AI4Protein/ssp_q3

---
license: apache-2.0
task_categories:
- token-classification
tags:
- chemistry
- biology
---

Dataset Summary

The study of a protein’s secondary structure (Sec. Struc. P.) forms a fundamental cornerstone in understanding its biological function. This secondary structure, comprising helices, strands, and various turns, bestows the protein with a specific three-dimensional configuration, which is critical for the formation of its tertiary structure. In the context of this work, a given protein sequence is classified into three distinct categories, each representing a different structural element: H - Helix (includes alpha-helix, 3-10 helix, and pi helix), E - Strand (includes beta-strand and beta-bridge), C - Coil (includes turns, bends, and random coils).

Data Fields

seq: a string containing the protein sequence

label: a sequence containing the structural label of each residue.

Original Dataset Name: biomap-research/ssp_q3

Original Author / Organization: Biomap

Original URL: https://huggingface.co/datasets/biomap-research/ssp_q3

Original License: Apache License 2.0

No changes were made to the data except for the column name. All credit and rights belong to the original authors.

许可证：Apache-2.0
任务类别：
- 词元分类（Token Classification）
标签：
- 化学
- 生物学

数据集概述
对蛋白质二级结构（Sec. Struc. P.）的研究是理解其生物学功能的核心基石。这类二级结构由螺旋、折叠链与各类转角构成，赋予蛋白质特定的三维构型，这对于其三级结构的形成至关重要。在本研究中，给定的蛋白质序列将被划分为三类不同的结构元素：H-螺旋（包括α-螺旋、3-10螺旋和π螺旋）、E-折叠链（包括β-折叠链与β-桥结构）、C-卷曲（包括转角、弯折与无规卷曲）。

数据字段
seq：包含蛋白质序列的字符串
label：包含每个残基结构标签的序列

原始数据集名称：biomap-research/ssp_q3
原始作者/机构：Biomap
原始链接：https://huggingface.co/datasets/biomap-research/ssp_q3
原始许可证：Apache许可证2.0
本数据集仅对列名进行了调整，未对原始数据作出任何修改，所有权益与荣誉均归属于原作者。