Request for Release of Processed Training Data

[Pan_Li]

I would like to express my appreciation for AlphaGenome has been incredibly useful for my research project. While the methodology section in the paper thoroughly describes the training data pre-processing pipeline, I’m concerned that independently replicating these steps might introduce inconsistencies with the original implementation. Would it be possible to consider releasing the processed training data? This would ensure methodological consistency and greatly facilitate reproducibility within the research community.