search

digitalcytometry / ecotyper

EcoTyper is a machine learning framework for large-scale identification of cell states and cellular ecosystems from gene expression data.
Other
184 stars 42 forks source link

Failure of Recovery of Ecotypes (Tutorial 3) in Spatial Transcriptomics data #80

Open corecontingency opened 1 year ago

corecontingency commented 1 year ago

I have run Tutorial 5: "De novo Discovery of Cell States and Ecotypes in scRNA-seq Data" with my own scRNA dataset, which ran appropriately. However, I am now trying to use that recovered ecotype from Tutorial 5 to run Tutorial 3: "Recovery of Cell States and Ecotypes in Visium Spatial Gene Expression Data" on my own spatial dataset, which is failing with the below error:

Plotting cell state heatmaps...
Plotting cell state heatmaps for NA...
Error in if (all(state_data$Malignant == 1)) { : 
  missing value where TRUE/FALSE needed
Execution halted

I am unsure what is causing this problem. Full error log here.

To reproduce my issue, here is the input data for Tutorial 5, and the extra input data for tutorial 3 here.

Thank you so much for your help - I have been banging my head against the wall on this one. Not sure why it is giving this error.

BALuca commented 1 year ago

Hello,

Thank you for providing the comprehensive output for debug. I noticed that the barcodes in the CARD_output.txt file contain "-". I would recommend to replace them with "." and try running Tutorial 3 again.

Best, The EcoTyper team

corecontingency commented 1 year ago

Hi, thank you very much for the help! It looks like that worked - and the old error message is gone.

Unfortunately, a new one has appeared, as seen below:

$ Rscript EcoTyper_recovery_visium.R -c /home/user/src/results_beta/prep/config_recovery_visium.yml

Loading visium data...

Loading user-provided cell type fractions...

Running cell state recovery on the visium dataset...
Running cell state recovery on: Schwann...
Running cell state recovery on: Immune...
Running cell state recovery on: Liver...
Running cell state recovery on: Tumor...
Running cell state recovery on: Mesenchymal...
Running cell state recovery on: Endothelial...
[1] ""

Calculating cell state abundances...
[1] "Rscript spatial_states.R discovery_scRNA_jansky Visium_ID_REDACTED Top_50 "
Reading adjusted fractions from folder: ../CIBERSORTx/fractions/visium/Visium_ID_REDACTED/Top_50
Calculating cell state abundance for Endothelial...
Error in `[.data.frame`(cell_fractions, , c(colnames(cell_fractions)[1],  : 
  undefined columns selected
Calls: [ -> [.data.frame
Execution halted
Error in RunJobQueue() : 
  EcoTyper failed. Please check the error message above!
Execution halted

Any thoughts on what might be going wrong this time?