DLAM: Deep Learning Predictions for Essential Proteins

A dataset containing predictions for protein essentiality generated by the DLAM deep learning model. The model integrates domain composition, subcellular localization, orthology, gene expression, and protein-protein interaction data. The dataset was authored by Shunxian Zhou and last updated on April 14, 2026.

Use Cases

• Benchmark new essential protein prediction models based on the reported performance metrics.
• Analyze the relationship between multi-source biological cues and protein essentiality based on the integrated features.
• Study the performance of attention-enhanced networks in biological classification tasks based on the described DLAM architecture.

Strengths

• Model performance is quantitatively reported with metrics like ROC-AUC, AP, and F1-score.
• Data is licensed under CC-BY-4.0, permitting reuse with attribution.
• The underlying model was evaluated on two established datasets, DIP and BioGRID.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is small at 194.5 KB, indicating limited scope.

Provenance

Source

figshare, authored by Shunxian Zhou.

Collection Method

Predictions generated by the DLAM deep learning framework.

Time Range

null

Freshness

Last updated 2026-04-14 22:01:29; freshness should be verified.

Geography

null