Schweitzer Fachinformationen
Wenn es um professionelles Wissen geht, ist Schweitzer Fachinformationen wegweisend. Kunden aus Recht und Beratung sowie Unternehmen, öffentliche Verwaltungen und Bibliotheken erhalten komplette Lösungen zum Beschaffen, Verwalten und Nutzen von digitalen und gedruckten Medien.
The book provides the direction for future research in deep learning in terms of its role in targeted treatment, biological systems, site-specific drug delivery, risk assessment in therapy, etc.
Deep Learning for Targeted Treatments describes the importance of the deep learning framework for patient care, disease imaging/detection, and health management. Since deep learning can and does play a major role in a patient's healthcare management by controlling drug delivery to targeted tissues or organs, the main focus of the book is to leverage the various prospects of the DL framework for targeted therapy of various diseases. In terms of its industrial significance, this general-purpose automatic learning procedure is being widely implemented in pharmaceutical healthcare.
Audience The book will be immensely interesting and useful to researchers and those working in the areas of clinical research, disease management, pharmaceuticals, R&D formulation, deep learning analytics, remote healthcare management, healthcare analytics, and deep learning in the healthcare industry.
Rishabha Malviya, PhD, is an associate professor in the Department of Pharmacy, School of Medical and Allied Sciences, Galgotias University. His areas of interest include formulation optimization, nanoformulation, targeted drug delivery, localized drug delivery, and characterization of natural polymers as pharmaceutical excipients. He has authored more than 150 research/review papers for national/international journals of repute. He has been granted more than 10 patents from different countries while a further 40 patents are published/under evaluation.
Gheorghita Ghinea, PhD, is a professor in Computing, Department of Computer Science Brunel University London. His research activities lie at the confluence of computer science, media, and psychology, and particularly interested in building semantically underpinned human-centered e-systems, particularly integrating human perceptual requirements. Has published more than 30+ articles and received 10+ research grants.
Rajesh Kumar Dhanaraj, PhD, is an associate professor in the School of Computing Science and Engineering at Galgotias University, Greater Noida, India. He has contributed 20+ books on various technologies and 35+ articles and papers in various refereed journals and international conferences and contributed chapters to the books. His research interests include machine learning, cyber-physical systems, and wireless sensor networks. He is an Expert Advisory Panel Member of Texas Instruments Inc USA.
Balamurugan Balusamy, PhD, is a professor at Galgotias University. He has published 30+ books on various technologies as well as more than 150 journal articles, conferences, and book chapters.
Sonali Sundram completed B. Pharm & M. Pharm (pharmacology) from AKTU, Lucknow, and is working at Galgotias University, Greater Noida. Her areas of interest are neurodegeneration, clinical research, and artificial intelligence. She has more than 8 patents to her credit.
Preface xvii
Acknowledgement xix
1 Deep Learning and Site-Specific Drug Delivery: The Future and Intelligent Decision Support for Pharmaceutical Manufacturing Science 1Dhanalekshmi Unnikrishnan Meenakshi, Selvasudha Nandakumar, Arul Prakash Francis, Pushpa Sweety, Shivkanya Fuloria, Neeraj Kumar Fuloria, Vetriselvan Subramaniyan and Shah Alam Khan
1.1 Introduction 2
1.2 Drug Discovery, Screening and Repurposing 5
1.3 DL and Pharmaceutical Formulation Strategy 11
1.3.1 DL in Dose and Formulation Prediction 11
1.3.2 DL in Dissolution and Release Studies 15
1.3.3 DL in the Manufacturing Process 16
1.4 Deep Learning Models for Nanoparticle-Based Drug Delivery 19
1.4.1 Nanoparticles With High Drug Delivery Capacities Using Perturbation Theory 20
1.4.2 Artificial Intelligence and Drug Delivery Algorithms 21
1.4.3 Nanoinformatics 22
1.5 Model Prediction for Site-Specific Drug Delivery 23
1.5.1 Prediction of Mode and a Site-Specific Action 23
1.5.2 Precision Medicine 26
1.6 Future Scope and Challenges 27
1.7 Conclusion 29
References 30
2 Role of Deep Learning, Blockchain and Internet of Things in Patient Care 39Akanksha Sharma, Rishabha Malviya and Sonali Sundram
2.1 Introduction 40
2.2 IoT and WBAN in Healthcare Systems 42
2.2.1 IoT in Healthcare 42
2.2.2 WBAN 44
2.2.2.1 Key Features of Medical Networks in the Wireless Body Area 44
2.2.2.2 Data Transmission & Storage Health 45
2.2.2.3 Privacy and Security Concerns in Big Data 45
2.3 Blockchain Technology in Healthcare 46
2.3.1 Importance of Blockchain 46
2.3.2 Role of Blockchain in Healthcare 47
2.3.3 Benefits of Blockchain in Healthcare Applications 48
2.3.4 Elements of Blockchain 49
2.3.5 Situation Awareness and Healthcare Decision Support with Combined Machine Learning and Semantic Modeling 51
2.3.6 Mobile Health and Remote Monitoring 53
2.3.7 Different Mobile Health Application with Description of Usage in Area of Application 54
2.3.8 Patient-Centered Blockchain Mode 55
2.3.9 Electronic Medical Record 57
2.3.9.1 The Most Significant Barriers to Adoption Are 60
2.3.9.2 Concern Regarding Negative Unintended Consequences of Technology 60
2.4 Deep Learning in Healthcare 62
2.4.1 Deep Learning Models 63
2.4.1.1 Recurrent Neural Networks (RNN) 63
2.4.1.2 Convolutional Neural Networks (CNN) 64
2.4.1.3 Deep Belief Network (DBN) 65
2.4.1.4 Contrasts Between Models 66
2.4.1.5 Use of Deep Learning in Healthcare 66
2.5 Conclusion 70
2.6 Acknowledgments 70
References 70
3 Deep Learning on Site-Specific Drug Delivery System 77Prem Shankar Mishra, Rakhi Mishra and Rupa Mazumder
3.1 Introduction 78
3.2 Deep Learning 81
3.2.1 Types of Algorithms Used in Deep Learning 81
3.2.1.1 Convolutional Neural Networks (CNNs) 82
3.2.1.2 Long Short-Term Memory Networks (LSTMs) 83
3.2.1.3 Recurrent Neural Networks 83
3.2.1.4 Generative Adversarial Networks (GANs) 84
3.2.1.5 Radial Basis Function Networks 84
3.2.1.6 Multilayer Perceptron 85
3.2.1.7 Self-Organizing Maps 85
3.2.1.8 Deep Belief Networks 85
3.3 Machine Learning and Deep Learning Comparison 86
3.4 Applications of Deep Learning in Drug Delivery System 87
3.5 Conclusion 90
References 90
4 Deep Learning Advancements in Target Delivery 101Sudhanshu Mishra, Palak Gupta, Smriti Ojha, Vijay Sharma, Vicky Anthony and Disha Sharma
4.1 Introduction: Deep Learning and Targeted Drug Delivery 102
4.2 Different Models/Approaches of Deep Learning and Targeting Drug 104
4.3 QSAR Model 105
4.3.1 Model of Deep Long-Term Short-Term Memory 105
4.3.2 RNN Model 107
4.3.3 CNN Model 108
4.4 Deep Learning Process Applications in Pharmaceutical 109
4.5 Techniques for Predicting Pharmacotherapy 109
4.6 Approach to Diagnosis 110
4.7 Application 113
4.7.1 Deep Learning in Drug Discovery 114
4.7.2 Medical Imaging and Deep Learning Process 115
4.7.3 Deep Learning in Diagnostic and Screening 116
4.7.4 Clinical Trials Using Deep Learning Models 116
4.7.5 Learning for Personalized Medicine 117
4.8 Conclusion 121
Acknowledgment 122
References 122
5 Deep Learning and Precision Medicine: Lessons to Learn for the Preeminent Treatment for Malignant Tumors 127Selvasudha Nandakumar, Shah Alam Khan, Poovi Ganesan, Pushpa Sweety, Arul Prakash Francis, Mahendran Sekar, Rukkumani Rajagopalan and Dhanalekshmi Unnikrishnan Meenakshi
5.1 Introduction 128
5.2 Role of DL in Gene Identification, Unique Genomic Analysis, and Precise Cancer Diagnosis 132
5.2.1 Gene Identification and Genome Data 133
5.2.2 Image Diagnosis 135
5.2.3 Radiomics, Radiogenomics, and Digital Biopsy 137
5.2.4 Medical Image Analysis in Mammography 138
5.2.5 Magnetic Resonance Imaging 139
5.2.6 CT Imaging 140
5.3 dl in Next-Generation Sequencing, Biomarkers, and Clinical Validation 141
5.3.1 Next-Generation Sequencing 141
5.3.2 Biomarkers and Clinical Validation 142
5.4 dl and Translational Oncology 144
5.4.1 Prediction 144
5.4.2 Segmentation 146
5.4.3 Knowledge Graphs and Cancer Drug Repurposing 147
5.4.4 Automated Treatment Planning 149
5.4.5 Clinical Benefits 150
5.5 DL in Clinical Trials-A Necessary Paradigm Shift 152
5.6 Challenges and Limitations 155
5.7 Conclusion 157
References 157
6 Personalized Therapy Using Deep Learning Advances 171Nishant Gaur, Rashmi Dharwadkar and Jinsu Thomas
6.1 Introduction 172
6.2 Deep Learning 174
6.2.1 Convolutional Neural Networks 175
6.2.2 Autoencoders 180
6.2.3 Deep Belief Network (DBN) 182
6.2.4 Deep Reinforcement Learning 184
6.2.5 Generative Adversarial Network 186
6.2.6 Long Short-Term Memory Networks 188
References 191
7 Tele-Health Monitoring Using Artificial Intelligence Deep Learning Framework 199Swati Verma, Rishabha Malviya, Md Aftab Alam and Bhuneshwar Dutta Tripathi
7.1 Introduction 200
7.2 Artificial Intelligence 200
7.2.1 Types of Artificial Intelligence 201
7.2.1.1 Machine Intelligence 201
7.2.1.2 Types of Machine Intelligence 203
7.2.2 Applications of Artificial Intelligence 204
7.2.2.1 Role in Healthcare Diagnostics 205
7.2.2.2 AI in Telehealth 205
7.2.2.3 Role in Structural Health Monitoring 205
7.2.2.4 Role in Remote Medicare Management 206
7.2.2.5 Predictive Analysis Using Big Data 207
7.2.2.6 AI's Role in Virtual Monitoring of Patients 208
7.2.2.7 Functions of Devices 208
7.2.2.8 Clinical Outcomes Through Remote Patient Monitoring 210
7.2.2.9 Clinical Decision Support 211
7.2.3 Utilization of Artificial Intelligence in Telemedicine 211
7.2.3.1 Artificial Intelligence-Assisted Telemedicine 212
7.2.3.2 Telehealth and New Care Models 213
7.2.3.3 Strategy of Telecare Domain 214
7.2.3.4 Role of AI-Assisted Telemedicine in Various Domains 216
7.3 AI-Enabled Telehealth: Social and Ethical Considerations 218
7.4 Conclusion 219
References 220
8 Deep Learning Framework for Cancer Diagnosis and Treatment 229Shiv Bahadur and Prashant Kumar
8.1 Deep Learning: An Emerging Field for Cancer Management 230
8.2 Deep Learning Framework in Diagnosis and Treatment of Cancer 232
8.3 Applications of Deep Learning in Cancer Diagnosis 233
8.3.1 Medical Imaging Through Artificial Intelligence 234
8.3.2 Biomarkers Identification in the Diagnosis of Cancer Through Deep Learning 234
8.3.3 Digital Pathology Through Deep Learning 235
8.3.4 Application of Artificial Intelligence in Surgery 236
8.3.5 Histopathological Images Using Deep Learning 237
8.3.6 MRI and Ultrasound Images Through Deep Learning 237
8.4 Clinical Applications of Deep Learning in the Management of Cancer 238
8.5 Ethical Considerations in Deep Learning-Based Robotic Therapy 239
8.6 Conclusion 240
Acknowledgments 240
References 241
9 Applications of Deep Learning in Radiation Therapy 247Akanksha Sharma, Ashish Verma, Rishabha Malviya and Shalini Yadav
9.1 Introduction 248
9.2 History of Radiotherapy 250
9.3 Principal of Radiotherapy 251
9.4 Deep Learning 251
9.5 Radiation Therapy Techniques 254
9.5.1 External Beam Radiation Therapy 257
9.5.2 Three-Dimensional Conformal Radiation Therapy (3D-CRT) 259
9.5.3 Intensity Modulated Radiation Therapy (IMRT) 260
9.5.4 Image-Guided Radiation Therapy (IGRT) 261
9.5.5 Intraoperative Radiation Therapy (IORT) 263
9.5.6 Brachytherapy 265
9.5.7 Stereotactic Radiosurgery (SRS) 268
9.6 Different Role of Deep Learning with Corresponding Role of Medical Physicist 269
9.6.1 Deep Learning in Patient Assessment 269
9.6.1.1 Radiotherapy Results Prediction 269
9.6.1.2 Respiratory Signal Prediction 271
9.6.2 Simulation Computed Tomography 271
9.6.3 Targets and Organs-at-Risk Segmentation 273
9.6.4 Treatment Planning 274
9.6.4.1 Beam Angle Optimization 274
9.6.4.2 Dose Prediction 276
9.6.5 Other Role of Deep Learning in Corresponds with Medical Physicists 277
9.7 Conclusion 280
References 281
10 Application of Deep Learning in Radiation Therapy 289Shilpa Rawat, Shilpa Singh, Md. Aftab Alam and Rishabha Malviya
10.1 Introduction 290
10.2 Radiotherapy 291
10.3 Principle of Deep Learning and Machine Learning 293
10.3.1 Deep Neural Networks (DNN) 294
10.3.2 Convolutional Neural Network 295
10.4 Role of AI and Deep Learning in Radiation Therapy 295
10.5 Platforms for Deep Learning and Tools for Radiotherapy 297
10.6 Radiation Therapy Implementation in Deep Learning 300
10.6.1 Deep Learning and Imaging Techniques 301
10.6.2 Image Segmentation 301
10.6.3 Lesion Segmentation 302
10.6.4 Computer-Aided Diagnosis 302
10.6.5 Computer-Aided Detection 303
10.6.6 Quality Assurance 304
10.6.7 Treatment Planning 305
10.6.8 Treatment Delivery 305
10.6.9 Response to Treatment 306
10.7 Prediction of Outcomes 307
10.7.1 Toxicity 309
10.7.2 Survival and the Ability to Respond 310
10.8 Deep Learning in Conjunction With Radiomoic 312
10.9 Planning for Treatment 314
10.9.1 Optimization of Beam Angle 315
10.9.2 Prediction of Dose 315
10.10 Deep Learning's Challenges and Future Potential 316
10.11 Conclusion 317
References 318
11 Deep Learning Framework for Cancer 333Pratishtha
11.1 Introduction 334
11.2 Brief History of Deep Learning 335
11.3 Types of Deep Learning Methods 336
11.4 Applications of Deep Learning 339
11.4.1 Toxicity Detection for Different Chemical Structures 339
11.4.2 Mitosis Detection 340
11.4.3 Radiology or Medical Imaging 341
11.4.4 Hallucination 342
11.4.5 Next-Generation Sequencing (NGS) 342
11.4.6 Drug Discovery 343
11.4.7 Sequence or Video Generation 343
11.4.8 Other Applications 343
11.5 Cancer 343
11.5.1 Factors 344
11.5.1.1 Heredity 345
11.5.1.2 Ionizing Radiation 345
11.5.1.3 Chemical Substances 345
11.5.1.4 Dietary Factors 345
11.5.1.5 Estrogen 346
11.5.1.6 Viruses 346
11.5.1.7 Stress 347
11.5.1.8 Age 347
11.5.2 Signs and Symptoms of Cancer 347
11.5.3 Types of Cancer Treatment Available 348
11.5.3.1 Surgery 348
11.5.3.2 Radiation Therapy 348
11.5.3.3 Chemotherapy 348
11.5.3.4 Immunotherapy 348
11.5.3.5 Targeted Therapy 349
11.5.3.6 Hormone Therapy 349
11.5.3.7 Stem Cell Transplant 349
11.5.3.8 Precision Medicine 349
11.5.4 Types of Cancer 349
11.5.4.1 Carcinoma 349
11.5.4.2 Sarcoma 349
11.5.4.3 Leukemia 350
11.5.4.4 Lymphoma and Myeloma 350
11.5.4.5 Central Nervous System (CNS) Cancers 350
11.5.5 The Development of Cancer (Pathogenesis) Cancer 350
11.6 Role of Deep Learning in Various Types of Cancer 350
11.6.1 Skin Cancer 351
11.6.1.1 Common Symptoms of Melanoma 351
11.6.1.2 Types of Skin Cancer 352
11.6.1.3 Prevention 353
11.6.1.4 Treatment 353
11.6.2 Deep Learning in Skin Cancer 354
11.6.3 Pancreatic Cancer 354
11.6.3.1 Symptoms of Pancreatic Cancer 355
11.6.3.2 Causes or Risk Factors of Pancreatic Cancer 355
11.6.3.3 Treatments of Pancreatic Cancer 355
11.6.4 Deep Learning in Pancreatic Cancer 355
11.6.5 Tobacco-Driven Lung Cancer 357
11.6.5.1 Symptoms of Lung Cancer 357
11.6.5.2 Causes or Risk Factors of Lung Cancer 358
11.6.5.3 Treatments Available for Lung Cancer 358
11.6.5.4 Deep Learning in Lung Cancer 358
11.6.6 Breast Cancer 359
11.6.6.1 Symptoms of Breast Cancer 360
11.6.6.2 Causes or Risk Factors of Breast Cancer 360
11.6.6.3 Treatments Available for Breast Cancer 361
11.6.7 Deep Learning in Breast Cancer 361
11.6.8 Prostate Cancer 362
11.6.9 Deep Learning in Prostate Cancer 362
11.7 Future Aspects of Deep Learning in Cancer 363
11.8 Conclusion 363
References 363
12 Cardiovascular Disease Prediction Using Deep Neural Network for Older People 369Nagarjuna Telagam, B.Venkata Kranti and Nikhil Chandra Devarasetti
12.1 Introduction 370
12.2 Proposed System Model 375
12.2.1 Decision Tree Algorithm 375
12.2.1.1 Confusion Matrix 376
12.3 Random Forest Algorithm 381
12.4 Variable Importance for Random Forests 383
12.5 The Proposed Method Using a Deep Learning Model 384
12.5.1 Prevention of Overfitting 386
12.5.2 Batch Normalization 386
12.5.3 Dropout Technique 386
12.6 Results and Discussions 386
12.6.1 Linear Regression 386
12.6.2 Decision Tree Classifier 388
12.6.3 Voting Classifier 389
12.6.4 Bagging Classifier 389
12.6.5 Naïve Bayes 390
12.6.6 Logistic Regression 390
12.6.7 Extra Trees Classifier 391
12.6.8 K-Nearest Neighbor [KNN] Algorithm 391
12.6.9 Adaboost Classifier 392
12.6.10 Light Gradient Boost Classifier 393
12.6.11 Gradient Boosting Classifier 393
12.6.12 Stochastic Gradient Descent Algorithm 393
12.6.13 Linear Support Vector Classifier 394
12.6.14 Support Vector Machines 394
12.6.15 Gaussian Process Classification 395
12.6.16 Random Forest Classifier 395
12.7 Evaluation Metrics 396
12.8 Conclusion 401
References 402
13 Machine Learning: The Capabilities and Efficiency of Computers in Life Sciences 407Shalini Yadav, Saurav Yadav, Shobhit Prakash Srivastava, Saurabh Kumar Gupta and Sudhanshu Mishra
13.1 Introduction 408
13.2 Supervised Learning 410
13.2.1 Workflow of Supervised Learning 410
13.2.2 Decision Tree 410
13.2.3 Support Vector Machine (SVM) 411
13.2.4 Naive Bayes 413
13.3 Deep Learning: A New Era of Machine Learning 414
13.4 Deep Learning in Artificial Intelligence (AI) 416
13.5 Using ML to Enhance Preventive and Treatment Insights 417
13.6 Different Additional Emergent Machine Learning Uses 418
13.6.1 Education 418
13.6.2 Pharmaceuticals 419
13.6.3 Manufacturing 419
13.7 Machine Learning 419
13.7.1 Neuroscience Research Advancements 420
13.7.2 Finding Patterns in Astronomical Data 420
13.8 Ethical and Social Issues Raised ! ! ! 421
13.8.1 Reliability and Safety 421
13.8.2 Transparency and Accountability 421
13.8.3 Data Privacy and Security 421
13.8.4 Malicious Use of AI 422
13.8.5 Effects on Healthcare Professionals 422
13.9 Future of Machine Learning in Healthcare 422
13.9.1 A Better Patient Journey 422
13.9.2 New Ways to Deliver Care 424
13.10 Challenges and Hesitations 424
13.10.1 Not Overlord Assistant Intelligent 424
13.10.2 Issues with Unlabeled Data 425
13.11 Concluding Thoughts 425
Acknowledgments 426
References 426
Index 431
Dhanalekshmi Unnikrishnan Meenakshi1*, Selvasudha Nandakumar2, Arul Prakash Francis3, Pushpa Sweety4, Shivkanya Fuloria5, Neeraj Kumar Fuloria5, Vetriselvan Subramaniyan6 and Shah Alam Khan1┼
1College of Pharmacy, National University of Science and Technology, Muscat, Oman
2Department of Biotechnology, Pondicherry University, Puducherry, India
3Department of Biochemistry and Molecular Biology, Pondicherry University, Puducherry, India
4Anna University, BIT Campus, Tiruchirappalli, India
5Faculty of Pharmacy, AIMST University, Bedong, Malaysia
6Faculty of Medicine, Bioscience and Nursing, MAHSA University, Selangor, Malaysia
Site-specific drug delivery [SSDD] is a smart localized and targeted delivery system that is used to improve drug efficiency, decrease drug-related toxicity, and prolong the duration of action by having protected interaction between a drug and the diseased tissue. SSDD system in association with the computational approaches is employed in discovery, design, and development of drugs to improve treatment outcomes. Artificial intelligence [AI] networks and tools are playing a prominent role in developing pharmaceutical products by employing fundamental paradigms. Among many computational techniques, deep learning [DL] technology utilizes artificial neural networks [ANN], belongs to machine learning [ML] approach that holds the key to measuring and forecasting a drug's affinity for specific targets. It can reduce both cost and time by speeding up the drug development process rationally with careful decisions. DL is considered as the primary strategy to predict bioactivity as it shows improved performance compared with other technologies in the field. DL can assist in evaluating the success of a target-based drug design and development before the actual laboratory synthesis or production of the drug molecule. This chapter highlights the potential applications of DL in assigning a specific drug target site by predicting the structure of the target protein and drug affinity for a successful treatment. It also spotlights the impactful applications of many types of DL in SSDD and its advantages over conventional SSDD systems. Furthermore, some formulations that are intended to lead to the target or site-specific delivery and DL role in docking and pharmacokinetics profiling are also addressed. Ongoing challenges, skepticism about the likelihood of success, and the paths to overcome by future technological advancements are also dealt with briefly. Due emphasis is given to the use of DL in reducing the economic burden of pharmaceutical industries to overcome costly failures and in developing target specific new drug candidate[s] for a successful therapeutic regimen beneficial to human life.
Keywords: Site-specific, target, drug delivery, deep learning, machine learning, artificial intelligence, computational approach, precision medicine
Site-specific drug delivery (SSDD) is an almost a century-old strategy but successful delivery of drugs to the target site without producing off-site unwanted adverse effects has not been realized yet. Random testing assays in the traditional development of SSDD identify only 3% of compounds that warrant further laboratory tests, and hence, it is vital to explore the drug-target interactions for every single pharmaceutical molecule. Modern drug discovery, which includes identifying and preparing drug-molecular targets with precision, is emerging to fill traditional SSDD gaps. Target-specific drug delivery promotes the delivery of medications to target sites without creating unwanted side effects elsewhere. Despite numerous publications and attention paid to the site-specific delivery that promises to "deliver" the medicine at the diseased site, the generation of target-specific therapeutic products has still been a challenge for researchers [1]. The obstructions met during the drug formulation process are mainly associated with the inability to foresee the impact of the combination of active pharmaceutical ingredients [APIs] and materials on the formulation parameters. A new drug formulation development process and the associated procedures need to satisfy the site-specific delivery and release profile. Moreover, it is a laborious task and the protocols to perform in vitro characterizations or modifications to obtain the desired profile are difficult for the formulators [2]. To bridge the knowledge gap and reduce the time required for selecting the best molecule for drug development, researchers have devised computational modeling approaches like molecular dynamics simulations, docking studies [3], and cheminformatics [4]. These helps in the evaluation of novel insights about the complex drug delivery systems, especially in atomic/cellular scale which experimental techniques cannot provide [5-7]. A revolution in data science has been observed in the last decades due to the usage of the graphics processing unit [GPU]. A large volume of drug-related data and techniques were generated and analyzed using artificial intelligence [AI] to predict drug interaction with the diseased targets in drug discovery. AI networks and tools are playing a prominent role in the development of pharmaceutical products by employing fundamental paradigms. In medicinal chemistry, several computational methods contributed to designing new drug candidates by relating the drug candidate's physicochemical properties, biological activity, and binding affinity [8]. Machine learning [ML], the branch of AI, has gained importance in drug discovery protocols and has become the most attractive and prominent research areas. ML supports the advancement of effective formulation through data-driven predictions using experimental data. A well-designed ML technique can significantly speed up the optimization of formulations with reduced cost [9]. Knowledge acquisition about the molecular characteristics of lead molecules has been made with the help of ML techniques like partial least squares [PLS], k-nearest neighbors [kNN], and artificial neural networks [ANN] [10]. ANN is the most prevalent ML technique in formulation prediction [9, 10].
Among the various methodologies of AI, deep learning [DL] had gained significant attention in several areas because of its ability to extract features from data [11]. Leading pharmaceutical industries in collaboration with different AI organizations are trying to develop effective and ideal drug candidates in the field of oncology and CNS complications. In recent years, several trials involving the combination of nanotechnology and DL are underway to study their potential role in drug formulation with SSDD. The role of DL in drug development and manufacturing is depicted in Figure 1.1. DL methods are representation-learning techniques that can discover multiple-level representations of increasing complexity from the raw data using nonlinear models [12]. Several recent trials have connected nanotechnology and DL to study their potential role in drug formulation with site-specific drug delivery [SSDD]. DL can predict the probable drug carrier candidate through target-based drug designing and development. DL methods play a significant role in drug delivery by predicting (i) drug loading in the carrier, (ii) the enhancement in permeability through the body barriers, and choosing the stable drug delivery systems from different carriers and matrices [13].
Figure 1.1 Role of DL in drug development and manufacturing.
DL has proved to be an effective tool for virtual screening and predicting quantitative structure-activity relationships from large chemical libraries [14]. Golkov et al. reported that the DL is very useful in predicting the biological functions of several chemical compounds from the raw data based on their electronic arrangements [15]. A previous study on DL revealed that it has collected evidence from the vast amount of data sets related to the genome and utilized for drug repurposing and precise treatments [16]. Various DL models have been used to forecast interactions between protein-ligand, scoring docking poses, and virtual screenings. Thus, DL has been utilized to discover several endpoints in medicinal chemistry [17].
A study on predicting protein-ligand interactions using molecular fingerprints and protein sequences as vector input showed that the essential amino acid residues responsible for drug-target interactions were predicted using vectors obtained from the model [18]. A previous study by Lee et al. detailed a predictive model to represent the DeepConv-drug-target interactions [DTIs] in ligand-target complex. The predictive models were built using over 32,000 drug-target structures from the DrugBank, IUPHAR, and KEGG data sets. DNN outperforms similarity-based models and traditional protein representations, according to the findings [19]. For the prediction of novel DTIs between marketed medications and targets, Wen et al. used a successful DL method called deep belief network [DBN] and developed a methodology called DeepDTIs. This method was tested using an appropriate method and associated to suitable algorithms, such as random forest [RF], Bernoulli Naive Bayesian [BNB], and decision tree [DT]. Results showed that the algorithm used in this method...
Dateiformat: ePUBKopierschutz: Adobe-DRM (Digital Rights Management)
Systemvoraussetzungen:
Das Dateiformat ePUB ist sehr gut für Romane und Sachbücher geeignet – also für „fließenden” Text ohne komplexes Layout. Bei E-Readern oder Smartphones passt sich der Zeilen- und Seitenumbruch automatisch den kleinen Displays an. Mit Adobe-DRM wird hier ein „harter” Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.Bitte beachten Sie: Wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!
Weitere Informationen finden Sie in unserer E-Book Hilfe.
