Document the hpa/ family on the card

README.md

@@ -1,5 +1,4 @@
 ---
-license: mit
 library_name: cell-fm
 tags:
   - biology
@@ -9,34 +8,22 @@ tags:
   - flow-matching
 ---
 
-# CELL-FM
+# CELL-FM weights
 
-Model checkpoints for **CELL-FM**, a flow-matching model that generates cell
-microscopy images from protein sequence.
-
-One subfolder per model family. Point a loader at the subfolder it needs; the
-demo code does this through `CELLFM_MODEL_REPO` + a path prefix.
-
-## `condenseq/` — sequence-conditioned condensate imaging
-
-Trained on CondenSeq, 160x160 GFP images. Drives the condensate titration demo:
-sequence in, condensate-probability curve out, integrated into AUC and AAC.
+Checkpoints behind the [CELL-FM CondenSeq demo](https://huggingface.co/spaces/BoHuangLab/CELL-FM).
 
 | File | Model | Source checkpoint |
 |---|---|---|
-| `condenseq/cellfm_seq2img.bin` | CELL-FM CS sequence-to-image generator, ESM-C 600M encoder included (745 M params) | `pretrain_condenseq/cellfm_seq2img/checkpoint-50000` |
+| `condenseq/cellfm_seq2img.bin` | CELL-FM CS sequence-to-image generator (includes the ESM-C 600M encoder) | `pretrain_condenseq/cellfm_seq2img/checkpoint-50000` |
 | `condenseq/vae.bin` | Image VAE, 160x160, 3 down blocks, 4 latent channels | `pretrain_condenseq/vae/checkpoint-50000` |
-| `condenseq/vit_cls.bin` | ViT condensed/diffuse classifier, 2-channel 160x160 input (26 M params) | `PT_CondenSeq_img_ViT_cls_R1/checkpoint-10000` |
-
-Hyperparameters mirror `scripts/cell_fm_cs/evaluate_seq2img.sh` and
-`scripts/vit_cls_condenseq_img/pretrain.sh` in the CELL-FM repository, and are set
-in `huggingface_space/pipeline.py` there.
-
-Reference values at 512 images / 100 ODE steps / seed 6: NUP98 WT gives AUC 0.4896
-and AAC 0.0001; its 1F->S mutant gives AUC 0.4561.
-
-## Adding a model family
-
-Upload under a new prefix (`hpa/`, `opencell_3d/`, ...) and add a section here.
-`upload_weights.py` in the demo takes a `{path_in_repo: local_checkpoint}` map, so
-new families need only a new entry.
+| `condenseq/vit_cls.bin` | ViT condensed/diffuse classifier, 2-channel 160x160 input | `PT_CondenSeq_img_ViT_cls_R1/checkpoint-10000` |
+| `hpa/cellfm_seq2img.bin` | CELL-FM virtual-staining generator for HPA, 256x256, 3-channel conditioning (includes the ESM-C 600M encoder) | `pretrain_hpa/cellfm_seq2img/checkpoint-50000` |
+| `hpa/vae.bin` | Image VAE, 256x256, 3 down blocks, 4 latent channels | `pretrain_hpa/vae/checkpoint-50000` |
+| `hpa/anchor_cell.npy` | The fixed cell every NLS-screening image is conditioned on: `(3, 256, 256)` float32 in [-1, 1], channels nucleus, ER, microtubules. HPA gene H3C13, cell crop `1194_B2_2_4` | built |
+| `hpa/anchor_masks.npz` | Two 256x256 boolean masks over that cell, `nucleus` and `cell`; cytoplasm is `cell & ~nucleus` | built |
+
+Hyperparameters for the CondenSeq models are set in `pipeline.py` in the Space and mirror
+`scripts/cell_fm_cs/evaluate_seq2img.sh` and
+`scripts/vit_cls_condenseq_img/pretrain.sh` in the CELL-FM repository. The HPA
+hyperparameters are spelled out in `notebooks/nls_screening.ipynb` and mirror
+`scripts/cell_fm/evaluate_virtual_staining_hpa_dict.sh`.