Automated design of multi-target ligands by generative deep learning
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
- Goethe University Frankfurt,Fraunhofer Institute for Translational Medicine and Pharmacology,Ludwig Maximilian University of Munich
- Organisation type
- Academia,Academia
- Country
- Germany
- Published
- 11 September 2024
- Authors
- Laura Isigkeit, Tim Hörmann, Espen Schallmayer, Katharina Scholz, Felix F. Lillich, Johanna H. M. Ehrler, Benedikt Hufnagel, Jasmin Büchner, Julian A. Marschner, Jörg Pabel, Ewgenij Proschak, Daniel Merk
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- 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.
- Parameters
- 5.8M
- Training data
- tokens
"The model was based on a recurrent neural network with long short-term memory (LSTM) cells and consisted of four layers with a total of 5,820,515 parameters: layer 1, BatchNormalization; layer 2, LSTM with 1024 units; layer 3, LSTM with 256 units; layer 4, BatchNormalization."
365,000 molecules × 10 augmentations = 3,650,000 total molecules 3,650,000 molecules × 140 tokens/molecule = 511,000,000 (5.11 × 10⁸) tokens Final estimate: 5.1e8 tokens
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Training code
- Open source
Code used in this study is available at Zenodo (https://doi.org/10.5281/zenodo.12795470) License: CC-BY-4.0
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
- Automated design of multi-target ligands by generative deep learning
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Automated design of multi-target ligands by generative deep learning was published by Goethe University Frankfurt,Fraunhofer Institute for Translational Medicine and Pharmacology,Ludwig Maximilian University of Munich, in Germany, in September 2024. The organisation is categorised as academia,Academia.
It works in Biology, and is recorded as doing drug discovery.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
Automated design of multi-target ligands by generative deep learning — common questions
When was Automated design of multi-target ligands by generative deep learning released?
Automated design of multi-target ligands by generative deep learning 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 Automated design of multi-target ligands by generative deep learning used for?
Automated design of multi-target ligands by generative deep learning works in Biology, and is recorded as handling drug discovery. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run Automated design of multi-target ligands by generative deep learning?
None. Automated design of multi-target ligands by generative deep learning 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 Automated design of multi-target ligands by generative deep learning open source?
The licensing for Automated design of multi-target ligands by generative deep learning 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 Automated design of multi-target ligands by generative deep learning have?
Automated design of multi-target ligands by generative deep learning has 5.8M parameters. "The model was based on a recurrent neural network with long short-term memory (LSTM) cells and consisted of four layers with a total of 5,820,515 parameters: layer 1, BatchNormalization; layer 2, LSTM with 1024 units; layer 3, LSTM with 256 units; layer 4, BatchNormalization.". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created Automated design of multi-target ligands by generative deep learning?
Automated design of multi-target ligands by generative deep learning was published by Goethe University Frankfurt,Fraunhofer Institute for Translational Medicine and Pharmacology,Ludwig Maximilian University of Munich, based in Germany, categorised as academia,Academia.
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.