Deep Learning for Life Sciences

May 9, 2019

9:00 am - 17:00 pm

Instructors: Matthijs Moed (SURFsara)

Helpers: Carlos Teijeiro Barjas (SURFsara), Haukur-Páll Jónsson (SURFsara)

Syllabus

Deep learning has become a really hot topic for different areas of research in order to extract information and correlations between huge amounts of data that are otherwise very difficult or even effectively impossible to process in a purely analytic way. This workshop will begin with a morning session that will be presenting an overview of machine learning techniques, and later on introducing the basics concepts needed to understand artificial neural networks. The afternoon session will be eminently practical and applied to life sciences. You may be able to learn the basic use of tools for image processing and tune the results of your neural network to achieve your goals. The hands-on exercises will be performed using the Python programming language in a Jupyter notebook.

Schedule

Day 1

09:00 - 09:30 Introduction to deep learning in life sciences
09:30 - 10:15 Your first neural network
10:15 - 10:30 Morning break
10:30 - 11:00 Deep learning's knobs and dials
11:00 - 12:00 Improving your network - hyperparameter tuning
12:00 - 13:00 Lunch break
13:00 - 13:30 Convolutional neural networks
13:30 - 14:30 Your first convolutional neural network
14:30 - 14:45 Afternoon break
14:45 - 15:15 Interpreting deep learning models and results
15:15 - 16:15 Inspecting a convolutional neural network
16:15 - 17:00 Consultancy time: discuss your own problem!

General Information

Who: The course is aimed at graduate students and other researchers, particularly from life sciences, who would like to know how the different deep learning techniques can be applied to their everyday work. No other experience is strictly necessary, but some affinity with general programming or scripting may be useful.

Where: SURF Utrecht. Kantoren Hoog Overborch (Hoog Catharijne), Moreelsepark 48, room 3.5, 3511 EP Utrecht. Get directions with OpenStreetMap or Google Maps.

When: May 9, 2019. Add to your Google Calendar.

Requirements: Participants must bring a laptop with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.).

Contact: Please email mateusz.kuzak@dtls.nl or carlos.teijeiro@surfsara.nl for more information.

Sponsors

This workshop is sponsored and supported by ELIXIR-EXCELERATE. ELIXIR-EXCELERATE is funded by the European Commission within the Research Infrastructures programme of Horizon 2020, grant agreement number 676559.

EXCELERATE

Survey

Post workshop survey

Setup

During this workshop you will be granted access to the computing facilities of SURFsara. In order to use them, you will need an up-to-date web browser in your own laptop. Additionally, it is highly recommended that your laptop has access to the software described below.

The Bash Shell

Bash is a commonly-used shell that gives you the power to do simple tasks more quickly.

Video Tutorial
  1. Download the Git for Windows installer.
  2. Run the installer and follow the steps below:
    1. Click on "Next" four times (two times if you've previously installed Git). You don't need to change anything in the Information, location, components, and start menu screens.
    2. Select “Use the nano editor by default” and click on “Next”.
    3. Keep "Use Git from the Windows Command Prompt" selected and click on "Next". If you forgot to do this programs that you need for the workshop will not work properly. If this happens rerun the installer and select the appropriate option.
    4. Click on "Next".
    5. Keep "Checkout Windows-style, commit Unix-style line endings" selected and click on "Next".
    6. Select "Use Windows' default console window" and click on "Next".
    7. Click on "Install".
    8. Click on "Finish".
  3. If your "HOME" environment variable is not set (or you don't know what this is):
    1. Open command prompt (Open Start Menu then type cmd and press [Enter])
    2. Type the following line into the command prompt window exactly as shown:

      setx HOME "%USERPROFILE%"

    3. Press [Enter], you should see SUCCESS: Specified value was saved.
    4. Quit command prompt by typing exit then pressing [Enter]

This will provide you with both Git and Bash in the Git Bash program.

The default shell in all versions of macOS is Bash, so no need to install anything. You access Bash from the Terminal (found in /Applications/Utilities). See the Git installation video tutorial for an example on how to open the Terminal. You may want to keep Terminal in your dock for this workshop.

The default shell is usually Bash, but if your machine is set up differently you can run it by opening a terminal and typing bash. There is no need to install anything.

Text Editor

When you're writing code, it's nice to have a text editor that is optimized for writing code, with features like automatic color-coding of key words. The default text editor on macOS and Linux is usually set to Vim, which is not famous for being intuitive. If you accidentally find yourself stuck in it, hit the Esc key, followed by :+Q+! (colon, lower-case 'q', exclamation mark), then hitting Return to return to the shell.

nano is a basic editor and the default that instructors use in the workshop. It is installed along with Git.

Others editors that you can use are Notepad++ or Sublime Text. Be aware that you must add its installation directory to your system path. Please ask your instructor to help you do this.

nano is a basic editor and the default that instructors use in the workshop. See the Git installation video tutorial for an example on how to open nano. It should be pre-installed.

Others editors that you can use are BBEdit or Sublime Text.

nano is a basic editor and the default that instructors use in the workshop. It should be pre-installed.

Others editors that you can use are Gedit, Kate or Sublime Text.

Python

Python is a popular language for research computing, and great for general-purpose programming as well. Installing all of its research packages individually can be a bit difficult, so we recommend Anaconda, an all-in-one installer.

Regardless of how you choose to install it, please make sure you install Python version 3.x (e.g., 3.6 is fine).

We will be running Python code using the Jupyter notebook, a programming environment that runs in a web browser. For this to work you will need a reasonably up-to-date browser. The current versions of the Chrome, Safari and Firefox browsers are all supported (some older browsers, including Internet Explorer version 9 and below, are not).

  1. Open https://www.anaconda.com/download/#linux with your web browser.
  2. Download the Python 3 installer for Linux.
    (The installation requires using the shell. If you aren't comfortable doing the installation yourself stop here and request help at the workshop.)
  3. Open a terminal window.
  4. Type 
    bash Anaconda3-
    and then press Tab. The name of the file you just downloaded should appear. If it does not, navigate to the folder where you downloaded the file, for example with: 
    cd Downloads
    Then, try again.
  5. Press Return. You will follow the text-only prompts. To move through the text, press Spacebar. Type yes and press enter to approve the license. Press enter to approve the default location for the files. Type yes and press enter to prepend Anaconda to your PATH (this makes the Anaconda distribution the default Python).
  6. Close the terminal window.