Pre-fitted Bayesian Models for Gene Panel Selection in Spatial Transcriptomics

Three pre-fitted Bayesian models for gene panel selection, each derived from a distinct spatial transcriptomics dataset. The models are fitted on data from the Zhang, Moffit, and Codeluppi datasets, as described in the associated paper. Author Yida Zhang from Harvard University made these models available via the paperswithcode platform.

Use Cases

• Simulating gene panel performance based on parameters fitted to the Zhang DARTFISH dataset
• Benchmarking new gene selection algorithms against models fitted to the Moffit MERFISH dataset
• Evaluating the transferability of Bayesian selection frameworks using the Codeluppi osmFISH model

Strengths

• Models are fitted on three distinct, named experimental datasets (Zhang, Moffit, Codeluppi)
• The associated paper provides a methodological context for the Bayesian framework

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

paperswithcode

Collection Method

Likely contains parameters from Bayesian models fitted to experimental spatial transcriptomics data.