CI-SpliceAI: Benchmark Data for Splice Site Prediction

Benchmark data for evaluating the CI-SpliceAI model, a machine learning tool for predicting splice site alterations. The data is hosted on GitHub and was last updated in May 2026. It was authored by Nathan Fortier and is shared under a CC-BY-4.0 license.

Use Cases

• Benchmarking splice site prediction models based on the provided genomic sequences.
• Comparing the performance of CI-SpliceAI against other algorithms using the benchmark data.
• Training new models for variant effect prediction on splicing based on the benchmark's structure.

Strengths

• Data is openly available under a permissive CC-BY-4.0 license.
• The dataset is versioned and hosted on GitHub, facilitating reproducibility and updates.
• The 14.0 MB file size suggests a focused, manageable benchmark dataset.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for large-scale training.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

GitHub repository YStrauch/CI-SpliceAI__Comparison

Freshness

Last updated 2026-05-13 17:42:52; freshness should be verified.