biopipen 0.7.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

biopipen/reports/tcr/CloneResidency.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 <script>
-    import { Image, DataTable } from "@@";
-    import { Dropdown } from "carbon-components-svelte";
+    import { Image, DataTable } from "$lib";
+    import { Dropdown } from "$ccs";
 
     let count_sample;
 
@@ -39,7 +39,7 @@
 
     <h{{h}}>Residency plots</h{{h}}>
 
-    {% if job.out.outdir | joinpaths: "sample_groups" | as_path | attr: "exists" | call %}
+    {% if job.out.outdir | joinpaths: "sample_groups" | exists %}
         {% for groupfile in job.out.outdir | glob: "sample_groups", "*.txt" %}
             {% set group = groupfile | stem %}
             <h{{h+1}}>{{group}}</h{{h+1}}>
@@ -57,7 +57,7 @@
 
     <h{{h}}>Clonotype overlapping</h{{h}}>
 
-    {% if job.out.outdir | joinpaths: "sample_groups" | as_path | attr: "exists" | call %}
+    {% if job.out.outdir | joinpaths: "sample_groups" | exists %}
         {% for groupfile in job.out.outdir | glob: "sample_groups", "*.txt" %}
             {% set group = groupfile | stem %}
             <h{{h+1}}>{{group}}</h{{h+1}}>

biopipen/reports/tcr/Immunarch.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 <script>
-    import { Image } from "@@";
-    import { Tabs, Tab, TabContent, Tile, UnorderedList, p } from "carbon-components-svelte";
+    import { Image } from "$lib";
+    import { Tabs, Tab, TabContent, Tile, UnorderedList, p } from "$ccs";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/tcr/SampleDiversity.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 <script>
-    import { Image } from "@@";
-    import { Tile } from "carbon-components-svelte";
+    import { Image } from "$lib";
+    import { Tile } from "$ccs";
 </script>
 
 

biopipen/reports/tcr/TCRClusteringStats.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image, DataTable } from "@@";
-    import { Tabs, Tab, TabContent } from "carbon-components-svelte";
+    import { Image, DataTable } from "$lib";
+    import { Tabs, Tab, TabContent } from "$ccs";
 </script>
 
 {%- macro report_job(job, h=1) -%}
@@ -25,7 +25,7 @@
     </svelte:fragment>
 </Tabs>
 
-{%- if job.out.outdir | joinpaths: "SharedClustersByGrouping" | as_path | attr: "is_dir" | call -%}
+{%- if job.out.outdir | joinpaths: "SharedClustersByGrouping" | isdir -%}
 <h{{h}}>Shared TCR clusters from groups</h{{h}}>
 <Image src={{job.out.outdir | joinpaths: "SharedClustersByGrouping/shared_clusters_by_grouping.png" | quote}} />
 {%- endif -%}

biopipen/reports/tcr/VJUsage.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 <h1>V-J usage plots</h1>

biopipen/reports/utils/gsea.liq

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import table_of_images -%}
 
 {%- macro fgsea_report_script() -%}
-import { Image, DataTable } from "../components";
+import { Image, DataTable } from "$lib";
 {%- endmacro -%}
 
 {%- macro fgsea_report(fgsea_dir, h, envs, nrows=100) -%}

biopipen/reports/utils/misc.liq

@@ -16,7 +16,7 @@
 
 
 {%- macro table_of_images_script() -%}
-import { Image } from "../components";
+import { Image } from "$lib";
 {%- endmacro -%}
 
 {%- macro table_of_images(srcs, caps=None, col=2, table_width=100) -%}

biopipen/reports/vcf/TruvariBenchSummary.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 <script>
-    import { DataTable, Image } from "@@";
+    import { DataTable, Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/vcf/TruvariConsistency.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image } from "@@";
-    import { Tile } from "carbon-components-svelte";
+    import { Image } from "$lib";
+    import { Tile } from "$ccs";
 </script>
 
 {%- macro report_job(job, h=1) -%}
@@ -13,7 +13,7 @@
 </pre>
 </Tile>
 
-{%- if job.out.outdir | joinpaths: "consistency.png" | as_path | attr: "exists" | call -%}
+{%- if job.out.outdir | joinpaths: "consistency.png" | exists -%}
 <h{{h}}>Heatmap of base CNV presence for each sample</h{{h}}>
 
 <Image src={{job.out.outdir | joinpaths: "consistency.png" | quote}} />

biopipen/scripts/bcftools/BcftoolsSort.py

@@ -0,0 +1,19 @@
+import cmdy
+
+infile = {{in.infile | quote}}  # pyright: ignore
+outfile = {{out.outfile | quote}}  # pyright: ignore
+bcftools = {{envs.bcftools | quote}}  # pyright: ignore
+gz = {{envs.gz | repr}}  # pyright: ignore
+args = {{envs.args | repr}}  # pyright: ignore
+tmpdir = {{envs.tmpdir | quote}}  # pyright: ignore
+index = {{envs.index | repr}}  # pyright: ignore
+
+args["_exe"] = bcftools
+args["_"] = infile
+args["o"] = outfile
+args["O"] = "z" if gz or index else "v"
+
+cmdy.bcftools.sort(**args).fg()
+
+if index:
+    cmdy.bcftools.index(outfile).fg()

biopipen/scripts/scrna/MarkersFinder.R

@@ -6,6 +6,7 @@ library(tidyr)
 library(tibble)
 library(Seurat)
 library(enrichR)
+library(ggplot2)
 library(future)
 library(tidyseurat)
 
@@ -36,7 +37,17 @@ do_enrich = function(case, markers) {
     print(paste("  Running enrichment for case:", case))
     casedir = file.path(outdir, case)
     dir.create(casedir, showWarnings = FALSE)
+    if (nrow(markers) == 0) {
+        print(paste("  No markers found for case:", case))
+        cat("No markers found.", file=file.path(casedir, "error.txt"))
+        return()
+    }
     markers_sig = markers %>% filter(!!parse_expr(sigmarkers))
+    if (nrow(markers_sig) == 0) {
+        print(paste("  No significant markers found for case:", case))
+        cat("No significant markers.", file=file.path(casedir, "error.txt"))
+        return()
+    }
     write.table(
         markers_sig,
         file.path(casedir, "markers.txt"),
@@ -45,27 +56,45 @@ do_enrich = function(case, markers) {
         col.names=TRUE,
         quote=FALSE
     )
-
-    enriched = enrichr(markers_sig$gene, dbs)
-    for (db in dbs) {
-        write.table(
-            enriched[[db]],
-            file.path(casedir, paste0("Enrichr-", db, ".txt")),
-            sep="\t",
-            row.names=FALSE,
-            col.names=TRUE,
-            quote=FALSE
-        )
-        png(
-            file.path(casedir, paste0("Enrichr-", db, ".png")),
-            res=100, height=1000, width=1000
-        )
-        if (nrow(markers_sig) == 0) {
-            print(ggplot() + annotate("text", x=1, y=1, label="No significant markers."))
-        } else {
+    if (nrow(markers_sig) < 5) {
+        for (db in dbs) {
+            write.table(
+                data.frame(Warning = "Not enough significant markers."),
+                file.path(casedir, paste0("Enrichr-", db, ".txt")),
+                sep="\t",
+                row.names=FALSE,
+                col.names=TRUE,
+                quote=FALSE
+            )
+            png(
+                file.path(casedir, paste0("Enrichr-", db, ".png")),
+                res=100, height=200, width=1000
+            )
+            print(
+                ggplot() +
+                annotate("text", x=1, y=1, label="Not enough significant markers.") +
+                theme_classic()
+            )
+            dev.off()
+        }
+    } else {
+        enriched = enrichr(markers_sig$gene, dbs)
+        for (db in dbs) {
+            write.table(
+                enriched[[db]],
+                file.path(casedir, paste0("Enrichr-", db, ".txt")),
+                sep="\t",
+                row.names=FALSE,
+                col.names=TRUE,
+                quote=FALSE
+            )
+            png(
+                file.path(casedir, paste0("Enrichr-", db, ".png")),
+                res=100, height=1000, width=1000
+            )
             print(plotEnrich(enriched[[db]], showTerms = 20, title=db))
+            dev.off()
         }
-        dev.off()
     }
 }
 
@@ -82,32 +111,41 @@ mutate_meta = function(obj, mutaters) {
 }
 
 do_case = function(case) {
-    print(paste("- Dealing with case:", case, "..."))
+    cat(paste("- Dealing with case:", case, "...\n"))
     casepms = cases$cases[[case]]
-    pmnames = names(casepms)
     obj = seurat_obj
-    if ("filter" %in% pmnames) {
+    if (!is.null(casepms$filter)) {
         obj = obj %>% filter(eval(parse(text=casepms$filter)))
     }
     obj = mutate_meta(obj, casepms$mutaters)
     casepms$mutaters = NULL
-    if ("filter2" %in% pmnames) {
+    if (!is.null(casepms$filter2)) {
         obj = obj %>% filter(eval(parse(text=casepms$filter2)))
     }
-
-    if (!"ident.1" %in% pmnames && !"ident.2" %in% pmnames) {
-        Idents(obj) = casepms$group.by
-        casepms$group.by = NULL
-        casepms$object = obj
-        allmarkers = do_call(FindAllMarkers, casepms)
-        # Is it always cluster?
-        for (group in sort(unique(allmarkers$cluster))) {
-            do_enrich(paste(case, group, sep="_"), allmarkers %>% filter(cluster == group))
+    if (!is.null(casepms$each)) {
+        eachs = unique(obj@meta.data[[casepms$each]])
+        for (each in eachs) {
+            print(paste("  Dealing with unit:", each, "..."))
+            eachobj = obj %>% filter(!!parse_expr(casepms$each) == each)
+            casepms$object = eachobj
+            markers = do_call(FindMarkers, casepms) %>% rownames_to_column("gene")
+            do_enrich(paste0(case, " (", each, ")"), markers)
         }
     } else {
-        casepms$object = obj
-        markers = do_call(FindMarkers, casepms) %>% rownames_to_column("gene")
-        do_enrich(case, markers)
+        if (is.null(casepms$ident.1) && is.null(casepms$ident.2)) {
+            Idents(obj) = casepms$group.by
+            casepms$group.by = NULL
+            casepms$object = obj
+            allmarkers = do_call(FindAllMarkers, casepms)
+            # Is it always cluster?
+            for (group in sort(unique(allmarkers$cluster))) {
+                do_enrich(paste(case, group, sep="_"), allmarkers %>% filter(cluster == group))
+            }
+        } else {
+            casepms$object = obj
+            markers = do_call(FindMarkers, casepms) %>% rownames_to_column("gene")
+            do_enrich(case, markers)
+        }
     }
 }
 

biopipen/scripts/tcgamaf/Maf2Vcf.py

@@ -0,0 +1,22 @@
+import cmdy
+
+infile = {{in.infile | quote}}  # pyright: ignore
+outfile = {{out.outfile | quote}}  # pyright: ignore
+outdir = {{out.outdir | quote}}  # pyright: ignore
+perl = {{envs.perl | quote}}  # pyright: ignore
+ref = {{envs.ref | repr}}  # pyright: ignore
+samtools = {{envs.samtools | quote}}  # pyright: ignore
+args = {{envs.args | repr}}  # pyright: ignore
+maf2vcf = {{biopipen_dir | append: "/scripts/tcgamaf/maf2vcf.pl" | repr}}  # pyright: ignore
+
+args['input-maf']  = infile
+args['output-vcf'] = outfile
+args['output-dir'] = outdir
+args['ref-fasta']  = ref
+
+cmd = cmdy.perl(maf2vcf, _exe=perl, **args).hold()
+
+print("Running:")
+print(cmd.strcmd)
+
+cmd.fg().run()

biopipen/scripts/tcgamaf/MafAddChr.py

@@ -0,0 +1,14 @@
+
+infile = {{in.infile | quote}}  # pyright: ignore
+outfile = {{out.outfile | quote}}  # pyright: ignore
+
+with open(infile) as fin, open(outfile, "w") as fout:
+    for line in fin:
+        if line.startswith("#") or line.startswith("Hugo_Symbol"):
+            fout.write(line)
+        else:
+            cols = line.split("\t")
+            if not cols[4].startswith("chr"):
+                cols[4] = f"chr{cols[4]}"
+            # "\n" at the last col kept
+            fout.write("\t".join(cols))