# \#scrna-seq

**URL:** https://discourse.scverse.org/tag/scrna-seq/1.md

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

---

## [Confused by percent\_top purpose in scanpy.pp.calculate\_qc\_metrics](https://discourse.scverse.org/t/confused-by-percent-top-purpose-in-scanpy-pp-calculate-qc-metrics/4032)

<div class="topic-metadata">

**Author:** [@anjpad](https://discourse.scverse.org/u/anjpad)\
**Replies:** 2\
**Last updated:** [August 19, 2026, 12:35pm UTC](https://discourse.scverse.org/t/confused-by-percent-top-purpose-in-scanpy-pp-calculate-qc-metrics/4032 "2026-08-19T12:35:03Z")

</div>

Hi! As I am a beginner at utilizing scanpy, I would like for someone to better help me understand the purpose of percent\_top when calculating qc metrics. How can adding a percent\_top argument change my preprocessing vs. …

---

## [Is older advice for estimating optimal number of epochs for model training of scVI still recommended?](https://discourse.scverse.org/t/is-older-advice-for-estimating-optimal-number-of-epochs-for-model-training-of-scvi-still-recommended/3932)

<div class="topic-metadata">

**Author:** [@timslittle](https://discourse.scverse.org/u/timslittle)\
**Replies:** 6\
**Last updated:** [March 1, 2026, 8:13am UTC](https://discourse.scverse.org/t/is-older-advice-for-estimating-optimal-number-of-epochs-for-model-training-of-scvi-still-recommended/3932 "2026-03-01T08:13:51Z")

</div>

Hi Team, Earlier docs for scVI mention that the number of epochs should scale downwards with number of obs/cells. E.g: “(\[For\] \> 100,000 cells) you may only need ~10 epochs.” I cannot find similar advice on the modern d…

---

## [\[Tool\] scVAE-Annotator: Automated Cell Type Annotation for scRNA-seq with VAE and Adaptive Marker Discovery](https://discourse.scverse.org/t/tool-scvae-annotator-automated-cell-type-annotation-for-scrna-seq-with-vae-and-adaptive-marker-discovery/3919)

<div class="topic-metadata">

**Author:** [@or4k2l](https://discourse.scverse.org/u/or4k2l)\
**Replies:** 7\
**Last updated:** [February 4, 2026, 7:03am UTC](https://discourse.scverse.org/t/tool-scvae-annotator-automated-cell-type-annotation-for-scrna-seq-with-vae-and-adaptive-marker-discovery/3919 "2026-02-04T07:03:23Z")

</div>

Hi community, I’d like to share scVAE-Annotator, a Python pipeline for automated cell type annotation in single-cell RNA-seq data that addresses common challenges in cell type identification. Key Features: VAE-based d…

---

## [Remove ribosomal genes driving variation (on PC plot)?](https://discourse.scverse.org/t/remove-ribosomal-genes-driving-variation-on-pc-plot/3902)

<div class="topic-metadata">

**Author:** [@npont](https://discourse.scverse.org/u/npont)\
**Replies:** 0\
**Last updated:** [December 17, 2025, 10:19am UTC](https://discourse.scverse.org/t/remove-ribosomal-genes-driving-variation-on-pc-plot/3902 "2025-12-17T10:19:59Z")

</div>

Hi all, Following the tutorial of scanpy about clustering ( Preprocessing and clustering — scanpy ), I plotted some QC metrics (computed with sc.pp.calculate\_qc\_metrics(adata, qc\_vars=\[“mt”, “ribo”\])) on the first four …

---

## [Question about complex experiment](https://discourse.scverse.org/t/question-about-complex-experiment/3864)

<div class="topic-metadata">

**Author:** [@dackjames](https://discourse.scverse.org/u/dackjames)\
**Replies:** 1\
**Last updated:** [November 25, 2025, 7:39pm UTC](https://discourse.scverse.org/t/question-about-complex-experiment/3864 "2025-11-25T19:39:01Z")

</div>

Hi everyone, I’m starting a fairly complex experiment that includes 10x single-cell, single-nucleus, and 10x multiome (snRNA-seq + scATAC-seq from the same nucleus), with control and treatment groups spread across all t…

---

## [Posterior probability interpretability (soft=True)](https://discourse.scverse.org/t/posterior-probability-interpretability-soft-true/3787)

<div class="topic-metadata">

**Author:** [@ondy](https://discourse.scverse.org/u/ondy)\
**Replies:** 1\
**Last updated:** [September 25, 2025, 12:46pm UTC](https://discourse.scverse.org/t/posterior-probability-interpretability-soft-true/3787 "2025-09-25T12:46:32Z")

</div>

Hello, I used scANVI to transfer cell type labels from a single-cell reference to my spatial transcriptomics data (MERFISH). I assigned labels at three hierarchical levels and then compared the prediction scores obtain…

---

## [What kind of data type does infercnvpy need as input?](https://discourse.scverse.org/t/what-kind-of-data-type-does-infercnvpy-need-as-input/3364)

<div class="topic-metadata">

**Author:** [@cuiyiran](https://discourse.scverse.org/u/cuiyiran)\
**Replies:** 0\
**Last updated:** [November 27, 2024, 3:43pm UTC](https://discourse.scverse.org/t/what-kind-of-data-type-does-infercnvpy-need-as-input/3364 "2024-11-27T15:43:10Z")

</div>

Hi, there, I’m using infercnvpy to run my own data which is quite convenient. Since I only have patient data and no normal control, I use the external reference as a control, and I wonder what kind of data type is approp…

---

## [Is it possible to add extra covariate categories to a trained SCVI model?](https://discourse.scverse.org/t/is-it-possible-to-add-extra-covariate-categories-to-a-trained-scvi-model/3276)

<div class="topic-metadata">

**Author:** [@wikiselev](https://discourse.scverse.org/u/wikiselev)\
**Replies:** 3\
**Last updated:** [October 4, 2024, 2:56pm UTC](https://discourse.scverse.org/t/is-it-possible-to-add-extra-covariate-categories-to-a-trained-scvi-model/3276 "2024-10-04T14:56:12Z")

</div>

I execute the following steps to predict cell types in a query dataset using a reference dataset: Train an SCVI model on a reference dataset with categorical covariates. Concatenate query and reference datasets. Create…

---

## [ZeroDivisionError using scvi-tools](https://discourse.scverse.org/t/zerodivisionerror-using-scvi-tools/2500)

<div class="topic-metadata">

**Author:** [@yojetsharma](https://discourse.scverse.org/u/yojetsharma)\
**Replies:** 15\
**Last updated:** [September 23, 2024, 3:07pm UTC](https://discourse.scverse.org/t/zerodivisionerror-using-scvi-tools/2500 "2024-09-23T15:07:33Z")

</div>

I am running snapatac2 tutorial wherein scvi-tools are used to map reference to query (so I am a new scvi-tools at the moment). Reference is a scRNA dataset and query is an atac seq: query= snap.pp.make\_gene\_matrix(atac…

---

## [Handling Non-Matching Categorical Labels in scArches](https://discourse.scverse.org/t/handling-non-matching-categorical-labels-in-scarches/2517)

<div class="topic-metadata">

**Author:** [@yojetsharma](https://discourse.scverse.org/u/yojetsharma)\
**Replies:** 0\
**Last updated:** [September 13, 2024, 8:46pm UTC](https://discourse.scverse.org/t/handling-non-matching-categorical-labels-in-scarches/2517 "2024-09-13T20:46:50Z")

</div>

I’m using scArches to compare gene expression profiles between disease and normal samples. My query dataset contains cells from stem cells of healthy individuals and patients, labeled as WT, LSP2, and LSP3. The reference…

---

## [Can I use the package scib-metrics on methods that don't output an embedding?](https://discourse.scverse.org/t/can-i-use-the-package-scib-metrics-on-methods-that-dont-output-an-embedding/2091)

<div class="topic-metadata">

**Author:** [@mlebel](https://discourse.scverse.org/u/mlebel)\
**Replies:** 6\
**Last updated:** [August 31, 2024, 3:17pm UTC](https://discourse.scverse.org/t/can-i-use-the-package-scib-metrics-on-methods-that-dont-output-an-embedding/2091 "2024-08-31T15:17:48Z")

</div>

Hello, I am currently testing several tools to integrate my data, and I would like to compare them using the metrics computed by scIB. I want to compare outputs of Seurat RPCA, Scanorama and scVI. As far as I understo…

---

## [Benchmarking CellHint with scib-metrics Benchmarker tool how to use embedding\_obsm\_keys](https://discourse.scverse.org/t/benchmarking-cellhint-with-scib-metrics-benchmarker-tool-how-to-use-embedding-obsm-keys/2216)

<div class="topic-metadata">

**Author:** [@bocchiv](https://discourse.scverse.org/u/bocchiv)\
**Replies:** 1\
**Last updated:** [April 25, 2024, 9:27pm UTC](https://discourse.scverse.org/t/benchmarking-cellhint-with-scib-metrics-benchmarker-tool-how-to-use-embedding-obsm-keys/2216 "2024-04-25T21:27:48Z")

</div>

Hi! I am integrating different single-cell atlases and testing different methods like scVI and scANVI and then benchamrking them using scib-metrics package to assess the quality of the integration. However, I also wante…

---

## [Access to each training example's original index in the input Anndata object](https://discourse.scverse.org/t/access-to-each-training-examples-original-index-in-the-input-anndata-object/2153)

<div class="topic-metadata">

**Author:** [@g12bftd](https://discourse.scverse.org/u/g12bftd)\
**Replies:** 0\
**Last updated:** [March 12, 2024, 4:18pm UTC](https://discourse.scverse.org/t/access-to-each-training-examples-original-index-in-the-input-anndata-object/2153 "2024-03-12T16:18:01Z")

</div>

I am training scvi with augmentations. For one of my augmentations, I need access to each cell’s original index in the full input adata object. What is the best way to go about this?

---

## [Is it possible only to calculate metrics related to cell type using scib?](https://discourse.scverse.org/t/is-it-possible-only-to-calculate-metrics-related-to-cell-type-using-scib/1683)

<div class="topic-metadata">

**Author:** [@HelloWorldLTY](https://discourse.scverse.org/u/HelloWorldLTY)\
**Replies:** 1\
**Last updated:** [August 15, 2023, 10:04pm UTC](https://discourse.scverse.org/t/is-it-possible-only-to-calculate-metrics-related-to-cell-type-using-scib/1683 "2023-08-15T22:04:33Z")

</div>

Hi, I am wondering if I can only calculate bio score based on scib\_metrics.Benchmark(). I tried to set batch\_key = None or False, but it does not work. Thanks a lot.

---

## [Could not find function "scvi.model.SCVI.setup\_anndata"](https://discourse.scverse.org/t/could-not-find-function-scvi-model-scvi-setup-anndata/1648)

<div class="topic-metadata">

**Author:** [@183136](https://discourse.scverse.org/u/183136)\
**Replies:** 0\
**Last updated:** [July 29, 2023, 8:42am UTC](https://discourse.scverse.org/t/could-not-find-function-scvi-model-scvi-setup-anndata/1648 "2023-07-29T08:42:26Z")

</div>

I want to integrate datasets with scVI in R，and fllowed the tutorial (Scanpy in R). But, when I setup AnnData for training by typing the following code, it’s error. I don’t sure how to solve it. \> library(reticulate) \> …

---

## [Show cluster numbers on scanpy UMAP plot like in Featureplot in Seurat](https://discourse.scverse.org/t/show-cluster-numbers-on-scanpy-umap-plot-like-in-featureplot-in-seurat/466)

<div class="topic-metadata">

**Author:** [@smk5g5](https://discourse.scverse.org/u/smk5g5)\
**Replies:** 5\
**Last updated:** [June 16, 2023, 4:08pm UTC](https://discourse.scverse.org/t/show-cluster-numbers-on-scanpy-umap-plot-like-in-featureplot-in-seurat/466 "2023-06-16T16:08:53Z")

</div>

Hi, Seurat allows us to set an Ident and when we do a feature plot we can label that feature plot with that ident. If I were to achieve something similar how would I go about it? Thanks

---

## [Plotting scanpy.tl.score\_genes() value using scanpy.pl.stacked\_violin()](https://discourse.scverse.org/t/plotting-scanpy-tl-score-genes-value-using-scanpy-pl-stacked-violin/897)

<div class="topic-metadata">

**Author:** [@seanb80](https://discourse.scverse.org/u/seanb80)\
**Replies:** 1\
**Last updated:** [November 4, 2022, 8:53am UTC](https://discourse.scverse.org/t/plotting-scanpy-tl-score-genes-value-using-scanpy-pl-stacked-violin/897 "2022-11-04T08:53:39Z")

</div>

Hi, I’m interested in using scanpy.pl.stacked\_violin() to plot multiple gene scores sc.tl.score\_genes(). As far as I can tell scanpy.pl.stacked\_violin() only takes var inputs and groups by an obs. Is there a way to do o…

---

## [How to concatenate anndata properly?](https://discourse.scverse.org/t/how-to-concatenate-anndata-properly/887)

<div class="topic-metadata">

**Author:** [@cookiemonster](https://discourse.scverse.org/u/cookiemonster)\
**Replies:** 2\
**Last updated:** [November 3, 2022, 8:13pm UTC](https://discourse.scverse.org/t/how-to-concatenate-anndata-properly/887 "2022-11-03T20:13:43Z")

</div>

I have 4 samples data trying to do batch effect cleaning but when I try to concatenate them it comes out like this sc.pp.filter\_genes(adata1, min\_cells =1) sc.pp.filter\_genes(adata2, min\_cells =1) sc.pp.filter\_genes(a…

---

## [How does one generate a DotPlot with scaled values?](https://discourse.scverse.org/t/how-does-one-generate-a-dotplot-with-scaled-values/715)

<div class="topic-metadata">

**Author:** [@rgranit](https://discourse.scverse.org/u/rgranit)\
**Replies:** 0\
**Last updated:** [August 29, 2022, 11:51am UTC](https://discourse.scverse.org/t/how-does-one-generate-a-dotplot-with-scaled-values/715 "2022-08-29T11:51:15Z")

</div>

Hi, In Seurat Dotplots Average expression is scaled (z-score) while in scanpy it shows the raw expression, how can one alter the scale of expression in scanpy? Thanks, Roy

---

## [Error in highly variable gene selection](https://discourse.scverse.org/t/error-in-highly-variable-gene-selection/276)

<div class="topic-metadata">

**Author:** [@win](https://discourse.scverse.org/u/win)\
**Replies:** 8\
**Last updated:** [March 21, 2022, 5:07am UTC](https://discourse.scverse.org/t/error-in-highly-variable-gene-selection/276 "2022-03-21T05:07:31Z")

</div>

Hi I am trying to use SCVI - tools for batch correction. I followed as in tutorial. I got the error in the step below. sc.pp.highly\_variable\_genes( adata, n\_top\_genes=2000, subset=True, layer="counts", …

---

## [Gene filtering prior to batch correction](https://discourse.scverse.org/t/gene-filtering-prior-to-batch-correction/123)

<div class="topic-metadata">

**Author:** [@Nusob888](https://discourse.scverse.org/u/Nusob888)\
**Replies:** 2\
**Last updated:** [July 9, 2021, 8:59am UTC](https://discourse.scverse.org/t/gene-filtering-prior-to-batch-correction/123 "2021-07-09T08:59:23Z")

</div>

Hi, I was wondering what your thoughts are on whether gene filtering should be performed prior to highly variable gene selection and scVI training? Publicly available datasets can have vastly different total captured g…

---

## [Minimum Cluster Size?](https://discourse.scverse.org/t/minimum-cluster-size/113)

<div class="topic-metadata">

**Author:** [@mr-september](https://discourse.scverse.org/u/mr-september)\
**Replies:** 2\
**Last updated:** [July 8, 2021, 12:07am UTC](https://discourse.scverse.org/t/minimum-cluster-size/113 "2021-07-08T00:07:27Z")

</div>

Hi! Just wondering, is there any (rough estimate is fine) guideline for minimum cluster size that will still produce generally clear and reliable results? Just to narrow down if there’s any other clusters I should look…