🦠 Model Request: Prediction of Aqueous Kinetic Solubility

[paulinebanye]

Model Name

Aqueous Kinetic Solubility

Model Description

This assay was used for kinetic solubility determination. Prediction of Aqueous solubility is one of the most important properties in drug discovery, as it has profound impact on various drug properties, including biological activity, pharmacokinetics (PK), toxicity, and in vivo efficacy.

Slug

aqueous-kinetic-solubility

Tags

admemodel, kineticsolubility, prediction, solubility

Publication

Predictive models of aqueous solubility of organic compounds built on A large dataset of high integrity

Code

https://github.com/ncats/ncats-adme

License

No response

[GemmaTuron]

/approve

[github-actions[bot]]

New Model Repository Created! 🎉

@pauline-banye ersilia model respository has been successfully created and is available at:

🔗 ersilia-os/eos8ykt

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 📚

• CONTRIBUTING.md
• About Pull Requests
• About Forks

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

[GemmaTuron]

I am adding this here to help in the model results interpretation. This model should give two probabilities, one for solubility (>10 ug/mL) and the other for High solubility: Compounds with solubility lower than 10 μg/mL are usually classified as insoluble. Selection of this classification criterion resulted in a balanced dataset with 51.1% soluble compounds and is favorable for QSAR modeling. On the other hand, a minimum solubility of 52 μg/mL was suggested for a compound with an average permeability to be completely absorbed.4 Therefore, a second classification threshold of 50 μg/mL was adopted in this study to separate compounds with ideal solubility for drug development

I'd try to give the output of both in a single file @pauline-banye

[GemmaTuron]

Hi @pauline-banye

Please can you summarize what is the issue you are encountering when running the model through the Ersilia CLI? you mentioned the output was incorrect. Also, have you been able to check that the output might be two values? Thanks!

[GemmaTuron]

@pauline-banye , see my coments above about the double output of this model. we need to make sure which one is the one we are passing to the end users. Have you compared results obtained with their code vs what is obtained by the model we have implemented?

[GemmaTuron]

This has been continued in #589