Comparison of R² and RMSE for pIC50 Across Chemical Representations

A dataset by Raúl Acosta-Murillo, last updated in March 2026, comparing the performance of different chemical representations for predicting pIC50 values. The 5.5 KB Excel file contains coefficient of determination (R²) and Root Mean Square Error (RMSE) values, with the highest-performing representation indicated in bold. The dataset's specific row count and column details are not provided in the metadata.

Use Cases

• Benchmarking chemical fingerprint performance for pIC50 prediction based on R² and RMSE metrics.
• Selecting optimal molecular representations for QSAR modeling based on comparative performance data.
• Evaluating the predictive accuracy of models like Ridge and Lasso on cancer bioactivity data.

Strengths

• Data is licensed under CC-BY-4.0, permitting open sharing and adaptation.
• File size is 5.5 KB, indicating a compact and easily downloadable dataset.
• Last update timestamp is precisely recorded as 2026-03 17:36:09.

Limitations

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

Provenance

Source

figshare, authored by Raúl Acosta-Murillo.

Collection Method

Likely contains aggregated or calculated performance metrics from computational experiments.

Time Range

The dataset's temporal coverage is not specified.

Freshness

Last updated 2026-03-17 17:36:09; freshness should be verified.

Geography

The dataset's spatial coverage is not specified.