4/ This perspective is basically a friendly nudge to the field: let’s build benchmarks that matter in the real world, not just on leaderboards.

Huge thanks to the committee for pulling this together!

Read the letter: polarishub.io/guidelines/m...

3/ Few highlights:

— Many benchmarks reward models for finding what we already know
— Drug discovery needs models that generalize, identify new biology, and flag problems early
— Simple baselines still beat fancy models
— We need clearer tasks, cleaner data, and shared frameworks

2/ Multiomics AI is moving fast, but the benchmarks aren’t keeping up with what drug discovery actually needs.

The letter lays out the gap clearly and makes the case for why our community needs better, more realistic ways to measure progress.

4/ Make sure to checkout our Open Access paper, associated code and thoughts on implementation 👇

📄 Open Access paper: pubs.acs.org/doi/full/10....

💻 Code on GitHub: github.com/polaris-hub/...

💭 Thoughts on implementation: polarishub.io/blog/imagini...

3/ We're especially thrilled that this paper is open access thanks to the JCIM editor's choice program.

We hope for the broad adoption of these guidelines to help close the gap between perceived progress and real-world impact in drug discovery.

2/ The initial preprint was refined with invaluable feedback:

✅ Community: Unique open-feedback period hosted on Github: github.com/polaris-hub/....

✅ Practical Learnings: Lessons learned from applying these guidelines in the ASAP Antiviral challenge.

✅ Peer Review: Formal review process at JCIM.

(3/3) Ready to explore the findings?

Now’s your chance. Analyze the data, test your ideas, and drop your insights in the Discord.

Join the Polaris community on Discord to dive deeper into the challenge results and share what you discover: discord.com/invite/cS6Nf...

(2/3) 📢 In addition, ASAP is hosting a virtual showcase tomorrow, April 30 at 11AM ET / 5PM BST featuring top performers from the challenge.

Speakers will present their methods, background, and post-hoc analyses now that the test data is live.

Register for the link: docs.google.com/forms/d/e/1F...

Stay updated on the Multiomics Steering Committee's work by subscribing to our mailing list: polarishub.io#subscribe-to...

and Rob Moccia (formerly Pfizer), Cuong Q. Nguyen (formerly GSK), Nate Robichaud (Nomic), William J. Godinez (Novartis), Tommaso Biancalani (Genentech), and Kristina Ulicna (Valence Labs). 🧵

Led by experts from academia and industry, the committee includes: Oren Kraus (Recursion), Judith Mueller (Merck), Ali Denton (Valence Labs), Fabian J. Theis (Helmholtz Munich), Paula A. Marin Zapata (Bayer), Anne E. Carpenter (Broad Institute), Ian Barrett (AstraZeneca)... 🧵

Multiomics data holds the potential to unravel biological complexity by providing complementary insights into cellular states of disease and their modulation through novel therapeutics.

We aim to propose clear definitions, identify benchmarking tasks, and encourage alignment on best practices. 🧵

🔔 Stay Updated!

For future challenges & collaborative opportunities, subscribe to our mailing list.

✉️ polarishub.io#subscribe-to...

📢 We value your feedback!

Help us improve future challenges, share your thoughts.

📄 Feedback Form: share-eu1.hsforms.com/23XmDlumfQBu...

📝 Next Steps:

ASAP Discovery & OpenADMET are writing a paper summarizing insights from the challenge.

All participants are invited to contribute. Join us on Discord: discord.gg/cS6Nfj58Gf

For detailed metrics, leaderboards, and further information, see the challenge page: antiviral.polarishub.io

Thanks for the feedback, @greglandrum.bsky.social! We're always looking for ways to improve the accessibility and value of the platform so we'll take this into consideration as we continue to build. 🙏

We also want to give a huge shoutout to the community for sharing feedback on the challenge! Let’s keep the conversation going.

Join us on Discord: discord.gg/VaCbn82CeD