Vitalii Kleshchevnikov

extending Predictive to support sampling by plate name

5

Following our earlier discussion with @fritzo and @adamgayoso , creating this issue. Would be great if `Predictive` class can support sampling of all variables in a given plate, automatically pulling...

Implementation of quantiles for messenger guides [WIP]

2

This PR contributes the implementation of quantiles for messenger guides - which resembles how this is done in AutoNormal. I see certain errors that I don't know how to address...

[WIP] Autonormal encoder

6

@martinjankowiak @fritzo @eb8680 following our conversation here https://github.com/YosefLab/scvi-tools/pull/930#pullrequestreview-661114030, creating this PR to discuss adding Autonormal encoder class. This class need users to specify encoder network class, data transformation, and `amortised_plate_sites`...

[WIP] adding init_to_mean

3

Hi! This PR adds init_to_mean function - also not sure where to add tests. What do you think?

dataloader which stratifies train-validation split by adata.obs columns

8

Would be great to have train validations split balanced by cell labels or batch - which is useful when there are rare populations. This can be addressed by adding a...

adding validation ELBO loss for pyro models

2

Would be great to have validation set ELBO loss for pyro models. As discussed with Adam here https://github.com/YosefLab/scvi-tools/pull/1059#discussion_r633935024 @adamgayoso I can implement this, but could you point me where this...

FeaturePlot using a column in meta.features to select gene for plotting

2

Hi Seurat team I am using ENSEMBL id as row names but I would like to be about to use FeaturePlot calling genes by symbol stored in assay's meta.features. It...

additive effects for background RNA correction in scVI

4

## Introduction I would argue that after 5+ years of analysing droplet-based sc/snRNA-seq data, we know the top-N technical RNA detection effects: 1. Per-batch (10x reaction/inlet) detection rate originating from...

Possible to select one motifs cluster per TF?

3

I see a lot of cases when a TF has motifs falling into distinct clusters. Is there a preferred strategy to select the likely correct WT motif for each TF...

Modifications to scVI that improve preservation of biological variance while correcting known tech effects

3

Implementing changes proposed in https://github.com/scverse/scvi-tools/issues/1903#issuecomment-1466746644 1. [library variance weight](https://github.com/scverse/scvi-tools/pull/1957/commits/ae9899aa12ae0d5477986f17babc697f282a6193) the prior `l_sigma` is an overestimate of the total variance attributed to the technical effect. A potential fix (and an easy...