🦠 Model Request: HDAC3i-Finder about ersilia

[Richiio]

Hi @GemmaTuron @HellenNamulinda. This model has been successfully tested and is working. Here is a pull request to that
https://github.com/ersilia-os/eos1n4b/pulls

[GemmaTuron]

Hi @HellenNamulinda and @Richiio

Thanks for the work. I completely agree with @HellenNamulinda that is best to return only the result as the probability, but, in order to keep it more consistent with other Ersilia models, I suggest to avoid modifying the service.py unless it is really essential - simply in the main.py select the probability column and return this as output, @Richiio . Hope this makes sense as well. Just to clarify, Hellen's option is good but we are really trying to homogenize models and keep the service and pack files as they are. Let me know once the changes are incorporated!

[Richiio]

@GemmaTuron New issue created for suggested model for incorporation

[GemmaTuron]

/approve

[github-actions]

New Model Repository Created! 🎉

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

🔗 ersilia-os/eos1n4b

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!

[Richiio]

Here is the output csv

output.csv

[HellenNamulinda]

Hello @Richiio,
Great work 👏

However, I have a suggestion for the output.
Running the model using the run.sh returns three columns,

SMILES,Bioactivity_pre,Probability_active
c1(nc2c([nH]1)ccc(c2)OC(F)F)S(=O)Cc1c(c(ccn1)OC)OC,Active,0.9937094449996948

And that might return a list(three values with column 1 and column2 being nulls) instead of a single value when run within ersilia.

Ersilia output for this model is a single float; Probability_active.
How about we return that probability? and not all the three three columns?

Since that output for run.sh is good as it helps one to know the input smiles and their scores, we shouldn't drop the columns at that point.

But a slight change in service.py

   R += [
                   {"outcome": [Float(x) for x in r]}
               ]  # <-- EDIT: Modify according to type of output (Float, String...)

to

                R += [
                    {"outcome": [Float(x) for x in r[1]}
                ]  # <-- EDIT: Modify according to type of output (Float, String...)

will return only the last column(Prob_active) whenever the model is run within ersilia.

[Richiio]

Thanks @HellenNamulinda. Null error has been fixed @GemmaTuron

[Richiio]

Output before edit

output2.csv

Output after edit

output.csv

[Richiio]

For the first implementation, we were having a list of [SMILES, bioactivity, prediction_active] but the second was modified to just return the prediction_active @HellenNamulinda @GemmaTuron

[HellenNamulinda]

Perfect @Richiio 👏 ,
I've seen the changes made in the PR

[GemmaTuron]

@Richiio I've left comments on the PR and on Slack, please check and update the code, thanks!

[GemmaTuron]

Hi @Richiio

Any updates on this model?

[GemmaTuron]

This model is incorporated, thanks @Richiio !