“Having Cas join as one of the first of our team has been a true joy! Both on a personal and professional level. For someone just starting his professional career he has exceptional skill in navigating complex problems, finding solutions and getting things done. He adapts to any changing team situation easily and effortlessly to keep adding value on a continuous basis. Hopefully our paths will cross again, and it goes without saying that I would highly recommend Cas for any team!”
About
I am an independent, inherently curious and perfectionistic student that strives to collaborate with an inspiring group of like-minded people on projects that I am proud of. Within a team where people treat each other as equals, I want to be challenged and use all of my capacities to have a positive effect on society. I have become fascinated by the mystery that the human mind proves to be and by the possibilities the field of artificial intelligence promises.
Activity
-
One of the harder issues we had to solve in building Cradle was to bring together a team of people from two very complex disciplines and get them to…
One of the harder issues we had to solve in building Cradle was to bring together a team of people from two very complex disciplines and get them to…
Liked by Cas Wognum
-
Such a pleasure to attend and present at the MDAnalysis 2024 UGM! Fantastic to see the next generation of computational molecular scientists making…
Such a pleasure to attend and present at the MDAnalysis 2024 UGM! Fantastic to see the next generation of computational molecular scientists making…
Liked by Cas Wognum
-
If curating drug discovery-related data bores you, try Auroris. We’re making it simple, easy, and potentially… fun 😅 All it takes is a few lines of…
If curating drug discovery-related data bores you, try Auroris. We’re making it simple, easy, and potentially… fun 😅 All it takes is a few lines of…
Liked by Cas Wognum
Experience
Education
-
-
-
Activities and Societies: Honours Double Master's Programme
Learnt a multi-disciplinary and history view of Artificial Intelligence, while remaining up-to-date with the latest developments in the field.
-
-
By studying computer science, I did not only become a more skilled programmer, but I also gained a deep understanding of how computers operate and learned to effectively design and work on large-scale software projects. The covered topics range from logic to operating systems and from data structures to computer graphics. I am proud to say that I never needed a resit and that I received my diploma cum laude. Within the curriculum, there is a lot of emphasis on practical group work, like…
By studying computer science, I did not only become a more skilled programmer, but I also gained a deep understanding of how computers operate and learned to effectively design and work on large-scale software projects. The covered topics range from logic to operating systems and from data structures to computer graphics. I am proud to say that I never needed a resit and that I received my diploma cum laude. Within the curriculum, there is a lot of emphasis on practical group work, like creating a taxi-scheduling algorithm and an artificial intelligence playing the game of draughts.
-
-
Extra mathematics certificate to answer to the prerequisites of studying computer science
-
-
Licenses & Certifications
Publications
-
Real-World Molecular Out-Of-Distribution: Specification and Investigation
Journal of Chemical Information and Modeling
This study presents a rigorous framework for investigating molecular out-of-distribution (MOOD) generalization in drug discovery. The concept of MOOD is first clarified through a problem specification that demonstrates how the covariate shifts encountered during real-world deployment can be characterized by the distribution of sample distances to the training set. We find that these shifts can cause performance to drop by up to 60% and uncertainty calibration by up to 40%. This leads us to…
This study presents a rigorous framework for investigating molecular out-of-distribution (MOOD) generalization in drug discovery. The concept of MOOD is first clarified through a problem specification that demonstrates how the covariate shifts encountered during real-world deployment can be characterized by the distribution of sample distances to the training set. We find that these shifts can cause performance to drop by up to 60% and uncertainty calibration by up to 40%. This leads us to propose a splitting protocol that aims to close the gap between the deployment and testing. Then, using this protocol, a thorough investigation is conducted to assess the impact of model design, model selection, and data set characteristics on MOOD performance and uncertainty calibration. We find that appropriate representations and algorithms with built-in uncertainty estimation are crucial to improving performance and uncertainty calibration. This study sets itself apart by its exhaustiveness and opens an exciting avenue to benchmark meaningful algorithmic progress in molecular scoring.
Projects
-
Sukkel voor de Liefde (short film)
In 30 dagen een film maken, dat was de uitdaging! 'Sukkel voor de Liefde' het resultaat! Ik ben ontzettend trots op alle cast en crewleden. We hebben een geweldig resultaat geleverd en zijn dan ook beloond met 'Het Gouden Kussen' en een gigantisch aantal views en lovend commentaar op Youtube.
Steven de Jong (bekend Nederlands regisseur):
"Super gemotiveerd, jong en talentvol! Fijne gasten die Cas en naamgenoot Steven... Daar gaan we nog flink van horen!"Other creatorsSee project -
Océ Exhibit
-
Oce, a Canon company, is a Dutch company that manufactures and develops large and complex printing systems for industrial printing. To optimize their systems and to analyze errors, Océ uses data analysis. As Océ generates huge amounts of data that are near impossible to manually interpret, our team was tasked with the creation of Exhibit: A web-based, 3D visualization platform for print system models and simulators. Exhibit is a tool that imports the generated data and gives precise statistics…
Oce, a Canon company, is a Dutch company that manufactures and develops large and complex printing systems for industrial printing. To optimize their systems and to analyze errors, Océ uses data analysis. As Océ generates huge amounts of data that are near impossible to manually interpret, our team was tasked with the creation of Exhibit: A web-based, 3D visualization platform for print system models and simulators. Exhibit is a tool that imports the generated data and gives precise statistics alongside an intuitive visualization.
Exhibit was developed as part of the Bachelor end project, which aims to give students at the Technical University of Eindhoven real-life experience with the development of large-scale software applications. Exhibit was developed with a team of twelve students and in close collaboration with the client using the agile methodology to increase customer satisfaction. A high code quality was enforced by using the continuous integration methodology. The entire process was properly documented via a total of 7 documents: The user requirements document, the software requirements document, the architectural design document, the acceptance test plan, the unit test plan, the software transfer document and the software user manual.Other creators -
Dungeons and Drawings (game)
-
For a course at the Technical University of Eindhoven, I was part of a team of 6 that designed their own game engine and a game on top of it from the ground up in just 10 weeks, using Java en OpenGL
Other creatorsSee project
Honors & Awards
-
Het Gouden Kussen
Sense.info
Steven Kramer en ik wonnen het Gouden Kussen met onze film 'Sukkel voor de Liefde', onderdeel van de campagne 'Maak seks lekker duidelijk'. Het juryrapport las:
"De makers van deze film laten heel goed zien waarom het moeilijk is om je eigen grenzen te blijven stellen als je verliefd bent. De relatie tussen de twee hoofdpersonen is heel herkenbaar voor veel jongeren. Overtuigend is verbeeld dat in veel situaties van grensoverschrijding er geen sprake is van een bewuste dader. Daarmee is…Steven Kramer en ik wonnen het Gouden Kussen met onze film 'Sukkel voor de Liefde', onderdeel van de campagne 'Maak seks lekker duidelijk'. Het juryrapport las:
"De makers van deze film laten heel goed zien waarom het moeilijk is om je eigen grenzen te blijven stellen als je verliefd bent. De relatie tussen de twee hoofdpersonen is heel herkenbaar voor veel jongeren. Overtuigend is verbeeld dat in veel situaties van grensoverschrijding er geen sprake is van een bewuste dader. Daarmee is het bijzonder goed gelukt om onze boodschap - wees duidelijk over je wensen en grenzen als het over seks gaat - heel dichtbij te brengen."
Languages
-
Nederlands
Native or bilingual proficiency
-
Engels
Native or bilingual proficiency
-
Frans
Limited working proficiency
Recommendations received
11 people have recommended Cas
Join now to viewMore activity by Cas
-
Here's a combo you should try if you want to upload a dataset to Polaris. (1) Use Auroris for data curation (2) Upload your notebook to Polaris…
Here's a combo you should try if you want to upload a dataset to Polaris. (1) Use Auroris for data curation (2) Upload your notebook to Polaris…
Liked by Cas Wognum
-
To help promote transparency reproducibility in data curation, we’re introducing Polaris Recipes! We want to make the ingredients (data sources)…
To help promote transparency reproducibility in data curation, we’re introducing Polaris Recipes! We want to make the ingredients (data sources)…
Liked by Cas Wognum
-
Excited to present joint work with Doree Sitkoff and team at #acsfall2024. If you are around on Monday you should stop by! (Monday, 2:30pm, room…
Excited to present joint work with Doree Sitkoff and team at #acsfall2024. If you are around on Monday you should stop by! (Monday, 2:30pm, room…
Liked by Cas Wognum
-
It shouldn't take more than a few lines of code to access datasets and benchmarks on Polaris. We're still improving the library and API but would…
It shouldn't take more than a few lines of code to access datasets and benchmarks on Polaris. We're still improving the library and API but would…
Liked by Cas Wognum
-
If you’re working at the intersection of ML and drug discovery, you’ve got enough problems on your plate. That’s why we want to make it as simple as…
If you’re working at the intersection of ML and drug discovery, you’ve got enough problems on your plate. That’s why we want to make it as simple as…
Liked by Cas Wognum
-
Here's a cool preprint (with code) from Ramon Miranda Quintana's group on a very fast method for clustering large chemical datasets. Using their…
Here's a cool preprint (with code) from Ramon Miranda Quintana's group on a very fast method for clustering large chemical datasets. Using their…
Liked by Cas Wognum
-
Here’s Cas Wognum talking a bit more about Polaris and our roadmap at MoML 2024. https://lnkd.in/ggTpKSWU ⚙️ Currently in the works: hosting…
Here’s Cas Wognum talking a bit more about Polaris and our roadmap at MoML 2024. https://lnkd.in/ggTpKSWU ⚙️ Currently in the works: hosting…
Liked by Cas Wognum
-
Excited to share our new paper on Contextual AI models for context-specific prediction in biology in Nature Methods led by a stellar student Michelle…
Excited to share our new paper on Contextual AI models for context-specific prediction in biology in Nature Methods led by a stellar student Michelle…
Liked by Cas Wognum
-
Let’s talk about data curation. Fun? 🤷 Important? Yes 🫡 High-quality, well-curated datasets are the foundation which we can build realistic…
Let’s talk about data curation. Fun? 🤷 Important? Yes 🫡 High-quality, well-curated datasets are the foundation which we can build realistic…
Liked by Cas Wognum
-
🎥 MoML recordings are out now! Learn more about AlphaFold 3, benchmarking in drug discovery, exploring combinatorial perturbations, molecular…
🎥 MoML recordings are out now! Learn more about AlphaFold 3, benchmarking in drug discovery, exploring combinatorial perturbations, molecular…
Liked by Cas Wognum
-
I'm very proud of the work we're doing Polaris - Benchmarks for methods that matter and I'm excited to finally share it publicly! Polaris is built…
I'm very proud of the work we're doing Polaris - Benchmarks for methods that matter and I'm excited to finally share it publicly! Polaris is built…
Shared by Cas Wognum
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More