Table of Contents

Update 03_2019: forked and tried to translate to english. Corrections are welcome.

I added a little (2018.12.12). Since the web interface is likely to be beyond the scope of introductory, I will consider how to do it.

• AsciiDoc Syntax Quick Reference

01 Introduction

• What is chemoinformatics?

• What is RDKit?

• Target audience

• Acknowledgment

• License

02 Let’s prepare the environment for chemoinformatics

• Anaconda(Python, Jupyter, scikit-learn)

• RDKit

03 Basics of Python programming

• Python basics

• Let’s use it conveniently with Jupyter notebook

• To do machine learning with Python

04 Public database for chemoinformatics

• ChEMBL

• PubChem

• Search for the information you want on ChEMBL

05 Handling Structural Information with RDKit

• What is SMILES?

• Let’s draw the structure

• How to handle multiple compounds at once?

06 Try to evaluate the similarity of compounds

• Descriptor, fingerprint

• Calculate similarity

• Virtual screening

07 valuation of similarity using graph structure

• Classification by major skeleton (MCS)

• Compound Network by Matched Molecular Pair

• Visualize MMP networks using Cytoscape

08 I want to have many compounds at once

• Chemical Spaceとは

• Mapping using tSNE

09 Basics of Quantitative Structure-Activity Relationship (QSAR)

• Consider the cause of the effect (Classification problem)

• Predict the efficacy of drugs (regression problem)

• Model applicability (applicability domain)

10 Introduction to Deep-Learning

• About TensorFlow and Keras

• Google colab

• Let’s install

11 Structure-activity relationship using deep-learning

• Predictive model construction using DNN

• I will devise a descriptor (neural fingerprint)

12 Let the computer think about chemical structure

• Structure generation using Recurrent Neural Network

13 Conclusion

• Final remarks and further reading