0.34.25 (#188)

Author: pwwang

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.34.24"
+__version__ = "0.34.25"

biopipen/ns/scrna.py

@@ -1862,6 +1862,7 @@ class ScFGSEA(Proc):
         group_by: The column name in metadata to group the cells.
         ident_1: The first group of cells to compare
         ident_2: The second group of cells to compare, if not provided, the rest of the cells that are not `NA`s in `group_by` column are used for `ident_2`.
+        assay: The assay to use. If not provided, the default assay will be used.
         each: The column name in metadata to separate the cells into different subsets to do the analysis.
         subset: An expression to subset the cells.
         gmtfile: The pathways in GMT format, with the gene names/ids in the same format as the seurat object.
@@ -1929,6 +1930,7 @@ class ScFGSEA(Proc):
     envs = {
         "mutaters": {},
         "ncores": config.misc.ncores,
+        "assay": None,
         "group_by": None,
         "ident_1": None,
         "ident_2": None,
@@ -3208,7 +3210,7 @@ class PseudoBulkDEG(Proc):
         "subset": None,
         "aggregate_by": None,
         "layer": "counts",
-        "assay": "RNA",
+        "assay": None,
         "error": False,
         "group_by": None,
         "ident_1": None,

biopipen/scripts/scrna/CellTypeAnnotation.R

@@ -30,7 +30,7 @@ rename_idents <- function(sobj, ident_col, mapping) {
         mapping$object <- sobj
         sobj <- do_call(RenameIdents, mapping)
     }
-    Idents(sobj) <- ident_col
+    sobj@meta.data[[ident_col]] <- Idents(sobj)
     sobj
 }
 

biopipen/scripts/scrna/PseudoBulkDEG.R

@@ -1,6 +1,7 @@
 library(rlang)
 library(dplyr)
 library(plotthis)
+library(Seurat)
 library(biopipen.utils)
 
 sobjfile <- {{in.sobjfile | r}}

biopipen/scripts/scrna/ScFGSEA.R

@@ -10,6 +10,7 @@ mutaters <- {{envs.mutaters | r}}  # nolint
 group_by <- {{envs.group_by | default: envs["group-by"] | default: None | r}}  # nolint
 ident_1 <- {{envs.ident_1 | default: envs["ident-1"] | default: None | r}}  # nolint
 ident_2 <- {{envs.ident_2 | default: envs["ident-2"] | default: None | r}}  # nolint
+assay <- {{envs.assay | r}}  # nolint
 each <- {{envs.each | r}}  # nolint
 subset <- {{envs.subset | r}}  # nolint
 gmtfile <- {{envs.gmtfile | r}}  # nolint
@@ -43,6 +44,7 @@ defaults <- list(
     group_by = group_by,
     ident_1 = ident_1,
     ident_2 = ident_2,
+    assay = assay,
     each = each,
     subset = subset,
     gmtfile = gmtfile,
@@ -230,7 +232,7 @@ do_case <- function(name) {
         case$ident_2 <- "Other"
         allclasses[allclasses != case$ident_1] <- "Other"
     }
-    exprs <- GetAssayData(sobj, layer = "data")
+    exprs <- GetAssayData(sobj, layer = "data", assay = case$assay)
 
     # get preranks
     log$info("  Getting preranks...")

docs/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Change Log
 
+## 0.34.25
+
+- fix(scrna.PseudoBulkDEG): change default assay from "RNA" to None so that default assay can be used by default
+- feat(scrna.ScFGSEA): add assay parameter to allow specification of assay in analysis
+- fix(scrna.CellTypeAnnotation): correct assignment of identities in rename_idents function
+
 ## 0.34.24
 
 - feat(tcr.ClonalStats): add save_data parameter to ClonalStats for saving plot data

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.34.24"
+version = "0.34.25"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

tests/test_scrna/Seurat/test.py

@@ -115,13 +115,33 @@ class CellTypeAnnotation(CellTypeAnnotation_):
     }
 
 
+class CellTypeAnnotationDirect(CellTypeAnnotation_):
+    requires = SeuratClustering
+    envs = {
+        "tool": "direct",
+        "cell_types": [
+            "Naive CD4+ T",
+            "B",
+            "Memory CD4+",
+            "Naive CD4+ T",
+            "DC",
+            "DC",
+            "CD8+ T",
+            "NK",
+            "FCFR3A+ Mono",
+            "CD8+ T",
+        ],
+        "merge": True,
+    }
+
+
 class TopExpressingGenes(TopExpressingGenes_):
     requires = CellTypeAnnotation
     envs = {"cases": {"Cluster": {}}}
 
 
 class SeuratSubClustering(SeuratSubClustering_):
-    requires = CellTypeAnnotation
+    requires = SeuratClustering
     envs = {
         "cache": False,
         "cases": {
@@ -245,7 +265,7 @@ class SeuratClusterStats(SeuratClusterStats_):
             },
             "Number of cells in each old cluster": {
                 "plot_type": "pie",
-                "ident": "seurat_clusters_id",
+                "ident": "seurat_clusters.0.2",
             },
         },
         "features": {