GEM x Adaptyv: RBX1 Binder Design Competition
Design protein binders targeting RBX1, a cancer-relevant E3 ubiquitin ligase component. Co-organized with the GEM Workshop at ICLR 2026.
Overview
- Stage 1Computational Design
Submit your protein binder designs targeting RBX1. Each team submits a method description (PDF, 2 pages max) and a ranked binder list (CSV, ≤100 sequences, ≤250 AA each). Designs must be de novo with a minimum edit distance of 25% to UniRef50 (25% CDR edit distance to SAbDab for single-domain antibodies).
Submissions OpenFeb 15, 2026/
Submissions CloseMar 26, 2026 - Stage 2Experimental Validation
A total of 300 designs are tested experimentally via bio-layer interferometry at Adaptyv's Foundry. Results announced at ICLR 2026 in Rio de Janeiro.
Validation startsApr 1, 2026/
Results releasedApr 26, 2026
- Stage 1Computational Design
Submit your protein binder designs targeting RBX1. Each team submits a method description (PDF, 2 pages max) and a ranked binder list (CSV, ≤100 sequences, ≤250 AA each). Designs must be de novo with a minimum edit distance of 25% to UniRef50 (25% CDR edit distance to SAbDab for single-domain antibodies).
Submissions OpenFeb 15, 2026/
Submissions CloseMar 26, 2026 - Stage 2Experimental Validation
A total of 300 designs are tested experimentally via bio-layer interferometry at Adaptyv's Foundry. Results announced at ICLR 2026 in Rio de Janeiro.
Validation startsApr 1, 2026/
Results releasedApr 26, 2026
About the Target
RBX1
PDB: 2LGV
Sequence
RBX1 (RING Box Protein 1) is a 108-amino acid component of the Cullin-RING E3 ubiquitin ligase (CRL) complex, the largest family of E3 ligases in humans. CRLs control degradation of roughly 20% of all cellular proteins, regulating cell cycle progression, DNA repair, and signal transduction. RBX1 recruits E2 ubiquitin-conjugating enzymes to the complex, serving as its catalytic subunit.
In this competition, co-organized with the GEM Workshop at ICLR 2026, the goal is to design protein binders against RBX1. The protein combines an intrinsically disordered N-terminal region with a stabilized C-terminal RING-H2 finger domain coordinating three zinc ions, a dual structural challenge for binder design. Disrupting RBX1 function could inhibit CRL-mediated protein degradation, with applications in cancer therapy where CRL activity is frequently dysregulated.
Teams submit up to 100 ranked binder sequences (≤250 AA each). Designs must be de novo — motif scaffolding and lead optimization are not allowed, with the exception of single-domain antibodies. Binder sequences must have a minimum edit distance of 25% of total sequence length to known proteins in UniRef50; for single-domain antibodies, CDR loops must have a minimum edit distance of 25% to known antibodies in SAbDab. Selected designs undergo experimental validation via bio-layer interferometry at Adaptyv's Foundry. Results will be announced at ICLR 2026 in Rio de Janeiro on April 26. All submitted sequences and experimental data are published as open-source on Proteinbase under the ODC-ODbL license.
Awards
- Best Designed Binder: $1,000 USD and a 3D printed protein structure
- Runner-up: $100 USD and a 3D printed protein structure
- All participants receive experimental data for all tested designs, inclusion in the open-source dataset on Proteinbase, and co-authorship in the community results paper.
Stages
Submission process
Rules
- Up to 100 proteins per submission.
- Each sequence must be 250 AA or shorter.
- You can submit 1 time(s) every 24 hours.
Selection
Submit your protein binder designs targeting RBX1. Each team submits a method description (PDF, 2 pages max) and a ranked binder list (CSV, ≤100 sequences, ≤250 AA each). Designs must be de novo with a minimum edit distance of 25% to UniRef50 (25% CDR edit distance to SAbDab for single-domain antibodies).
Top Ranked Designs
Submissions selected by a panel of experts for their novelty and originality