biopipen 0.27.6__tar.gz → 0.27.7__tar.gz

{biopipen-0.27.6 → biopipen-0.27.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.6
+Version: 0.27.7
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.27.7/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.27.7"

{biopipen-0.27.6 → biopipen-0.27.7}/biopipen/core/filters.py

@@ -235,8 +235,8 @@ def _render_fgsea(
     with Path(cont["dir"]).joinpath("fgsea.txt").open() as f:
         next(f)  # skip header
         for line in f:
-            pathway, _ = line.split("\t", 1)
-            pathways.append(pathway)
+            items = line.strip().split("\t")
+            pathways.append((items[0], items[-1]))
             if len(pathways) >= n_pathways:
                 break
 
@@ -263,6 +263,7 @@ def _render_fgsea(
                         {
                             "kind": "table",
                             "src": str(Path(cont["dir"]).joinpath("fgsea.txt")),
+                            "data": {"excluded": {"slug"}},
                         }
                     ],
                 },
@@ -274,10 +275,10 @@ def _render_fgsea(
             "ui": "table_of_images",
             "contents": [
                 {
-                    "src": str(Path(cont["dir"]) / f"fgsea_{pw.replace('/', '-')}.png"),
+                    "src": str(Path(cont["dir"]) / f"fgsea_{slug}.png"),
                     "title": pw,
                 }
-                for pw in pathways
+                for pw, slug in pathways
             ]
         },
     ]

{biopipen-0.27.6 → biopipen-0.27.7}/biopipen/ns/scrna.py

@@ -1241,7 +1241,7 @@ class TopExpressingGenes(Proc):
     }
 
 
-class ExprImpution(Proc):
+class ExprImputation(Proc):
     """This process imputes the dropout values in scRNA-seq data.
 
     It takes the Seurat object as input and outputs the Seurat object with
@@ -1317,13 +1317,13 @@ class ExprImpution(Proc):
         },
         "alra_args": {},
     }
-    script = "file://../scripts/scrna/ExprImpution.R"
+    script = "file://../scripts/scrna/ExprImputation.R"
 
 
 class SCImpute(Proc):
     """Impute the dropout values in scRNA-seq data.
 
-    Deprecated. Use `ExprImpution` instead.
+    Deprecated. Use `ExprImputation` instead.
 
     Input:
         infile: The input file for imputation

{biopipen-0.27.6 → biopipen-0.27.7}/biopipen/ns/scrna_metabolic_landscape.py

@@ -566,8 +566,8 @@ class ScrnaMetabolicLandscape(ProcGroup):
             input_data = lambda ch: tibble(
                 srtobj=ch.iloc[:, 0],
                 metafile=[None],
-                mutaters=[self.opts.mutaters],
             )
+            envs = {"mutaters": self.opts.mutaters}
 
         return MetabolicSeuratMetadataMutater
 
@@ -577,10 +577,10 @@ class ScrnaMetabolicLandscape(ProcGroup):
         if self.opts.noimpute:
             return self.p_mutater
 
-        from .scrna import ExprImpution
+        from .scrna import ExprImputation
 
         @annotate.format_doc(indent=3)
-        class MetabolicExprImpution(ExprImpution):
+        class MetabolicExprImputation(ExprImputation):
             """{{Summary}}
 
             You can turn off the imputation by setting the `noimpute` option
@@ -588,7 +588,7 @@ class ScrnaMetabolicLandscape(ProcGroup):
             """
             requires = self.p_mutater
 
-        return MetabolicExprImpution
+        return MetabolicExprImputation
 
     @ProcGroup.add_proc
     def p_pathway_activity(self) -> Type[Proc]:

biopipen-0.27.7/biopipen/scripts/scrna/ExprImputation.R

@@ -0,0 +1,7 @@
+{% if envs.tool == "rmagic" %}
+{% include biopipen_dir + "/scripts/scrna/ExprImputation-rmagic.R" %}
+{% elif envs.tool == "scimpute" %}
+{% include biopipen_dir + "/scripts/scrna/ExprImputation-scimpute.R" %}
+{% elif envs.tool == "alra" %}
+{% include biopipen_dir + "/scripts/scrna/ExprImputation-alra.R" %}
+{% endif %}

{biopipen-0.27.6 → biopipen-0.27.7}/biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R

@@ -50,8 +50,18 @@ do_one_group <- function(obj, features, group, outputdir, h1) {
     classes[classes != group] <- "_REST"
     classes[classes == group] <- groupname
     if (any(table(classes) < 5)) {
-        msg <- paste("Group", group, "has less than 5 cells, or only 5 cells left.")
+        msg <- paste("  Skipped. One of the groups has less than 5 cells.")
         log_warn(msg)
+        # write a warning.txt to odir with the message and table(classes)
+        write(paste0(msg, "\n\n"), file = file.path(odir, "warning.txt"))
+        write.table(
+            table(classes),
+            file = file.path(odir, "warning.txt"),
+            sep = "\t",
+            quote = FALSE,
+            row.names = FALSE,
+            append = TRUE
+        )
         return(
             list(
                 list(kind = "error", content = msg),

{biopipen-0.27.6 → biopipen-0.27.7}/biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R

@@ -84,14 +84,18 @@ do_one_comparison <- function(
 
     odir = file.path(groupdir, paste0(subset_prefix, compname))
     dir.create(odir, showWarnings = FALSE)
-    if (ncol(exprs_case) < 3 || ncol(exprs_control) < 3) {
-        log_warn("          Skip (not enough cells)")
-        add_report(
+    if (ncol(exprs_case) < 5 || ncol(exprs_control) < 5) {
+        log_warn("  Skipped (not enough cells).")
+        wfile <- file.path(odir, "warning.txt")
+        write("Skipped (not enough cells)\n\n", file = wfile)
+        write(paste0("n_cells (Case):", ncol(exprs_case)), file = wfile, append = TRUE)
+        write(paste0("n_cells (Control):", ncol(exprs_control)), file = wfile, append = TRUE)
+
+        return(list(
             list(kind = "error", content = "Not enough cells"),
             h1 = groupname,
             h2 = compname
-        )
-        return (NULL)
+        ))
     }
     if (fgsea) {
         ranks = prerank(

{biopipen-0.27.6 → biopipen-0.27.7}/biopipen/utils/gsea.R

@@ -2,11 +2,36 @@ library(ggplot2)
 library(dplyr)
 library(tibble)
 
-.slugify <- function(x, non_alphanum_replace="-", collapse_replace=TRUE, tolower=FALSE) {
-    x <- gsub("[^[:alnum:]_]", non_alphanum_replace, x)
-    if(collapse_replace) x <- gsub(paste0(non_alphanum_replace, "+"), non_alphanum_replace, x)
-    if(tolower) x <- tolower(x)
-    x
+if (!exists("slugify")) {
+    slugify <- function(x, non_alphanum_replace="-", collapse_replace=TRUE, tolower=FALSE) {
+        subs <- list(
+            "š"="s", "œ"="oe", "ž"="z", "ß"="ss", "þ"="y", "à"="a", "á"="a", "â"="a",
+            "ã"="a", "ä"="a", "å"="a", "æ"="ae", "ç"="c", "è"="e", "é"="e", "ê"="e",
+            "ë"="e", "ì"="i", "í"="i", "î"="i", "ï"="i", "ð"="d", "ñ"="n", "ò"="o",
+            "ó"="o", "ô"="o", "õ"="o", "ö"="o", "ø"="oe", "ù"="u", "ú"="u", "û"="u",
+            "ü"="u", "ý"="y", "ÿ"="y", "ğ"="g", "ı"="i", "ij"="ij", "ľ"="l", "ň"="n",
+            "ř"="r", "ş"="s", "ť"="t", "ų"="u", "ů"="u", "ý"="y", "ź"="z", "ż"="z",
+            "ſ"="s", "α"="a", "β"="b", "γ"="g", "δ"="d", "ε"="e", "ζ"="z", "η"="h",
+            "θ"="th", "ι"="i", "κ"="k", "λ"="l", "μ"="m", "ν"="n", "ξ"="x", "ο"="o",
+            "π"="p", "ρ"="r", "σ"="s", "τ"="t", "υ"="u", "φ"="ph", "χ"="ch", "ψ"="ps",
+            "ω"="o", "ά"="a", "έ"="e", "ή"="h", "ί"="i", "ό"="o", "ύ"="u", "ώ"="o",
+            "ϐ"="b", "ϑ"="th", "ϒ"="y", "ϕ"="ph", "ϖ"="p", "Ϛ"="st", "ϛ"="st", "Ϝ"="f",
+            "ϝ"="f", "Ϟ"="k", "ϟ"="k", "Ϡ"="k", "ϡ"="k", "ϰ"="k", "ϱ"="r", "ϲ"="s",
+            "ϳ"="j", "ϴ"="th", "ϵ"="e", "϶"="p"
+        )
+        # replace latin and greek characters to the closest english character
+        for (k in names(subs)) {
+            x <- gsub(k, subs[[k]], x)
+        }
+        x <- gsub("[^[:alnum:]_]", non_alphanum_replace, x)
+        if(collapse_replace) x <- gsub(
+            paste0(gsub("([][{}()+*^$|\\\\?.])", "\\\\\\1", non_alphanum_replace), "+"),
+            non_alphanum_replace,
+            x
+        )
+        if(tolower) x <- tolower(x)
+        x
+    }
 }
 
 localizeGmtfile <- function(gmturl, cachedir = tempdir()) {
@@ -25,7 +50,12 @@ localizeGmtfile <- function(gmturl, cachedir = tempdir()) {
         if (nrow(items) == 0) {
             stop(paste0("Empty GMT file: ", gmtfile, ", from ", gmturl))
         }
-        if (nchar(items$V2[1]) < nchar(items$V1[1]) && nchar(items$V2[1]) > 0) {
+        if (
+            is.character(items$V2[1]) &&
+            nchar(items$V2[1]) < nchar(items$V1[1]) &&
+            nchar(items$V2[1]) > 0 &&
+            is.na(suppressWarnings(as.numeric(items$V2[1])))
+        ) {
             warning(paste0(
                 "The second column is shorter, switching the first and second columns in GMT file ",
                 gmtfile,
@@ -153,7 +183,8 @@ runFGSEA = function(
 
     write.table(
         gsea_res %>%
-            mutate(leadingEdge = sapply(leadingEdge, function(x) paste(x, collapse=","))),
+            mutate(leadingEdge = sapply(leadingEdge, function(x) paste(x, collapse=",")),
+                   slug = sapply(pathway, slugify)),
         file = file.path(outdir, "fgsea.txt"),
         row.names = FALSE,
         col.names = TRUE,
@@ -172,16 +203,16 @@ runFGSEA = function(
 
     tablefig = file.path(outdir, "gsea_table.png")
     png(tablefig, res=100, width=1000, height=200 + 40 * length(topPathways))
-    plotGseaTable(
+    print(plotGseaTable(
         envs$pathways[topPathways],
         ranks,
         gsea_res,
         gseaParam = if (!is.null(envs$gseaParam)) envs$gseaParam else 1
-    )
+    ))
     dev.off()
 
     for (pathway in topPathways) {
-        enrfig = file.path(outdir, paste0("fgsea_", .slugify(pathway), ".png"))
+        enrfig = file.path(outdir, paste0("fgsea_", slugify(pathway), ".png"))
         png(enrfig, res=100, width=1000, height=800)
         print(plotEnrichment(
             envs$pathways[[pathway]],

{biopipen-0.27.6 → biopipen-0.27.7}/biopipen/utils/misc.R

@@ -33,6 +33,7 @@ bQuote <- function(x) {
 }
 
 #' Slugify a string
+#' Remember also update the one in gsea.R
 #' @param x A string
 #' @param non_alphanum_replace Replace non-alphanumeric characters
 #' @param collapse_replace Collapse consecutive non-alphanumeric character replacements

{biopipen-0.27.6 → biopipen-0.27.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.27.6"
+version = "0.27.7"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

{biopipen-0.27.6 → biopipen-0.27.7}/setup.py

@@ -81,7 +81,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.27.6',
+    'version': '0.27.7',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.27.6/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.27.6"

biopipen-0.27.6/biopipen/scripts/scrna/ExprImpution.R

@@ -1,7 +0,0 @@
-{% if envs.tool == "rmagic" %}
-{% include biopipen_dir + "/scripts/scrna/ExprImpution-rmagic.R" %}
-{% elif envs.tool == "scimpute" %}
-{% include biopipen_dir + "/scripts/scrna/ExprImpution-scimpute.R" %}
-{% elif envs.tool == "alra" %}
-{% include biopipen_dir + "/scripts/scrna/ExprImpution-alra.R" %}
-{% endif %}