ML Dataset Cyanobacteria

These contain the positive and negative dataset of cyanobacterial promoter sequences; where each sequence is 100 bases long. The positive dataset has been generated by taking the 100 bases upstream of each gene sequence. The negative dataset has been generated by taking -300 to -200 of particular gene (300 to 200 base upstream sequences are taken)

本数据集包含蓝细菌启动子序列的正负样本集，所有序列长度均为100个碱基。正样本集通过提取每个基因序列上游的100个碱基构建而成。负样本集则通过提取特定基因上游-300至-200区间的序列构建而成，即选取该基因上游300到200位的碱基序列。