bm2-lab/sclearn

scLearn：Learning for single cell assignment

sclearn's Issues

how to get the accuracy that you provided in the paper

Dear authors,
When I ran the codes that you shared in the github, what I got are as follows:
"[1] "The number of missing features in the query data is 79 "
[1] "The rate of missing features in the query data is 0.0671768707482993 "'
and the reference dataset is deng-reads.rds, the query dataset is zeisel.rds.
But I can't get the accuracy that you provided in the papers.
Like this "deng_zeisel scLearn 0.996"
Is something missing when I ran the codes.
I will appreciate it if you can helo me out of this. Thank you for your time.

running scLearn on seurat object

the meaning of additional information in predict_result

I ran the codes that you provided in github, and I got the scLearn_predict_result. But I have a problem about the the meaning of additional information in predict_result. I have read the codes that how to get additional information, still have no clues. What'more, I can't find the types of query cells, so I don't know how to get the accuracy of scLearn. You don't provide the types of query cells and the method of how to get the accuracy. I really hope to receive your reply. I will appreciate it if you can solve my problems.

Downloading the pre-trained models not possible

It is not possible to download the pre-trained models! It requires to create an account, verify it by the passcode sent by SMS, but each time the process fails with no explanation whatsoever.

How to distinguish similar cell types?

Dear authors,
I find it is hard to distinguish some cell types if they are similar in the reference dataset using default parameters. There are too many 'unassigned' in the output. I wonder how to adjust the parameters in scLearn_model_learning() to get a less strict model? Thanks.

The of installation scLearn failed

Hi, When I used the command devtools::install_github("bm2-lab/scLearn"), I got the bug information:

Installing package into ‘C:/Software/R/Rlibrary’
(as ‘lib’ is unspecified)
* installing *source* package 'scLearn' ...
** using staged installation
** R
** byte-compile and prepare package for lazy loading
Error: (converted from warning) package 'dml' was built under R version 4.0.3
Execution halted
ERROR: lazy loading failed for package 'scLearn'
* removing 'C:/Software/R/Rlibrary/scLearn'

I have checked my R version which was version 4.0.2 and the R version for package more than 3.6.1. By the way I also reinstalled the dml package, but it came to failed again. Have you ever met this bug or how could I fix it? THX

Request preprocessed scRNA-seq dataset

Could you kindly release the preprocessed scRNA-seq dataset.
I download the PBMC dataset from "https://singlecell.broadinstitute.org/single_cell/study/SCP424/single-cell-comparison-pbmc-data#study-download", but I found some cell type labels (InDrop2 and pbmc1_10x_v2 ) are missing in meta.txt.

Error when run the example data

Hello, I encounter a error when run the:
scLearn_predict_result<-scLearn_cell_assignment(scLearn_model_learning_result,data_qc_query$expression_profile).
The message is:
[1] "The number of missing features in the query data is 0 "
[1] "The rate of missing features in the query data is 0 "
Error in scLearn_model_learning_result$trans_matrix_learned[[r]] %*% expression_profile_query_hvg :
non-conformable arguments

could you give me some advice for this error? The R version is 4.0.2.

run into error when performing cell assignment codes

Dear authors,
When I ran this code"scLearn_predict_result<-scLearn_cell_assignment(scLearn_model_learning_result,data_qc_query$expression_profile,diff=0.05,threshold_use=TRUE,vote_rate=0.6)", there was a error:
Error in scLearn_cell_assignment(scLearn_model_learning_result, data_qc_query$expression_profile, :
参数没有用(threshold_use = TRUE).
Even if I changed the value of threshold_use to FALSE, it still has problem.
Can you explain to me that why this happenen? Thank you for your time.

Cell assignment Error occurred

Hello, I encounter a error when run the Cell assignment part:

data2<-readRDS('pancreas_human_segerstolpe.rds')
rawcounts2<-assays(data2)[[1]]
Error in (function (classes, fdef, mtable) :
unable to find an inherited method for function ‘assays’ for signature ‘"list"’

The pancreas_human_segerstolpe.rds file was downloaded from pre-trained scLearn models of the 30 datasets.
How should I deal with such error? Looking forward to your reply .