lamm-mit/silkome-full-idv-grouped
收藏资源简介:
lamm-mit/silkome-full-idv-grouped 是一个按idv分组的全类别蜘蛛丝蛋白质组(Silkome)数据集,用于从所有可用的蜘蛛丝蛋白质序列类别中预测牵引丝纤维级别的机械性能(如韧性、弹性模量、强度和应变),这些序列与相同的测量纤维/性能标识符相关联。该数据集源自lamm-mit/silkome-full,但不是每行放置一个蛋白质序列,而是将具有相同idv的序列行分组为一个样本,形成从序列集到机械性能的映射。这种设计适用于ESMC嵌入模型,后接集合级聚合模型,以分析序列类别组成和序列-性能关系。
lamm-mit/silkome-full-idv-grouped is an idv-grouped all-category Silkome dataset for predicting dragline fiber-level mechanical properties from all available Silkome sequence categories associated with the same measured fiber/property identifier. This dataset is derived from lamm-mit/silkome-full. Instead of placing one protein sequence in each row, this dataset groups sequence rows with the same idv into one sample, mapping all available Silkome sequences for one idv to mechanical properties like toughness, elastic modulus, strength, and strain. This formulation is designed for ESMC embedding models followed by a set-level aggregation model, enabling analysis of sequence category composition and sequence-property relationships.




