UdanDTI
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
- Organisation type
- Academia
- Country
- China
- Published
- 15 September 2024
- Authors
- Pei-Dong Zhang, Jianzhu Ma, Ting Chen
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein-ligand contact prediction, Drug discovery
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
- tokens
- Epochs
- 200
BindingDB: 20,675 + 20,675 = 41,350 BioSNAP: 13,830 + 13,830 = 27,660 Human 3364+3364 = 6728 Total interactions: 75738 "The maximum length of the sequence input to the encoder was 290 for drugs and 1200 for proteins" Assuming 500 tokens on average per drug-protein interaction Dataset size: 75738*500
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- How it was established
- Hardware
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 A40 PCIe
- Chips used
- 1
- Power draw
- 325 W
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Escaping the Drug-Bias Trap: Using Debiasing Design to Improve Interpretability and Generalization of Drug-Target Interaction Prediction
- Last updated
- 28 November 2025
What the numbers mean
Background
UdanDTI was published by Tsinghua University, in China, in September 2024. The organisation is categorised as academia.
It works in Biology, and is recorded as doing protein-ligand contact prediction, Drug discovery.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
UdanDTI — common questions
Who created UdanDTI?
UdanDTI was published by Tsinghua University, based in China, categorised as academia.
When was UdanDTI released?
UdanDTI was published in September 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 UdanDTI used for?
UdanDTI works in Biology, and is recorded as handling protein-ligand contact prediction, Drug discovery. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
What GPU do I need to run UdanDTI?
None. UdanDTI 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 UdanDTI open source?
The licensing for UdanDTI 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 UdanDTI have?
No parameter count has been published for UdanDTI, which is why no memory or speed figure appears on this page.
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.