biopipen 0.23.6__tar.gz → 0.23.8__tar.gz

{biopipen-0.23.6 → biopipen-0.23.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.23.6
+Version: 0.23.8
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.23.8/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.23.8"

{biopipen-0.23.6 → biopipen-0.23.8}/biopipen/ns/scrna.py

@@ -1463,6 +1463,7 @@ class ScFGSEA(Proc):
         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`.
         each: The column name in metadata to separate the cells into different subsets to do the analysis.
+        subset: An expression to subset the cells.
         section: The section name for the report. Worked only when `each` is not specified. Otherwise, the section name will be constructed from `each` and its value.
             This allows different cases to be put into the same section in the report.
         gmtfile: The pathways in GMT format, with the gene names/ids in the same format as the seurat object.
@@ -1513,6 +1514,7 @@ class ScFGSEA(Proc):
         "ident-1": None,
         "ident-2": None,
         "each": None,
+        "subset": None,
         "section": "DEFAULT",
         "gmtfile": "",
         "method": "s2n",

{biopipen-0.23.6 → biopipen-0.23.8}/biopipen/scripts/scrna/ScFGSEA.R

@@ -14,6 +14,7 @@ group.by <- {{envs["group-by"] | r}}  # nolint
 ident.1 <- {{envs["ident-1"] | r}}  # nolint
 ident.2 <- {{envs["ident-2"] | r}}  # nolint
 each <- {{envs.each | r}}  # nolint
+subset <- {{envs.subset | r}}  # nolint
 section <- {{envs.section | r}}  # nolint
 gmtfile <- {{envs.gmtfile | r}}  # nolint
 method <- {{envs.method | r}}  # nolint
@@ -43,6 +44,7 @@ expand_cases <- function() {
                 ident.1 = ident.1,
                 ident.2 = ident.2,
                 each = each,
+                subset = subset,
                 section = section,
                 gmtfile = gmtfile,
                 method = method,
@@ -63,6 +65,7 @@ expand_cases <- function() {
                 ident.1 = ident.1,
                 ident.2 = ident.2,
                 each = each,
+                subset = subset,
                 section = section,
                 gmtfile = gmtfile,
                 method = method,
@@ -136,6 +139,9 @@ do_case <- function(name, case) {
     # prepare expression matrix
     log_info("  Preparing expression matrix...")
     sobj <- srtobj %>% filter(!is.na(!!sym(case$group.by)))
+    if (!is.null(case$subset)) {
+        sobj <- sobj %>% filter(!!!parse_exprs(case$subset))
+    }
     if (!is.null(case$ident.2)) {
         sobj <- sobj %>% filter(!!sym(case$group.by) %in% c(case$ident.1, case$ident.2))
     }

{biopipen-0.23.6 → biopipen-0.23.8}/biopipen/scripts/scrna/SeuratPreparing.R

@@ -99,8 +99,8 @@ load_sample = function(sample) {
     }
     obj <- CreateSeuratObject(exprs, project=sample)
     # filter the cells that don't have any gene expressions
-    cell_exprs = colSums(obj@assays$RNA)
-    obj = subset(obj, cells = names(cell_exprs[cell_exprs > 0]))
+    # cell_exprs = colSums(obj@assays$RNA)
+    # obj = subset(obj, cells = names(cell_exprs[cell_exprs > 0]))
     obj = RenameCells(obj, add.cell.id = sample)
     # Attach meta data
     for (mname in names(mdata)) {
@@ -128,13 +128,7 @@ log_info("Reading samples individually ...")
 obj_list = lapply(samples, load_sample)
 
 log_info("Merging samples ...")
-if (length(obj_list) >= 2) {
-    y = c()
-    for (i in 2:length(obj_list)) y = c(y, obj_list[[i]])
-    sobj = merge(obj_list[[1]], y)
-} else {
-    sobj = obj_list[[1]]
-}
+sobj = Reduce(merge, obj_list)
 
 log_info("Adding metadata for QC ...")
 sobj$percent.mt = PercentageFeatureSet(sobj, pattern = "^MT-")
@@ -297,28 +291,36 @@ add_report(
     h1 = "Filters and QC"
 )
 
-log_info("Perform integration ...")
+.formatArgs <- function(args) {
+    paste(capture.output(str(args)), collapse = ", ")
+}
+
+log_info("Performing transformation/scaling ...")
 # Not joined yet
 # sobj[["RNA"]] <- split(sobj[["RNA"]], f = sobj$Sample)
 if (envs$use_sct) {
     log_info("- Running SCTransform ...")
     SCTransformArgs <- envs$SCTransform
+    log_info("  SCTransform: {.formatArgs(SCTransformArgs)}")
     SCTransformArgs$object <- sobj
     sobj <- do_call(SCTransform, SCTransformArgs)
     # Default is to use the SCT assay
 } else {
     log_info("- Running NormalizeData ...")
     NormalizeDataArgs <- envs$NormalizeData
+    log_info("  NormalizeData: {.formatArgs(NormalizeDataArgs)}")
     NormalizeDataArgs$object <- sobj
     sobj <- do_call(NormalizeData, NormalizeDataArgs)
 
     log_info("- Running FindVariableFeatures ...")
     FindVariableFeaturesArgs <- envs$FindVariableFeatures
+    log_info("  FindVariableFeatures: {.formatArgs(FindVariableFeaturesArgs)}")
     FindVariableFeaturesArgs$object <- sobj
     sobj <- do_call(FindVariableFeatures, FindVariableFeaturesArgs)
 
     log_info("- Running ScaleData ...")
     ScaleDataArgs <- envs$ScaleData
+    log_info("  ScaleData: {.formatArgs(ScaleDataArgs)}")
     ScaleDataArgs$object <- sobj
     sobj <- do_call(ScaleData, ScaleDataArgs)
 }
@@ -326,13 +328,13 @@ if (envs$use_sct) {
 log_info("- Running RunPCA ...")
 RunPCAArgs <- envs$RunPCA
 RunPCAArgs$npcs <- if (is.null(RunPCAArgs$npcs)) { 50 } else { min(RunPCAArgs$npcs, ncol(sobj) - 1) }
+log_info("  RunPCA: {.formatArgs(RunPCAArgs)}")
 RunPCAArgs$object <- sobj
 sobj <- do_call(RunPCA, RunPCAArgs)
 
 if (!envs$no_integration) {
     log_info("- Running IntegrateLayers ...")
     IntegrateLayersArgs <- envs$IntegrateLayers
-    IntegrateLayersArgs$object <- sobj
     method <- IntegrateLayersArgs$method
     if (!is.null(IntegrateLayersArgs$reference) && is.character(IntegrateLayersArgs$reference)) {
         log_info("  Using reference samples: {paste(IntegrateLayersArgs$reference, collapse = ', ')}")
@@ -359,6 +361,8 @@ if (!envs$no_integration) {
     if (is.null(IntegrateLayersArgs$new.reduction)) {
         IntegrateLayersArgs$new.reduction <- new_reductions[[method]]
     }
+    log_info("  IntegrateLayers: {.formatArgs(IntegrateLayersArgs)}")
+    IntegrateLayersArgs$object <- sobj
     sobj <- do_call(IntegrateLayers, IntegrateLayersArgs)
     # Save it for dimension reduction plots
     sobj@misc$integrated_new_reduction <- IntegrateLayersArgs$new.reduction

{biopipen-0.23.6 → biopipen-0.23.8}/biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R

@@ -1,4 +1,5 @@
 source("{{biopipen_dir}}/utils/misc.R")
+source("{{biopipen_dir}}/utils/gsea.R")
 source("{{biopipen_dir}}/utils/plot.R")
 
 library(scater)

{biopipen-0.23.6 → biopipen-0.23.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.23.6"
+version = "0.23.8"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

{biopipen-0.23.6 → biopipen-0.23.8}/setup.py

@@ -75,7 +75,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.23.6',
+    'version': '0.23.8',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.23.6/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.23.6"