Ginkgo, Apheris and pharma majors launch 10,000-antibody ML-ready dataset consortium
david_van_dijk · x · 2026-09-30
Ginkgo Datapoints and Apheris launched the Antibody Developability Consortium with founding members AbbVie, argenx, Lundbeck and Takeda, aiming to build the largest ML-ready antibody developability dataset: 10,000 antibodies selected for diversity and characterized to one standard.
- Context: fewer than 250 public IgG sequences have paired developability measurements, and pharma's in-house datasets cluster around their own programs with incompatible assays.
- Approach: a diversity algorithm runs across members' candidate sequences inside Apheris's secure environment.
- Commenter David van Dijk highlights the experiment design: choosing antibodies for diversity first, then measuring uniformly, effectively asks what data a useful model actually needs rather than inheriting whatever was collected.
Related event: Ginkgo and Pharma Partners Launch Antibody Developability Consortium(2 posts)→
More from Research
- GamowLabs' LabBench: AI Agents Struggle to Pick the Next Best Wet-Lab Experiment — danielmckinn0n · 2026-09-30
- Toby Ord: Opus 5.5 system card yields lambda values matching OpenAI's agent parallelism estimates — tobyordoxford · 2026-09-30
- davidad Ships Interactive Playground to Test His Bayesian Cognition Model Across Systems — davidad · 2026-09-30
- Microsoft Research's Social-R1 uses RL to train genuine social reasoning in AI — burkov · 2026-09-30
- Verifying all of nixpkgs: 95% of machine code for ~$134M by end of 2027, study models — ctjlewis · 2026-09-30
- 'LLMs as a Cognitive Virus' paper with Krakauer and Levin questioned for weak LLM specificity — hn1000 · 2026-09-30