# \#gimvi

**URL:** https://discourse.scverse.org/tag/gimvi/27.md

[Latest](https://discourse.scverse.org/latest.md) · [Categories](https://discourse.scverse.org/categories.md) · [Tags](https://discourse.scverse.org/tags.md)

---

## [GIMVI genes imputation](https://discourse.scverse.org/t/gimvi-genes-imputation/3507)

<div class="topic-metadata">

**Author:** [@alexis](https://discourse.scverse.org/u/alexis)\
**Replies:** 1\
**Last updated:** [February 26, 2025, 9:47am UTC](https://discourse.scverse.org/t/gimvi-genes-imputation/3507 "2025-02-26T09:47:51Z")

</div>

Hello ! I have a very basic question on GIMVI model. This model is designed to “input missing genes on spatial data”, based on a single-cell reference. However, the tutorial resitricts the single-cell reference to genes…

---

## [Can gimvi be used to symmetrically impute missing genes in two spatial datasets?](https://discourse.scverse.org/t/can-gimvi-be-used-to-symmetrically-impute-missing-genes-in-two-spatial-datasets/801)

<div class="topic-metadata">

**Author:** [@cornhundred](https://discourse.scverse.org/u/cornhundred)\
**Replies:** 1\
**Last updated:** [December 10, 2022, 3:01am UTC](https://discourse.scverse.org/t/can-gimvi-be-used-to-symmetrically-impute-missing-genes-in-two-spatial-datasets/801 "2022-12-10T03:01:42Z")

</div>

Hi, we have two spatial (MERFISH) datasets with partially overlapping gene panels. It seems possible to use gimvi to impute the genes from one dataset (e.g., panel 1 genes) into another dataset (e.g., panel 2 genes), but…

---

## [Understanding gimVI loss logits](https://discourse.scverse.org/t/understanding-gimvi-loss-logits/804)

<div class="topic-metadata">

**Author:** [@tony](https://discourse.scverse.org/u/tony)\
**Replies:** 0\
**Last updated:** [October 6, 2022, 9:46pm UTC](https://discourse.scverse.org/t/understanding-gimvi-loss-logits/804 "2022-10-06T21:46:34Z")

</div>

Thanks for sharing the idea and codes of gimVI. I am trying to understand the loss from the code here, and please correct me if I am wrong here. Lets say we have a sequence data denoted as seq (e.g. n\* 3000), and spati…

---

## [Understanding GIMVI trainingplan](https://discourse.scverse.org/t/understanding-gimvi-trainingplan/145)

<div class="topic-metadata">

**Author:** [@thisisyichenzhang](https://discourse.scverse.org/u/thisisyichenzhang)\
**Replies:** 4\
**Last updated:** [July 29, 2021, 1:13am UTC](https://discourse.scverse.org/t/understanding-gimvi-trainingplan/145 "2021-07-29T01:13:18Z")

</div>

Hi, I am trying to understand the adversarial training in the GIMVItraining plan. If I understand it correctly, the purpose of this is to encourage latent space mixing, e.g., the latent code learnt from adata\_seq can al…

---

## [gimVI seq and spatial mixing](https://discourse.scverse.org/t/gimvi-seq-and-spatial-mixing/31)

<div class="topic-metadata">

**Author:** [@scrnaseq](https://discourse.scverse.org/u/scrnaseq)\
**Replies:** 4\
**Last updated:** [December 22, 2020, 4:16am UTC](https://discourse.scverse.org/t/gimvi-seq-and-spatial-mixing/31 "2020-12-22T04:16:58Z")

</div>

Thank you for these great set of tools! I’ve been following the gimVI tutorial for integrating my scRNA-seq data with spatial data, but I’ve noticed that the seq and spatial data don’t mix well when I plot the model-outp…
