OpenSMILES Specification Data

该数据集展示了smirk和smirk-gpe分词器的性能，它们能够完整地表示OpenSMILES规范。同时，smirk分词器的源代码可在GitHub上获取，附带有示例笔记本。该任务的目的是评估分词器在分子建模中的覆盖范围和性能。This dataset showcases the performance of the smirk and smirk-gpe tokenizers, which are fully compliant with the OpenSMILES specification. Meanwhile, the source code of the smirk tokenizer is publicly available on GitHub, with accompanying example notebooks. The goal of this task is to assess the coverage and performance of these tokenizers in molecular modeling.