Approximately 10,000 novel Polyhydroxyalkanoate synthase protein sequences were generated using a conditional variational autoencoder trained on native sequences from Uniprot. The dataset includes 16 sequences selected for in vivo validation based on conserved residues and structural features. Two novel enzymes with 87 and 98 amino acid substitutions were confirmed active in yeast S. cerevisiae.
Use Cases
- Training generative models for protein sequence design based on native enzyme sequences.
- Benchmarking novel enzyme activity predictions based on structural features like conserved catalytic amino acids.
- Analyzing sequence diversity and amino acid substitution patterns in engineered PHA synthases.
Strengths
- Contains approximately 10,000 generated protein sequences.
- Includes 16 sequences with documented selection criteria for validation.
- Two sequences were experimentally confirmed active in yeast.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Dataset size is 148.7 KB, indicating a limited scope.
Provenance
- Source
- figshare, author Tuula Tenkanen.
- Collection Method
- Sequences generated by a conditional variational autoencoder trained on native protein sequences from Uniprot.
- Freshness
- Last updated 2026-03-19 17:34:30; freshness should be verified.