Machine learning with active pharmaceutical ingredient/polymer interaction mechanism:Prediction for complex phase behaviors of pharmaceuticals and formulations  

作　　者：Kai Ge Yiping Huang Yuanhui Ji 

机构地区：[1]Jiangsu Province Hi-Tech Key Laboratory for Biomedical Research,School of Chemistry and Chemical Engineering,Southeast University,Nanjing 211189,China

出　　处：《Chinese Journal of Chemical Engineering》2024年第2期263-272,共10页中国化学工程学报（英文版）

基　　金：the financial support from the National Natural Science Foundation of China(22278070,21978047,21776046)。

摘　　要：The high throughput prediction of the thermodynamic phase behavior of active pharmaceutical ingredients(APIs)with pharmaceutically relevant excipients remains a major scientific challenge in the screening of pharmaceutical formulations.In this work,a developed machine-learning model efficiently predicts the solubility of APIs in polymers by learning the phase equilibrium principle and using a few molecular descriptors.Under the few-shot learning framework,thermodynamic theory(perturbed-chain statistical associating fluid theory)was used for data augmentation,and computational chemistry was applied for molecular descriptors'screening.The results showed that the developed machine-learning model can predict the API-polymer phase diagram accurately,broaden the solubility data of APIs in polymers,and reproduce the relationship between API solubility and the interaction mechanisms between API and polymer successfully,which provided efficient guidance for the development of pharmaceutical formulations.

关 键 词：Multi-task machine learning Density functional theory Hydrogen bond interaction MISCIBILITY SOLUBILITY 

分 类 号：TQ460.6[化学工程—制药化工] TP181[自动化与计算机技术—控制理论与控制工程]