LEAF-1 pretraining corpus: cfDNA fragments
This record documents the cell-free DNA (cfDNA) portion of the pretraining corpus of LEAF-1, a DNA language model of cell-free DNA and chromatin-accessibility fragments. The fragment files themselves (211 GB bgzip-compressed, 34.0 billion fragments) are too large for Zenodo and are hosted on Hugging Face: huggingface.c...