Thanks for releasing the ProtiCelli code and checkpoints — great work in the bioRxiv preprint.
The README documents Model.download_checkpoints() for pre-trained weights, but I don't see a link or instructions for the underlying training/evaluation data (the 1.23M HPA images used to train ProtiCelli, or the held-out evaluation split used for the benchmarks in the paper).
Would it be possible to release:
The list of image/protein/cell-line identifiers (or accession numbers) used for the train/val/test splits, and
Any preprocessing metadata needed to reproduce the exact splits (e.g., HPA image IDs, antibody IDs)?
This would help with reproducing the reported metrics and benchmarking follow-up work.
Thanks!
Thanks for releasing the ProtiCelli code and checkpoints — great work in the bioRxiv preprint.
The README documents Model.download_checkpoints() for pre-trained weights, but I don't see a link or instructions for the underlying training/evaluation data (the 1.23M HPA images used to train ProtiCelli, or the held-out evaluation split used for the benchmarks in the paper).
Would it be possible to release:
The list of image/protein/cell-line identifiers (or accession numbers) used for the train/val/test splits, and
Any preprocessing metadata needed to reproduce the exact splits (e.g., HPA image IDs, antibody IDs)?
This would help with reproducing the reported metrics and benchmarking follow-up work.
Thanks!