Deep learning for prediction of pharmaceutical formulations.
10.1016/j.apsb.2018.09.010
- Author:
Yilong YANG
1
;
Zhuyifan YE
1
;
Yan SU
1
;
Qianqian ZHAO
1
;
Xiaoshan LI
2
;
Defang OUYANG
1
Author Information
1. State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences (ICMS), University of Macau, Macau, China.
2. Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau, China.
- Publication Type:Journal Article
- Keywords:
ANNs, artificial neural networks;
APIs, active pharmaceutical ingredients;
Automatic dataset selection algorithm;
DNNs, deep neural networks;
Deep learning;
ESs, expert systems;
FDA, U.S. Food and Drug Administration;
HPMC, hydroxypropyl methylene cellulose;
MAE, mean absolute error;
MD-FIS, the Maximum Dissimilarity algorithm with the small group filter and representative initial set selection;
MLR, multiple linear regression;
OFDF, oral fast disintegrating films;
Oral fast disintegrating films;
Oral sustained release matrix tablets;
PLSR, partial least squared regression;
Pharmaceutical formulation;
QSAR, quantitative structure activity relationships;
QbD, quality by design;
RF, random forest;
RMSE, root mean squared error;
SRMT, sustained release matrix tablets;
SVM, support vector machine;
Small data;
k-NN, k-nearest neighbors
- From:
Acta Pharmaceutica Sinica B
2019;9(1):177-185
- CountryChina
- Language:English
-
Abstract:
Current pharmaceutical formulation development still strongly relies on the traditional trial-and-error methods of pharmaceutical scientists. This approach is laborious, time-consuming and costly. Recently, deep learning has been widely applied in many challenging domains because of its important capability of automatic feature extraction. The aim of the present research is to apply deep learning methods to predict pharmaceutical formulations. In this paper, two types of dosage forms were chosen as model systems. Evaluation criteria suitable for pharmaceutics were applied to assess the performance of the models. Moreover, an automatic dataset selection algorithm was developed for selecting the representative data as validation and test datasets. Six machine learning methods were compared with deep learning. Results showed that the accuracies of both two deep neural networks were above 80% and higher than other machine learning models; the latter showed good prediction of pharmaceutical formulations. In summary, deep learning employing an automatic data splitting algorithm and the evaluation criteria suitable for pharmaceutical formulation data was developed for the prediction of pharmaceutical formulations for the first time. The cross-disciplinary integration of pharmaceutics and artificial intelligence may shift the paradigm of pharmaceutical research from experience-dependent studies to data-driven methodologies.
