CGL and Rho-GTPase Data for Measuring Irreversibility from Learned Representations

Chih-Wei Joshua Liu from the Massachusetts Institute of Technology provides data and results for the paper 'Measuring irreversibility from learned representations of biological patterns'. The archive includes raw data from CGL simulations and Rho-GTPase experiments, along with results from FVAE model training. Additional data and results are included for analyses related to a specific figure.

Use Cases

• Training representation learning models based on CGL simulation data mentioned in the description
• Evaluating irreversibility metrics based on learned representations from Rho-GTPase experimental data
• Reproducing the analysis for Figure S10 based on the provided 'vary_near_critical' data and results

Strengths

• Data is directly associated with a published research paper from MIT
• Includes both simulated (CGL) and experimental (Rho-GTPase) data sources
• Provides complete training results for the FVAE model used in the study

Limitations

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

Provenance

Source

Massachusetts Institute of Technology

Collection Method

Likely contains data from computational simulations (CGL) and laboratory experiments (Rho-GTPase).