This repository contains course materials for the course "Machine Learning in Drug Design." In the labs directory, there are materials covering the following topics:
- 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
- ???
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.
Python will be used throughout the course. The environment setup steps are shown below:
- Install miniconda following the instructions for your operating system.
- Download this repository:
git clone https://github.com/gmum/mldd25.git.- You need to have Git installed.
- Install environment from the YAML file:
conda env create -f environment.yml.
Important! If you would like to use your GPU to train neural networks, add the line pytorch-cuda={cuda version} in the environment.yml file. The current CUDA version is 12.1, but you should check your graphics card compatibility first.
The final course grade is equal to the project grade, if the laboratories have been passed.
The laboratory grade is based on the assignments turned in. Class attendance is mandatory and two unexcused absences are allowed. More unexcused absences will result in failing the course (NZAL).
| percentage | grade |
|---|---|
| >90% | 5 |
| >80% | 4.5 |
| >70% | 4 |
| >60% | 3.5 |
| >50% | 3 |
| ≤50% | 2 |
Automatic grader available at mldd.matinf.uj.edu.pl