Synthesis of Metal-Organic Frameworks: capturing chemical intuition

A methodology using machine learning to capture chemical intuition from a set of partially failed attempts to synthesize the metal-organic framework HKUST-1. The dataset, reported by Seyed Mohamad Moosavi of École Polytechnique Fédérale de Lausanne, reconstructs a typical track of failed experiments from a successful search for optimal synthesis conditions. It illustrates the importance of quantifying unwritten guidelines used by synthetic chemists for novel materials synthesis.

Use Cases

• Predicting optimal synthesis conditions for metal-organic frameworks based on learned patterns from failed experiments.
• Training models to capture and quantify the chemical intuition of synthetic chemists.
• Analyzing the relationship between synthesis parameters and material properties like surface area.

Strengths

• Focuses on a specific, high-value material (HKUST-1) with the highest reported surface area.
• Addresses the underreported domain of failed experiments, a key source of chemical intuition.

Limitations

• Row count is 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

École Polytechnique Fédérale de Lausanne

Collection Method

Reconstructed from a track of failed experiments in a successful search for optimal synthesis conditions.