Request for Model Evaluation Code Release

[i-am-your-brother]

Thank you for releasing the DNA-Diffusion codebase — it’s been really helpful for exploring generative DNA sequence modeling.

I noticed that while the repository includes training and inference scripts, the code used for evaluating the model (e.g., computing the reported performance metrics in the paper) doesn’t seem to be included.

Would it be possible to release the evaluation code as well? This would help the community:

Reproduce the paper’s results more faithfully

Compare new models fairly against DNA-Diffusion

Ensure consistency in evaluation pipelines

If the evaluation depends on specific datasets or preprocessing steps, pointers to those resources would also be greatly appreciated.

Thanks again for your work and for making it available to the community!

[github-actions[bot]]

This issue is stale because it has been open for 60 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 7 days since being marked as stale.

[ssenan]

Hi thanks for your interest in the evaluation code. Some other members of the lab are working on building a library to make this more reproducible for users doing research in this area. Once they have made it public I'll have them link the GitHub in this issue