MolE representations (Molecular representation through redundancy reduced Embeddings) are task-independent, learned molecular embeddings generated through a self-supervised deep learning approach. They are designed to encode chemically meaningful information about molecules without needing labeled training data.
This model was incorporated on 2025-06-23.
- Ersilia Identifier:
eos4ex3 - Slug:
mole-representations
- Task:
Representation - Subtask:
Featurization - Biomedical Area:
Any - Target Organism:
Not Applicable - Tags:
Descriptor
- Input:
Compound - Input Dimension:
1
- Output Dimension:
1000 - Output Consistency:
Fixed - Interpretation: Vector representation of a molecule
Below are the Output Columns of the model:
| Name | Type | Direction | Description |
|---|---|---|---|
| dim_000 | float | Dimension 0 of the Molecular representation through redundancy reduced Embeddings | |
| dim_001 | float | Dimension 1 of the Molecular representation through redundancy reduced Embeddings | |
| dim_002 | float | Dimension 2 of the Molecular representation through redundancy reduced Embeddings | |
| dim_003 | float | Dimension 3 of the Molecular representation through redundancy reduced Embeddings | |
| dim_004 | float | Dimension 4 of the Molecular representation through redundancy reduced Embeddings | |
| dim_005 | float | Dimension 5 of the Molecular representation through redundancy reduced Embeddings | |
| dim_006 | float | Dimension 6 of the Molecular representation through redundancy reduced Embeddings | |
| dim_007 | float | Dimension 7 of the Molecular representation through redundancy reduced Embeddings | |
| dim_008 | float | Dimension 8 of the Molecular representation through redundancy reduced Embeddings | |
| dim_009 | float | Dimension 9 of the Molecular representation through redundancy reduced Embeddings |
10 of 1000 columns are shown
- Source:
Local - Source Type:
External - DockerHub: https://hub.docker.com/r/ersiliaos/eos4ex3
- Docker Architecture:
AMD64,ARM64 - S3 Storage: https://ersilia-models-zipped.s3.eu-central-1.amazonaws.com/eos4ex3.zip
- Model Size (Mb):
1534 - Environment Size (Mb):
5808 - Image Size (Mb):
7983.47
Computational Performance (seconds):
- 10 inputs:
44.35 - 100 inputs:
36.48 - 10000 inputs:
1037.47
- Source Code: https://github.com/rolayoalarcon/MolE/tree/main
- Publication: https://www.nature.com/articles/s41467-025-58804-4
- Publication Type:
Peer reviewed - Publication Year:
2025 - Ersilia Contributor: arnaucoma24
This package is licensed under a GPL-3.0 license. The model contained within this package is licensed under a MIT license.
Notice: Ersilia grants access to models as is, directly from the original authors, please refer to the original code repository and/or publication if you use the model in your research.
To use this model locally, you need to have the Ersilia CLI installed. The model can be fetched using the following command:
# fetch model from the Ersilia Model Hub
ersilia fetch eos4ex3Then, you can serve, run and close the model as follows:
# serve the model
ersilia serve eos4ex3
# generate an example file
ersilia example -n 3 -f my_input.csv
# run the model
ersilia run -i my_input.csv -o my_output.csv
# close the model
ersilia closeThe Ersilia Open Source Initiative is a tech non-profit organization fueling sustainable research in the Global South. Please cite the Ersilia Model Hub if you've found this model to be useful. Always let us know if you experience any issues while trying to run it. If you want to contribute to our mission, consider donating to Ersilia!