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

biopipen/scripts/bam/ControlFREEC.py

@@ -5,20 +5,20 @@ import shutil
 from diot import Diot
 from biopipen.utils.misc import dict_to_cli_args, run_command
 
-bamfile = {{ in.bamfile | repr }}  # pyright: ignore
-snpfile = {{ in.snpfile | repr }}  # pyright: ignore
-outdir = {{ out.outdir | repr }}  # pyright: ignore
-freec = {{ envs.freec | repr }}  # pyright: ignore
+bamfile = {{ in.bamfile | quote }}  # pyright: ignore # noqa
+snpfile = {{ in.snpfile | quote }}  # pyright: ignore
+outdir = {{ out.outdir | quote }}  # pyright: ignore
+freec: str = {{ envs.freec | repr }}  # pyright: ignore
 ncores = {{ envs.ncores | repr }}  # pyright: ignore
 bedtools = {{ envs.bedtools | repr }}  # pyright: ignore
 sambamba = {{ envs.sambamba | repr }}  # pyright: ignore
 samtools = {{ envs.samtools | repr }}  # pyright: ignore
 tabix = {{ envs.tabix | repr }}  # pyright: ignore
-rscript = {{ envs.rscript | repr }}  # pyright: ignore
-ref = {{ envs.ref | repr }}  # pyright: ignore
-refdir = {{ envs.refdir | repr }}  # pyright: ignore
+rscript: str = {{ envs.rscript | repr }}  # pyright: ignore
+ref = {{ envs.ref | quote }}  # pyright: ignore
+refdir = {{ envs.refdir | quote }}  # pyright: ignore
 binsize = {{ envs.binsize | repr }}  # pyright: ignore
-args = {{ envs.args | repr }}  # pyright: ignore
+args = {{ envs.args | dict }}  # pyright: ignore
 
 chrLenFile = f"{ref}.fai"
 if snpfile:
@@ -33,7 +33,7 @@ if snpfile:
             }
         ),
         stdout="return",
-    ).strip().splitlines()
+    ).strip().splitlines()  # type: ignore
 
     kept_seqs = []
     with open(chrLenFile, "r") as fin, open(chrLenFile2, "w") as fout:
@@ -92,7 +92,7 @@ run_command(
 
 # plot cnvs
 # get makeGraph.R
-freec_path = os.path.realpath(shutil.which(freec).strip())
+freec_path = os.path.realpath(shutil.which(freec).strip())  # type: ignore
 mkgraph = os.path.join(os.path.dirname(freec_path), "makeGraph.R")
 if not os.path.exists(mkgraph):
     raise RuntimeError("makeGraph.R not found")
@@ -102,7 +102,7 @@ try:
 except IndexError:
     raise RuntimeError("Control-FREEC failed to run") from None
 
-rscript_path = os.path.realpath(shutil.which(rscript).strip())
+rscript_path = os.path.realpath(shutil.which(rscript).strip())  # type: ignore
 rpath = os.path.join(os.path.dirname(rscript_path), "R")
 
 plotcmd = f"cat {mkgraph} | R --slave --args {config.general.ploidy} {ratiofile}"

biopipen/scripts/bed/Bed2Vcf.py

@@ -8,14 +8,14 @@ from pysam import FastaFile
 
 from biopipen.utils.misc import run_command
 
-inbed = {{in.inbed | quote}}  # pyright: ignore
-outvcf = {{out.outvcf | quote}}  # pyright: ignore
-tmpoutvcf = {{out.outvcf | append: ".tmp" | quote}}  # pyright: ignore
+inbed: str = {{in.inbed | quote}}  # pyright: ignore # noqa
+outvcf: str = {{out.outvcf | quote}}  # pyright: ignore
+tmpoutvcf: str = {{out.outvcf | str | append: ".tmp" | quote}}  # pyright: ignore
 joboutdir = Path({{job.outdir | quote}})  # pyright: ignore
-ref = {{envs.ref | quote}}  # pyright: ignore
+ref: str = {{envs.ref | quote}}  # pyright: ignore
 headers = {{envs.headers | repr}}  # pyright: ignore
 infos = {{envs.infos | repr}}  # pyright: ignore
-base = {{envs.base | int}}  # pyright: ignore
+base: int = {{envs.base | int}}  # pyright: ignore
 formats = {{envs.formats | repr}}  # pyright: ignore
 index = {{envs.index | repr}}  # pyright: ignore
 bcftools = {{envs.bcftools | quote}}  # pyright: ignore

biopipen/scripts/bed/BedConsensus.py

@@ -1,16 +1,16 @@
 import sys
 from math import ceil
-from pathlib import Path
+from pathlib import Path, PosixPath  # noqa: F401
 
 from biopipen.utils.misc import run_command
 
-bedfiles = {{in.bedfiles | repr}}  # pyright: ignore
-outfile = Path({{out.outbed | repr}})  # pyright: ignore
+bedfiles: list[Path] = {{in.bedfiles | each: as_path}}  # pyright: ignore # noqa
+outfile = Path({{out.outbed | quote}})  # pyright: ignore
 bedtools_path = {{envs.bedtools | repr}}  # pyright: ignore
-cutoff = {{envs.cutoff | repr}}  # pyright: ignore
+cutoff: float = {{envs.cutoff | repr}}  # pyright: ignore
 distance = {{envs.distance | repr}}  # pyright: ignore
 chrsize = {{envs.chrsize | repr}}  # pyright: ignore
-bedfiles = [Path(bedfile) for bedfile in bedfiles]
+# bedfiles = [Path(bedfile) for bedfile in bedfiles]
 # In case there are duplicated stems
 stems = [f"{bedfile.stem}__{i}" for i, bedfile in enumerate(bedfiles)]
 

biopipen/scripts/bed/BedLiftOver.sh

@@ -1,11 +1,13 @@
+# shellcheck disable=SC2148,SC1083
 inbed={{ in.inbed | quote }}
 outbed={{ out.outbed | quote }}
 rejfile={{ job.outdir | joinpaths: "rejected.bed" | quote }}
 liftover={{ envs.liftover | quote }}
 chain={{ envs.chain | quote }}
 
+# shellcheck disable=SC2154
 $liftover \
-    $inbed \
-    $chain \
-    $outbed \
-    $rejfile
+    "$inbed" \
+    "$chain" \
+    "$outbed" \
+    "$rejfile"

biopipen/scripts/bed/BedtoolsIntersect.py

@@ -1,10 +1,10 @@
 from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args, logger
 
-afile = Path({{in.afile | repr}})  # pyright: ignore # noqa: #999
-bfile = Path({{in.bfile | repr}})  # pyright: ignore
-outfile = {{out.outfile | repr}}  # pyright: ignore
-envs = {{envs | repr}}  # pyright: ignore
+afile = Path({{in.afile | quote}})  # pyright: ignore # noqa: #999
+bfile = Path({{in.bfile | quote}})  # pyright: ignore
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+envs: dict = {{envs | dict}}  # pyright: ignore
 
 bedtools = envs.pop("bedtools")
 sort = envs.pop("sort")

biopipen/scripts/bed/BedtoolsMakeWindows.py

@@ -1,9 +1,9 @@
 from pathlib import Path
 from biopipen.utils.misc import run_command, logger
 
-infile = Path({{in.afile | repr}})  # pyright: ignore # noqa: #999
-outfile = Path({{in.bfile | repr}})  # pyright: ignore
-bedtools = {{envs.bedtools | repr}}  # pyright: ignore
+infile = Path({{in.afile | quote}})  # pyright: ignore # noqa: #999
+outfile = Path({{in.bfile | quote}})  # pyright: ignore
+bedtools: str = {{envs.bedtools | quote}}  # pyright: ignore
 window = {{envs.window | repr}}  # pyright: ignore
 step = {{envs.step | repr}}  # pyright: ignore
 nwin = {{envs.nwin | repr}}  # pyright: ignore

biopipen/scripts/bed/BedtoolsMerge.py

@@ -1,8 +1,8 @@
-from biopipen.utils import run_command, dict_to_cli_args
+from biopipen.utils.misc import run_command, dict_to_cli_args
 
-inbed = {{in.inbed | repr}}  # pyright: ignore # noqa: #999
-outbed = {{out.outbed | repr}}  # pyright: ignore
-envs = {{envs | repr}}  # pyright: ignore
+inbed = {{in.inbed | quote}}  # pyright: ignore # noqa: #999
+outbed = {{out.outbed | quote}}  # pyright: ignore
+envs: dict = {{envs | dict}}  # pyright: ignore
 bedtools = envs.pop("bedtools", "bedtools")
 
 envs[""] = [bedtools, "merge"]

biopipen/scripts/cellranger/CellRangerCount.py

@@ -1,15 +1,16 @@
 import uuid
 import re
-from pathlib import Path
+import os.path
+from pathlib import Path, PosixPath  # noqa: F401
 from biopipen.utils.misc import run_command
 
-fastqs = {{in.fastqs | repr}}  # pyright: ignore  # noqa
-outdir = {{out.outdir | quote}}  # pyright: ignore
+fastqs: list[Path] = {{in.fastqs | each: as_path}}  # pyright: ignore  # noqa
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 id = {{out.outdir | basename | quote}}  # pyright: ignore
 
 cellranger = {{envs.cellranger | quote}}  # pyright: ignore
 tmpdir = Path({{envs.tmpdir | quote}})  # pyright: ignore
-ref = {{envs.ref | quote}}  # pyright: ignore
+ref: str = {{envs.ref | quote}}  # pyright: ignore
 ncores = {{envs.ncores | int}}  # pyright: ignore
 include_introns = {{envs.include_introns | repr}}  # pyright: ignore
 create_bam = {{envs.create_bam | repr}}  # pyright: ignore
@@ -26,7 +27,17 @@ if len(fastqs) == 1 and fastqs[0].is_dir():
 # soft-link the fastq files to the temporary directory
 for fastq in fastqs:
     fastq = Path(fastq)
-    (fastqdir / fastq.name).symlink_to(fastq)
+    fqnames = re.split(r"(_S\d+_)", fastq.name)
+    if len(fqnames) != 3:
+        raise ValueError(
+            fr"Expect one and only one '_S\d+_' in fastq file name: {fastq.name}"
+        )
+
+    linked = fastqdir / f"{id}{fqnames[1]}{fqnames[2]}"
+    if linked.exists():
+        linked.unlink()
+
+    linked.symlink_to(fastq)
 
 other_args = {{envs | dict_to_cli_args: dashify=True, exclude=['no_bam', 'create_bam', 'include_introns', 'cellranger', 'transcriptome', 'ref', 'tmpdir', 'id', 'ncores']}}  # pyright: ignore
 
@@ -49,9 +60,9 @@ command = [
 
 # check cellranger version
 #   cellranger cellranger-7.2.0
-version = run_command([cellranger, "--version"], stdout = "RETURN")
-version = version.replace("cellranger", "").replace("-", "").strip()
-version = list(map(int, version.split(".")))
+version: str = run_command([cellranger, "--version"], stdout = "RETURN")  # type: ignore
+version = version.replace("cellranger", "").replace("-", "").strip()  # type: ignore
+version: list[int] = list(map(int, version.split(".")))  # type: ignore
 if version[0] >= 8:
     command += ["--create-bam", create_bam]
 elif create_bam != "true":
@@ -77,7 +88,7 @@ try:
         '<script src="web_summary.js"></script>',
         web_summary_content,
     ))
-    web_summary_js.write_text(regex.search(web_summary_content).group(1))
+    web_summary_js.write_text(regex.search(web_summary_content).group(1))  # type: ignore
 except Exception as e:
     print(f"Error modifying web_summary.html: {e}")
     raise e

biopipen/scripts/cellranger/CellRangerSummary.R

@@ -1,17 +1,16 @@
-{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
-
 library(rlang)
 library(dplyr)
-library(ggplot2)
-library(ggprism)
-
-theme_set(theme_prism())
+library(plotthis)
+library(biopipen.utils)
 
 indirs <- {{in.indirs | r}}
 outdir <- {{out.outdir | r}}
 joboutdir <- {{job.outdir | r}}
 group <- {{envs.group | r}}
 
+logger <- get_logger()
+reporter <- get_reporter()
+
 if (is.character(group)) {
     group <- read.csv(group, header = FALSE, row.names = NULL)
     colnames(group) <- c("Sample", "Group")
@@ -25,11 +24,11 @@ if (is.character(group)) {
 }
 
 cellranger_type <- NULL
-log_info("Reading and merging metrics for each sample ...")
+logger$info("Reading and merging metrics for each sample ...")
 metrics <- NULL
 for (indir in indirs) {
     sample <- basename(indir)
-    log_debug("- Reading metrics for sample: ", sample)
+    logger$debug("- Reading metrics for sample: ", sample)
     metric <- read.csv(
         file.path(indir, "outs", "metrics_summary.csv"),
         header = TRUE, row.names = NULL, check.names = FALSE)
@@ -46,12 +45,12 @@ for (indir in indirs) {
     if (!is.null(metrics)) {
         missing_cols <- setdiff(colnames(metrics), colnames(metric))
         if (length(missing_cols) > 0) {
-            log_warn('- Missing columns: {paste0(missing_cols, collapse = ", ")} in sample: {sample}')
+            logger$warn('- Missing columns: {paste0(missing_cols, collapse = ", ")} in sample: {sample}')
             metric[missing_cols] <- NA
         }
         missing_cols <- setdiff(colnames(metric), colnames(metrics))
         if (length(missing_cols) > 0) {
-            log_warn('- Missing columns: {paste0(missing_cols, collapse = ", ")} in samples before {sample}')
+            logger$warn('- Missing columns: {paste0(missing_cols, collapse = ", ")} in samples before {sample}')
             metrics[missing_cols] <- NA
         }
     }
@@ -81,7 +80,7 @@ write.table(
     row.names = FALSE
 )
 
-add_report(
+reporter$add(
     list(kind = "descr", content = "Metrics for all samples"),
     list(kind = "table", src = file.path(outdir, "metrics.txt")),
     h1 = "Metrics of all samples"
@@ -132,13 +131,13 @@ if (cellranger_type == "vdj") {
         `Total Genes Detected Median UMI Counts per Cell` = "The number of genes with at least one UMI count in any cell."
     )
 }
-log_info("Plotting metrics ...")
+logger$info("Plotting metrics ...")
 for (metric in colnames(metrics)) {
     if (metric == "Sample") { next }
     metric_name <- sub(" \\(%\\)$", "", metric)
-    log_info("- {metric_name}")
+    logger$info("- {metric_name}")
 
-    add_report(
+    reporter$add(
         list(
             kind = "descr",
             content = METRIC_DESCR[[metric_name]] %||% paste0("Metric: ", metric)
@@ -147,17 +146,13 @@ for (metric in colnames(metrics)) {
     )
 
     # barplot
-    p <- ggplot(metrics, aes(x = Sample, y = !!sym(metric))) +
-        geom_bar(stat = "identity", fill = "steelblue") +
-        labs(x = "Sample", y = metric) +
-        theme(axis.text.x = element_text(angle = 90, hjust = 1))
-
+    p <- BarPlot(metrics, x = "Sample", y = metric, x_text_angle = 90)
     figfile <- file.path(outdir, paste0(slugify(metric), ".barplot.png"))
-    png(figfile, height = 600, res = 100, width = nrow(metrics) * 30 + 200)
+    png(figfile, height = 600, res = 100, width = max(nrow(metrics) * 30 + 200, 400))
     print(p)
     dev.off()
 
-    add_report(
+    reporter$add(
         list(src = figfile, name = "By Sample"),
         ui = "table_of_images",
         h1 = metric
@@ -170,21 +165,17 @@ for (metric in colnames(metrics)) {
         left_join(metrics, by = "Sample") %>%
         mutate(Group = factor(Group, levels = unique(Group)))
 
-    p <- ggplot(pdata, aes(x = Group, y = !!sym(metric))) +
-        geom_boxplot(fill = "steelblue") +
-        labs(x = "Group", y = metric) +
-        theme(axis.text.x = element_text(angle = 90, hjust = 1))
-
+    p <- BoxPlot(pdata, x = "Group", y = metric, x_text_angle = 90)
     figfile <- file.path(outdir, paste0(slugify(metric), ".boxplot.png"))
-    png(figfile, height = 600, res = 100, width = length(unique(pdata$Group)) * 30 + 200)
+    png(figfile, height = 600, res = 100, width = max(length(unique(pdata$Group)) * 30 + 200, 400))
     print(p)
     dev.off()
 
-    add_report(
+    reporter$add(
         list(src = figfile, name = "By Group"),
         ui = "table_of_images",
         h1 = metric
     )
 }
 
-save_report(joboutdir)
+reporter$save(joboutdir)

biopipen/scripts/cellranger/CellRangerVdj.py

@@ -1,16 +1,16 @@
 import uuid
 import re
-from pathlib import Path
+from pathlib import Path, PosixPath  # noqa: F401
 from biopipen.utils.misc import run_command
 
-fastqs = {{in.fastqs | repr}}  # pyright: ignore  # noqa
-outdir = {{out.outdir | quote}}  # pyright: ignore
-id = {{out.outdir | basename | quote}}  # pyright: ignore
+fastqs: list[Path] = {{in.fastqs | each: as_path}}  # pyright: ignore  # noqa
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
+id: str = {{out.outdir | basename | quote}}  # pyright: ignore
 
-cellranger = {{envs.cellranger | quote}}  # pyright: ignore
+cellranger: str = {{envs.cellranger | quote}}  # pyright: ignore
 tmpdir = Path({{envs.tmpdir | quote}})  # pyright: ignore
-ref = {{envs.ref | quote}}  # pyright: ignore
-ncores = {{envs.ncores | int}}  # pyright: ignore
+ref: str = {{envs.ref | quote}}  # pyright: ignore
+ncores: int = {{envs.ncores | int}}  # pyright: ignore
 
 # create a temporary unique directory to store the soft-linked fastq files
 fastqdir = tmpdir / f"cellranger_count_{uuid.uuid4()}"
@@ -60,7 +60,7 @@ try:
         '<script src="web_summary.js"></script>',
         web_summary_content,
     ))
-    web_summary_js.write_text(regex.search(web_summary_content).group(1))
+    web_summary_js.write_text(regex.search(web_summary_content).group(1))  # type: ignore
 except Exception as e:
     print(f"Error modifying web_summary.html: {e}")
     raise e

biopipen/scripts/cnvkit/CNVkitAccess.py

@@ -1,11 +1,11 @@
-from pathlib import Path
+from pathlib import Path, PosixPath  # noqa: F401
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-excfiles = {{in.excfiles | repr}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
-reffile = {{envs.ref | quote}}  # pyright: ignore
-cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore
-min_gap_size = {{envs.min_gap_size | quote}}  # pyright: ignore
+excfiles: list[Path] = {{in.excfiles | each: as_path}}  # pyright: ignore # noqa
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+reffile: str = {{envs.ref | quote}}  # pyright: ignore
+cnvkit: str = {{envs.cnvkit | quote}}  # pyright: ignore
+min_gap_size: str = {{envs.min_gap_size | quote}}  # pyright: ignore
 
 
 def main():

biopipen/scripts/cnvkit/CNVkitAutobin.py

@@ -1,26 +1,33 @@
-from pathlib import Path
+from __future__ import annotations
+
+from pathlib import Path, PosixPath  # noqa: F401
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-bamfiles = {{in.bamfiles | repr}}  # pyright: ignore
-accfile = {{in.accfile | quote}}  # pyright: ignore
-baitfile = {{in.baitfile | repr}}  # pyright: ignore
-target_file = {{out.target_file | quote}}  # pyright: ignore
-antitarget_file = {{out.antitarget_file | quote}}  # pyright: ignore
-reffile = {{envs.ref | quote}}  # pyright: ignore
-cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore
-method = {{envs.method | quote}}  # pyright: ignore
-bp_per_bin = {{envs.bp_per_bin | repr}}  # pyright: ignore
-target_max_size = {{envs.target_max_size | repr}}  # pyright: ignore
-target_min_size = {{envs.target_min_size | repr}}  # pyright: ignore
-antitarget_max_size = {{envs.antitarget_max_size | repr}}  # pyright: ignore
-antitarget_min_size = {{envs.antitarget_min_size | repr}}  # pyright: ignore
-annotate = {{envs.annotate | repr}}  # pyright: ignore
-short_names = {{envs.short_names | repr}}  # pyright: ignore
+bamfiles: list[Path] = {{in.bamfiles | each: as_path}}  # pyright: ignore # noqa
+accfile: str | None = {{in.accfile | quote}}  # pyright: ignore
+baitfile: str | None = {{in.baitfile | quote}}  # pyright: ignore
+target_file: str | None = {{out.target_file | quote}}  # pyright: ignore
+antitarget_file: str | None = {{out.antitarget_file | quote}}  # pyright: ignore
+reffile: str = {{envs.ref | quote}}  # pyright: ignore
+cnvkit: str = {{envs.cnvkit | quote}}  # pyright: ignore
+method: str = {{envs.method | quote}}  # pyright: ignore
+bp_per_bin: int = {{envs.bp_per_bin | repr}}  # pyright: ignore
+target_max_size: int = {{envs.target_max_size | repr}}  # pyright: ignore
+target_min_size: int = {{envs.target_min_size | repr}}  # pyright: ignore
+antitarget_max_size: int = {{envs.antitarget_max_size | repr}}  # pyright: ignore
+antitarget_min_size: int = {{envs.antitarget_min_size | repr}}  # pyright: ignore
+annotate: str | None = {{envs.annotate | quote}}  # pyright: ignore
+short_names: bool = {{envs.short_names | repr}}  # pyright: ignore
+
+if baitfile == "None":
+    baitfile = None
+if accfile == "None":
+    accfile = None
 
 
 def main():
 
-    args = dict(
+    args: dict = dict(
         f=Path(reffile).expanduser(),
         m=method,
         g=accfile,
@@ -30,7 +37,7 @@ def main():
         target_min_size=target_min_size,
         antitarget_max_size=antitarget_max_size,
         antitarget_min_size=antitarget_min_size,
-        annotate=Path(annotate).expanduser(),
+        annotate=False if annotate is None else Path(annotate).expanduser(),
         short_names=short_names,
         target_output_bed=target_file,
         antitarget_output_bed=antitarget_file,

biopipen/scripts/cnvkit/CNVkitBatch.py

@@ -3,8 +3,8 @@ from pathlib import Path
 import pandas
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-metafile = {{in.cnsfile | quote}}  # pyright: ignore
-outdir = {{out.outdir | quote}}  # pyright: ignore
+metafile: str = {{in.cnsfile | quote}}  # pyright: ignore  # noqa
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore
 method = {{envs.method | quote}}  # pyright: ignore
 segment_method = {{envs.segment_method | quote}}  # pyright: ignore
@@ -13,7 +13,7 @@ count_reads = {{envs.count_reads | repr}}  # pyright: ignore
 drop_low_coverage = {{envs.drop_low_coverage | repr}}  # pyright: ignore
 ncores = {{envs.ncores | repr}}  # pyright: ignore
 rscript = {{envs.rscript | quote}}  # pyright: ignore
-ref = {{envs.ref | quote}}  # pyright: ignore
+ref: str = {{envs.ref | quote}}  # pyright: ignore
 targets = {{envs.targets | repr}}  # pyright: ignore
 antitargets = {{envs.antitargets | repr}}  # pyright: ignore
 annotate = {{envs.annotate | repr}}  # pyright: ignore
@@ -30,7 +30,7 @@ scatter = {{envs.scatter | repr}}  # pyright: ignore
 diagram = {{envs.diagram | repr}}  # pyright: ignore
 type_tumor = {{envs.type_tumor | repr}}  # pyright: ignore
 type_normal = {{envs.type_normal | repr}}  # pyright: ignore
-type_col = {{envs.type_col | quote}}  # pyright: ignore
+type_col: str = {{envs.type_col | quote}}  # pyright: ignore
 
 
 def gen_access():
@@ -38,7 +38,7 @@ def gen_access():
         return access
 
     accessfile = Path(outdir) / "access.bed"
-    args = dict(
+    args: dict = dict(
         exclude=access_excludes or False,
         s=access_min_gap_size or False,
         o=accessfile,

biopipen/scripts/cnvkit/CNVkitCall.py

@@ -1,14 +1,14 @@
 from pathlib import Path
 from biopipen.utils.misc import run_command
 
-cnsfile = {{in.cnsfile | quote}}  # pyright: ignore
-cnrfile = {{in.cnrfile | quote}}  # pyright: ignore
+cnsfile: str = {{in.cnsfile | quote}}  # pyright: ignore  # noqa
+cnrfile: str = {{in.cnrfile | quote}}  # pyright: ignore
 vcf = {{in.vcf | repr}}  # pyright: ignore
 sample_id = {{in.sample_id | repr}}  # pyright: ignore
 normal_id = {{in.normal_id | repr}}  # pyright: ignore
 sample_sex = {{in.sample_sex | repr}}  # pyright: ignore
 purity = {{in.purity | repr}}  # pyright: ignore
-outdir = {{out.outdir | quote}}  # pyright: ignore
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore
 center = {{envs.center | repr}}  # pyright: ignore
 center_at = {{envs.center_at | repr}}  # pyright: ignore

biopipen/scripts/cnvkit/CNVkitCoverage.py

@@ -1,10 +1,10 @@
 from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-bamfile = {{in.bamfile | quote}}  # pyright: ignore
+bamfile: str = {{in.bamfile | quote}}  # pyright: ignore  # noqa
 target_file = {{in.target_file | quote}}  # pyright: ignore
 outfile = {{out.outfile | quote}}  # pyright: ignore
-reffile = {{envs.reffile | quote}}  # pyright: ignore
+reffile: str = {{envs.reffile | quote}}  # pyright: ignore
 cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore
 count = {{envs.count | repr}}  # pyright: ignore
 min_mapq = {{envs.min_mapq | repr}}  # pyright: ignore

biopipen/scripts/cnvkit/CNVkitDiagram.py

@@ -4,10 +4,10 @@ from diot import Diot
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
 
-cnrfile = {{in.cnrfile | quote}}  # pyright: ignore
+cnrfile = {{in.cnrfile | quote}}  # pyright: ignore  # noqa
 cnsfile = {{in.cnsfile | quote}}  # pyright: ignore
 sample_sex = {{in.sample_sex | repr}}  # pyright: ignore
-outdir = {{out.outdir | quote}}  # pyright: ignore
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore
 convert = {{envs.convert | quote}}  # pyright: ignore
 convert_args = {{envs.convert_args | repr}}  # pyright: ignore
@@ -16,7 +16,7 @@ min_probes = {{envs.min_probes | repr}}  # pyright: ignore
 male_reference = {{envs.male_reference | repr}}  # pyright: ignore
 no_shift_xy = {{envs.no_shift_xy | repr}}  # pyright: ignore
 title = {{envs.title | repr}}  # pyright: ignore
-cases = {{envs.cases | repr}}  # pyright: ignore
+cases: dict | None = {{envs.cases | repr}}  # pyright: ignore
 
 
 def do_case(name, case):
@@ -35,7 +35,7 @@ def do_case(name, case):
     pdffile = Path(outdir).joinpath(f"{name}.heatmap.pdf")
     pngfile = Path(outdir).joinpath(f"{name}.heatmap.png")
 
-    args = dict(
+    args: dict = dict(
         **case,
         s=cnsfile,
         o=pdffile,
@@ -44,7 +44,7 @@ def do_case(name, case):
     args[""] = [cnvkit, "diagram"]
     run_command(dict_to_cli_args(args, dashify=True), fg=True)
 
-    conv_args = dict(**conv_args, _=[pdffile, pngfile])
+    conv_args: dict = dict(**conv_args, _=[pdffile, pngfile])
     conv_args[""] = [convert]
     run_command(
         dict_to_cli_args(conv_args, prefix="-", dashify=True),

biopipen/scripts/cnvkit/CNVkitFix.py

@@ -2,11 +2,11 @@ from pathlib import Path
 
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-target_file = {{in.target_file | quote}}  # pyright: ignore
+target_file = {{in.target_file | quote}}  # pyright: ignore  # noqa
 antitarget_file = {{in.antitarget_file | quote}}  # pyright: ignore
 reference_file = {{in.reference | quote}}  # pyright: ignore
 sample_id = {{in.sample_id | repr}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
 cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore
 cluster = {{envs.cluster | repr}}  # pyright: ignore
 no_gc = {{envs.no_gc | repr}}  # pyright: ignore
@@ -18,7 +18,7 @@ emptyfile.touch()
 
 def main():
 
-    args = dict(
+    args: dict = dict(
         i=sample_id,
         o=outfile,
         c=cluster,

biopipen/scripts/cnvkit/CNVkitGuessBaits.py

@@ -5,16 +5,16 @@ from pathlib import Path, PosixPath  # for as_path
 
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-bamfiles = {{in.bamfiles | repr}}  # pyright: ignore
+bamfiles = {{in.bamfiles | repr}}  # pyright: ignore  # noqa
 atfile = {{in.atfile | repr}}  # pyright: ignore
 
 targetfile = {{out.targetfile | repr}}  # pyright: ignore
 covfile = {{out.targetfile | as_path | attr: "with_suffix" | call: ".cnn" | repr}}  # pyright: ignore
 
-cnvkit = {{envs.cnvkit | repr}}  # pyright: ignore
+cnvkit: str = {{envs.cnvkit | repr}}  # pyright: ignore
 samtools = {{envs.samtools | repr}}  # pyright: ignore
 ncores = {{envs.ncores | repr}}  # pyright: ignore
-ref = {{envs.ref | repr}}  # pyright: ignore
+ref: str = {{envs.ref | repr}}  # pyright: ignore
 guided = {{envs.guided | repr}}  # pyright: ignore
 min_depth = {{envs.min_depth | repr}}  # pyright: ignore
 min_gap = {{envs.min_gap | repr}}  # pyright: ignore
@@ -32,10 +32,14 @@ else:
     params["min-gap"] = min_gap
     params["min-length"] = min_length
 
-biopipen_dir = {{biopipen_dir | repr}}  # pyright: ignore
+biopipen_dir: str = {{biopipen_dir | quote}}  # pyright: ignore
 
 # get the python path from cnvkit.py
-cnvkit_path = Path(which(cnvkit))
+cnvkit_found = which(cnvkit)
+if cnvkit_found is None:
+    raise ValueError(f"cnvkit executable not found: {cnvkit}")
+
+cnvkit_path = Path(cnvkit_found)
 # Modify cnvkit.py to a unique tmp path, named with timestamp
 # to find the python path
 tmp_cnvkit_path = Path("/tmp/cnvkit-{}.py".format(time.time()))