oral delivery system are taken into consideration, and improvements to the formulations to achieve better results are described in a step-wise approach to reach the most-optimized model. Once simulations are performed, results are compared to determine what would be the best peptide to support as an oral adjuvant. According to our results, MTP-PE, the currently approved and commercialized peptide, could have potential to be incorporated into an oral formulation. It would be interesting to proceed with further in vivo experiments to determine the behavior of this peptide when administered orally with a proper formulation to overcome the challenges of oral delivery systems.