pages/contribute.md

PRIMO is an open benchmark, and it is deliberately incomplete. The Boards page shows exactly how far it reaches today, the live boards, and names the gaps as open cards. Everything past that still needs somebody to bring it.

PRIMO was started by Scienta Lab. The intent is community governance; how that actually works is part of what the first partners will define.

Add a cohort

PRIMO has no shortage of models. What is hard to find is an omics cohort with patient-level clinical labels, whether that is drug response, a severity score or a molecular subtype. If you hold one, or know a group that does, tell us:

• modality and roughly how many patients
• what is labelled, and how many patients carry that label
• disease and tissue
• licence, and whether the data can be redistributed

Propose a cohort

There is no formal acceptance process yet. We are writing it with the first partners, and we would rather admit that than invent rules nobody has agreed to. What you will get today is a real answer and a technical conversation.

Add a task, without bringing any data

This one costs you nothing but an idea. Ask a better question of the cohorts already here: a label we are not predicting, a transfer split nobody has tried, or a metric that would say more than the one we use. Methodology counts here as much as data does.

Propose a task

Add a modality or a therapeutic area

The OPEN cards on the Boards page mark the omics layers and clinical areas PRIMO does not reach yet. Read them as gaps waiting for someone rather than as a roadmap we are already working through. Opening one takes a single cohort with clinical labels, and not a whole atlas.

Claim an open board

Become a founding partner

Founding partners shape PRIMO rather than just appear on it: a voice on the methodology, co-signature on what we publish, and early access to the results.

Talk to us about partnership · primomics.org

Smaller ways in

• Question the method. Open a thread in the Space's Community tab.
• Submit a model. Baselines are on the leaderboard already; beat them.
• Read the paper: OpenReview
• Look at the data: PRIMOmics/primo