Data Sets and Results for "Improved data sets and evaluation methods for the automatic prediction of DNA-binding proteins"

Data sets and results for "Improved data sets and evaluation methods for the automatic prediction of DNA-binding proteins"<br> <br> The file "dna_binding_protein_sequences.zip" has the training and testing sets from the paper:<br> <br> RLL - "random_&lt;train/test&gt;_full_1000.csv"<br> RSL - "random_&lt;train/test&gt;_40.csv"<br> RS&amp;LL - "random_&lt;train/test&gt;_40_1000.csv"<br> RLL where included positive examples have verified DNA binding activity - "random_&lt;train/test&gt;_hq_1000.csv"<br> The 10 RS&amp;LL data sets - "random_&lt;train/test&gt;_40_1000.csv" + "random_&lt;train/test&gt;_40_1000_cv_&lt;0-8&gt;.csv" The results files are named similarly. See "see_results.ipynb" in the codebase that supplement these data sets<br> The species data sets are derived from "uniprot_data_bac.tab" and "uniprot_data_not_bac.tab." See code. <br> <br> The ESM embeddings used by the XGBoost model are in "dna_binding_protein_esm.zip"《用于DNA结合蛋白自动预测的改进数据集与评估方法》配套数据集及实验结果 文件`dna_binding_protein_sequences.zip`包含本文所用的训练集与测试集，具体如下： RLL：对应`random_<train/test>_full_1000.csv` RSL：对应`random_<train/test>_40.csv` RS&LL：对应`random_<train/test>_40_1000.csv` 包含经验证DNA结合活性正样本的RLL数据集：对应`random_<train/test>_hq_1000.csv` 10组RS&LL数据集由`random_<train/test>_40_1000.csv`与`random_<train/test>_40_1000_cv_<0-8>.csv`组成。 结果文件的命名规则与上述数据集一致，可参阅配套代码库中的`see_results.ipynb`以获取这些数据集的补充信息。 物种相关数据集源自`uniprot_data_bac.tab`与`uniprot_data_not_bac.tab`，具体实现可参阅配套代码。 XGBoost模型所用的ESM嵌入特征存储于`dna_binding_protein_esm.zip`中。