stereopep-ano/stereopep

该数据集包含多个配置，专注于肽类化合物的立体化学和性质研究。主要配置包括：1) StereoPep：提供肽序列、SMILES表示、B值（可能为生物活性指标）、Z值和长度，用于训练、验证和测试；2) diastereomer_pairs：包含非对映异构体对，比较序列、SMILES和B值差异；3) point_mutant_pairs：涉及点突变对，展示突变位置、残基变化和B值变化；4) terminal_tag_pairs：研究末端标签对肽序列和性质的影响。数据集适用于机器学习模型在肽设计、立体化学分析和性质预测中的应用。This dataset includes multiple configurations focused on the stereochemistry and properties of peptide compounds. Key configurations are: 1) StereoPep: Provides peptide sequences, SMILES representations, B-values (likely indicating biological activity or physical properties), Z-values, and lengths, used for training, validation, and testing; 2) diastereomer_pairs: Contains diastereomer pairs, comparing sequences, SMILES, and B-value differences; 3) point_mutant_pairs: Involves point mutant pairs, showing mutation positions, residue changes, and B-value variations; 4) terminal_tag_pairs: Studies the effects of terminal tags on peptide sequences and properties. The dataset is suitable for machine learning models in peptide design, stereochemical analysis, and property prediction.