Genentech/enformer-data

该数据集包含了用于训练、验证和测试Enformer模型的特定基因组区间，Enformer模型是一个深度学习架构，用于从DNA序列预测功能基因组轨迹。区间提供了人类和小鼠基因组的版本。按照出版物中的方法，我们使用hg38参考基因组将Basenji2数据集的输入序列从原来的131,072 bp扩展到196,608 bp。数据集包含两个TSV文件，分别对应人类（hg38）和小鼠（mm10）的基因组区间，以及两个用于创建这些文件的Jupyter笔记本。

This dataset contains the specific genomic intervals used for training, validating, and testing the Enformer model, a deep learning architecture for predicting functional genomic tracks from DNA sequence. The intervals are provided for both human and mouse genomes. As done in the publication, we modified the Basenji2 dataset by extending the input sequence to 196,608 bp from the original 131,072 bp using the hg38 reference genome. The dataset includes two TSV files for human (hg38) and mouse (mm10) genomic intervals, along with two Jupyter notebooks for creating these files.