文献类型：期刊文献

英文题名：Predicting physical stability of solid dispersions by machine learning techniques

作者：Han, Run[1];Xiong, Hui[2];Ye, Zhuyifan[1];Yang, Yilong[1];Huang, Tianhe[1];Jing, Qiufang[2];Lu, Jiahong[1];Pan, Hao[3];Ren, Fuzheng[2];Ouyang, Defang[1]

机构：[1]Univ Macau, ICMS, State Key Lab Qual Res Chinese Med, Macau, Peoples R China;[2]East China Univ Sci & Technol, Engn Res Ctr Pharmaceut Proc Chem, Minist Educ, Shanghai Key Lab New Drug Design,Sch Pharm, Shanghai 200237, Peoples R China;[3]Liaoning Univ, Sch Pharmaceut Sci, 66 Chongshanzhong Rd, Shenyang 110036, Liaoning, Peoples R China

年份：2019

卷号：311

起止页码：16

外文期刊名：JOURNAL OF CONTROLLED RELEASE

收录：;EI(收录号：20193607395500);WOS:【SCI-EXPANDED(收录号:WOS:000497990100002)】；

基金：Current research is financially supported by the Macau FDCT research grant (0029/2018/A1) and Shanghai Key Laboratory of New Drug Design (Grant No. 17DZ2271000). Molecular modeling was performed in part at the High-Performance Computing Cluster (HPCC) which is supported by Information and Communication Technology Office (ICTO) of the University of Macau.

语种：英文

外文关键词：Solid dispersion; Physical stability; Machine learning; Molecular modeling

摘要：Amorphous solid dispersion (SD) is an effective solubilization technique for water-insoluble drugs. However, physical stability issue of solid dispersions still heavily hindered the development of this technique. Traditional stability experiments need to be tested at least three to six months, which is time-consuming and unpredictable. In this research, a novel prediction model for physical stability of solid dispersion formulations was developed by machine learning techniques. 646 stability data points were collected and described by over 20 molecular descriptors. All data was classified into the training set (60%), validation set (20%), and testing set (20%) by the improved maximum dissimilarity algorithm (MD-FIS). Eight machine learning approaches were compared and random forest (RF) model achieved the best prediction accuracy (82.5%). Moreover, the RF models revealed the contribution of each input parameter, which provided us the theoretical guidance for solid dispersion formulations. Furthermore, the prediction model was confirmed by physical stability experiments of 17 beta-estradiol (ED)-PVP solid dispersions and the molecular mechanism was investigated by molecular modeling technique. In conclusion, an intelligent model was developed for the prediction of physical stability of solid dispersions, which benefit the rational formulation design of this technique. The integrated experimental, theoretical, modeling and data-driven AI methodology is also able to be used for future formulation development of other dosage forms.