neuralbioinfo/PhaStyle-ESCHERICHIA

neuralbioinfo/PhaStyle-ESCHERICHIA数据集包含来自大肠杆菌属的噬菌体序列，这些序列被处理为512bp和1022bp的片段。该数据集用于评估ProkBERT PhaStyle模型的泛化性能，特别是基于核苷酸序列预测噬菌体生活方式（溶菌性或温和性）。数据集分为两个部分：segmentdb_512（43,800行，512bp片段）和segmentdb_1022（21,900行，1022bp片段）。每条记录包含字段如唯一标识符、原始序列标识符、生活方式标签、标签的数值表示、序列方向、片段长度和片段在原始序列中的起始位置。

The neuralbioinfo/PhaStyle-ESCHERICHIA dataset consists of phage sequences from the Escherichia genus, processed into 512bp and 1022bp segments. This dataset is used for evaluating the generalization performance of the ProkBERT PhaStyle model, specifically for predicting the lifestyle of phages (virulent or temperate) based on nucleotide sequences. The dataset is split into two parts: segmentdb_512 (43,800 rows, 512bp segments) and segmentdb_1022 (21,900 rows, 1022bp segments). Each record contains fields such as a unique identifier, the identifier of the original sequence, lifestyle label, numeric representation of the label, sequence orientation, segment length, and the starting position of the segment within the original sequence.