🦠 Model Request: S2DV HepG2 toxicity

emmakodes commented 1 year ago

Model Name

S2DV HepG2 toxicity

Model Description

The model adopts a natural language processing technique to analyze compound SMILES strings, enabling an accurate representation of the relationship between compounds and their substructures. This technique helps the model predict liver toxicity, verified by wet-lab experiments.

Slug

s2dv-hepg2-toxicity

Tag

ChEMBL, Toxicity

Publication

https://pubmed.ncbi.nlm.nih.gov/35062019/

Source Code

https://github.com/NTU-MedAI/S2DV

License

Apache-2.0 license

GemmaTuron commented 1 year ago

Let's focus first on #655 and if that works we will continue with this one

emmakodes commented 1 year ago

Okay noted @GemmaTuron

GemmaTuron commented 1 year ago

/approve

github-actions[bot] commented 1 year ago

New Model Repository Created! 🎉

@emmakodes ersilia model respository has been successfully created and is available at:

🔗 ersilia-os/eos2fy6

Next Steps ⭐

Now that your new model respository has been created, you are ready to start contributing to it!

Here are some brief starter steps for contributing to your new model repository:

Note: Many of the bullet points below will have extra links if this is your first time contributing to a GitHub repository

🍴 Get started by creating a fork of your new model repository - docs
👯 Clone your forked repository - docs
✏️ Make edits to your new forked model repository - docs - Edits might include:
- Updating the README.md file to accurately describe your model
- Add source code for your model
- Adding documentation for your model
🚀 Open a Pull Request from your forked repository to the original repository. This will allow you to bring your local changes into the new ersilia model repository that was just created! - docs

Additional Resources 📚

If you have any questions, please feel free to open an issue and get support from the community!

emmakodes commented 1 year ago

Hello @GemmaTuron here is the output prediction after I run S2DV HepG2 toxicity model within the Ersilia CLI output_eos2fy6.csv

and here is the pull request: https://github.com/ersilia-os/eos2fy6/pull/1

emmakodes commented 1 year ago

Hello @emmakodes, I having an error of returning null for all the output of the model. The model is being fetched correctly, but the predictions produced are None all the time. The API schema it looks like this

{
    "run": {
        "input": {
            "key": {
                "type": "string"
            },
            "input": {
                "type": "string"
            },
            "text": {
                "type": "string"
            }
        },
        "output": {
            "outcome": {
                "meta": [
                    "fingerprint"
                ],
                "type": null
            }
        }
    }
}

The metadata.json look like :

{
    "Identifier": "eos6aun",
    "Slug": "rxn-fingerprint",
    "Status": "In progress",
    "Title": "RXNFP - chemical reaction fingerprints",
    "Description": "Predicts and  shows fingerprints for chemical reactions",
    "Mode": "Pretrained",
    "Input": [
        "Compound"
    ],
    "Input Shape": "Single",
    "Task": [
        "Generative"
    ],
    "Output": [
        "Fingerprint"
    ],
    "Output Type": [
        "Float"
    ],
    "Interpretation": "This model receives smiles as input and returns as output the fingerprint scores for each smiles,the fingerprint scores are used to give . ",
    "Tag": [
        "Fingerprint",
        "Chemical Reactions Maps"
    ],
    "Publication": "https://chemrxiv.org/engage/chemrxiv/article-details/60c753a0bdbb89acf8a3a4b5",
    "Source Code": "https://github.com/rxn4chemistry/rxnfp/tree/master/",
    "License": "MIT"
}

I don't need to modify the service.py since I am returning a Float.When I run the model but itself everything works fine. What could be the problem?

Hello @samuelmaina it would have been nicer you post above on the issue of 'eos6aun' model since it is a different model from this model.

You are working on the model right?

What I am thinking is it seems the model is not accepting the right input

samuelmaina commented 1 year ago

@emmakodes it's a new model and I want to incorporate it.Let me try your suggestions out.I will post the issue in the model issue if the problem persists. Thanks.

GemmaTuron commented 1 year ago

Hi @samuelmaina

please move this discussion to the right issue

samuelmaina commented 1 year ago

I will move it.Sorry.

ersilia-os / ersilia