Mechanochemical Co-crystallization Training Data and Chemical Descriptors

University of Bath research data supports a study on mechanochemical co-crystallization. The dataset comprises three parts: raw PXRD data for training, Excel files with reaction outcomes and chemical descriptors, and a Python algorithm for prediction. Author Jan Roland Gröls published this data via paperswithcode.

Use Cases

• Training predictive models for co-crystallization outcomes based on chemical descriptors.
• Analyzing relationships between reaction conditions and results using tabular reaction data.
• Validating computational methods against experimental PXRD data.

Strengths

• Data is structured into three distinct, purpose-built components: training data, algorithm inputs, and code.
• Includes raw experimental data (PXRD) alongside processed chemical descriptors.

Limitations

• Row count and dataset scale are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

University of Bath, Jan Roland Gröls

Collection Method

Supports a research publication; likely contains experimental and computational data.