Comments (3)
With regard to my dataset, the raw counts are indeed already accessible through the Dataset10X
class:
I could theoretically simply run something like:
cd4_t_helper = Dataset10X("cd4_t_helper", dense=False, new_n_genes=None)
regulatory_t = Dataset10X("regulatory_t", dense=False, new_n_genes=None)
naive_t = Dataset10X("naive_t", dense=False, new_n_genes=None)
memory_t = Dataset10X("memory_t", dense=False, new_n_genes=None)
cytotoxic_t = Dataset10X("cytotoxic_t", dense=False, new_n_genes=None)
naive_cytotoxic = Dataset10X("naive_cytotoxic", dense=False, new_n_genes=None)
fresh_68k_pbmc_donor_a = Dataset10X("fresh_68k_pbmc_donor_a", dense=False, new_n_genes=None)
cite_seq_pbmc = CiteSeqDataset("pbmc")
t_cells = GeneExpressionDataset.concat_datasets(cd4_t_helper,regulatory_t,naive_t,memory_t,cytotoxic_t,naive_cytotoxic)
all_concatenated_pbmcs = GeneExpressionDataset.concat_datasets(t_cells, fresh_68k_pbmc_donor_a, cite_seq_pbmc, shared_batches=False)
However, initially I would work with the .rds
data coming from this repo, as well as its preprocessing scripts, which gave me additional information:
-
the
gene_symbols
without which I can't merge the datasets with citeSeq (10X Datasets only use the ENSEMBL version for the gene names, and I didn't find any mapping yet). -
the
predicted labels
from the original "Massively Parallel ..." paper, which one has to compute for himself (they don't give it in an output file).
from scvi-tools.
@imyiningliu @Edouard360 Are there additional datasets we plan to keep using, that aren't wrapped by scVI, beyond what Yining added in #97 ? If not, let's close this issue.
from scvi-tools.
Let me add scmap datasets, and I'll be good
from scvi-tools.
Related Issues (20)
- Question about the output of scVI and scANVI HOT 2
- Specifying cell types in the new MRVI tool HOT 1
- Discussion thread: New DestVI model that supports Visium HD (single-cell spatial transcriptomics) data - Timeline, releases and alternatives HOT 2
- Error in py_call_impl(callable, call_args$unnamed, call_args$named) HOT 2
- AttributeError: module 'numpy' has no attribute 'str'. HOT 5
- How to modify scANVI to handle continuous cell labels? HOT 1
- solo.predict() should take an argument to return Non-softmax transformed values, and return logits like previous iterations to allow for non-breaking change that was implemented in 1.1.3 HOT 2
- Update release checklist and documentation for new release workflow HOT 1
- scvi-tools 1.2.0 HOT 3
- Autotuning with Ray: DeprecationWarning: The `RunConfig(local_dir)` argument is deprecated. You should set the `RunConfig(storage_path)` instead. HOT 2
- Use explicit configs instead of kwargs
- autotune throws error for ContrastiveVI (and possibly other external modules) HOT 1
- Fix custom dataloader registry
- ModelTuner.fit Returns error: The `RunConfig(local_dir)` argument is deprecated. HOT 8
- Error in model training HOT 2
- Reproducibility issue of MRVI HOT 4
- In Jupyter Notebook on Windows, the kernel keeps crashing when running Model hyperparameter tuning with scVI. HOT 22
- How to increase num_workers in pytorch DataLoader? HOT 1
- error in scanvi_ref HOT 7
- Memory error running CellAssign depending on size of marker gene set reference HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from scvi-tools.