In this course, CH485 - Artificial Intelligence and Chemistry, we will learn data science for chemistry. After successfully finishing this course, students could be confident in their ability to understand and implement AI models for chemical/molecular applications.
This repository is managed by Seongok Ryu, and lecture notes/example codes about contents treated in the class will be uploaded.
- Practice 01 : Introduction / Linear & Logistic Regression
- Practice 02 : Support Vector Machine (SVM)
- Practice 03 : Multi-layer perception (MLP), activation functions (sigmoid, tanh, ReLU, ...)
- Practice 04 : Application of convolutional neural networks (CNN) on SMILES - learning molecular properties
- Practice 05 : Application of graph convolutional network (GCN) on molecular graph - learning molecular properties
- Practice 06 : Application of recurrent neural networks (RNN) on SMILES - learning molecular properties
- Practice 07 : Application of gated graph neural network (GGNN) on molecular graph - learning molecular properties
- Practice 08 : Variational autoencoder (VAE) and conditional variational autoencoder (CVAE) for molecular design
- Practice 09 : Molecular design from continuous latent space
- Practice 10 : Molecular design with graph generative models