LLOV Model Results: 500 Parameter Combinations for Bat NPC1 Binding

58.7 MB of model results evaluating LLOV binding strength to bat NPC1. The data includes evaluation metrics for 500 sets of parameter combinations, results from 100 bootstrap iterations, and SHAP values for variable importance. Author Adrian Castellanos published the dataset on figshare under a CC-BY-4.0 license, with a last update in May 2026.

Use Cases

• Benchmarking model performance based on evaluation metrics for 500 parameter combinations.
• Assessing model stability and confidence intervals based on 100 bootstrap iterations.
• Interpreting model predictions and feature importance based on SHAP values for each variable.
• Selecting optimal hyperparameters for similar bioinformatics tasks based on the grid of tested values.

Strengths

• Includes results for 500 distinct parameter combinations, allowing for systematic hyperparameter exploration.
• Provides robustness analysis through 100 bootstrap iterations for the chosen parameter set.
• Offers model interpretability with SHAP values calculated for each variable across the bootstrap iterations.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for specific modeling tasks.
• Description metadata is limited; actual data quality and structure require manual inspection.

Provenance

Source

figshare

Collection Method

Results from a computational model evaluating LLOV binding to bat NPC1.

Freshness

Last updated 2026-05-20 13:40:38; freshness should be verified.