szdziedzic / mldd23

The repository for the course "Machine Learning in Drug Design" taught at the Jagiellonian University in 2023. The page is hosted by the machine learning research group GMUM.

Machine Learning in Drug Design (2023)

This repository contains course materials for the course "Machine Learning in Drug Design." In the labs directory, there are materials covering the following topics:

1. Python and machine learning basics (revision)
   • Textual representations of molecules: SMILES
   • Vector representations of molecules: descriptors and fingerprints
   • Introduction to RDKit
   • Classical ML models: Linear Regression, Random Forest, Support Vector Machines
2. ???

About us

GMUM (Machine Learning Research Group) is a group at the Jagiellonian University working on various aspects of machine learning, and in particular deep learning - in both fundamental and applied settings. The group is led by prof. Jacek Tabor.

Some of the research directions our group pursues include:

• generative models: efficient training and sampling; inpainting; super-resolution,
• theoretical understanding of deep learning and optimization,
• natural language processing,
• drug design and cheminformatics,
• unsupervised learning and clustering,
• computer vision and medical image analysis.

We are hosting machine learning seminars that are open to the public. You can check the schedule on our website and join online (links posted on our Facebook). You can also add seminar info to your Google calendar.

Environment Setup

Python will be used throughout the course. The environment setup steps are shown below:

1. Install miniconda following the instructions for your operating system.
2. Download this repository: git clone https://github.com/gmum/mldd23.git.
   • You need to have Git installed.
3. Install environment from the YAML file: conda env create -f environment.yml (or conda env create -f environment-gpu.yml for the GPU version).

In the environments directory, you can find environment files with the exact versions of packages for each operating system (including a GPU environment for Windows).

Important! If you would like to use your GPU to train neural networks, update the line pytorch-cuda={cuda version} in the environment-gpu.yml file. The current CUDA version is 11.7, but you should check your graphics card compatibility first.

Literature

???