Exploring a new paradigm for serum-accessible component rules of natural medicines using machine learning and development and validation of a direct predictive model

In the field of pharmaceutical research, Lipinski's Rule of Five (RO5) was once widely regarded as the prevailing standard for the development of novel drugs. Despite the fact that an increasing number of recently approved drugs no longer adhere to this rule, it continues to serve as a valuable guiding principle in the field of drug discovery. The present study aims to establish a set of rules specifically for the serum-accessible components of natural medicines. A comprehensive literature review was conducted to collect data on serum-accessible components of natural medicines, and machine learning methods were then applied to analyse and screen molecular features distinguishing serum-accessible components from non-serum-accessible ones. The most critical rules for serum-accessible components of natural medicines were identified, and these were named the "Natural Medicine's Rule of 5 (NMRO5)." We then compared the molecular property distributions and predictive performance of NMRO5 with RO5. Then, we developed a predictive model capable of directly assessing the possibility of a molecule being serum-accessible. This model was validated using in vivo experiments on multiple natural medicines. Furthermore, we performed molecular modifications on serum-accessible components to "violate" NMRO5, conducting both forward and reverse validations to confirm the reliability of NMRO5. The results obtained revealed that NMRO5 is characterised by the following: higher TPSA, MaxEState, and PEOE VSA1 values, and lower LogP and MinEState values. This indicates that natural medicine components with these properties are more likely to be serum-accessible or remain in plasma rather than being rapidly eliminated. The investigation revealed significant disparities among the five molecular properties of NMRO5, and the predictive performance of eight models based on NMRO5 consistently outperformed those based on RO5. This finding suggests that NMRO5 provides a more reliable framework for determining whether a molecule is serum-accessible compared to RO5. Finally, we developed a direct predictive model for serum-accessible components, achieving an accuracy of 0.7257, an F1 score of 0.7223, and an AUC of 0.7553.