Add support for Cellranger 10 (#20)

* Adding support for Cell Ranger 10

* Fix: during final check only store type information if present in file

* Fix: changing the order where silhouette output files are saved and handling the scenario when only one cluster is generated

* Fix: edit generateSummaryFiles_MULTI.py so that values less than or equal to 1 in decimal form would be reported as percentages

* Bump version

Author: chenv3

VERSION

@@ -1 +1 @@
-3.1.0
+3.2.0

cell-seek

@@ -517,11 +517,11 @@ def parsed_arguments(name, description):
                                 options: hg38, mm10, hg2024, mm2024.
                                   Example: --genome hg38
         {3}{4}Analysis options:{5}
-          --cellranger {{7.1.0, 7.2.0, 8.0.0, 9.0.0}}
+          --cellranger {{7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0}}
                                 The version of CellRanger to run. This option specifies
                                 which version of CellRanger to use when running GEX,
                                 CITE, or MULTI. Please select one of the following
-                                options: 7.1.0, 7.2.0, 8.0.0, 9.0.0
+                                options: 7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0
                                   Example: --cellranger 7.1.0
           --aggregate  {{mapped,none}}
                                 Cell Ranger aggregate. This option defines the
@@ -1047,7 +1047,7 @@ def parsed_arguments(name, description):
         type=str.lower,
         required=False,
         default="",
-        choices=["7.1.0", "7.2.0", "8.0.0", "9.0.0"],
+        choices=["7.1.0", "7.2.0", "8.0.0", "9.0.0", "10.0.0"],
         help=argparse.SUPPRESS,
     )
 

config/modules.json

@@ -1,6 +1,6 @@
 {
     "tools": {
-        "cellranger": {"7.1.0": "cellranger/7.1.0", "7.2.0": "cellranger/7.2.0", "8.0.0": "cellranger/8.0.0", "9.0.0": "cellranger/9.0.0"},
+        "cellranger": {"7.1.0": "cellranger/7.1.0", "7.2.0": "cellranger/7.2.0", "8.0.0": "cellranger/8.0.0", "9.0.0": "cellranger/9.0.0", "10.0.0": "cellranger/10.0.0"},
 	"cellranger-atac": "cellranger-atac/2.1.0",
 	"cellranger-arc": "cellranger-arc/2.0.1",
         "python2": "python/2.7",

docs/usage/run.md

@@ -84,11 +84,11 @@ Each of the following arguments are required. Failure to provide a required argu
 > ***Example:*** `--genome hg2024`
 
 ---  
-  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0}`
+  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0}`
 > **The version of Cell Ranger to run.**   
 > *type: string*
 >   
-> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0
+> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0
 >
 > ***Example:*** `--cellranger 7.1.0`
 
@@ -269,11 +269,11 @@ Each of the following arguments are required. Failure to provide a required argu
 > ***Example:*** `--genome hg38`
 
 ---  
-  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0}`
+  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0}`
 > **The version of Cell Ranger to run.**   
 > *type: string*
 >   
-> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0
+> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0
 >
 > ***Example:*** `--cellranger 7.1.0`
 
@@ -355,11 +355,11 @@ Each of the following arguments are required. Failure to provide a required argu
 > ***Example:*** `--genome hg38`
 
 ---  
-  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0}`
+  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0}`
 > **The version of Cell Ranger to run.**   
 > *type: string*
 >   
-> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0
+> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0
 >
 > ***Example:*** `--cellranger 7.1.0`
 
@@ -523,11 +523,11 @@ Each of the following arguments are required. Failure to provide a required argu
 > ***Example:*** `--genome hg38`
 
 ---  
-  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0}`
+  `--cellranger {7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0}`
 > **The version of Cell Ranger to run.**   
 > *type: string*
 >   
-> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0
+> This option specifies which version of Cell Ranger to use when running GEX, VDJ, CITE, or MULTI pipelines. Please select one of the following options: 7.1.0, 7.2.0, 8.0.0, 9.0.0, 10.0.0
 >
 > ***Example:*** `--cellranger 7.1.0`
 

src/run.py

@@ -828,9 +828,10 @@ def finalcheck(config, flag, delimeter=','):
                 values = contents.get(i, set())
                 values.add(linelist[indices[i]])
                 contents[i] = values
-            value = name_type.get(linelist[indices['name']], set())
-            value.add(linelist[indices['type']])
-            name_type[linelist[indices['name']]] = value
+            if 'type' in indices:
+                value = name_type.get(linelist[indices['name']], set())
+                value.add(linelist[indices['type']])
+                name_type[linelist[indices['name']]] = value
 
     # Compiles the sample names and fastq paths from the input (config)
     samples  = set([re.sub("_S[0-9]+_L00[0-9]", "", i) for i in config['samples']])

workflow/scripts/generateSummaryFiles_MULTI.py

@@ -128,7 +128,10 @@ def write_sheet(workbook, stats, samples, headers, filter):
                     if i.count('.') > 1:
                         worksheet.write(row, col, i.replace(',', ''))
                     else:
-                        worksheet.write(row, col, float(i.replace(',','')), formatFrac)
+                        if float(i.replace(',','')) <= 1:
+                            worksheet.write(row, col, float(i.replace(',','')), formatPer)
+                        else:
+                            worksheet.write(row, col, float(i.replace(',','')), formatFrac)
                 elif len(re.findall('\D', ''.join(re.findall('[^,]', i)))) > 0:
                     worksheet.write(row, col, i)
                 else:

workflow/scripts/seuratSampleQC.R

@@ -226,11 +226,11 @@ for(resolution in c(0.1, seq(0.2,1.0,0.2), 1.5, 2.0)){
   try({
     clusters <- Idents(seur)
     sil<-silhouette(as.numeric(clusters), dist=d)
+    write.csv(sil, paste0('SilhouetteResult_res.', resolution, '.csv'), row.names=F, quote=F)
     pdf(paste0("SilhouettePlot_res.",resolution,".pdf"))
     print(plot(sil, col=as.factor(clusters[order(clusters, decreasing=FALSE)]), main=paste("Silhouette plot of Seurat clustering - resolution ", resolution, sep=""), lty=2))
     print(abline(v=mean(sil[,3]), col="red4", lty=2))
     dev.off()
-    write.csv(sil, paste0('SilhouetteResult_res.', resolution, '.csv'), row.names=F, quote=F)
   })
 }
 

workflow/scripts/seuratSampleQCReport.Rmd

@@ -161,7 +161,7 @@ sil_files <- Sys.glob(file.path(seuratdir, "SilhouetteResult_res*.csv"))
 resolutions <- sapply(files, function(x) (x %>% basename %>% tools::file_path_sans_ext() %>% strsplit(split='res.'))[[1]][2]) %>% str_sort(numeric=T)
 sil_mean <- sapply(resolutions, function(resolution) {filename <- grep(paste0('res.', resolution, '.csv'), sil_files, value=T); if(length(filename) > 0) { data <- read.csv(filename); mean(data$sil_width)} else{-Inf}})
 
-if (max(sil_mean) > -Inf) {
+if (max(sil_mean, na.rm=T) > -Inf) {
   cat("The average silhouette score and a silhouette plot was calculated for each cluster resolution. This was done by calculating the score for each cell using the euclidean distance generated based on the cell's principal components to obtain an independent measure of the clustering results. The silhouette score ranges from -1 to 1, where: \n\n* 1 means that clusters are far apart and data points close to each other are assigned the same cluster label\n\n* 0 means that the distance between clusters are not signifcant and data points are close to more than one cluster\n\n* -1 means that clusters may be incorrectly assigned and data points are closer to other clusters than other data points in its own cluster\n\nThe resolution with the highest detected average silhouette score is resolution", sil_mean %>% which.max %>% names, "\n\n")
 }