sing-group / master-bioinformatica-aplicada-2022-2023

Machine Learning in Bioinformatics class at the "Máster en Bioinformática Aplicada a Medicina Personalizada y Salud (Curso 2022-2023)"

Machine Learning in Bioinformatics

Máster en Bioinformática Aplicada a Medicina Personalizada y Salud (Curso 2022-2023)

Scheduling

First week (1-3 March 2023)

• Day 1 (01.03.2023):
  • 1/2 Theory
  • 1/2 Practice: Setting up the environment for the Hands-On practice sessions
• Day 2 (02.03.2022):
  • 1/2 Theory
  • 1/2 Theory: presentation of a real case-study (the PolyDeep project)
• Day 3 (03.03.2022):
  • 1/2 Theory
  • 1/2 Project: Session I (project presentation and creation of work groups)

Second week (13-17 March 2023)

• Day 4 (13.03.2023):
  • Practice: Hands-On (Machine Learning Basics in Python with scikit-learn Part I)
• Day 5 (14.03.2023):
  • Practice: Hands-On (Machine Learning Basics in Python with scikit-learn Part II)
• Day 6 (15.03.2023):
  • 1/2 Theory
  • 1/2 Project: Session II (with problem and dataset presentation)
• Day 7 (16.03.2023):
  • Project: Session III
• Day 8 (17.03.2023):
  • Project Session: IV (with results presentation)

Theory

The theory slides are available here.

Practice

Install Docker in your system

Follow the steps in the official page to install Docker https://docs.docker.com/engine/install/ubuntu/

Make sure the docker user group exists.

sudo groupadd docker

Add your user to the docker group.

sudo usermod -aG docker $USER

Reboot the system and the changes will be applied.

Pulling the Docker images

Run the following comands to pull the Docker image for the hands-on practice sessions:

docker pull singgroup/jupyter-machine-learning:2022-2023

During the hands-on sessions (Machine Learning Basics in Python with scikit-learn), we are going to use the Breast Cancer Data available at the UCI Machine Learning Repository. More information about this dataset can be found here and here.

Go to an empty folder and run the following commands to download the data:

mkdir data

wget https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data -O data/wdbc.data

sed -i '1iid,diagnosis,radius_mean,texture_mean,perimeter_mean,area_mean,smoothness_mean,compactness_mean,concavity_mean,concave points_mean,symmetry_mean,fractal_dimension_mean,radius_se,texture_se,perimeter_se,area_se,smoothness_se,compactness_se,concavity_se,concave_points_se,symmetry_se,fractal_dimension_se,radius_worst,texture_worst,perimeter_worst,area_worst,smoothness_worst,compactness_worst,concavity_worst,concave points_worst,symmetry_worst,fractal_dimension_worst' data/wdbc.data

Alternatively, the file is also available here.

Clone or download this repository and then run the following command (from the local repository) to use the Docker image to start a Jupyter notebook with the required libraries already installed:

docker run --rm -p 8888:8888 -v "$(pwd)":"$(pwd)" -w "$(pwd)" singgroup/jupyter-machine-learning:2022-2023

The resources/notebook-ml-1.ipynb file contains the notebook to develop during these sessions.

Project

The information about the project is available here.

References

• Practical Statistics for Data Scientists: 50 Essential Concepts
• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition

Additional Resources

• Ten quick tips for machine learning in computational biology [10.1186/s13040-017-0155-3]
• LIBSVM -- A Library for Support Vector Machines
• scikit-learn: machine learning in Python