1
|
Iwata H, Hayashi Y, Hasegawa A, Terayama K, Okuno Y. Classification of scanning electron microscope images of pharmaceutical excipients using deep convolutional neural networks with transfer learning. Int J Pharm X 2022; 4:100135. [PMID: 36325273 PMCID: PMC9619299 DOI: 10.1016/j.ijpx.2022.100135] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Revised: 10/12/2022] [Accepted: 10/13/2022] [Indexed: 11/06/2022] Open
Abstract
Convolutional Neural Networks (CNNs) are image analysis techniques that have been applied to image classification in various fields. In this study, we applied a CNN to classify scanning electron microscopy (SEM) images of pharmaceutical raw material powders to determine if a CNN can evaluate particle morphology. We tested 10 pharmaceutical excipients with widely different particle morphologies. SEM images for each excipient were acquired and divided into training, validation, and test sets. Classification models were constructed by applying transfer learning to pretrained CNN models such as VGG16 and ResNet50. The results of a 5-fold cross-validation showed that the classification accuracy of the CNN model was sufficiently high using either pretrained model and that the type of excipient could be classified with high accuracy. The results suggest that the CNN model can detect differences in particle morphology, such as particle size, shape, and surface condition. By applying Grad-CAM to the constructed CNN model, we succeeded in finding particularly important regions in the particle image of the excipients. CNNs have been found to have the potential to be applied to the identification and characterization of raw material powders for pharmaceutical development.
Collapse
Affiliation(s)
- Hiroaki Iwata
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan
| | - Yoshihiro Hayashi
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan,Pharmaceutical Technology Division, Nichi-Iko Pharmaceutical Co., Ltd., 205-1, Shimoumezawa Namerikawa-shi, Toyama 936-0857, Japan,Correspondence to: Y. Hayashi, Pharmaceutical Technology Division, Nichi-Iko Pharmaceutical Co., Ltd.; 205-1, Shimoumezawa Namerikawa-shi, Toyama 936-0857, Japan.
| | - Aki Hasegawa
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan
| | - Kei Terayama
- Graduate School of Medical Life Science, Yokohama City University, Tsurumi-ku, Yokohama 230-0045, Japan
| | - Yasushi Okuno
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan,RIKEN Center for Computational Science, Kobe 650-0047, Japan,Correspondence to: Y. Okuno, Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan.
| |
Collapse
|
2
|
Moon J, Lee B, Ra JS, Kim KT. Predicting PBT and CMR properties of substances of very high concern (SVHCs) using QSAR models, and application for K-REACH. Toxicol Rep 2020; 7:995-1000. [PMID: 32874922 PMCID: PMC7451722 DOI: 10.1016/j.toxrep.2020.08.014] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2020] [Revised: 07/29/2020] [Accepted: 08/10/2020] [Indexed: 11/26/2022] Open
Abstract
BIOWIN is effective for predicting persistence and bioaccumulation. Toxtree is effective for predicting carcinogenicity and mutagenicity. WoE approach enhances the sensitivity. It is recommended to set a conservative criteria of log Kow more than 4.5 in K-REACH.
Quantitative structure-activity relationship (QSAR) models have been applied to predict a variety of toxicity endpoints. Their performance needs to be validated, in a variety of cases, to increase their applicability to chemical regulation. Using the data set of substances of very high concern (SVHCs), the performance of QSAR models were evaluated to predict the persistence and bioaccumulation of PBT, and the carcinogenicity and mutagenicity of CMR. BIOWIN and Toxtree showed higher sensitivity than other QSAR models – the former for persistence and bioaccumulation, the latter for carcinogenicity. In terms of mutagenicity, the sensitivities of QSAR models were underestimated, Toxtree was more accurate and specific than lazy structure–activity relationships (LAZARs) and Computer Assisted Evaluation of industrial chemical Substances According to Regulations (CAESAR). Using the weight of evidence (WoE) approach, which integrates results of individual QSAR models, enhanced the sensitivity of each toxicity endpoint. On the basis of obtained results, in particular the prediction of persistence and bioaccumulation by KOWWIN, a conservative criterion is recommended of log Kow greater than 4.5 in K-REACH, without an upper limit. This study suggests that reliable production of toxicity data by QSAR models is facilitated by a better understanding of the performance of these models.
Collapse
Key Words
- AD, applicability domain
- AFC, atom/fragment contribution
- BCF, bioconcentration factor
- CAESAR, Computer Assisted Evaluation of industrial chemical Substances According to Regulations
- CAS, chemicals abstracts service
- CMR
- CMR, carcinogenic, mutagenic or toxic for reproduction
- DSSTox, distributed structure-searchable toxicity
- ECHA, European Chemical Agency
- EDC, endocrine disrupting chemicals
- EPI, estimation programs interface
- FN, false negative
- FP, false positive
- GHS, globally harmonized system of classification and labelling of chemicals
- K-REACH
- Kow, octanol-water coefficient
- LAZAR, lazy structure–activity relationships
- PBT
- PBT, persistent, bioaccumulative and toxic
- PFCAs, perfluorinated carboxylic acids
- PFDA, nonadecafluorodecanoic acid
- QMRF, QSAR model reporting format
- QPRF, QSAR prediction reporting format
- QSAR
- QSAR, quantitative structure-activity relationship
- REACH, registration, evaluation, authorization and restriction of chemicals
- SA, structure alters
- SMILES, simplified molecular-input line-entry system
- SVHCs
- SVHCs, substances of very high concern
- TN, ture negative
- TP, ture positive
- US EPA, United States Environmental Protection Agency
- UVCBs, complex reaction products or biological materials
- WoE, weight of evidence
Collapse
Affiliation(s)
- Joonsik Moon
- Department of Environmental Energy Engineering, Seoul National University of Science and Technology, Seoul, 01811, Republic of Korea
| | - Byongcheun Lee
- Risk Assessment Division, National Institute of Environmental Research, Incheon, 22689, Republic of Korea
| | - Jin-Sung Ra
- Eco-testing and Risk Assessment Center, Korea Institute of Industrial Technology (KITECH), Ansan, 15588, Republic of Korea
| | - Ki-Tae Kim
- Department of Environmental Energy Engineering, Seoul National University of Science and Technology, Seoul, 01811, Republic of Korea
| |
Collapse
|
3
|
Ambure P, Bhat J, Puzyn T, Roy K. Identifying natural compounds as multi-target-directed ligands against Alzheimer's disease: an in silico approach. J Biomol Struct Dyn 2018; 37:1282-1306. [PMID: 29578387 DOI: 10.1080/07391102.2018.1456975] [Citation(s) in RCA: 34] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
Abstract
Alzheimer's disease (AD) is a multi-factorial disease, which can be simply outlined as an irreversible and progressive neurodegenerative disorder with an unclear root cause. It is a major cause of dementia in old aged people. In the present study, utilizing the structural and biological activity information of ligands for five important and mostly studied vital targets (i.e. cyclin-dependant kinase 5, β-secretase, monoamine oxidase B, glycogen synthase kinase 3β, acetylcholinesterase) that are believed to be effective against AD, we have developed five classification models using linear discriminant analysis (LDA) technique. Considering the importance of data curation, we have given more attention towards the chemical and biological data curation, which is a difficult task especially in case of big data-sets. Thus, to ease the curation process we have designed Konstanz Information Miner (KNIME) workflows, which are made available at http://teqip.jdvu.ac.in/QSAR_Tools/ . The developed models were appropriately validated based on the predictions for experiment derived data from test sets, as well as true external set compounds including known multi-target compounds. The domain of applicability for each classification model was checked based on a confidence estimation approach. Further, these validated models were employed for screening of natural compounds collected from the InterBioScreen natural database ( https://www.ibscreen.com/natural-compounds ). Further, the natural compounds that were categorized as 'actives' in at least two classification models out of five developed models were considered as multi-target leads, and these compounds were further screened using the drug-like filter, molecular docking technique and then thoroughly analyzed using molecular dynamics studies. Finally, the most potential multi-target natural compounds against AD are suggested.
Collapse
Key Words
- 3D, three-dimensional
- ACh, acetylcholine
- AChE, acetylcholinesterase
- AD, Alzheimer’s disease
- ADME, absorption, distribution, metabolism, and elimination
- APP, amyloid precursor protein
- AUROC, area under the ROC curve
- Alzheimer’s disease
- Aβ, amyloid beta
- BACE1, beta-APP-cleaving enzyme 1
- CDK5, cyclin-dependant kinase 5
- FDA, food and drug administration
- FN, false negative
- FP, false positive
- GSK-3β, glycogen synthase kinase 3β
- HTVS, high-throughput virtual screening
- InChI, International Chemical Identifier
- KNIME, Konstanz Information Miner
- LBDD, ligand-based drug design
- LDA, linear discriminant analysis
- MAO-B, monoamine oxidase B
- MMGBSA, molecular mechanics/generalized born surface area
- MMPBSA, molecular mechanics/Poisson–Boltzmann surface area
- MMPs, matched molecular pairs
- MSA, molecular spectrum analysis
- MTDLs, multi-target-directed ligands
- NMDA, N-methyl-D-aspartate
- PDB, protein data bank
- PP, posterior probability
- QSAR, quantitative structure–activity relationship
- RMSD, root-mean-square deviation
- ROC, receiver operating curve
- ROS, reactive oxygen species
- SBDD, structure-based drug design
- SDF, structure data format
- SMILES, simplified molecular-input line-entry system
- TN, true negative
- TP, true positive
- big data
- data curation
- linear discriminant analysis
- molecular docking
- molecular dynamics
- multi-target drug design
- natural compounds
Collapse
Affiliation(s)
- Pravin Ambure
- a Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology , Jadavpur University , Kolkata 700 032 , India
| | - Jyotsna Bhat
- b Laboratory of Environmental Chemometrics, Faculty of Chemistry , University of Gdańsk , ul. Wita Stwosza 63, Gdańsk 80-308 , Poland
| | - Tomasz Puzyn
- b Laboratory of Environmental Chemometrics, Faculty of Chemistry , University of Gdańsk , ul. Wita Stwosza 63, Gdańsk 80-308 , Poland
| | - Kunal Roy
- a Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology , Jadavpur University , Kolkata 700 032 , India
| |
Collapse
|
4
|
Besenczi R, Tóth J, Hajdu A. A review on automatic analysis techniques for color fundus photographs. Comput Struct Biotechnol J 2016; 14:371-384. [PMID: 27800125 PMCID: PMC5072151 DOI: 10.1016/j.csbj.2016.10.001] [Citation(s) in RCA: 25] [Impact Index Per Article: 3.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2016] [Revised: 10/01/2016] [Accepted: 10/03/2016] [Indexed: 12/25/2022] Open
Abstract
In this paper, we give a review on automatic image processing tools to recognize diseases causing specific distortions in the human retina. After a brief summary of the biology of the retina, we give an overview of the types of lesions that may appear as biomarkers of both eye and non-eye diseases. We present several state-of-the-art procedures to extract the anatomic components and lesions in color fundus photographs and decision support methods to help clinical diagnosis. We list publicly available databases and appropriate measurement techniques to compare quantitatively the performance of these approaches. Furthermore, we discuss on how the performance of image processing-based systems can be improved by fusing the output of individual detector algorithms. Retinal image analysis using mobile phones is also addressed as an expected future trend in this field.
Collapse
Key Words
- ACC, accuracy
- AMD, age-related macular degeneration
- AUC, area under the receiver operator characteristics curve
- Biomedical imaging
- Clinical decision support
- DR, diabetic retinopathy
- FN, false negative
- FOV, field-of-view
- FP, false positive
- FPI, false positive per image
- Fundus image analysis
- MA, microaneurysm
- NA, not available
- OC, optic cup
- OD, optic disc
- PPV, positive predictive value (precision)
- ROC, Retinopathy Online Challenge
- RS, Retinopathy Online Challenge score
- Retinal diseases
- SCC, Spearman's rank correlation coefficient
- SE, sensitivity
- SP, specificity
- TN, true negative
- TP, true positive
- kNN, k-nearest neighbor
Collapse
Affiliation(s)
- Renátó Besenczi
- Faculty of Informatics, University of Debrecen 4002 Debrecen PO Box 400, Hungary
| | - János Tóth
- Faculty of Informatics, University of Debrecen 4002 Debrecen PO Box 400, Hungary
| | - András Hajdu
- Faculty of Informatics, University of Debrecen 4002 Debrecen PO Box 400, Hungary
| |
Collapse
|
5
|
Briggs K, Barber C, Cases M, Marc P, Steger-Hartmann T. Value of shared preclinical safety studies - The eTOX database. Toxicol Rep 2014; 2:210-221. [PMID: 28962354 PMCID: PMC5598263 DOI: 10.1016/j.toxrep.2014.12.004] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2014] [Revised: 12/05/2014] [Accepted: 12/09/2014] [Indexed: 11/26/2022] Open
Abstract
First analysis of the eTOX database for 1214 drugs or drug candidates. Shared data mainly from short term <20 days preclinical studies in rat via oral route. Identified the most frequent treatment related findings. Evaluated predictivity of clinical chemistry biomarkers. Present a first use case of the database during early drug development.
A first analysis of a database of shared preclinical safety data for 1214 small molecule drugs and drug candidates extracted from 3970 reports donated by thirteen pharmaceutical companies for the eTOX project (www.etoxproject.eu) is presented. Species, duration of exposure and administration route data were analysed to assess if large enough subsets of homogenous data are available for building in silico predictive models. Prevalence of treatment related effects for the different types of findings recorded were analysed. The eTOX ontology was used to determine the most common treatment-related clinical chemistry and histopathology findings reported in the database. The data were then mined to evaluate sensitivity of established in vivo biomarkers for liver toxicity risk assessment. The value of the database to inform other drug development projects during early drug development is illustrated by a case study.
Collapse
Key Words
- ALP, alkaline phosphatase
- ALT, alanine aminotransferase
- AST, aspartate aminotransferase
- Biomarkers
- CDISC, Clinical Data Interchange Standards Consortium
- CRO, contract research organisation
- DILI, drug induced liver injury
- Data mining
- Data sharing
- EFPIA, European Federation of Pharmaceutical Industries and Associations
- FN, false negative
- FP, false positive
- GLP, good laboratory practice
- ICH, International Conference on Harmonisation
- IMI, Innovative Medicines Initiative
- INHAND, International Harmonization of Nomenclature and Diagnostic Criteria
- IT, information technology
- MCC, Matthews correlation coefficient
- OECD, Organisation for Economic Co-operation and Development
- Ontology
- PDF, Portable Document Format
- PDF/A, ISO-standardized version of PDF specialized for the digital preservation of electronic documents.
- QA, quality assurance
- SEND, Standard for Exchange of Nonclinical Data
- SME, small-to-medium enterprise
- TN, true negative
- TP, true positive
- Toxicology
- ULN, upper limit of normal
- eTOX, integrating bioinformatics and chemoinformatics approaches for the development of expert systems allowing the in silico prediction of toxicities
Collapse
Affiliation(s)
- Katharine Briggs
- Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds LS11 5PS, United Kingdom
| | - Chris Barber
- Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds LS11 5PS, United Kingdom
| | - Montserrat Cases
- Research Programme on Biomedical Informatics (GRIB), Hospital del Mar Medical Research Institute (IMIM), Department of Experimental and Health Sciences, Universitat Pompeu Fabra, C/Dr Aiguader 88, E-08003 Barcelona, Spain
| | - Philippe Marc
- PreClinical Safety, Novartis Institute for Biomedical Research, Klybeckstrasse 141, CH-4057 Basel, Switzerland
| | - Thomas Steger-Hartmann
- Bayer Pharma AG, Bayer HealthCare, Investigational Toxicology, Müllerstrasse 178, D-13353 Berlin, Germany
| |
Collapse
|