hutaobo/stGPT-Xenium-L3-CNN-v0.1

stGPT-Xenium L3 CNN v0.1

stGPT-Xenium is a Xenium-first morpho-molecular representation model series for spatial pathology research. This repository contains the first public model artifact in the series: L3-CNN-v0.1, a lightweight CNN-based pilot checkpoint for contour-level XeniumSlide learning.

stGPT learns the morpho-molecular tissue representation; spatho turns it into auditable spatial pathology evidence.

Release Status

• Public research artifact.
• Not a diagnostic model and not for clinical decision support.
• First checkpoint in the stGPT-Xenium series, intended for reproducibility, interface testing, and transparent model-development tracking.
• This is not a universal foundation model yet; stronger multi-case and slide-holdout models will be released as later versions.

What This Checkpoint Is

• Model family: stGPT-Xenium
• Release: L3-CNN-v0.1
• Backend: lightweight CNN contour H&E encoder
• Training unit: XeniumSlide contour/region-level image-gene-spatial learning
• Representative checkpoint case: Xenium_Prime_Human_Prostate_FFPE_outs
• Selected from a 39-case L3 morphology-ready A100 pilot where all cases completed successfully

A100 Pilot Summary

• Uploaded/trained L3 cases: 39/39
• Completed metrics: 39/39
• Failed cases: 0
• Checkpoint records: 273
• Error rows: 0
• Mean final validation loss across 39 cases: ~0.180
• Mean final validation gene loss: ~0.00162
• Mean final validation neighbor loss: ~0.0317

Selected checkpoint metrics:

• last_val_loss: 0.1554184090346098
• last_val_gene_loss: 0.0013655137008754
• last_val_neighbor_loss: 0.0067438320256769
• last_val_image_gene_loss: 3.0473387241363525

Files

• checkpoint_best.pt: representative best checkpoint.
• config.yaml: stGPT config used for this case on A100.
• metrics.json: per-step training metrics for this checkpoint.
• stgpt_model_manifest.json: provenance and checksums.
• training_telemetry_summary.json: pilot-level telemetry summary.
• case_metric_summary_all_cases.csv: aggregate training metrics for all 39 pilot cases.
• checkpoint_manifest_all_cases.csv: checkpoint provenance for all pilot cases.

Evidence and Data Policy

A companion private evidence/provenance repository tracks telemetry, evaluation tables, ablations, and model-development evidence. Raw 10x-derived assets are not redistributed here:

• no xenium_slide.zarr
• no H&E patch PNGs
• no OME-TIF or raw image files
• no raw expression matrices

Users should obtain public 10x Genomics Xenium datasets from the original 10x dataset pages and rebuild local XeniumSlide artifacts under the applicable source terms.

Intended Use

Use this checkpoint for:

• testing the stGPT model/package interface
• reproducing the v0.1 checkpoint loading path
• comparing against future stGPT-Xenium releases
• research-only spatial transcriptomics and computational pathology method development

Do not use this checkpoint for:

• diagnosis
• treatment decisions
• clinical reporting
• claims of universal tissue or organ generalization

Limitations

• Single representative checkpoint, not a multi-case global model.
• CNN image encoder baseline; Virchow-precomputed and ablation evidence are tracked separately and will inform later releases.
• Validation is pilot-level and per-case; slide-holdout and cross-case generalization are future release targets.
• Public 10x source data must be accessed from original sources, not from this model repository.

Version Series

Planned naming convention:

• stGPT-Xenium-L3-CNN-v0.1: first public pilot checkpoint, this repo.
• stGPT-Xenium-L3-Virchow-v0.2: planned frozen pathology-encoder checkpoint.
• stGPT-Xenium-Foundation-v1.0: future multi-case/slide-holdout foundation release.