MODEL INTELLIGENCE / VERIFIED RESEARCH
ABOPD
Antibody CDR design via on-policy distillation of diffusion models.
Developer: ABOPD research authors (little1d GitHub)
Overview
- Developer
- ABOPD research authors (little1d GitHub)
- Category
- antibody-specific design
- Commercial rights
- Unverified
- License fee
- Unverified
- Open weights
- Yes
- Last verified
- 2026-10-16
- Added to FoldScout
- 2026-10-16
Capabilities
Research code for antibody complementarity-determining region sequence/structure generation using a diffusion-model post-training approach. The official repository provides inference code and links model weights hosted separately on Hugging Face; wet-lab performance claims require independent validation.
When to use it
Use as a research candidate for antibody CDR generative design; resolve checkpoint commercial-use rights with authors before integrating into a commercial program.
Compute
Compute classification: single-gpu. This is a planning estimate, not a throughput benchmark; check the linked model installation documents for exact requirements.
Commercial licensing
Commercial permission — Unverified
The GitHub repository LICENSE is Apache-2.0 for code. A separate model checkpoint is hosted on Hugging Face; its model card does not publish a clear commercial-use/weight license. Thus code rights are not sufficient to classify the complete model as commercial OK.
License fee — Unverified
Repository code may be free to use commercially under Apache-2.0, but model weights and dependency commercial fees have not been verified. Do not assume commercial permission or no cost.
Free downloads do not necessarily permit company use. Code, checkpoints, external dependencies and compute expenses require separate review.
Official references
From computational design to experimental evidence
Validate your designed binder.
Seq2Study connects AI-designed proteins and antibodies with expression, affinity, stability and developability testing.