Derek van Tilborg (@DerekvTilborg) header
Derek van Tilborg (@DerekvTilborg) profile picture

Derek van Tilborg

@DerekvTilborg

PhD candidate in molecular fortune telling @TUeindhoven 🇳🇱 - @molecularML. Follow me on BlueSky: https://xitter.gq/t.co/BPTUmQWs31

 The Netherlands
Joined September 2018
  • Tweets98
  • Following485
  • Followers662
17Media
Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)Photo by Derek van Tilborg (@DerekvTilborg)
Happy to finally share our latest paper on active deep learning in low-data drug discovery in @NatComputSci! We tried to answer some open questions to get ready for prospective application 🧵👇 #AI #chemistry #drugdiscovery @fra_grisoni @molecularML rdcu.be/dViua
Image from Derek van Tilborg (@DerekvTilborg)
3
10
3
71
9,135
We just preprinted a fresh study on molecular machine learning on OOD molecules 🧠 Using joint modeling, we could detect distribution shifts, estimate prediction reliability, and capture meaningful molecular patterns! doi.org/10.26434/chemrxiv-20… #AI #chemistry @molecularML
Image from Derek van Tilborg (@DerekvTilborg)
4
5
33
1,934
I have moved to bluer pastures. Follow me at BlueSky at derekvtilborg.bsky.social
99
I want to delete my twitter account because of the Muskonian nature of this platform. What is the best alternative medium to stay in touch with the scientific community?
1
303
Derek van Tilborg retweeted
Andrea Gardin (@agardinon) profile picture
Andrea Gardin@agardinon4 Dec 2024
🚨Excited to share our new preprint: "Automated navigation of condensate phase behavior with active machine learning" doi.org/10.26434/chemrxiv-20… @fra_grisoni @molecularML In collaboration with: Luc Brunsveld & Jan van Hest groups! #MachineLearning #PhaseSeparation #automation 👇
Image from Andrea Gardin (@agardinon)
2
8
2
28
3,674
A must read if you're doing molecular machine learning chemrxiv.org/engage/chemrxiv…

Practically significant method comparison protocols for machine learning in small molecule drug...

Machine Learning (ML) methods that relate molecular structure to properties are frequently proposed as in-silico surrogates for expensive or time-consuming experiments. In small molecule drug...

chemrxiv.org
1
5
4,048
A good read on the perceived success of molecular machine learning. Don't forget your statistical tests guys! nature.com/articles/s42256-0…
2
7
454
Derek van Tilborg retweeted
Francesca Grisoni (@fra_grisoni) profile picture
Francesca Grisoni@fra_grisoni3 Oct 2024
📢 JOB ALERT 📢 My team @molecularML is searching for a #postdoc with a background in medicinal chemistry! 👩‍🔬👨‍🔬🧪 Do you have the experience? Are you eager to contribute to #AI for discovering new drugs? 👉Then DM me! Funded by @ERC_Research and located at @TUeindhoven 🚀
Image from Francesca Grisoni (@fra_grisoni)
1
45
2
95
9,727
We also played with the molecular diversity of the start data. We found that it doesn't really matter! Even if you start out with very low molecular diversity, you will quickly get rid of it with active learning (a) compared to a control method (b).
Image from Derek van Tilborg (@DerekvTilborg)
1
1
5
260
We end the paper with some guidelines that came out of our systematic analysis. 1. Active learning will find you more hits, but you need to do several rounds of it 2. The acquisition method is by far the most important 3. ECFPs > GNNs 4. Biased start data isn't too problematic
1
6
286
De novo drug design was getting stale until @Rza_ozcelik came along with state space models to spice it up. Even though I'm totally biased, I think its really well done work :)
Rıza Özçelik (@Rza_ozcelik) profile pictureRıza Özçelik@Rza_ozcelik25 Jul 2024
🥳🥳I'm thrilled that our work that introduces the state space models (SSMs) into de novo design is now published at @NatureComms 🎉 🎉 nature.com/articles/s41467-0… w/ Sarah de Ruiter, Emanuele Criscuolo, and @fra_grisoni @molecularML
Chemical language modeling with structured state space sequence models

Chemical language modeling with structured state space sequence models

Nature Communications - Artificial Intelligence (AI) is accelerating drug discovery. Here the authors introduce a new approach to de novo molecule design - structured state space sequence models -...

nature.com
3
361
Playing with #AI is nice, but applying it is the real deal! Within 3 cycles, we optimized nanoparticle uptake in cancer cells by almost 15 fold. Cool for drug delivery, but mostly a lot of fun🧪 @AnaOrPe_ @rvdmnanomeds @fra_grisoni @Fluo_renzo paper: doi.org/10.1039/D4DD00104D
Image from Derek van Tilborg (@DerekvTilborg)
Francesca Grisoni (@fra_grisoni) profile pictureFrancesca Grisoni@fra_grisoni10 Jun 2024
Thrilled of our collaboration with the team of @Fluo_renzo, spearheaded by a great duo @AnaOrPe_ & @DerekvTilborg. 🚀 We show the integration of active #machinelearning, microfluidics, and imaging for nanoparticle design. Just out on @digital_rsc 💪🏻 pubs.rsc.org/en/content/arti…
Machine learning-guided high throughput nanoparticle design†

Machine learning-guided high throughput nanoparticle design†

Designing nanoparticles with desired properties is a challenging endeavor, due to the large combinatorial space and complex structure–function relationship

pubs.rsc.org
2
2
20
1,050
Our (mini) review on deep learning for low-data drug discovery is now out! doi.org/10.1016/j.sbi.2024.1… There are honestly few things I enjoy as much as writing a review. It's so satisfying Especially together with @hlnbrnkmnn @emanuelecriscu9 Luke Rossen @Rza_ozcelik @fra_grisoni
Derek van Tilborg (@DerekvTilborg) profile pictureDerek van Tilborg@DerekvTilborg25 Jan 2024
Check out our new review on "Deep learning for low-data #drugdiscovery"! We discuss ML strategies to deal with our most pressing problem; ✨ low-data ✨ doi.org/10.26434/chemrxiv-20… @hlnbrnkmnn @emanuelecriscu9 Luke Rossen @Rza_ozcelik @fra_grisoni @molecularML #AI #chemistry
Image from Derek van Tilborg (@DerekvTilborg)
1
17
50
6,811
2. Multi-staged training, where we discuss transfer learning, reinforcement learning, and active learning.
Image from Derek van Tilborg (@DerekvTilborg)
1
1
458
And 3. Context-enriched training, where we talk about the applications of multimodal training and multi-task learning. Besides these three main avenues of dealing with low-data problems, we end the review by highlighting challenges and future opportunities. 🧠✨🧪
1
362
@fra_grisoni had the idea of writing this review in 1 day with the group. We all came prepared and crunched out a messy draft in one work day. The rest definitely took more than a day (a lot longer), but it was a nice kickstart and teambuilding event :)
2
319
We cover three main topics: 1. Data augmentation, where we talk about how to augment molecular data.
Image from Derek van Tilborg (@DerekvTilborg)
1
1
537
Check out our new review on "Deep learning for low-data #drugdiscovery"! We discuss ML strategies to deal with our most pressing problem; ✨ low-data ✨ doi.org/10.26434/chemrxiv-20… @hlnbrnkmnn @emanuelecriscu9 Luke Rossen @Rza_ozcelik @fra_grisoni @molecularML #AI #chemistry
Image from Derek van Tilborg (@DerekvTilborg)
2
15
3
78
18,790
Load more