Hybrid Computational-Experimental Data for Self-Assembling Peptide Design

Supporting data for a paper on hybrid computational-experimental design of self-assembling π-conjugated peptides. The data was produced by researchers at the University of Chicago, including Kirill Shmilovich and Andrew L. Ferguson. The repository contains code and data supporting the paper's findings.

Use Cases

• Training machine learning models for peptide property prediction based on computational and experimental features.
• Validating computational design workflows with experimental results mentioned in the paper.
• Benchmarking new algorithms for materials discovery against the provided hybrid dataset.

Strengths

• Data is directly tied to a peer-reviewed scientific publication, providing academic context.
• The hybrid approach combines computational and experimental data, which may increase reliability.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

University of Chicago research group.

Collection Method

Generated through a hybrid computational-experimental workflow described in the associated paper.