Machine Learning Model for Photocatalytic Aldehyde Coupling with SHAP Interpretation

439 literature data points were used to develop an interpretable machine learning workflow for photocatalytic aldehyde coupling reactions. The dataset, authored by Jinya Li and last updated on 2026-05-22, supports model development and external validation. SHAP analysis was applied to identify key steric and electronic descriptors for reaction understanding and optimization.

Use Cases

• Training predictive models for photocatalytic coupling yields based on steric and electronic descriptors.
• Interpreting reaction mechanisms using SHAP analysis on the provided chemical features.
• Benchmarking new machine learning workflows for chemical reaction optimization against the published model.
• Guiding experimental design for sustainable synthesis by identifying key reaction parameters.

Strengths

• Dataset contains 439 curated literature data points.
• Model robustness is supported by external validation as mentioned in the description.
• Workflow is interpretable, utilizing SHAP analysis to identify key descriptors.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect publication bias inherent to the literature sources compiled.

Provenance

Source

figshare

Collection Method

Compiled from 439 literature data points.

Freshness

Last updated 2026-05-22 20:05:10; freshness should be verified.