Answering many of the questions in the field of cancer informatics (and in health care in general), often requires researchers to incorporate data from different sources. Typically, this is done by centralizing the data. In other words, data are brought to the where the algorithms are. Unfortunately, this brings several organizational, operational, political, and ethical challenges, such as loss of data control, logistics of data transmission, data governance, and protection of patient privacy.

Federated learning has emerged as a technology with the potential to overcome these limitations. In this case, we flip things around and we bring the algorithms to where the data are. For this purpose, at IKNL we have developed our open-source priVAcy preserviNg federaTed leArninG infrastructurE for Secure Insight eXchange – or VANTAGE6 for short.

Read More

As a teenager (and even during my years at college), I had a blast playing with the LEGO Mindstorms sets. One of them ones was the Droid Developer Kit (9748). Basically, it allowed you to build Star Wars droids and put them in action using the included Micro Scout (which included a motor, a light sensor, and seven built-in programs). I still have my original kit and with the Star Wars fever caused by The Mandalorian (and all the announced shows coming in the near future), I thought this Christmas break was the perfect occasion to jump back into this set.

Read More

Recently, I started getting into LEGO again. More interestingly, I started experimenting with Bricklink Studio (or Studio, in short), a great CAD tool for creating your own (virtual) models brick by brick. One of its best features is the wide variety of parts at your disposal. However, every now and then you can come across a part or two that aren’t registered in Studio’s catalogue, but that exist already as a model. This is especially true if you are using parts from very old sets. Fortunately, there is a way to add them and make them available for your creations.

Read More

Today, the version 0.2.0 of DeepSurvK is released!

Read More

I started working on my first Python package (which is far from ready, but I will definitely post about it when I have a version worth sharing). When trying to find resources of how to publish it to make it available for the community, I felt a bit overwhelmed. The setup for it to work properly involves a lot of individual files. These need to be in the right structure with the right content. As you can imagine, this is very prone to errors.

Read More

Recently, I migrated my personal website from Wordpress to GitHub Pages using Jekyll. After some trial and error, I managed to have everything up and running. However, Jekyll tagging (i.e., generating the pages that contain a collection of posts filtered by a tag) requires additional plugins which are not supported by GitHub Pages. Long Qian wrote a fantastic tutorial on how to implement this functionality with a Python script. Unfortunately, this still requires running the script, adding the files to the staging area, committing them, and pushing them to GitHub. That’s a lot of steps for every time that I want to add a new tag. Not only is it prone to errors, but let’s be honest: ain’t nobody got time for that.

Read More

Recently, I decided to move my website from Wordpress to a Jekyll and GitHub Pages. As you can see, my website is quite simple: a few posts and a couple of fixed pages. Jekyll and GitHub Pages make a very good job in accommodating my needs.

However, it can be a bit tricky setting up everything. In this post I would like to share a quick guide on how to set everything up.

Read More

Recently, I finished a personal project in which I analyzed the results of the “Who is your favorite Pokemon” survey. After that, I wanted to generate a more interactive visualization in which the user could choose a specific Pokemon and see its results. After pondering different options, I decided to do so in Bokeh because of a few reasons. First of all, you can generate your visualizations using Python only. Furthermore, it is very easy to incorporate Bokeh in Jupyter notebooks, which is great to generate a first version of the prototype. Lastly, a few colleagues of mine have used it for their projects at work and have been very happy with it.

Read More

Previously, I looked into Pokémon’s popularity from all 7 generations. However, I felt the visualizations were a bit static. Furthermore, you couldn’t get details on your preferred Pokémon. Therefore, I decided to extend this project and created an interactive dashboard using Bokeh and Binder to visualize the results of the survey. It allows you to choose whatever Pokémon you want and see its preference ranking compared to all Pokémon, compared to all Pokéon of its generation, and how did people voted for it in time during the period in which the survey was open (notice how the color of that plot corresponds to the Pokémon’s dominant color)

Read More

The newest entries of the Poké main series, Pokémon Sword and Pokémon Shield will be released later this year. However, the new generation of pocket monsters came with the news that you won’t be able to complete the national Pokédex. In other words, you won’t be able to capture all the Pokémon from previous 7 generations. In a series where “Gotta catch’em all” is its catch phrase, this caused a huge backslash by some members of the community. Their main argument was that “every Pokémon is someone’s favorite”. Is this actually true?

Read More