biopipen 0.34.13__tar.gz → 0.34.15__tar.gz

{biopipen-0.34.13 → biopipen-0.34.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: biopipen
-Version: 0.34.13
+Version: 0.34.15
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.34.15/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.34.15"

{biopipen-0.34.13 → biopipen-0.34.15}/biopipen/scripts/scrna/CellTypeAnnotation-celltypist.R

@@ -111,7 +111,8 @@ if (file.exists(celltypist_outfile) &&
         command <- paste(command, "-v")
     }
     log$info("Running celltypist:")
-    print("- {command}")
+    # print("- {command}")
+    log$debug("  {command}")
     rc <- system(command)
     if (rc != 0) {
         stop("Failed to run celltypist. Check the job.stderr file to see the error message.")

{biopipen-0.34.13 → biopipen-0.34.15}/biopipen/scripts/scrna/MarkersFinder.R

@@ -600,6 +600,28 @@ run_case <- function(name) {
 
             if (length(allenrich_plots) > 0 && !is.null(enriches) && nrow(enriches) > 0) {
                 log$info("- Visualizing all enrichments together ...")
+                # add other metadata columns if any by mapping groupname
+                # only add the metadata columns from object if there is a single value mapped
+                metacols <- srtobj@meta.data %>% group_by(!!sym(each)) %>%
+                    summarize(across(everything(), ~ n_distinct(.) == 1), .groups = "keep") %>%
+                    select(where(~ all(. == TRUE))) %>%
+                    colnames()
+
+                if (length(metacols) > 1) {
+                    metadf <- srtobj@meta.data[, metacols, drop = FALSE]  %>%
+                        distinct(!!sym(each), .keep_all = TRUE)
+
+                    for (col in setdiff(metacols, each)) {
+                        if (col %in% colnames(enriches)) {
+                            warning("Column name conflict: {col}, adding with suffix '_meta'", immediate. = TRUE)
+                            metadf[[paste0(col, "_meta")]] <- metadf[[col]]
+                            metadf[[col]] <- NULL
+                        }
+                    }
+
+                    enriches <- left_join(enriches, metadf, by = each)
+                }
+
                 process_allenriches(enriches, allenrich_plots, name, each)
             }
         }
@@ -607,8 +629,14 @@ run_case <- function(name) {
         return(invisible())
     }
 
-    case$object <- if (is.null(subset_)) srtobj else filter(srtobj, !!parse_expr(subset_))
+    # Let RunSeuratDEAnalysis handle the subset
+    case$subset <- subset_
+    case$object <- srtobj
     markers <- do_call(RunSeuratDEAnalysis, case)
+    case$object <- NULL  # Release memory
+    gc()
+
+    subobj <- if (is.null(subset_)) srtobj else filter(srtobj, !!parse_expr(subset_))
 
     if (is.null(case$ident_1)) {
         all_idents <- unique(as.character(markers[[case$group_by]]))
@@ -621,7 +649,7 @@ run_case <- function(name) {
 
             attr(ident_markers, "ident_1") <- ident
             enrich <- process_markers(ident_markers, info = info, case = list(
-                object = case$object,
+                object = subobj,
                 dbs = dbs,
                 group_by = case$group_by,
                 sigmarkers = sigmarkers,
@@ -638,7 +666,7 @@ run_case <- function(name) {
             log$info("- Visualizing all markers together ...")
             process_allmarkers(
                 markers,
-                object = case$object,
+                object = subobj,
                 comparison_by = case$group_by,
                 plotcases = allmarker_plots,
                 casename = name,
@@ -653,12 +681,35 @@ run_case <- function(name) {
 
         if (length(allenrich_plots) > 0) {
             log$info("- Visualizing all enrichments together ...")
+            # add other metadata columns if any by mapping groupname
+            # only add the metadata columns from object if there is a single value mapped
+            metacols <- subobj@meta.data %>% group_by(!!sym(case$group_by)) %>%
+                summarize(across(everything(), ~ n_distinct(.) == 1), .groups = "keep") %>%
+                select(where(~ all(. == TRUE))) %>%
+                colnames()
+
+            if (length(metacols) > 1) {
+                metadf <- subobj@meta.data[, metacols, drop = FALSE]  %>%
+                    distinct(!!sym(case$group_by), .keep_all = TRUE)
+
+                for (col in setdiff(metacols, case$group_by)) {
+                    if (col %in% colnames(enriches[[1]])) {
+                        warning("Column name conflict: {col}, adding with suffix '_meta'", immediate. = TRUE)
+                        metadf[[paste0(col, "_meta")]] <- metadf[[col]]
+                        metadf[[col]] <- NULL
+                    }
+                }
+
+                for (ne in names(enriches)) {
+                    enriches[[ne]] <- left_join(enriches[[ne]], metadf, by = case$group_by)
+                }
+            }
             process_allenriches(enriches, allenrich_plots, name, case$group_by)
         }
     } else {
         info <- case_info(name, outdir, create = TRUE)
         enrich <- process_markers(markers, info = info, case = list(
-            object = case$object,
+            object = subobj,
             dbs = dbs,
             group_by = case$group_by,
             sigmarkers = sigmarkers,

{biopipen-0.34.13 → biopipen-0.34.15}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.34.13"
+version = "0.34.15"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

{biopipen-0.34.13 → biopipen-0.34.15}/setup.py

@@ -86,7 +86,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.34.13',
+    'version': '0.34.15',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.34.13/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.34.13"