biopipen 0.32.1__py3-none-any.whl → 0.33.0__py3-none-any.whl

biopipen/scripts/tcr/Immunarch-diversity.R

@@ -353,7 +353,14 @@ run_general = function(casename, d, case, ddir, value_col = "Value") {
             width = width * case$ncol
         }
     }
-    png(file.path(ddir, "diversity.png"), width = width, height = height, res = res)
+
+    div_plot = file.path(ddir, "diversity.png")
+    png(div_plot, width = width, height = height, res = res)
+    print(p)
+    dev.off()
+
+    div_plot_pdf = file.path(ddir, "diversity.pdf")
+    pdf(div_plot_pdf, width = width / res, height = height / res)
     print(p)
     dev.off()
 
@@ -407,7 +414,7 @@ run_general = function(casename, d, case, ddir, value_col = "Value") {
     add_report(
         list(
             name = "Diversity Plot",
-            contents = list(list(kind = "image", src = file.path(ddir, "diversity.png")))
+            contents = list(list(kind = "image", src = div_plot, download = div_plot_pdf))
         ),
         list(
             name = "Diversity Table",
@@ -559,6 +566,10 @@ run_raref_single = function(d, case, ddir, suffix = "", save_p = TRUE) {
         png(file.path(ddir, "raref.png"), width = devpars$width, height = devpars$height, res = devpars$res)
         print(p)
         dev.off()
+
+        pdf(file.path(ddir, "raref.pdf"), width = devpars$width / devpars$res, height = devpars$height / devpars$res)
+        print(p)
+        dev.off()
     } else {
         return (list(p = p, width = devpars$width))
     }
@@ -628,6 +639,14 @@ run_raref_multi = function(d, case, ddir) {
     )
     print(p)
     dev.off()
+
+    pdf(
+        file.path(ddir, paste0("raref-", slugify(case$separate_by), ".pdf")),
+        width = width / res,
+        height = height / res
+    )
+    print(p)
+    dev.off()
 }
 
 # Run the diversity estimation for one case
@@ -673,7 +692,8 @@ run_div_case = function(casename) {
             add_report(
                 list(
                     kind = "image",
-                    src = file.path(ddir, paste0("raref-", slugify(case$separate_by), ".png"))
+                    src = file.path(ddir, paste0("raref-", slugify(case$separate_by), ".png")),
+                    download = file.path(ddir, paste0("raref-", slugify(case$separate_by), ".pdf"))
                 ),
                 h1 = "Rarefraction",
                 h2 = casename
@@ -683,7 +703,8 @@ run_div_case = function(casename) {
             add_report(
                 list(
                     kind = "image",
-                    src = file.path(ddir, "raref.png")
+                    src = file.path(ddir, "raref.png"),
+                    download = file.path(ddir, "raref.pdf")
                 ),
                 h1 = "Rarefraction",
                 h2 = casename

biopipen/scripts/tcr/Immunarch-geneusage.R

@@ -126,10 +126,16 @@ do_one_case_geneusage = function(name, case, gu_dir) {
     print(p + scale_fill_biopipen())
     dev.off()
 
+    ofig_pdf = file.path(odir, paste0(name, ".pdf"))
+    pdf(ofig_pdf, width = case$devpars$width / case$devpars$res, height = case$devpars$height / case$devpars$res)
+    print(p + scale_fill_biopipen())
+    dev.off()
+
     add_report(
         list(
             kind = "table_image",
             src = ofig,
+            download = ofig_pdf,
             descr = paste0(
                  "Distribution of known gene segments following the ",
                  '<a href="http://www.imgt.org/IMGTrepertoire/LocusGenes/" target="_blank">IMGT</a> ',
@@ -165,15 +171,23 @@ do_one_case_geneusage = function(name, case, gu_dir) {
             ap = do_call(vis, avis_args)
             if (aname == "DEFAULT") {
                 aofig = file.path(odir, paste0(name, "-analysis.png"))
+                aofig_pdf = file.path(odir, paste0(name, "-analysis.pdf"))
             } else {
                 aofig = file.path(odir, paste0(name, "-", aname, "-analysis.png"))
+                aofig_pdf = file.path(odir, paste0(name, "-", aname, "-analysis.pdf"))
             }
             png(aofig, width = case$analyses$cases[[aname]]$devpars$width, height = case$analyses$cases[[aname]]$devpars$height, res = case$analyses$cases[[aname]]$devpars$res)
             print(ap)
             dev.off()
 
+            pdf(aofig_pdf,
+                width = case$analyses$cases[[aname]]$devpars$width / case$analyses$cases[[aname]]$devpars$res,
+                height = case$analyses$cases[[aname]]$devpars$height / case$analyses$cases[[aname]]$devpars$res)
+            print(ap)
+            dev.off()
+
             add_report(
-                list(src = aofig, name = aname),
+                list(src = aofig, name = aname, download = aofig_pdf),
                 h1 = "Gene Usage",
                 h2 = ifelse(name == "DEFAULT", "#", name),
                 h3 = "Gene Usage Analysis",

biopipen/scripts/tcr/Immunarch-kmer.R

@@ -105,6 +105,11 @@ do_one_case_kmer = function(name, case, kmer_dir) {
     print(p)
     dev.off()
 
+    ofig_pdf = file.path(odir, "Allsamples.pdf")
+    pdf(ofig_pdf, width = case$devpars$width / case$devpars$res, height = case$devpars$height / case$devpars$res)
+    print(p)
+    dev.off()
+
     add_report(
         list(
             kind = "descr",
@@ -116,7 +121,7 @@ do_one_case_kmer = function(name, case, kmer_dir) {
     )
 
     add_report(
-        list(kind = "image", src = ofig),
+        list(kind = "image", src = ofig, download = ofig_pdf),
         h1 = "Kmer and sequence motif analysis",
         h2 = ifelse(name == "DEFAULT", "#", name),
         h3 = "Kmer sequence occurrences"
@@ -150,9 +155,17 @@ do_one_case_kmer = function(name, case, kmer_dir) {
                 print(ap)
                 dev.off()
 
+                aofig_pdf = gsub(".png$", ".pdf", aofig)
+                pdf(aofig_pdf,
+                    width = case$profiles$cases[[aname]]$devpars$width / case$profiles$cases[[aname]]$devpars$res,
+                    height = case$profiles$cases[[aname]]$devpars$height / case$profiles$cases[[aname]]$devpars$res)
+                print(ap)
+                dev.off()
+
                 add_report(
                     list(
                         src = aofig,
+                        download = aofig_pdf,
                         name = paste0(sample, ifelse(aname == "DEFAULT", "", paste0(" - ", aname)))
                     ),
                     h1 = "Kmer and sequence motif analysis",

biopipen/scripts/tcr/Immunarch-overlap.R

@@ -138,10 +138,16 @@ do_one_case_overlap = function(name, case, ov_dir) {
     print(p)
     dev.off()
 
+    ofig_pdf = file.path(odir, paste0(name, ".pdf"))
+    pdf(ofig_pdf, width = case$devpars$width / case$devpars$res, height = case$devpars$height / case$devpars$res)
+    print(p)
+    dev.off()
+
     add_report(
         list(
             kind = "table_image",
             src = ofig,
+            download = ofig_pdf,
             descr = paste0(
                 "Repertoire overlap is the most common approach to measure repertoire similarity, ",
                 "using method <code>", case$method, "</code>, ",
@@ -179,15 +185,23 @@ do_one_case_overlap = function(name, case, ov_dir) {
             ap = do_call(vis, avis_args)
             if (aname == "DEFAULT") {
                 aofig = file.path(odir, paste0(name, "-analysis.png"))
+                aofig_pdf = file.path(odir, paste0(name, "-analysis.pdf"))
             } else {
                 aofig = file.path(odir, paste0(name, "-", aname, "-analysis.png"))
+                aofig_pdf = file.path(odir, paste0(name, "-", aname, "-analysis.pdf"))
             }
             png(aofig, width = case$analyses$cases[[aname]]$devpars$width, height = case$analyses$cases[[aname]]$devpars$height, res = case$analyses$cases[[aname]]$devpars$res)
             print(ap)
             dev.off()
 
+            pdf(aofig_pdf,
+                width = case$analyses$cases[[aname]]$devpars$width / case$analyses$cases[[aname]]$devpars$res,
+                height = case$analyses$cases[[aname]]$devpars$height / case$analyses$cases[[aname]]$devpars$res)
+            print(ap)
+            dev.off()
+
             add_report(
-                list(src = aofig, name = aname),
+                list(src = aofig, name = aname, download = aofig_pdf),
                 h1 = "Repertoire Overlaps",
                 h2 = ifelse(name == "DEFAULT", "#", name),
                 h3 = "Repertoire Overlap Analysis",

biopipen/scripts/tcr/Immunarch-spectratyping.R

@@ -69,8 +69,17 @@ do_one_case_spectratyping = function(name, case, spect_dir) {
         print(vis(spec_obj))
         dev.off()
 
+        spectfile_pdf = file.path(odir, paste0(slugify(sample), ".spect.pdf"))
+        pdf(
+            spectfile_pdf,
+            width = case$devpars$width / case$devpars$res,
+            height = case$devpars$height / case$devpars$res
+        )
+        print(vis(spec_obj))
+        dev.off()
+
         add_report(
-            list(src = spectfile, name = sample),
+            list(src = spectfile, name = sample, download = spectfile_pdf),
             h1 = "Spectratyping",
             h2 = name,
             ui = "table_of_images"

biopipen/scripts/tcr/Immunarch-tracking.R

@@ -88,6 +88,11 @@ run_tracking_case = function(casename) {
         print(vis(imm_tracking))
         dev.off()
 
+        tracking_pdf = file.path(tracking_dir, paste0(slugify(casename), ".pdf"))
+        pdf(tracking_pdf, height=10, width=6 + 1.5 * length(subjects))
+        print(vis(imm_tracking))
+        dev.off()
+
         add_report(
             list(
                 kind = "descr",
@@ -105,6 +110,7 @@ run_tracking_case = function(casename) {
         add_report(
             list(
                 src = tracking_png,
+                download = tracking_pdf,
                 name = if (casename == "DEFAULT") NULL else casename
             ),
             h1 = "Tracking of clonotypes",

biopipen/scripts/tcr/Immunarch-vjjunc.R

@@ -110,7 +110,40 @@ do_one_case_vjjunc <- function(name, case) {
         }, bg.border = NA) # here set bg.border to NA is important
         dev.off()
 
+        # figfile_pdf <- file.path(odir, paste0(slugify(by_name), ".pdf"))
+        # png(figfile_pdf, width = case$devpars$width / case$devpars$res, height = case$devpars$height / case$devpars$res)
+        # circos.clear()
+        # tryCatch({
+        #     chordDiagram(
+        #         gsd,
+        #         annotationTrack = c("grid", "axis"),
+        #         preAllocateTracks = list(track.height = 0.25)
+        #     )
+        # }, error = function(e) {
+        #     log_warn("Error encountered: {e$message}, setting gap.after ...")
+        #     circos.par(gap.after = c(rep(1, nrow(gsd) - 1), 5, rep(1, nrow(gsd) - 1), 5))
+        #     chordDiagram(
+        #         gsd,
+        #         annotationTrack = c("grid", "axis"),
+        #         preAllocateTracks = list(track.height = 0.25)
+        #     )
+
+        # })
+        # circos.track(track.index = 1, panel.fun = function(x, y) {
+        #     circos.text(
+        #         CELL_META$xcenter,
+        #         CELL_META$ylim[1],
+        #         CELL_META$sector.index,
+        #         cex = .8,
+        #         facing = "clockwise",
+        #         niceFacing = TRUE,
+        #         adj = c(-0.2, 0.5)
+        #     )
+        # }, bg.border = NA) # here set bg.border to NA is important
+        # dev.off()
+
         add_report(
+            # list(src = figfile, name = by_name, download = figfile_pdf),
             list(src = figfile, name = by_name),
             h1 = "V-J Junction Circos Plots",
             h2 = ifelse(name == "DEFAULT", "#" , name),

biopipen/scripts/tcr/ScRepLoading.R

@@ -0,0 +1,127 @@
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+
+library(rlang)
+library(bracer)
+library(scRepertoire)
+
+metafile <- {{in.metafile | quote}}
+outfile <- {{out.outfile | quote}}
+combineTCR_args <- {{envs.combineTCR | r}}
+exclude <- {{envs.exclude | r}}
+if (length(exclude) == 1) {
+    exclude <- strsplit(exclude, ",")[[1]]
+}
+
+log_info("Loading metadata ...")
+metadata <- read.table(metafile, header = TRUE, sep = "\t", row.names = NULL, check.names = FALSE)
+stopifnot("Error: Column `Sample` is not found in metafile." = "Sample" %in% colnames(metadata))
+stopifnot("Error: Column `TCRData` is not found in metafile." = "TCRData" %in% colnames(metadata))
+rownames(metadata) <- metadata$Sample
+
+# helper function
+get_contig_annofile <- function(dir, sample, warn = TRUE) {
+    if (is.na(dir) || !is.character(dir) || nchar(dir) == 0 || dir == "NA") {
+        warning(paste0("No path found for sample: ", sample), immediate. = TRUE)
+        return (NULL)
+    }
+    if (file.exists(dir) && !dir.exists(dir)) {
+        return(dir)
+    }
+
+    annofilepat <- paste0("*", "{all,filtered}", "_contig_annotations.csv*")  # .gz
+    annofiles <- glob(file.path(as.character(dir), annofilepat))
+    if (length(annofiles) == 0) {
+        stop(
+            "Cannot find neither `filtered_contig_annotations.csv[.gz]` nor",
+            "`all_contig_annotations.csv[.gz]` in given TCRData for sample: ",
+            sample
+        )
+    }
+    if (length(annofiles) > 1) {
+        if (warn) {
+            warning("Found more than one file in given TCRData for sample: ", sample, immediate. = TRUE)
+        }
+        for (annofile in annofiles) {
+            # use filtered if both filtered_ and all_ are found
+            if (grepl("filtered", annofile)) {
+                annofiles <- annofile
+                break
+            }
+            # give a warning if only all_ is found
+            if (warn) {
+                warning("Using all_contig_annotations as filtred_config_annotations not found ",
+                        "in given TCRData for sample: ", sample,
+                        immediate. = TRUE
+                )
+            }
+        }
+    }
+    annofiles[1]
+}
+
+# for (i in seq_len(nrow(metadata))) {
+#     sample <- as.character(metadata$Sample[i])
+#     annofile <- get_contig_annofile(metadata$TCRData[i], sample)
+#     if (is.null(annofile)) { next }
+
+#     anno <- read.delim2(annofile, sep = ",", header = TRUE, stringsAsFactors = FALSE)
+#     # Add cdr1, cdr2, fwr1, fwr2, etc columns
+#     anno$cdr1 <- anno$cdr1 %||% ""
+#     anno$cdr1_nt <- anno$cdr1_nt %||% ""
+#     anno$cdr2 <- anno$cdr2 %||% ""
+#     anno$cdr2_nt <- anno$cdr2_nt %||% ""
+#     anno$fwr1 <- anno$fwr1 %||% ""
+#     anno$fwr1_nt <- anno$fwr1_nt %||% ""
+#     anno$fwr2 <- anno$fwr2 %||% ""
+#     anno$fwr2_nt <- anno$fwr2_nt %||% ""
+#     anno$fwr3 <- anno$fwr3 %||% ""
+#     anno$fwr3_nt <- anno$fwr3_nt %||% ""
+#     anno$fwr4 <- anno$fwr4 %||% ""
+#     anno$fwr4_nt <- anno$fwr4_nt %||% ""
+
+#     annotfile = file.path(datadir, paste0(sample, ".csv"))
+#     write.table(anno, annotfile, sep = ",", quote = FALSE, row.names = FALSE, col.names = TRUE)
+# }
+
+log_info("Reading TCR data ...")
+contig_list <- lapply(seq_len(nrow(metadata)), function(i) {
+    sample <- as.character(metadata$Sample[i])
+    annofile <- get_contig_annofile(metadata$TCRData[i], sample)
+    if (is.null(annofile)) { return (NULL) }
+
+    log_info("- Sample: {sample} ...")
+    anno <- read.delim2(annofile, sep = ",", header = TRUE, stringsAsFactors = FALSE)
+    # Add cdr1, cdr2, fwr1, fwr2, etc columns for compatibility
+    anno$cdr1 <- anno$cdr1 %||% ""
+    anno$cdr1_nt <- anno$cdr1_nt %||% ""
+    anno$cdr2 <- anno$cdr2 %||% ""
+    anno$cdr2_nt <- anno$cdr2_nt %||% ""
+    anno$fwr1 <- anno$fwr1 %||% ""
+    anno$fwr1_nt <- anno$fwr1_nt %||% ""
+    anno$fwr2 <- anno$fwr2 %||% ""
+    anno$fwr2_nt <- anno$fwr2_nt %||% ""
+    anno$fwr3 <- anno$fwr3 %||% ""
+    anno$fwr3_nt <- anno$fwr3_nt %||% ""
+    anno$fwr4 <- anno$fwr4 %||% ""
+    anno$fwr4_nt <- anno$fwr4_nt %||% ""
+
+    anno
+})
+names(contig_list) <- as.character(metadata$Sample)
+contig_list <- contig_list[!sapply(contig_list, is.null)]
+
+log_info("Combining TCR data and adding meta data ...")
+if (isTRUE(combineTCR_args$samples)) {
+    combineTCR_args$samples <- names(contig_list)
+}
+combineTCR_args$input.data <- contig_list
+screp_data <- do_call(combineTCR, combineTCR_args)
+for (col in colnames(metadata)) {
+    if (col %in% exclude) { next }
+    screp_data <- addVariable(screp_data, col, metadata[names(screp_data), col])
+}
+
+rm(contig_list, combineTCR_args)
+
+log_info("Saving TCR data ...")
+saveRDS(screp_data, outfile)

biopipen/scripts/tcr/TCRClusterStats.R

@@ -69,6 +69,7 @@ cluster_size_distribution = function(name) {
 
     outfile = file.path(odir, "cluster_size_distribution.txt")
     outplot = file.path(odir, "cluster_size_distribution.png")
+    outplot_pdf = file.path(odir, "cluster_size_distribution.pdf")
     write.table(clsizes, outfile, quote = FALSE, sep = "\t", row.names = FALSE, col.names = TRUE)
 
     plotGG(
@@ -82,14 +83,15 @@ cluster_size_distribution = function(name) {
             "scale_fill_biopipen()"
         ),
         devpars = case$devpars,
-        outfile = outplot
+        outfile = c(outplot, outplot_pdf)
     )
 
     add_report(
         list(
             src = outplot,
             name = ifelse(name == "DEFAULT", FALSE, name),
-            descr = paste0("Cluster size distribution for each ", case$by)
+            descr = paste0("Cluster size distribution for each ", case$by),
+            download = outplot_pdf
         ),
         ui = "table_of_images",
         h1 = "Cluster Size Distribution"
@@ -162,6 +164,8 @@ shared_clusters = function(name) {
         row_samples = samples
     }
 
+    hmplot = file.path(odir, "shared_clusters.png")
+    hmplot_pdf = file.path(odir, "shared_clusters.pdf")
     # Plot heatmap
     plotHeatmap(
         plotdata,
@@ -178,12 +182,13 @@ shared_clusters = function(name) {
             }
         ),
         devpars = case$devpars,
-        outfile = file.path(odir, "shared_clusters.png")
+        outfile = c(hmplot, hmplot_pdf)
     )
 
     add_report(
         list(
-            src = file.path(odir, "shared_clusters.png"),
+            src = hmplot,
+            download = hmplot_pdf,
             name = ifelse(name == "DEFAULT", FALSE, name),
             descr = paste0("Shared TCR clusters across samples")
         ),
@@ -219,16 +224,18 @@ shared_clusters_by_grouping = function(name) {
     }
 
     outfile = file.path(odir, "shared_clusters.png")
+    outfile_pdf = file.path(odir, "shared_clusters.pdf")
     plotVenn(
         data,
         ggs = 'ggtitle("Shared TCR Clusters")',
         devpars = case$devpars,
-        outfile = outfile
+        outfile = c(outfile, outfile_pdf)
     )
 
     add_report(
         list(
             src = outfile,
+            download = outfile_pdf,
             name = ifelse(name == "DEFAULT", FALSE, name),
             descr = paste0("Shared TCR clusters across ", grouping)
         ),
@@ -275,6 +282,7 @@ sample_diversity = function(name) {
     }
     outfile = file.path(odir, "diversity.txt")
     outplot = file.path(odir, "diversity.png")
+    outplot_pdf = file.path(odir, "diversity.pdf")
     div = repDiversity(data, .method = case$method)
     write.table(
         if (ncol(div) == 1) {
@@ -320,7 +328,7 @@ sample_diversity = function(name) {
             args = list(mapping = mapping),
             ggs = ggs,
             devpars = case$devpars,
-            outfile = outplot
+            outfile = c(outplot, outplot_pdf)
         )
     } else {
         if (is.null(case$by) || length(case$by) == 0) {
@@ -338,6 +346,14 @@ sample_diversity = function(name) {
         )
         print(p)
         dev.off()
+
+        pdf(
+            outplot_pdf,
+            width=case$devpars$width / case$devpars$res,
+            height=case$devpars$height / case$devpars$res
+        )
+        print(p)
+        dev.off()
     }
 
     add_report(
@@ -359,7 +375,8 @@ sample_diversity = function(name) {
                 ),
                 list(
                     kind = "image",
-                    src = outplot
+                    src = outplot,
+                    download = outplot_pdf
                 )
             )
         ),

biopipen/scripts/tcr/TCRDock.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import os
 import sys
 from pathlib import Path
@@ -7,10 +9,10 @@ import pandas as pd
 from tempfile import gettempdir
 from biopipen.utils.misc import logger, run_command
 
-configfile = {{in.configfile | repr}}  # pyright: ignore
-outdir = Path({{out.outdir | repr}})  # pyright: ignore
-envs = {{envs | dict | repr}}  # pyright: ignore
-python = sys.executable
+configfile: str = {{in.configfile | quote}}  # pyright: ignore  # noqa
+outdir = Path({{out.outdir | quote}})  # pyright: ignore
+envs: dict = {{envs | dict | repr}}  # pyright: ignore
+python: str | list[str] = sys.executable
 
 args = envs.copy()
 config = rtoml.load(Path(configfile))
@@ -18,8 +20,8 @@ args.update(config)
 model_name = args.pop("model_name")
 model_file = Path(args.pop("model_file"))
 data_dir = args.pop("data_dir", None)
-tcrdock = args.pop("tcrdock", None)
-tmpdir = args.pop("tmpdir", gettempdir())
+tcrdock: Path | str | None = args.pop("tcrdock", None)
+tmpdir: str = args.pop("tmpdir", gettempdir())
 python = args.pop("python", python)
 
 if not isinstance(python, (list, tuple)):
@@ -46,6 +48,8 @@ if not tcrdock:
     ]
     run_command(cmd, fg=True, cwd=str(tcrdock))
 
+tcrdock = str(tcrdock)
+
 if not model_file.is_absolute():
     model_file = Path(data_dir) / "params" / model_file
 

biopipen/scripts/tcr/TESSA.R

@@ -198,10 +198,15 @@ png(file.path(result_dir, "Cluster_size_dist.png"), width=8, height=8, units="in
 print(p)
 dev.off()
 
+pdf(file.path(result_dir, "Cluster_size_dist.pdf"), width=8, height=8)
+print(p)
+dev.off()
+
 add_report(
     list(
         src = file.path(result_dir, "Cluster_size_dist.png"),
-        descr = "Histogram of cluster size distribution"
+        descr = "Histogram of cluster size distribution",
+        download = file.path(result_dir, "Cluster_size_dist.pdf")
     ),
     list(
         src = file.path(result_dir, "clone_size.png"),

biopipen/scripts/tcr/vdjtools-patch.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 # run the command and capture the stdout
-out=$(command $@)
+out=$(command "$@")
 
 echo "$out"
 

biopipen/scripts/vcf/BcftoolsAnnotate.py

@@ -6,11 +6,11 @@ from biopipen.utils.reference import tabix_index
 from biopipen.utils.misc import logger
 from biopipen.scripts.vcf.bcftools_utils import run_bcftools
 
-infile = {{in.infile | repr}}  # pyright: ignore # noqa: E999
-annfile = {{in.annfile | repr}}  # pyright: ignore
-outfile = {{out.outfile | repr}}  # pyright: ignore
-joboutdir = {{job.outdir | repr}}  # pyright: ignore
-envs = {{envs | dict | repr}}  # pyright: ignore
+infile: str = {{in.infile | quote}}  # pyright: ignore # noqa: E999
+annfile: str = {{in.annfile | quote}}  # pyright: ignore
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+joboutdir: str = {{job.outdir | quote}}  # pyright: ignore
+envs: dict = {{envs | dict | repr}}  # pyright: ignore
 
 bcftools = envs.pop("bcftools")
 tabix = envs.pop("tabix")
@@ -25,14 +25,14 @@ if isinstance(columns, list):
     columns = ",".join(columns)
 
 if "c" in envs:
-    logger.warning("Ignoring envs\[c], use envs\[columns] instead.")
+    logger.warning(r"Ignoring envs\[c], use envs\[columns] instead.")
     del envs["c"]
 
 if isinstance(remove, list):
     remove = ",".join(remove)
 
 if "x" in envs:
-    logger.warning("Ignoring envs\[x], use envs\[remove] instead.")
+    logger.warning(r"Ignoring envs\[x], use envs\[remove] instead.")
     del envs["x"]
 
 envs_has_annfile = "a" in envs or "annotations" in envs
@@ -43,7 +43,7 @@ if header:
 
 if annfile and envs_has_annfile:
     logger.warning(
-        "Ignoring envs\[a/annotations] because in.annfile is provided."
+        r"Ignoring envs\[a/annotations] because in.annfile is provided."
     )
     with suppress(KeyError):
         del envs["a"]

biopipen/scripts/vcf/BcftoolsFilter.py

@@ -3,11 +3,11 @@ from pathlib import Path, PosixPath  # noqa: F401
 from biopipen.utils.misc import logger
 from biopipen.scripts.vcf.bcftools_utils import run_bcftools
 
-infile = {{in.infile | repr}}  # pyright: ignore # noqa: #999
-outfile = {{out.outfile | repr}}  # pyright: ignore
+infile: str | Path = {{in.infile | quote}}  # pyright: ignore # noqa: #999
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
 outdir = Path(outfile).parent
 
-envs = {{envs | dict | repr}}  # pyright: ignore
+envs: dict = {{envs | dict | repr}}  # pyright: ignore
 bcftools = envs.pop("bcftools")
 tabix = envs.pop("tabix")
 keep = envs.pop("keep")

biopipen/scripts/vcf/BcftoolsMerge.py

@@ -0,0 +1,31 @@
+from biopipen.utils.reference import tabix_index
+from biopipen.utils.misc import logger
+from biopipen.scripts.vcf.bcftools_utils import run_bcftools
+
+infiles: list = {{in.infiles | each: as_path}}  # pyright: ignore # noqa: E999
+outfile = {{out.outfile | repr}}  # pyright: ignore
+joboutdir = {{job.outdir | repr}}  # pyright: ignore
+envs: dict = {{envs | dict | repr}}  # pyright: ignore
+
+bcftools = envs.pop("bcftools")
+tabix = envs.pop("tabix")
+ncores = envs.pop("ncores")
+gz = envs.pop("gz")
+index = envs.pop("index")
+
+envs.setdefault("force-single", True)
+envs.setdefault("missing-to-ref", True)
+
+if index and not gz:
+    logger.warning("Forcing envs.gz to True because envs.index is True.")
+    gz = True
+
+if "O" not in envs and "output-type" not in envs and "output_type" not in envs:
+    envs["O"] = "z" if gz else "v"
+
+envs[""] = [bcftools, "merge"]
+envs["o"] = outfile
+envs["threads"] = ncores
+envs["_"] = infiles
+
+run_bcftools(envs, bcftools=bcftools, index=index, tabix=tabix)