iiinova — where your digital self keeps evolving

Would be cool to see how OpenFold does on this new benchmark! 👀

(And the science, of course!)

020

Love the logo and name! 🎸

120

The benchmarking platform for drug discovery

And if you're curious, you can learn more about what we actually mean by "ML-ready" in our recent blog: polarishub.io/blog/reprodu...

polarishub.io

Polaris

000

A few weeks back I got in touch with @ninjani.bsky.social about creating a "ML-ready" version of a PLINDER dataset. Excited to release a first attempt at this! 💬 Let us know how we did discord.gg/uGCZB7PXmX bsky.app/profile/dkoe...

120

New leaderboard on @polarishub.io for Runs 'N Poses! 🎸 Anyone has any protein-ligand co-folding methods laying around they would like to put to the test? polarishub.io/benchmarks/p... Great work @peterskrinjar.bsky.social @jeeberhardt.bsky.social @torstenschwede.bsky.social @ninjani.bsky.social

194

bsky.app/profile/pola...

Peter Škrinjar @peterskrinjar.bsky.social · 08/02/2025

Reposted by Cas

Excited to share our latest preprint evaluating AlphaFold3, Boltz-1, Chai-1 and Protenix for predicting protein-ligand interactions, featuring our newly introduced benchmark dataset 🌹Runs N’ Poses🌹! www.biorxiv.org/content/10.1... 🧵👇 (1/n)

biorxiv.org

Have protein-ligand co-folding methods moved beyond memorisation?

Deep learning has driven major breakthroughs in protein structure prediction, however the next critical advance is accurately predicting how proteins interact with other molecules, especially small mo...

412438

Cas @caswognum.nl · 07/02/2025

@polarishub.io has a benchmarking API which ensures you use the exact same split and metrics as everyone else. See the screenshot. We're aiming to serve as a source of truth for machine learning in drug discovery. For context, see: polarishub.io/blog/reprodu... Would love to hear your feedback!

020

Cas @caswognum.nl · 07/02/2025

Interesting! This would be a nice “baseline” to have for the associated Polaris benchmark. polarishub.io/benchmarks/b....

polarishub.io

adme-fang-reg-v1

biogen

Cas @caswognum.nl · 04/02/2025

With the increased activity on the platform recently, things have been breaking in new ways (sorry Windows users!), but I love it! It shows that people are actually using Polaris! Our team is fixing issues as soon as we can and it’s helping us improve the overall robustness. Keep ‘m coming! 🏗️

010

Reposted by Cas

Polaris @polarishub.io · 31/01/2025

🚨 Extension Alert: The intermediate leaderboard submission deadline for the antiviral challenge has been extended to midnight on February 7th! Don't miss this chance to see how you stack up against other participants! Submit your results today: polarishub.io/competitions

022

Cas @caswognum.nl · 30/01/2025

With @polarishub.io we early on decided to purposefully restrict the flexibility of our datasets and benchmarks. We understand that this can be frustrating at times, but we believe it’s an important step to improve reproducibility. Our team is here to help if you need support! Reach out on Github.

030

Reposted by Cas

Polaris @polarishub.io · 27/01/2025

💡Have questions about the data behind the antiviral challenge?💡 This week, @asapdiscovery.bsky.social and @omsf.io are hosting 3 virtual office hour sessions with the experimentalists behind the data! RSVP here: docs.google.com/forms/d/e/1F...

143

Cas @caswognum.nl · 28/01/2025

Only a few days left to submit your predictions for the first, intermediate leaderboard. We’ve got an incredibly passionate team on standby to help solve any issues you may run into and we’d love to hear your feedback. 🧑‍💻 Github: github.com/polaris-hub/... 💬 Discord: discord.gg/vBFd8p6H7u

discord.gg

Join the Polaris Discord Server!

Check out the Polaris community on Discord - hang out with 368 other members and enjoy free voice and text chat.

030

Cas @caswognum.nl · 24/01/2025

This is the kind of content I'm here for! 🤯

Cas @caswognum.nl · 23/01/2025

If you have been waiting for the right time to start working on the ASAP Discovery challenge, this is it! 🏆 For all results submitted up until January 31st, we will publish an intermediate leaderboard. Get your first set of results in now and see how you stack up against your peers.

010

Cas @caswognum.nl · 21/01/2025

The @polarishub.io discord is feeling very lively right now. I love learning with and from all of you!💡 If you haven't yet, join us and put your methods to the test to learn what is working and what's not in ADMET, potency and pose prediction. Get started in a few lines of code. Great video by Lu!

020

Reposted by Cas

John Chodera @jchodera.bsky.social · 17/01/2025

Incredibly excited to see how well ADMET, affinity, and pose prediction models *actually* perform in the ASAP x OpenADMET x PolarisHub blind challenge: polarishub.io/competitions

polarishub.io

Polaris

The benchmarking platform for drug discovery

0163

Reposted by Cas

The ASAP Discovery Consortium @asapdiscovery.bsky.social · 15/01/2025

Working on predictive models for drug discovery? Here's your chance to see how well your models actually work! Together with @polarishub.io and OpenADMET, we've launched a blind prospective challenge to see how well predictive models for drug discovery can actually predict real drug discovery data!

064

Cas @caswognum.nl · 14/01/2025

Get started with just a few lines of code!

000

Cas @caswognum.nl · 14/01/2025

The @asapdiscovery.bsky.social x OpenADMET (@omsf.io) blind challenge is live! 🚀 You're free to use any publicly available training data, but the challenge provides 770 ligand poses, 1031 potency datapoints and 434 ADMET datapoints as a consistently generated training set. Come learn with us! 🏆

120

Reposted by Cas

Polaris @polarishub.io · 10/01/2025

🎥 At NeurIPS, we had the opportunity to chat with the authors of several dataset and benchmarking papers that are relevant to machine learning for drug discovery. First up—a quick interview with the team behind WelQrate! 🧵 youtu.be/pbatKLphJAE

youtu.be

NeurIPS 2024 Series - A Chat with the WelQrate Team

YouTube video by PolarisHQ

121

Reposted by Cas

Zarr @zarr.dev · 09/01/2025

🎉 Zarr-Python 3 is here! 🎉 - Full support for Zarr v3 spec - Chunk-sharding for more efficient data storage - Major performance boosts with async I/O & parallel compression 💻 pip install --upgrade zarr 💻 conda install --channel conda-forge zarr Blog post: buff.ly/3C3OwYw

25520

That’s something we wholeheartedly agree on! 🌍 Anyways - I don’t intend to pretend I have all the answers. Still learning and I appreciate you entertaining my arguments. I see how the current implementation of crypto is flawed, but that doesn’t necessarily make the underlying technology worthless.

100

On a tangent: One thing I’ve always found a little weird is that we’re only getting paid once (or maybe twice) a month. If you don’t need a central, administrative agency and the costs of transactions go down, you could instead think of streaming money! I find that possibility fascinating!

100

I also don’t get how crypto would facilitate criminality... If the identity of a wallet’s owner is clear, which new regulation (at least in the EU) is requiring, and coins like Concordium (CDD) are addressing, crypto is - if anything- more transparent. All transactions are public after all.

100

Hm… I agree that the popular discourse around crypto is hype driven, which leads to a lot of volatility and weird valuations. Nevertheless, I see the value of the technology. You can no longer just create new money out of thin air and it reduces the dependency on a central, administrative agency.

100

Zarr @zarr.dev · 04/01/2025

At the risk of sounding naive, but could crypto (or at least the technology behind crypto) play a role in addressing this? I’ve been wanting to read the (Dutch) book “Ons geld is stuk” by the Slagter brothers for a while now, which seems to make some similar observations at a first glance!

100

Reposted by Cas

Hi, Zarr community! 👋 🚨 Big news: Zarr-Python 3.0 is dropping next week! 🚨 If your project depends on Zarr-Python, make sure to check out the migration guide to get ready for the update. Guide: buff.ly/3W0cLxd More updates soon! 🧑🏻‍💻

buff.ly

02713

Cas @caswognum.nl · 18/12/2024

We would love to hear what you think! Share your thought in Discord: discord.gg/VaCbn82CeD Thanks to all that already participated in the user interviews so far and a big shout-out to Kun Zhu for leading the work during a very successful internship.

discord.gg

Join the Polaris Discord Server!

Check out the Polaris community on Discord - hang out with 305 other members and enjoy free voice and text chat.

000

Cas @caswognum.nl · 18/12/2024

After publishing our guidelines on Method Comparison with the Small Molecule Steering Committee about a month ago (doi.org/10.26434/che...), the team has been hard at work to think of new ways in which we could simplify the adoption of these guidelines through the Polaris Hub.

doi.org

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

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 discover...