biopipen 0.27.6__py3-none-any.whl → 0.27.7__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.27.6"
+__version__ = "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/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/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/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/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/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/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/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.dist-info → biopipen-0.27.7.dist-info}/METADATA

@@ -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-0.27.6.dist-info → biopipen-0.27.7.dist-info}/RECORD

@@ -1,9 +1,9 @@
-biopipen/__init__.py,sha256=BwKhBzWMdVser1JHOUEX0Aa2nBqgua67wsNi17fRle0,23
+biopipen/__init__.py,sha256=2q8A1v0my4JKqq2Mun4r1CJc3a3hPBoWgXjeUKWcOpQ,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=20RCI30Peee1EQdfb_UbV3Hf74XUPndJnYZlUThytsw,1781
 biopipen/core/defaults.py,sha256=yPeehPLk_OYCf71IgRVCWuQRxLAMixDF81Ium0HtPKI,344
-biopipen/core/filters.py,sha256=HLrjXGsvvjRtTWIAmg_f4IMymWaRD769HlDwsCTh170,12424
+biopipen/core/filters.py,sha256=-OIzS5F_yNZ0Nk5Ci16BepPWqLOGBmYVqX3W98RSK9Y,12488
 biopipen/core/proc.py,sha256=60lUP3PcUAaKbDETo9N5PEIoeOYrLgcSmuytmrhcx8g,912
 biopipen/core/testing.py,sha256=lZ_R5ZbYPO2NPuLHdbzg6HbD_f4j8paVVbyeUqwg6FE,3411
 biopipen/ns/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -21,8 +21,8 @@ biopipen/ns/gsea.py,sha256=EsNRAPYsagaV2KYgr4Jv0KCnZGqayM209v4yOGGTIOI,7423
 biopipen/ns/misc.py,sha256=fzn0pXvdghMkQhu-e3MMapPNMyO6IAJbtTzVU3GbFa0,3246
 biopipen/ns/plot.py,sha256=fzJAKKl4a_tsVkLREGCQTFVHP049m33LdWgeYRb6v7M,5483
 biopipen/ns/rnaseq.py,sha256=bKAa6friFWof4yDTWZQahm1MS-lrdetO1GqDKdfxXYc,7708
-biopipen/ns/scrna.py,sha256=7Gs1xxQoGM3TKxaQvbgKNyMDEsgatFopImzC-RcOEoA,103946
-biopipen/ns/scrna_metabolic_landscape.py,sha256=EhOtHQyoH-jRpzDoOI_06UbjEg6mhvbDEHKhek01bPk,28334
+biopipen/ns/scrna.py,sha256=qpMBKqkn_Cx6clpiNUpZjxGZIBzL3zPvO4m_Lxt4O0o,103952
+biopipen/ns/scrna_metabolic_landscape.py,sha256=6AhaynGG3lNRi96N2tReVT46BJMuEwooSSd2irBoN80,28347
 biopipen/ns/snp.py,sha256=EQ2FS0trQ7YThPmBVTpS66lc2OSfgQ6lCh6WnyP-C2g,5499
 biopipen/ns/stats.py,sha256=yJ6C1CXF84T7DDs9mgufqUOr89Rl6kybE5ji8Vnx6cw,13693
 biopipen/ns/tcgamaf.py,sha256=AFbUJIxiMSvsVY3RcHgjRFuMnNh2DG3Mr5slLNEyz6o,1455
@@ -126,10 +126,10 @@ biopipen/scripts/scrna/CellTypeAnnotation-sctype.R,sha256=1nKRtzhVoJ9y0yMg1sgI6u
 biopipen/scripts/scrna/CellTypeAnnotation.R,sha256=OwLM_G4D7TG4HhIJjQxgIQM92X86lsWp9MVyXTTkLSc,618
 biopipen/scripts/scrna/CellsDistribution.R,sha256=isDr5-EWvOeWwVZdjOSsdX3QUpEaDvQFulIYawqFaQc,18854
 biopipen/scripts/scrna/DimPlots.R,sha256=-mXOTMnpPxvR30XLjwcohFfFx7xTqWKKiICwJiD6yEo,1554
-biopipen/scripts/scrna/ExprImpution-alra.R,sha256=w3W1txJcdWg52-SETY2Z0lO7maDNfiMjBYIGN587YW0,843
-biopipen/scripts/scrna/ExprImpution-rmagic.R,sha256=jYIfqZpnvjKJkvItLnemPVtUApHBYQi1_L8rHVbEe1M,735
-biopipen/scripts/scrna/ExprImpution-scimpute.R,sha256=mg40qCUW7-nP5oHPvARq7dmtoahM0GRFWXQpum0BXVk,1082
-biopipen/scripts/scrna/ExprImpution.R,sha256=7768ezrr59xUZDXq8lO9jj2XhnkSsx-xxBmOD9_DO7c,313
+biopipen/scripts/scrna/ExprImputation-alra.R,sha256=w3W1txJcdWg52-SETY2Z0lO7maDNfiMjBYIGN587YW0,843
+biopipen/scripts/scrna/ExprImputation-rmagic.R,sha256=jYIfqZpnvjKJkvItLnemPVtUApHBYQi1_L8rHVbEe1M,735
+biopipen/scripts/scrna/ExprImputation-scimpute.R,sha256=mg40qCUW7-nP5oHPvARq7dmtoahM0GRFWXQpum0BXVk,1082
+biopipen/scripts/scrna/ExprImputation.R,sha256=GcdZJpkDpq88hRQjtLZY5-byp8V43stEFm5T-pQbU6A,319
 biopipen/scripts/scrna/MarkersFinder.R,sha256=M7fHTbHHErZ9JbLmjDkx-6yVIay0_h0MkvgFegnqL44,22918
 biopipen/scripts/scrna/MetaMarkers.R,sha256=9ve1X0TrDzS_ZEW6HtU3n8R-uPx7q-hYMMNFVDSE8wQ,11272
 biopipen/scripts/scrna/ModuleScoreCalculator.R,sha256=JSHd-_-KiFqW8avCGxgU4T-C5BtDr2u0kwIvEu2lFIg,4188
@@ -157,8 +157,8 @@ biopipen/scripts/scrna/Subset10X.R,sha256=T2nJBTwOe12AIKC2FZsMSv6xx3s-67CYZokpz5
 biopipen/scripts/scrna/TopExpressingGenes.R,sha256=kXMCYHVytgVgO_Uq66fKKFCFV2PPXE8VREy_0yYPLpU,7475
 biopipen/scripts/scrna/celltypist-wrapper.py,sha256=f5M8f4rU5nC7l17RS0YVmUPpLLz4D6PIcgWtA77UExM,1722
 biopipen/scripts/scrna/sctype.R,sha256=NaUJkABwF5G1UVm1CCtcMbwLSj94Mo24mbYCKFqo1Bw,6524
-biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R,sha256=nSBNn1BMwqoApTqmvzLeRhFu2JW_mNhOXICxmBYIP6E,4813
-biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R,sha256=ic8Fy8QqYDGh_izmvZVJ3KL66podg_CSF5ITL3FZsvo,5196
+biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R,sha256=sOnHSH0Ld-tXSIXJPnXLYgRtEru5M0g3HRxbrHWQ_0U,5170
+biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R,sha256=RPSxEHWk50Fyw5YPBVVGeWwd55Hi0zjbipLuM5O4tjs,5465
 biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R,sha256=95DLX1Rz0tobOuDZ8V9YdGgO0KiNthhccoeeOK21tno,16216
 biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R,sha256=rQ9iwGh9FNRZlJJzM4QItdyXmebfzLAq05ZAjb1kGUw,9831
 biopipen/scripts/snp/MatrixEQTL.R,sha256=zOR_mhn_sUXuxqgV82TPvDp-E1i5aJVA45QixyRP8no,5930
@@ -230,9 +230,9 @@ biopipen/utils/caching.R,sha256=qANQqH8p-VpvD8V4VSoqSfp0TFr4esujC7x3OFZsJMw,1687
 biopipen/utils/common_docstrs.py,sha256=Ow-g-yS5P7DEO37cP1X-xioRbYWygfQHxIuLIaDdrjs,6288
 biopipen/utils/gene.R,sha256=BzAwlLA8hO12vF-3t6IwEuTEeLa_jBll4zm_5qe3qoE,1243
 biopipen/utils/gene.py,sha256=qE_BqTayrJWxRdniffhcz6OhZcw9GUoOrj2EtFWH9Gw,2246
-biopipen/utils/gsea.R,sha256=2sN3AM0XjLWbTv6cB3JHCBWjuhmD4wEjPaaBY7wkhCI,7542
+biopipen/utils/gsea.R,sha256=BUr4pwfo7ZyinOyNa4O4dDxA1c50qWb3lpph374Yw_A,9239
 biopipen/utils/io.R,sha256=jIYdqdn0iRWfQYAZa5CjXi3fikqmYvPPLIXhobRe8sw,537
-biopipen/utils/misc.R,sha256=jXusPDCxSIaYRq_qm4khUsu9nyMhbpBVcj8BVn4j8Ic,10629
+biopipen/utils/misc.R,sha256=Y9J8gZDuPPYFxYNQtDEvKAk5j-K8j_-n0DunYvu_Hv8,10671
 biopipen/utils/misc.py,sha256=KJziAFY4Kl-0ZsO93vteY9gRLZg9BSYig-TDocHY36k,3601
 biopipen/utils/mutate_helpers.R,sha256=Bqy6Oi4rrPEPJw0Jq32bVAwwBfZv7JJL9jFcK5x-cek,17649
 biopipen/utils/plot.R,sha256=pzl37PomNeUZPxohHZ2w93j3Fc4T0Qrc62FF-9MTKdw,4417
@@ -240,7 +240,7 @@ biopipen/utils/reference.py,sha256=6bPSwQa-GiDfr7xLR9a5T64Ey40y24yn3QfQ5wDFZkU,4
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=pJjYP8bIZpNAtTQ32rOXhZxaM1Y-6D-xUcK3pql9tbk,4316
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.27.6.dist-info/METADATA,sha256=t7ROsmFyR6-E4YXGAwiuNxRjZz5IX6_H7mT1rs9OSfE,882
-biopipen-0.27.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.27.6.dist-info/entry_points.txt,sha256=wu70aoBcv1UahVbB_5237MY-9M9_mzqmWjDD-oi3yz0,621
-biopipen-0.27.6.dist-info/RECORD,,
+biopipen-0.27.7.dist-info/METADATA,sha256=uIwtisFh-OLK9tI5oR7psOVDH_lSUIT8Dy6iWzgmyyE,882
+biopipen-0.27.7.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+biopipen-0.27.7.dist-info/entry_points.txt,sha256=wu70aoBcv1UahVbB_5237MY-9M9_mzqmWjDD-oi3yz0,621
+biopipen-0.27.7.dist-info/RECORD,,

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 %}