Scaffold-Lab: Evaluation Metrics for Protein Backbone Generation Methods

A 5.5 KB dataset from figshare, last updated on 2026-05-22. It contains evaluation results from the Scaffold-Lab framework, which systematically assesses seven protein backbone generation methods. The dataset was authored by Zhuoqi Zheng and is licensed under CC-BY-4.0.

Use Cases

• Benchmarking protein backbone generation methods based on the described metrics of designability, novelty, and diversity.
• Identifying performance bottlenecks in unconditional generation of long proteins based on the study's findings.
• Analyzing the structural properties of generated protein backbones based on the framework's evaluation scope.
• Comparing the efficiency of different generation algorithms based on the metrics included in the unified framework.

Strengths

• Provides a unified evaluation framework (Scaffold-Lab) for systematic comparison of methods.
• Assesses seven representative methods across a range of metrics mentioned in the description.
• Dataset is openly available under a permissive CC-BY-4.0 license.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope or summary-level data.

Provenance

Source

figshare

Collection Method

Likely contains results from the systematic evaluation performed by the Scaffold-Lab framework.

Time Range

null

Freshness

Last updated 2026-05-22 17:46:25; freshness should be verified.

Geography

null