Match!

Deep learning for in vitro prediction of pharmaceutical formulations

Published on Jan 1, 2019in Acta Pharmaceutica Sinica B5.808
· DOI :10.1016/j.apsb.2018.09.010
Yilong Yang4
Estimated H-index: 4
(UM: University of Macau),
Zhuyifan Ye2
Estimated H-index: 2
(UM: University of Macau)
+ 3 AuthorsDefang Ouyang12
Estimated H-index: 12
(UM: University of Macau)
Sources
Abstract
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.
  • References (37)
  • Citations (7)
📖 Papers frequently viewed together
2018
3 Authors (Thi Ngan Dong, ..., Megha Khosla)
2010
78% of Scinapse members use related papers. After signing in, all features are FREE.
References37
Newest
#1Run Han (UM: University of Macau)H-Index: 2
#2Yilong Yang (UM: University of Macau)H-Index: 4
Last. Defang Ouyang (UM: University of Macau)H-Index: 12
view all 4 authors...
Abstract Oral disintegrating tablets (ODTs) are a novel dosage form that can be dissolved on the tongue within 3 min or less especially for geriatric and pediatric patients. Current ODT formulation studies usually rely on the personal experience of pharmaceutical experts and trial-and-error in the laboratory, which is inefficient and time-consuming. The aim of current research was to establish the prediction model of ODT formulations with direct compression process by artificial neural network (...
7 CitationsSource
#1Alexandru KorotcovH-Index: 3
#2Valery TkachenkoH-Index: 12
Last. Sean EkinsH-Index: 59
view all 4 authors...
Machine learning methods have been applied to many data sets in pharmaceutical research for several decades. The relative ease and availability of fingerprint type molecular descriptors paired with Bayesian methods resulted in the widespread use of this approach for a diverse array of end points relevant to drug discovery. Deep learning is the latest machine learning algorithm attracting attention for many of pharmaceutical applications from docking to virtual screening. Deep learning is based o...
32 CitationsSource
#1Xue Han (CDUTCM: Chengdu University of Traditional Chinese Medicine)H-Index: 1
#2Hong Jiang (CDUTCM: Chengdu University of Traditional Chinese Medicine)H-Index: 1
Last. Ming Yang (JUTCM: Jiangxi University of Traditional Chinese Medicine)H-Index: 6
view all 10 authors...
Abstract Traditional Chinese herbs (TCH) are currently gaining attention in disease prevention and health care plans. However, their general bitter taste hinders their use. Despite the development of a variety of taste evaluation methods, it is still a major challenge to establish a quantitative detection technique that is objective, authentic and sensitive. Based on the two-bottle preference test (TBP), we proposed a novel quantitative strategy using a standardized animal test and a unified qua...
5 CitationsSource
Multitask deep learning has emerged as a powerful tool for computational drug discovery. However, despite a number of preliminary studies, multitask deep networks have yet to be widely deployed in the pharmaceutical and biotech industries. This lack of acceptance stems from both software difficulties and lack of understanding of the robustness of multitask deep networks. Our work aims to resolve both of these barriers to adoption. We introduce a high-quality open-source implementation of multita...
44 CitationsSource
#1Weixiang Zhang (UM: University of Macau)H-Index: 2
#2Qianqian Zhao (UM: University of Macau)H-Index: 3
Last. Defang Ouyang (UM: University of Macau)H-Index: 12
view all 6 authors...
The past three decades have witnessed an upsurge of publications in pharmaceutics and the drug delivery field. This review provides a landscape of global research advances in pharmaceutics in the period 1980–2014 from publications, countries and institutions, and their collaborations. The scientific knowledge mapping analysis showed that the research frontier shifted from conventional pharmaceutical techniques (1980–1992) to advanced drug delivery systems (1993–2014). The history of drug deliver...
3 CitationsSource
#1Han Altae-TranH-Index: 2
#2Bharath RamsundarH-Index: 11
Last. Vijay S. PandeH-Index: 82
view all 4 authors...
Recent advances in machine learning have made significant contributions to drug discovery. Deep neural networks in particular have been demonstrated to provide significant boosts in predictive power when inferring the properties and activities of small-molecule compounds (Ma, J. et al. J. Chem. Inf. Model. 2015, 55, 263–274). However, the applicability of these techniques has been limited by the requirement for large amounts of training data. In this work, we demonstrate how one-shot learning ca...
103 CitationsSource
#1Quentin Vanhaelen (Johns Hopkins University)H-Index: 7
#2Polina Mamoshina (Johns Hopkins University)H-Index: 7
Last. Alex Zhavoronkov (Johns Hopkins University)H-Index: 26
view all 8 authors...
Here, we provide a comprehensive overview of the current status of in silico repurposing methods by establishing links between current technological trends, data availability and characteristics of the algorithms used in these methods. Using the case of the computational repurposing of fasudil as an alternative autophagy enhancer, we suggest a generic modular organization of a repurposing workflow. We also review 3D structure-based, similarity-based, inference-based and machine learning (ML)-bas...
33 CitationsSource
#1Ian Goodfellow (Google)H-Index: 52
#2Yoshua Bengio (UdeM: Université de Montréal)H-Index: 122
Last. Aaron Courville (UdeM: Université de Montréal)H-Index: 56
view all 3 authors...
Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book ...
12.3k Citations
#1Sean Ekins (Collaborative Drug Discovery)H-Index: 59
Over the past decade we have witnessed the increasing sophistication of machine learning algorithms applied in daily use from internet searches, voice recognition, social network software to machine vision software in cameras, phones, robots and self-driving cars. Pharmaceutical research has also seen its fair share of machine learning developments. For example, applying such methods to mine the growing datasets that are created in drug discovery not only enables us to learn from the past but to...
41 CitationsSource
#1Igor I. Baskin (MSU: Moscow State University)H-Index: 25
#2David A. Winkler (Flinders University)H-Index: 34
Last. Igor V. TetkoH-Index: 44
view all 3 authors...
ABSTRACTIntroduction: Neural networks are becoming a very popular method for solving machine learning and artificial intelligence problems. The variety of neural network types and their application to drug discovery requires expert knowledge to choose the most appropriate approach.Areas covered: In this review, the authors discuss traditional and newly emerging neural network approaches to drug discovery. Their focus is on backpropagation neural networks and their variants, self-organizing maps ...
46 CitationsSource
Cited By7
Newest
Abstract Cell-based therapeutics promise to transform the treatment of a wide range of diseases including cancer, genetic and degenerative disorders, or severe injuries. Many of the commercial and clinical development of cell therapy products require cryopreservation and storage of cellular starting materials, intermediates and/or final products at cryogenic temperature. Dimethyl sulfoxide (Me2SO) has been the cryoprotectant of choice in most biobanking situations due to its exceptional performa...
Source
#1Yuan HeH-Index: 1
#2Zhuyifan Ye (UM: University of Macau)H-Index: 2
Last. Defang OuyangH-Index: 12
view all 8 authors...
Abstract Nanocrystals have exhibited great advantage for enhancing the dissolution rate of water insoluble drugs due to the reduced size to nanoscale. However, current pharmaceutical approaches for nanocrystals formulation development highly depend on the expert experience and trial-and-error attempts which remain time and resource consuming. In this research, we utilized machine learning techniques to predict the particle size and polydispersity index (PDI) of nanocrystals. Firstly, 910 nanocry...
Source
Over the past few years, we have seen fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. At the same time, the amount of data collected in a wide array of scientific domains is dramatically increasing in both size and complexity. Taken together, this suggests many exciting opportunities for deep learning applications in scientific settings. But a significant challenge to this is simply knowing where to start. The sheer breadth and ...
2 Citations
#1Takuya Oishi (University of Toyama)H-Index: 1
#2Yoshihiro Hayashi (University of Toyama)H-Index: 7
Last. Yoshinori Onuki (University of Toyama)H-Index: 15
view all 8 authors...
Abstract Our aim was to understand better the causal relationships between material attributes (MAs), process parameters (PPs), and critical quality attributes (CQAs) using an originally created large dataset and regularized linear regression models. In this study, we focused on the following three points: (1) creation of a dataset comprising several tablet production methods, (2) the influence of interaction terms of MAs and/or PPs, and (3) comparison of regularized linear regression models wit...
Source
#1Xiangyu Ma (University of Texas at Austin)H-Index: 2
#2Nada Kittikunakorn (University of Texas at Austin)H-Index: 1
Last. Daniel Skomski (MSD: Merck & Co.)H-Index: 8
view all 10 authors...
Abstract Tablet defects encountered during the manufacturing of oral formulations can result in quality concerns, timeline delays, and elevated financial costs. Internal tablet cracking is not typically measured in routine inspections but can lead to batch failures such as tablet fracturing. X-ray computed tomography (XRCT) has become well-established to analyze internal cracks of oral tablets. However, XRCT normally generates very large quantities of image data (thousands of 2D slices per data ...
Source
#1Lorenzo Gentiluomo (LMU: Ludwig Maximilian University of Munich)H-Index: 2
#2Dierk RoessnerH-Index: 2
Last. Wolfgang Frieß (LMU: Ludwig Maximilian University of Munich)H-Index: 12
view all 3 authors...
Abstract An important aspect of initial developability assessments as well formulation development and selection of therapeutic proteins is the evaluation of data obtained under accelerated stress condition, i.e. at elevated temperatures. We propose the application of artificial neural networks (ANNs) to predict long term stability in real storage condition from accelerated stability studies and other high-throughput biophysical properties e.g. the first apparent temperature of unfolding (Tm). O...
Source
#1Alexis N Simpkins (UF: University of Florida)
#2Miroslaw Janowski (UMB: University of Maryland, Baltimore)H-Index: 20
Last. Ann M. Stowe (UK: University of Kentucky)H-Index: 1
view all 7 authors...
Stroke remains one of the leading causes of long-term disability and mortality despite recent advances in acute thrombolytic therapies. In fact, the global lifetime risk of stroke in adults over the age of 25 is approximately 25%, with 24.9 million cases of ischemic stroke and 18.7 million cases of hemorrhagic stroke reported in 2015. One of the main challenges in developing effective new acute therapeutics and enhanced long-term interventions for stroke recovery is the heterogeneity of stroke, ...
1 CitationsSource
#2Djordje MedarevićH-Index: 6
Last. Svetlana IbrićH-Index: 19
view all 7 authors...
The aim of this work was to investigate effects of the formulation factors on tablet printability as well as to optimize and predict extended drug release from cross-linked polymeric ibuprofen printlets using an artificial neural network (ANN). Printlets were printed using digital light processing (DLP) technology from formulations containing polyethylene glycol diacrylate, polyethylene glycol, and water in concentrations according to D-optimal mixture design and 0.1% w/w riboflavin and 5% w/w i...
1 CitationsSource
#1Run Han (UM: University of Macau)H-Index: 2
#2Hui Xiong (ECUST: East China University of Science and Technology)H-Index: 3
Last. Defang Ouyang (UM: University of Macau)H-Index: 12
view all 10 authors...
Abstract 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 stab...
2 CitationsSource
The constitutive androstane receptor (CAR) plays pivotal roles in drug-induced liver injury through the transcriptional regulation of drug-metabolizing enzymes and transporters. Thus, identifying regulatory factors for CAR activation is important for understanding its mechanisms. Numerous studies conducted previously on CAR activation and its toxicity focused on in vivo or in vitro analyses, which are expensive, time consuming, and require many animals. We developed a computational model that pr...
3 CitationsSource