# Modify gene identifiers stored in existing scVI model

**URL:** <https://discourse.scverse.org/t/modify-gene-identifiers-stored-in-existing-scvi-model/3602>\
**Category:** scvi-tools\
**Created:** [April 11, 2025, 2:52pm UTC](https://discourse.scverse.org/t/modify-gene-identifiers-stored-in-existing-scvi-model/3602 "2025-04-11T14:52:14Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![pcm32](https://yyz1.discourse-cdn.com/flex035/user_avatar/discourse.scverse.org/pcm32/32/1160_2.png) [@pcm32](https://discourse.scverse.org/u/pcm32)\
**Post date:** [April 11, 2025, 2:52pm UTC](https://discourse.scverse.org/t/modify-gene-identifiers-stored-in-existing-scvi-model/3602/1 "2025-04-11T14:52:14Z")

</div>

Hi! I trained a lot of scVI models with different parameters to asses their impact, however I realised at the end of the exercise that the original AnnData file was indexed in var through a simple numeric index (so the index wasn’t either gene identifiers nor gene symbols). It took quite a while to train all the models. Is it possible to modify, perhaps loading as a torch object, the models so that I can only change the gene labels used in the model (so that I can use them for cell type labelling with other datasets)?

If I load the model through torch:

```auto
model = torch.load(f"{model_path}/model.pt", map_location=torch.device("cpu"))

```

I can see these two dictionary elements with arrays containing my gene indices:

```auto
>> model['var_names']
array(['67', '83', '125', ..., '60058', '60060', '60159'], dtype=object)
>> model['attr_dict']['registry_']['field_registries']['X']['state_registry']['column_names']
array(['67', '83', '125', ..., '60058', '60060', '60159'], dtype=object)

```

They contain the same values, but they are different elements in memory (if I modify one, the other remains as it was). Would it suffice to replace the values in these arrays? Or is there something else in the torch model that would require being changed? Or is there a method from scvi that would allow me to replace these indices more cleanly without the need to fix this through torch and then re-serialise?

Thanks!

---

<div class="post-metadata">

**Author:** ![ori-kron-wis](https://yyz1.discourse-cdn.com/flex035/user_avatar/discourse.scverse.org/ori-kron-wis/32/1099_2.png) [@ori-kron-wis](https://discourse.scverse.org/u/ori-kron-wis)\
**Post date:** [April 20, 2025, 1:59pm UTC](https://discourse.scverse.org/t/modify-gene-identifiers-stored-in-existing-scvi-model/3602/2 "2025-04-20T13:59:04Z")

</div>

if I understood you correctly, you can load the saved model simply with  
`model = SCVI.load(pretrained_scvi_path, adata=adata_tmp)`  
and adata\_tmp will be the other adata you use, where its var\_names might be different than originally trained, like other indices(although it should be the same number of genes and order matters). The rest of registry for model will initialise correctly. You should be able to fine tune training then.

I think you method will work also though. you can compare them.

Not sure it will help here but another more general option will be to use `prepare_query_anndata` and than `load_query_data` with the new dataset, but here it will look for common gene indices between the model and new adata, order them as the model expect and pad with 0 those that are missing. You might use that once you already fixed the saved models.