CoPRA
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Tsinghua University,University College London (UCL),Monash University,Beijing University of Posts and Telecommunications
- Organisation type
- Academia,Academia,Academia,Academia
- Country
- China, United Kingdom of Great Britain and Northern Ireland, Australia
- Published
- 21 August 2024
- Authors
- Rong Han, Xiaohong Liu, Tong Pan, Jing Xu, Xiaoyu Wang, Wuyang Lan, Zhenyu Li, Zixuan Wang, Jiangning Song, Guangyu Wang, Ting Chen
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein-RNA binding affinity prediction
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- 1,966,080,310 tokens
Summary: 1. Chain pairs: 30,000 2. Poses per pair: 3 Total datapoints: 30,000 × 3 = 90,000 3. Tokens per datapoint: - Protein residues: 200 - RNA bases: 100 Total tokens per datapoint: 200 + 100 = 300 4. Final calculation: 90,000 datapoints × 300 tokens/datapoint = 27,000,000 tokens
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA A100
- Chips used
- 4
- Power draw
- 3.2 kW
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
- Citations
- 7
Sources
Where this record came from and when it was last checked.
- Reference
- CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
CoPRA was published by Tsinghua University,University College London (UCL),Monash University,Beijing University of Posts and Telecommunications, in China, in August 2024. The organisation is categorised as academia,Academia,Academia,Academia.
It works in Biology, and is recorded as doing protein-RNA binding affinity prediction.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
Around 1,966,080,310 tokens went into training it.
Answers
CoPRA — common questions
What GPU do I need to run CoPRA?
None. CoPRA is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is CoPRA open source?
The licensing for CoPRA was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does CoPRA have?
No parameter count has been published for CoPRA, which is why no memory or speed figure appears on this page.
Who created CoPRA?
CoPRA was published by Tsinghua University,University College London (UCL),Monash University,Beijing University of Posts and Telecommunications, based in China, categorised as academia,Academia,Academia,Academia.
When was CoPRA released?
CoPRA was published in August 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is CoPRA used for?
CoPRA works in Biology, and is recorded as handling protein-RNA binding affinity prediction. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.