Data-Driven Design of Organic Semiconductors Exhibiting Low Reorganization Energy via Hier

A dataset of organic semiconductor-like molecules generated by a machine learning framework combining hierarchical variational autoencoders, Gaussian mixture regression, and Bayesian optimization. The data was created by Yamato Nakanishi and published on figshare in June 2026. It includes molecules designed to exhibit low reorganization energy and high carrier mobility.

Use Cases

• Training generative models for molecular design based on latent space representations.
• Optimizing organic semiconductor candidates for high carrier mobility based on reorganization energy.
• Analyzing the relationship between molecular structure descriptors and electronic transport properties.

Strengths

• Dataset is associated with a published methodology combining HVAE, GMR, and Bayesian optimization.
• Includes a molecule identified as having a new minimum hole reorganization energy via sulfur-to-nitrogen substitution.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data size is 59.7 KB, indicating a very limited scope.

Provenance

Source

figshare

Collection Method

Generated via a data-driven framework combining hierarchical variational autoencoder, Gaussian mixture regression, and Bayesian optimization.

Freshness

Last updated 2026-06-04 05:03:38; freshness should be verified.