Data Science in Chemistry: Artificial Intelligence, Big Data, Chemometrics and Quantum Computing with Jupyter

Thorsten Gressling

Published by De Gruyter 2021

Data Science in Chemistry

Artificial Intelligence, Big Data, Chemometrics and Quantum Computing with Jupyter

Thorsten Gressling

In the series De Gruyter Textbook

https://doi.org/10.1515/9783110629453

Overview
Contents

About this book

The ever-growing wealth of information has led to the emergence of a fourth paradigm of science. This new field of activity – data science – includes computer science, mathematics and a given specialist domain. This book focuses on chemistry, explaining how to use data science for deep insights and take chemical research and engineering to the next level. It covers modern aspects like Big Data, Artificial Intelligence and Quantum computing.

A uniquely concise introduction for chemists looking to tap the potential of data science.
Contains numerous working examples in Jupyter.

Author / Editor information

Dr. Gressling received his PhD in solid-state and theoretical chemistry from Kiel University in 1996. After three decades of working in software development and the emerging field of data science, he is now employed as Business Leader Artificial Intelligence at the software consultancy ARS.

Topics

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

(Deutsch)

Language: English
Publisher: De Gruyter
Audience: Students and educators in Chemistry or Chemical Engineering; scientists looking to harness data to advance their research.
Pages
- Front matter: 18
- Main content: 522
Illustrations
- Illustrations: 19
- Coloured Illustrations: 105
- Tables: 1
Keywords: Massendaten; Künstliche Intelligenz; Theoretische Chemie

eBook

Published: November 23, 2020
ISBN: 9783110629453

Paperback

Published: November 23, 2020
ISBN: 9783110629392