80 DeepChem: binding affinity

Kapitel in diesem Buch

1. Frontmatter I
2. Preface V
3. Contents VII
4. Introduction XIII
5. Technical setup and naming conventions XV
6. 1 Data science: introduction 1
7. 2 Data science: the “fourth paradigm” of science 4
8. 3 Relations to other domains and cheminformatics 8
9. Part A: IT, data science, and AI
10. IT basics (cloud, REST, edge)
11. 4 Cheminformatics application landscape 13
12. 5 Cloud, fog, and AI runtime environments 15
13. 6 DevOps, DataOps, and MLOps 19
14. 7 High-performance computing (HPC) and cluster 23
15. 8 REST and MQTT 28
16. 9 Edge devices and IoT 34
17. Programming
18. 10 Python and other programming languages 41
19. 11 Python standard libraries and Conda 45
20. 12 IDE’s and workflows 55
21. 13 Jupyter notebooks 61
22. 14 Working with notebooks and extensions 68
23. 15 Notebooks and Python 73
24. 16 Versioning code and Jupyter notebooks 80
25. 17 Integration of Knime and Excel 83
26. Data engineering
27. 18 Big data 91
28. 19 Jupyter and Spark 96
29. 20 Files: structure representations 102
30. 21 Files: other formats 106
31. 22 Data retrieval and processing: ETL 111
32. 23 Data pipelines 114
33. 24 Data ingestion: online data sources 117
34. 25 Designing databases 125
35. 26 Data science workflow and chemical descriptors 130
36. Data science as field of activity
37. 27 Community and competitions 139
38. 28 Data science libraries 143
39. 29 Deep learning libraries 145
40. 30 ML model sources and marketplaces 148
41. 31 Model metrics: MLFlow and Ludwig 152
42. Introduction to ML and AI
43. 32 First generation (logic and symbols) 161
44. 33 Second generation (shallow models) 164
45. 34 Second generation: regression 170
46. 35 Decision trees 179
47. 36 Second generation: classification 182
48. 37 Second generation: clustering and dimensionality reduction 190
49. 38 Third generation: deep learning models (ANN) 196
50. 39 Third generation: SNN – spiking neural networks 204
51. 40 xAI: eXplainable AI 206
52. Part B: Jupyter in cheminformatics
53. Physical chemistry
54. 41 Crystallographic data 213
55. 42 Crystallographic calculations 215
56. 43 Chemical kinetics and thermochemistry 219
57. 44 Reaction paths and mixtures 223
58. 45 The periodic table of elements 227
59. 46 Applied thermodynamics 230
60. Material science
61. 47 Material informatics 235
62. 48 Molecular dynamics workflows 237
63. 49 Molecular mechanics 241
64. 50 VASP 245
65. 51 Gaussian (ASE) 249
66. 52 GROMACS 251
67. 53 AMBER, NAMD, and LAMMPS 255
68. 54 Featurize materials 261
69. 55 ASE and NWChem 266
70. Organic chemistry
71. 56 Visualization 273
72. 57 Molecules handling and normalization 280
73. 58 Features and 2D descriptors (of carbon compounds) 287
74. 59 Working with molecules and reactions 294
75. 60 Fingerprint descriptors (1D) 299
76. 61 Similarities 306
77. Engineering, laboratory, and production
78. 62 Laboratory: SILA and AnIML 313
79. 63 Laboratory: LIMS and daily calculations 319
80. 64 Laboratory: robotics and cognitive assistance 325
81. 65 Chemical engineering 330
82. 66 Reactors, process flow, and systems analysis 334
83. 67 Production: PLC and OPC/UA 338
84. 68 Production: predictive maintenance 342
85. Part C: Data science
86. Data engineering in analytic chemistry
87. 69 Titration and calorimetry 349
88. 70 NMR 352
89. 71 X-ray-based characterization: XAS, XRD, and EDX 354
90. 72 Mass spectroscopy 359
91. 73 TGA, DTG 361
92. 74 IR and Raman spectroscopy 364
93. 75 AFM and thermogram analysis 368
94. 76 Gas chromatography-mass spectrometry (GC-MS) 373
95. Applied data science and chemometrics
96. 77 SVD chemometrics example 379
97. 78 Principal component analysis (PCA) 383
98. 79 QSAR: quantitative structure–activity relationship 386
99. 80 DeepChem: binding affinity 389
100. 81 Stoichiometry and reaction balancing 393
101. Applied artificial intelligence
102. 82 ML Python libraries in chemistry 399
103. 83 AI in drug design 405
104. 84 Automated machine learning 409
105. 85 Retrosynthesis and reaction prediction 412
106. 86 ChemML 419
107. 87 AI in material design 423
108. Knowledge and information
109. 88 Ontologies and inferencing 429
110. 89 Analyzing networks 436
111. 90 Knowledge ingestion: labeling and optical recognition 443
112. 91 Content mining and knowledge graphs 450
113. Part D: Quantum computing and chemistry Introduction
114. 92 Quantum concepts 461
115. 93 QComp: technology vendors 471
116. 94 Quantum computing simulators 477
117. 95 Quantum algorithms 480
118. 96 Quantum chemistry software (QChem) 485
119. Quantum Computing Applications
120. 97 Application examples 491
121. 98 Simulating molecules using VQE 495
122. 99 Studies on small clusters of LiH, BeH₂, and NaH 500
123. 100 Quantum machine learning (QAI) 504
124. Code index 511
125. Index 519