# Help

**URL:** https://discourse.scverse.org/c/help/27.md?page=6

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

**Page:** 7

---

## [Cannot load filtered\_contig\_annotations.csv](https://discourse.scverse.org/t/cannot-load-filtered-contig-annotations-csv/2211)

<div class="topic-metadata">

**Author:** [@morganbravo1](https://discourse.scverse.org/u/morganbravo1)\
**Replies:** 6\
**Last updated:** [March 3, 2025, 3:53pm UTC](https://discourse.scverse.org/t/cannot-load-filtered-contig-annotations-csv/2211 "2025-03-03T15:53:03Z")

</div>

Hi, I keep getting an error " no fielded named ‘shape’." How should I continue? thanks, Morgan # Load the BCR data adata\_bcr = ir.io.read\_10x\_vdj( "/home/jovyan/shared/Morgan/unsortApr24\_VDJ/outs/filtered\_contig\_…

---

## [Issue with retrain scANVI model](https://discourse.scverse.org/t/issue-with-retrain-scanvi-model/3523)

<div class="topic-metadata">

**Author:** [@Xicici-Yan](https://discourse.scverse.org/u/Xicici-Yan)\
**Replies:** 1\
**Last updated:** [March 3, 2025, 9:06am UTC](https://discourse.scverse.org/t/issue-with-retrain-scanvi-model/3523 "2025-03-03T09:06:43Z")

</div>

Hi, all After reanno all cells, I reloaded scVI model (setting labels\_key=‘anno’) and set cell\_type\_key = 'FinalLv1'. Then setting scanvi\_model = sca.models.SCANVI.from\_scvi\_model( vae\_model, adata=source\_adat…

---

## [Issue with scVI model device](https://discourse.scverse.org/t/issue-with-scvi-model-device/3520)

<div class="topic-metadata">

**Author:** [@Xicici-Yan](https://discourse.scverse.org/u/Xicici-Yan)\
**Replies:** 2\
**Last updated:** [March 3, 2025, 5:18am UTC](https://discourse.scverse.org/t/issue-with-scvi-model-device/3520 "2025-03-03T05:18:05Z")

</div>

Hi, all When training scVI models, I wanted to change the device used. So, I set vae.to\_device(‘cuda:1’) to use another gpu. However, it didn’t work as the warning info showed LOCALRNAK:0. How could I use other divices …

---

## [In which direction is the LCF calculated when using the function differential\_expression?](https://discourse.scverse.org/t/in-which-direction-is-the-lcf-calculated-when-using-the-function-differential-expression/3514)

<div class="topic-metadata">

**Author:** [@ashenflower](https://discourse.scverse.org/u/ashenflower)\
**Replies:** 1\
**Last updated:** [March 2, 2025, 2:52pm UTC](https://discourse.scverse.org/t/in-which-direction-is-the-lcf-calculated-when-using-the-function-differential-expression/3514 "2025-03-02T14:52:14Z")

</div>

I am sorry if this sounds like a stupid question, but I looked around and I could not find a proper answer. Given idx1, idx2 as parameters to my my model.differential\_expression, if I find that for a given gene the LFC …

---

## [Rank\_genes\_groups pts and DE](https://discourse.scverse.org/t/rank-genes-groups-pts-and-de/3519)

<div class="topic-metadata">

**Author:** [@Slack90](https://discourse.scverse.org/u/Slack90)\
**Replies:** 0\
**Last updated:** [February 27, 2025, 7:35pm UTC](https://discourse.scverse.org/t/rank-genes-groups-pts-and-de/3519 "2025-02-27T19:35:16Z")

</div>

Hi, I am using ran rank\_genes\_groups specifying pts as true as I want the percentage of cells in the cluster that have the gene I am calling. This is what I am using: sc.tl.rank\_genes\_groups(adata, 'cell type', pts = T…

---

## [Scanpy.rank\_genes\_groups after pp.regress\_out](https://discourse.scverse.org/t/scanpy-rank-genes-groups-after-pp-regress-out/3517)

<div class="topic-metadata">

**Author:** [@quincey](https://discourse.scverse.org/u/quincey)\
**Replies:** 0\
**Last updated:** [February 27, 2025, 6:47am UTC](https://discourse.scverse.org/t/scanpy-rank-genes-groups-after-pp-regress-out/3517 "2025-02-27T06:47:24Z")

</div>

Hello, I was using scanpy to integrate some datasets, this is my workflow: adata = ad.concat(h5ad\_list, join=‘outer’, uns\_merge=‘unique’) adata.var\[“mt”\] = adata.var\_names.str.startswith(“MT-”) sc.pp.calculate\_qc\_met…

---

## [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…

---

## [Import annadata failed: Intel oneMKL FATAL ERROR: Cannot load mkl\_intel\_thread.2.dll](https://discourse.scverse.org/t/import-annadata-failed-intel-onemkl-fatal-error-cannot-load-mkl-intel-thread-2-dll/3513)

<div class="topic-metadata">

**Author:** [@rmd13](https://discourse.scverse.org/u/rmd13)\
**Replies:** 1\
**Last updated:** [February 26, 2025, 9:51am UTC](https://discourse.scverse.org/t/import-annadata-failed-intel-onemkl-fatal-error-cannot-load-mkl-intel-thread-2-dll/3513 "2025-02-26T09:51:18Z")

</div>

I installed annadata into Anaconda3 on Win8.1 D:\\GreenSoft\\Anaconda3\\Scripts\\activate.bat D:\\GreenSoft\\Anaconda3 conda create --name annadata conda activate annadata conda install anndata -c conda-forg…

---

## [Function in scanvi that can help compute the probability of having a latent cell state given a cell type](https://discourse.scverse.org/t/function-in-scanvi-that-can-help-compute-the-probability-of-having-a-latent-cell-state-given-a-cell-type/3511)

<div class="topic-metadata">

**Author:** [@mikeshen](https://discourse.scverse.org/u/mikeshen)\
**Replies:** 1\
**Last updated:** [February 26, 2025, 8:46am UTC](https://discourse.scverse.org/t/function-in-scanvi-that-can-help-compute-the-probability-of-having-a-latent-cell-state-given-a-cell-type/3511 "2025-02-26T08:46:02Z")

</div>

Hi, I would like to compute p(z|c) from a trained scanvi model where z represents a latent state and c represents a cell-type. I know in the scanvi framework there is a learnable probability p(z|c,u) where u is just a l…

---

## [Set of guidelines for SCVI and VisiumHD data](https://discourse.scverse.org/t/set-of-guidelines-for-scvi-and-visiumhd-data/3508)

<div class="topic-metadata">

**Author:** [@alexis](https://discourse.scverse.org/u/alexis)\
**Replies:** 0\
**Last updated:** [February 25, 2025, 3:28pm UTC](https://discourse.scverse.org/t/set-of-guidelines-for-scvi-and-visiumhd-data/3508 "2025-02-25T15:28:54Z")

</div>

Hello everyone, I am using a lot the high quality models provided in the scvi ecosystem. I am using scvi models for various tasks: deconvolution, integration, dimensionality reduction … However, I am not sure to what e…

---

## [Reg negative and positive TF activity values](https://discourse.scverse.org/t/reg-negative-and-positive-tf-activity-values/3504)

<div class="topic-metadata">

**Author:** [@dub2s](https://discourse.scverse.org/u/dub2s)\
**Replies:** 0\
**Last updated:** [February 24, 2025, 5:00am UTC](https://discourse.scverse.org/t/reg-negative-and-positive-tf-activity-values/3504 "2025-02-24T05:00:45Z")

</div>

Hii, I was playing around with decoupler-py to infer TF activities in a pseudobulk’d scRNA-seq data. In the data, I have different cell-types and two conditions. I wanted to identify TFs with differential activity betwe…

---

## [Differential Expression and Batch Correction](https://discourse.scverse.org/t/differential-expression-and-batch-correction/3492)

<div class="topic-metadata">

**Author:** [@jpagolia](https://discourse.scverse.org/u/jpagolia)\
**Replies:** 1\
**Last updated:** [February 20, 2025, 3:17pm UTC](https://discourse.scverse.org/t/differential-expression-and-batch-correction/3492 "2025-02-20T15:17:05Z")

</div>

Hello, thank you for this excellent tool! I’ve reviewed the online documentation and many posts (e.g. 57) on this forum regarding batch correction and the .differential\_expression() method, but I’m still confused about i…

---

## [SOLO/scVI .train() error related to batch\_size?](https://discourse.scverse.org/t/solo-scvi-train-error-related-to-batch-size/1591)

<div class="topic-metadata">

**Author:** [@bennjmo](https://discourse.scverse.org/u/bennjmo)\
**Replies:** 6\
**Last updated:** [February 20, 2025, 1:26pm UTC](https://discourse.scverse.org/t/solo-scvi-train-error-related-to-batch-size/1591 "2025-02-20T13:26:12Z")

</div>

I am getting this error when i run vae.train() ultimately for SOLO “ValueError: Expected more than 1 value per channel when training, got input size torch.Size(\[1, 128\])” I found a few posts on github, but i’m too daft…

---

## [scVelo between conditions](https://discourse.scverse.org/t/scvelo-between-conditions/3498)

<div class="topic-metadata">

**Author:** [@SimonE1220](https://discourse.scverse.org/u/SimonE1220)\
**Replies:** 0\
**Last updated:** [February 20, 2025, 11:56am UTC](https://discourse.scverse.org/t/scvelo-between-conditions/3498 "2025-02-20T11:56:41Z")

</div>

Dear all, ist it possible to calculate the differences between two conditons and display them in the RNA velocity embedding map. I have the assumption that the treatments changes the dynamic of the cells. Or is there an…

---

## [Really hard to plot categories palette](https://discourse.scverse.org/t/really-hard-to-plot-categories-palette/3486)

<div class="topic-metadata">

**Author:** [@christophechu](https://discourse.scverse.org/u/christophechu)\
**Replies:** 1\
**Last updated:** [February 14, 2025, 10:58pm UTC](https://discourse.scverse.org/t/really-hard-to-plot-categories-palette/3486 "2025-02-14T22:58:21Z")

</div>

As I’ve mentioned in the github. How to plot with our own palette?

---

## [Help with harmony and scanpy](https://discourse.scverse.org/t/help-with-harmony-and-scanpy/3477)

<div class="topic-metadata">

**Author:** [@bioinf](https://discourse.scverse.org/u/bioinf)\
**Replies:** 3\
**Last updated:** [February 14, 2025, 9:05pm UTC](https://discourse.scverse.org/t/help-with-harmony-and-scanpy/3477 "2025-02-14T21:05:56Z")

</div>

Hello, I am interested in using harmony to integrate some samples but I am not sure if I am doing it correctly. I have 6 samples with 2 conditions (3 control/3 treated) I do the following steps: Merge samples QC Nor…

---

## [I have always had a question: do I need to scale my adata before running sc.tl.score\_genes?](https://discourse.scverse.org/t/i-have-always-had-a-question-do-i-need-to-scale-my-adata-before-running-sc-tl-score-genes/2305)

<div class="topic-metadata">

**Author:** [@christophechu](https://discourse.scverse.org/u/christophechu)\
**Replies:** 4\
**Last updated:** [February 14, 2025, 6:29pm UTC](https://discourse.scverse.org/t/i-have-always-had-a-question-do-i-need-to-scale-my-adata-before-running-sc-tl-score-genes/2305 "2025-02-14T18:29:53Z")

</div>

I have always had a question: do I need to scale my adata before running sc.tl.score\_genes?

---

## [Pertpy: AttributeError: module 'pertpy.plot' has no attribute 'coda'](https://discourse.scverse.org/t/pertpy-attributeerror-module-pertpy-plot-has-no-attribute-coda/1846)

<div class="topic-metadata">

**Author:** [@hmnzo5gy](https://discourse.scverse.org/u/hmnzo5gy)\
**Replies:** 5\
**Last updated:** [February 14, 2025, 9:30am UTC](https://discourse.scverse.org/t/pertpy-attributeerror-module-pertpy-plot-has-no-attribute-coda/1846 "2025-02-14T09:30:51Z")

</div>

Pertpy works fine if install with pip install pertpy However when installed from github gh repo clone theislab/pertpy cd pertpy pip install . When running pertpy.pl.coda.boxplots(), I keep encountering the following …

---

## [Dealing with multiple samples](https://discourse.scverse.org/t/dealing-with-multiple-samples/1465)

<div class="topic-metadata">

**Author:** [@grst](https://discourse.scverse.org/u/grst)\
**Replies:** 9\
**Last updated:** [February 13, 2025, 12:49pm UTC](https://discourse.scverse.org/t/dealing-with-multiple-samples/1465 "2025-02-13T12:49:32Z")

</div>

Hi spatialdata folks, I was wondering what is the intended way to work with images from different samples (e.g. 10 tumor slides from responders and 10 non-responders) when the goal is to compare features from groups wit…

---

## [Question about interpreting the DEGs associated with disease changes using MrVI](https://discourse.scverse.org/t/question-about-interpreting-the-degs-associated-with-disease-changes-using-mrvi/3480)

<div class="topic-metadata">

**Author:** [@zitiansunsh1ne](https://discourse.scverse.org/u/zitiansunsh1ne)\
**Replies:** 2\
**Last updated:** [February 11, 2025, 7:46am UTC](https://discourse.scverse.org/t/question-about-interpreting-the-degs-associated-with-disease-changes-using-mrvi/3480 "2025-02-11T07:46:11Z")

</div>

Dear the developers of MrVI, Thank you very much for developing this amazing tool. I am confused on the output from DE analysis, and how DEGs are defined. From the manuscript, the DEG was selected based on both p-value\<0…

---

## [Weird output combat integration two datasets](https://discourse.scverse.org/t/weird-output-combat-integration-two-datasets/3469)

<div class="topic-metadata">

**Author:** [@Slack90](https://discourse.scverse.org/u/Slack90)\
**Replies:** 2\
**Last updated:** [February 6, 2025, 7:43pm UTC](https://discourse.scverse.org/t/weird-output-combat-integration-two-datasets/3469 "2025-02-06T19:43:49Z")

</div>

Hi, I am trying to integrate two datasets, and I have tested several methods, including scvi, BBKKN, scanorama, combat and some others in R (RCCA, and Harmony). In some cases I see weird integration output such as the o…

---

## [TotalVI not fully integrating CITEseq cells with GEX and missing protein values](https://discourse.scverse.org/t/totalvi-not-fully-integrating-citeseq-cells-with-gex-and-missing-protein-values/3473)

<div class="topic-metadata">

**Author:** [@timslittle](https://discourse.scverse.org/u/timslittle)\
**Replies:** 1\
**Last updated:** [February 6, 2025, 4:38pm UTC](https://discourse.scverse.org/t/totalvi-not-fully-integrating-citeseq-cells-with-gex-and-missing-protein-values/3473 "2025-02-06T16:38:49Z")

</div>

Hi Team, Apologies if I’m doing something wrong here! I have a CITEseq dataset in which some cells have good quality RNAseq values but poor quality ADT, so these ADT values have been removed. I tried using TotalVI to i…

---

## [How to deal with negative logfoldchange in dotplot](https://discourse.scverse.org/t/how-to-deal-with-negative-logfoldchange-in-dotplot/3472)

<div class="topic-metadata">

**Author:** [@LioLnr](https://discourse.scverse.org/u/LioLnr)\
**Replies:** 0\
**Last updated:** [February 6, 2025, 10:43am UTC](https://discourse.scverse.org/t/how-to-deal-with-negative-logfoldchange-in-dotplot/3472 "2025-02-06T10:43:23Z")

</div>

Hello, I have simply ran scanpy.tl.rank\_genes\_groups(). After obtaining the results per cluster with scanpy.get.rank\_genes\_groups\_df(), I filter them using a pval threshold of 0.05 and a lfc threshold of 1. Unfortunatl…

---

## [Lazy loading of Zarr from S3](https://discourse.scverse.org/t/lazy-loading-of-zarr-from-s3/3442)

<div class="topic-metadata">

**Author:** [@josh-gree](https://discourse.scverse.org/u/josh-gree)\
**Replies:** 3\
**Last updated:** [January 30, 2025, 5:03pm UTC](https://discourse.scverse.org/t/lazy-loading-of-zarr-from-s3/3442 "2025-01-30T17:03:43Z")

</div>

Hi wonder if anyone could help me to understand if this is possible; ad = anndata.read\_zarr('s3://foo/bar/baz.zarr') qux = ad.varm\['qux'\] Such that only qux is ever pulled from s3 - and the rest of the data is never mo…

---

## [Differential gene expression shows very low raw\_means](https://discourse.scverse.org/t/differential-gene-expression-shows-very-low-raw-means/3465)

<div class="topic-metadata">

**Author:** [@SimonE1220](https://discourse.scverse.org/u/SimonE1220)\
**Replies:** 2\
**Last updated:** [January 30, 2025, 3:24pm UTC](https://discourse.scverse.org/t/differential-gene-expression-shows-very-low-raw-means/3465 "2025-01-30T15:24:43Z")

</div>

Dear all, I used the differential gene expression function, however I only get a very little amount of DEGs and they have a very low raw\_mean1 and 2. If I use MAST for example I get much more DEGs de\_results\_HFD\_L1 = …

---

## [The mean of the the scVI ZINB model distribution (related to supplementary note 3)](https://discourse.scverse.org/t/the-mean-of-the-the-scvi-zinb-model-distribution-related-to-supplementary-note-3/3459)

<div class="topic-metadata">

**Author:** [@Sandeep-S-K](https://discourse.scverse.org/u/Sandeep-S-K)\
**Replies:** 4\
**Last updated:** [January 29, 2025, 5:00pm UTC](https://discourse.scverse.org/t/the-mean-of-the-the-scvi-zinb-model-distribution-related-to-supplementary-note-3/3459 "2025-01-29T17:00:29Z")

</div>

Thanks for the great tool. I had a subtle question about the the scVI model. In supplementary note 3 the mean of the ZINB (ignoring the zero inflated portion) comes to r \* \\lambda \* \\frac{p}{p+1}. Given that the (r, \\la…

---

## [Tensor nan error when training scANVI model](https://discourse.scverse.org/t/tensor-nan-error-when-training-scanvi-model/1677)

<div class="topic-metadata">

**Author:** [@lconan](https://discourse.scverse.org/u/lconan)\
**Replies:** 6\
**Last updated:** [January 29, 2025, 4:20pm UTC](https://discourse.scverse.org/t/tensor-nan-error-when-training-scanvi-model/1677 "2025-01-29T16:20:53Z")

</div>

Hi, I ran into tensor nan error when using scANVI set up with scVI model, hope someone can help me~ setup anndata with scvi.model.SCVI.setup\_anndata(combined\_adata, layer = "counts", categ…

---

## [How to appropriately transfer annotations from anndata to seurat](https://discourse.scverse.org/t/how-to-appropriately-transfer-annotations-from-anndata-to-seurat/3457)

<div class="topic-metadata">

**Author:** [@Slack90](https://discourse.scverse.org/u/Slack90)\
**Replies:** 2\
**Last updated:** [January 24, 2025, 11:44pm UTC](https://discourse.scverse.org/t/how-to-appropriately-transfer-annotations-from-anndata-to-seurat/3457 "2025-01-24T23:44:41Z")

</div>

Hi, I processed my rna seq data and annotated them using scvi, and I would like to integrate the data using R. Specifically, this is my anndata structure: AnnData object with n\_obs × n\_vars = 16712 × 10494 obs: 'se…

---

## [Best practice for handling custom points during SCVI training](https://discourse.scverse.org/t/best-practice-for-handling-custom-points-during-scvi-training/3418)

<div class="topic-metadata">

**Author:** [@alessimichele](https://discourse.scverse.org/u/alessimichele)\
**Replies:** 4\
**Last updated:** [January 24, 2025, 10:37am UTC](https://discourse.scverse.org/t/best-practice-for-handling-custom-points-during-scvi-training/3418 "2025-01-24T10:37:57Z")

</div>

Hi everyone, I’m working on a custom implementation with scvi-tools and have a design question regarding the best way to handle specific points selected during training. In my setup, at the end of each epoch, I select …

---

## [Integrating TRUST4 outputs into anndata GEX](https://discourse.scverse.org/t/integrating-trust4-outputs-into-anndata-gex/3426)

<div class="topic-metadata">

**Author:** [@fonseca.dfm](https://discourse.scverse.org/u/fonseca.dfm)\
**Replies:** 3\
**Last updated:** [January 22, 2025, 6:27pm UTC](https://discourse.scverse.org/t/integrating-trust4-outputs-into-anndata-gex/3426 "2025-01-22T18:27:12Z")

</div>

Hi I love this community but I am struggling to integrate scRNA vdj annotations coming out of TRUST4 with my GEX data. I am mostly using python so I tried using dandelion (read\_airr fuction), but somehow it doesnt recog…

[Previous page](https://discourse.scverse.org/c/help/27.md?page=5)

[Next page](https://discourse.scverse.org/c/help/27.md?page=7)