biopipen 0.29.2__tar.gz → 0.31.0__tar.gz

{biopipen-0.29.2 → biopipen-0.31.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.29.2
+Version: 0.31.0
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang
@@ -14,9 +14,9 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Provides-Extra: runinfo
 Requires-Dist: datar[pandas] (>=0.15.6,<0.16.0)
-Requires-Dist: pipen-board[report] (>=0.15,<0.16)
-Requires-Dist: pipen-cli-run (>=0.13,<0.14)
-Requires-Dist: pipen-filters (>=0.13,<0.14)
-Requires-Dist: pipen-poplog (>=0.1.2,<0.2.0)
-Requires-Dist: pipen-runinfo (>=0.6,<0.7) ; extra == "runinfo"
-Requires-Dist: pipen-verbose (>=0.11,<0.12)
+Requires-Dist: pipen-board[report] (>=0.16,<0.17)
+Requires-Dist: pipen-cli-run (>=0.14,<0.15)
+Requires-Dist: pipen-filters (>=0.14,<0.15)
+Requires-Dist: pipen-poplog (>=0.2.0,<0.3.0)
+Requires-Dist: pipen-runinfo (>=0.7,<0.8) ; extra == "runinfo"
+Requires-Dist: pipen-verbose (>=0.12,<0.13)

biopipen-0.31.0/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.31.0"

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/core/config.toml

@@ -13,6 +13,8 @@ liftover = "liftOver"
 # gatk, installed via conda
 gatk = "gatk"
 gatk4 = "gatk"
+# google cloud sdk
+gcloud = "gcloud"
 # vdjtools, installed via conda
 vdjtools = "vdjtools"
 # cnvkit.py

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/core/filters.py

@@ -221,6 +221,27 @@ def r(
     return repr(obj)
 
 
+@filtermanager.register
+def source_r(path: str | Path) -> str:
+    """Source an R script.
+
+    In addition to generating `source(path)`, we also include the mtime for the script
+    to trigger the job not cached when the script is updated.
+
+    Args:
+        path: The path to the R script
+
+    Returns:
+        The R code to source the script
+    """
+    path = Path(path)
+    mtime = int(path.stat().st_mtime)
+    return (
+        f"# Last modified: {mtime}\n"
+        f"source('{path}')"
+    )
+
+
 @register_component("fgsea")
 def _render_fgsea(
     cont: Mapping[str, Any],

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/ns/plot.py

@@ -354,3 +354,58 @@ class QQPlot(Proc):
         "ggs": None,
     }
     script = "file://../scripts/plot/QQPlot.R"
+
+
+class Scatter(Proc):
+    """Generate scatter plot using ggplot2.
+
+    [`ggpmisc`](https://cran.r-project.org/web/packages/ggpmisc/index.html) is used
+    for the stats and labels.
+    See also https://cran.r-project.org/web/packages/ggpmisc/vignettes/model-based-annotations.html
+
+    Input:
+        infile: The input file for data
+            It should contain at least two columns for x and y values.
+            Header is required.
+
+    Output:
+        outfile: The output figure file
+
+    Envs:
+        x_col: The column for x values
+            An integer (1-based) or a string indicating the column name.
+        y_col: The column for y values
+            An integer (1-based) or a string indicating the column name.
+        devpars (ns): The parameters for `png()`
+            - res (type=int): The resolution
+            - width (type=int): The width
+            - height (type=int): The height
+        args (ns): Additional arguments for `geom_point()`
+            See <https://ggplot2.tidyverse.org/reference/geom_point.html>.
+            - <more>: Additional arguments for `geom_point()`
+        mapping: Extra mapping for all geoms, including `stats`.
+            Should be `aes(color = group)` but all these are valid: `color = group` or
+            `(color = group)`.
+        ggs (list): Additional ggplot expression to adjust the plot.
+        formula: The formula for the model
+        stats (type=json): The stats to add to the plot.
+            A dict with keys available stats in `ggpmisc` (without `stat_`).
+            See <https://cran.r-project.org/web/packages/ggpmisc/vignettes/model-based-annotations.html#statistics>.
+            The values should be the arguments for the stats.
+            If you want a stat to be added multiple times, add a suffix `#x` to the key.
+            For example, `poly_line#1` and `poly_line#2` will add two polynomial lines.
+    """  # noqa: E501
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}.scatter.png"
+    lang = config.lang.rscript
+    envs = {
+        "x_col": 1,
+        "y_col": 2,
+        "devpars": {"res": 100, "width": 1000, "height": 800},
+        "args": {},
+        "mapping": None,
+        "ggs": [],
+        "formula": "y ~ x",
+        "stats": {},
+    }
+    script = "file://../scripts/plot/Scatter.R"

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/ns/scrna.py

@@ -204,9 +204,15 @@ class SeuratPreparing(Proc):
                 - scvi: Same as `scVIIntegration`.
             - <more>: See <https://satijalab.org/seurat/reference/integratelayers>
 
+        doublet_detector (choice): The doublet detector to use.
+            - none: Do not use any doublet detector.
+            - DoubletFinder: Use `DoubletFinder` to detect doublets.
+            - doubletfinder: Same as `DoubletFinder`.
+            - scDblFinder: Use `scDblFinder` to detect doublets.
+            - scdblfinder: Same as `scDblFinder`.
+
         DoubletFinder (ns): Arguments to run [`DoubletFinder`](https://github.com/chris-mcginnis-ucsf/DoubletFinder).
             See also <https://demultiplexing-doublet-detecting-docs.readthedocs.io/en/latest/DoubletFinder.html>.
-            To disable `DoubletFinder`, set `envs.DoubletFinder` to `None` or `False`; or set `pcs` to `0`.
             - PCs (type=int): Number of PCs to use for 'doubletFinder' function.
             - doublets (type=float): Number of expected doublets as a proportion of the pool size.
             - pN (type=float): Number of doublets to simulate as a proportion of the pool size.
@@ -215,6 +221,12 @@ class SeuratPreparing(Proc):
                 Since parallelization of the function usually exhausts memory, if big `envs.ncores` does not work
                 for `DoubletFinder`, set this to a smaller number.
 
+        scDblFinder (ns): Arguments to run [`scDblFinder`](https://rdrr.io/bioc/scDblFinder/man/scDblFinder.html).
+            - dbr (type=float): The expected doublet rate.
+            - ncores (type=int): Number of cores to use for `scDblFinder`.
+                Set to `None` to use `envs.ncores`.
+            - <more>: See <https://rdrr.io/bioc/scDblFinder/man/scDblFinder.html>.
+
         cache (type=auto): Whether to cache the information at different steps.
             If `True`, the seurat object will be cached in the job output directory, which will be not cleaned up when job is rerunning.
             The cached seurat object will be saved as `<signature>.<kind>.RDS` file, where `<signature>` is the signature determined by
@@ -251,7 +263,9 @@ class SeuratPreparing(Proc):
             "min_cells": 5,
         },
         "IntegrateLayers": {"method": "harmony"},
-        "DoubletFinder": {"PCs": 0, "pN": 0.25, "doublets": 0.075, "ncores": 1},
+        "doublet_detector": "none",
+        "DoubletFinder": {"PCs": 10, "pN": 0.25, "doublets": 0.075, "ncores": 1},
+        "scDblFinder": {"dbr": 0.075, "ncores": 1},
         "cache": config.path.tmpdir,
     }
     script = "file://../scripts/scrna/SeuratPreparing.R"
@@ -307,10 +321,6 @@ class SeuratClustering(Proc):
                 The results will be saved in `seurat_clusters_<resolution>`.
                 The final resolution will be used to define the clusters at `seurat_clusters`.
             - <more>: See <https://satijalab.org/seurat/reference/findclusters>
-        clustree_devpars (ns): The device parameters for the clustree plots.
-            - res (type=int): The resolution of the plots.
-            - height (type=int): The height of the plots.
-            - width (type=int): The width of the plots.
         cache (type=auto): Whether to cache the information at different steps.
             If `True`, the seurat object will be cached in the job output directory, which will be not cleaned up when job is rerunning.
             The cached seurat object will be saved as `<signature>.<kind>.RDS` file, where `<signature>` is the signature determined by
@@ -338,7 +348,6 @@ class SeuratClustering(Proc):
         "RunUMAP": {"dims": 30},
         "FindNeighbors": {},
         "FindClusters": {"resolution": 0.8},
-        "clustree_devpars": {"res": 100, "height": 1000, "width": 800},
         "cache": config.path.tmpdir,
     }
     script = "file://../scripts/scrna/SeuratClustering.R"
@@ -392,10 +401,6 @@ class SeuratSubClustering(Proc):
                 The results will be saved in `<casename>_<resolution>`.
                 The final resolution will be used to define the clusters at `<casename>`.
             - <more>: See <https://satijalab.org/seurat/reference/findclusters>
-        clustree_devpars (ns): The device parameters for the clustree plots.
-            - res (type=int): The resolution of the plots.
-            - height (type=int): The height of the plots.
-            - width (type=int): The width of the plots.
         cache (type=auto): Whether to cache the information at different steps.
             If `True`, the seurat object will be cached in the job output directory, which will be not cleaned up when job is rerunning.
             The cached seurat object will be saved as `<signature>.<kind>.RDS` file, where `<signature>` is the signature determined by
@@ -419,7 +424,6 @@ class SeuratSubClustering(Proc):
         "RunUMAP": {"dims": 30},
         "FindNeighbors": {},
         "FindClusters": {"resolution": 0.8},
-        "clustree_devpars": {"res": 100, "height": 1000, "width": 800},
         "cache": config.path.tmpdir,
         "cases": {"subcluster": {}},
     }
@@ -488,6 +492,22 @@ class SeuratClusterStats(Proc):
     Envs:
         mutaters (type=json): The mutaters to mutate the metadata to subset the cells.
             The mutaters will be applied in the order specified.
+        clustrees_defaults (ns): The parameters for the clustree plots.
+            - devpars (ns): The device parameters for the clustree plot.
+                - res (type=int): The resolution of the plots.
+                - height (type=int): The height of the plots.
+                - width (type=int): The width of the plots.
+            - prefix: string indicating columns containing clustering information.
+                The trailing dot is not necessary and will be added automatically.
+                When `_auto`, clustrees will be plotted when there is `FindClusters` or
+                `FindClusters.*` in the `obj@commands`.
+                The latter is generated by `SeuratSubClustering`.
+                This will be ignored when `envs.clustrees` is specified.
+            - <more>: Other arguments passed to `clustree::clustree()`.
+                See <https://rdrr.io/cran/clustree/man/clustree.html>
+        clustrees (type=json): The cases for clustree plots.
+            Keys are the names of the plots and values are the dicts inherited from `env.clustrees_defaults` except `prefix`.
+            There is no default case for `clustrees`.
         hists_defaults (ns): The default parameters for histograms.
             This will plot histograms for the number of cells along `x`.
             For example, you can plot the number of cells along cell activity score.
@@ -521,14 +541,19 @@ class SeuratClusterStats(Proc):
             This is to do some basic statistics on the clusters. For more comprehensive analysis,
             see `RadarPlots` and `CellsDistribution`.
             The parameters from the cases can overwrite the default parameters.
-            - frac (flag): Whether to output the fraction of cells instead of number.
+            - frac (choice): How to calculate the fraction of cells.
+                - group: calculate the fraction in each group.
+                    The total fraction of the cells of idents in each group will be 1.
+                    When `group-by` is not specified, it will be the same as `all`.
+                - ident: calculate the fraction in each ident.
+                    The total fraction of the cells of groups in each ident will be 1.
+                    Only works when `group-by` is specified.
+                - cluster: alias of `ident`.
+                - all: calculate the fraction against all cells.
+                - none: do not calculate the fraction, use the number of cells instead.
             - pie (flag): Also output a pie chart?
             - circos (flag): Also output a circos plot?
             - table (flag): Whether to output a table (in tab-delimited format) and in the report.
-            - frac_ofall (flag): Whether to output the fraction against all cells,
-                instead of the fraction in each group.
-                Does not work for circos plot.
-                Only works when `frac` is `True` and `group-by` is specified.
             - transpose (flag): Whether to transpose the cluster and group, that is,
                 using group as the x-axis and cluster to fill the plot.
                 For circos plot, when transposed, the arrows will be drawn from the idents (by `ident`) to the
@@ -667,6 +692,11 @@ class SeuratClusterStats(Proc):
     lang = config.lang.rscript
     envs = {
         "mutaters": {},
+        "clustrees_defaults": {
+            "devpars": {"res": 100, "height": 1000, "width": 800},
+            "prefix": "_auto",
+        },
+        "clustrees": {},
         "hists_defaults": {
             "x": None,
             "x_order": [],
@@ -683,12 +713,11 @@ class SeuratClusterStats(Proc):
         },
         "hists": {},
         "stats_defaults": {
-            "frac": False,
+            "frac": "none",
             "pie": False,
             "circos": False,
             "table": False,
             "position": "auto",
-            "frac_ofall": False,
             "transpose": False,
             "ident": "seurat_clusters",
             "group-by": None,
@@ -706,7 +735,7 @@ class SeuratClusterStats(Proc):
             "Number of cells in each cluster by Sample": {
                 "group-by": "Sample",
                 "table": True,
-                "frac": True,
+                "frac": "group",
             },
         },
         "ngenes_defaults": {
@@ -1733,6 +1762,8 @@ class CellTypeAnnotation(Proc):
             - assay: When converting a Seurat object to AnnData, the assay to use.
                 If input is h5seurat, this defaults to RNA.
                 If input is Seurat object in RDS, this defaults to the default assay.
+        merge (flag): Whether to merge the clusters with the same cell types.
+            Otherwise, a suffix will be added to the cell types (ie. `.1`, `.2`, etc).
         newcol: The new column name to store the cell types.
             If not specified, the `seurat_clusters` column will be overwritten.
             If specified, the original `seurat_clusters` column will be kept and `Idents` will be kept as the original `seurat_clusters`.
@@ -1785,6 +1816,7 @@ class CellTypeAnnotation(Proc):
             "over_clustering": "seurat_clusters",
             "assay": None,
         },
+        "merge": False,
         "newcol": None,
         "outtype": "input",
     }
@@ -1831,6 +1863,14 @@ class SeuratMap2Ref(Proc):
                 If the default assay of reference is `SCT`, then `SCTransform` will be used.
         split_by: The column name in metadata to split the query into multiple objects.
             This helps when the original query is too large to process.
+        skip_if_normalized: Skip normalization if the query is already normalized.
+            Since the object is supposed to be generated by `SeuratPreparing`, it is already normalized.
+            However, a different normalization method may be used.
+            If the reference is normalized by the same method as the query, the normalization can be skipped.
+            Otherwise, the normalization cannot be skipped.
+            The normalization method used for the query set is determined by the default assay.
+            If `SCT`, then `SCTransform` is used; otherwise, `NormalizeData` is used.
+            You can set this to `False` to force re-normalization (with or without the arguments previously used).
         SCTransform (ns): Arguments for [`SCTransform()`](https://satijalab.org/seurat/reference/sctransform)
             - do-correct-umi (flag): Place corrected UMI matrix in assay counts layer?
             - do-scale (flag): Whether to scale residuals to have unit variance?
@@ -1876,6 +1916,7 @@ class SeuratMap2Ref(Proc):
         "ref": None,
         "refnorm": "auto",
         "split_by": None,
+        "skip_if_normalized": True,
         "SCTransform": {
             "do-correct-umi": False,
             "do-scale": False,
@@ -2174,7 +2215,6 @@ class MetaMarkers(Proc):
     plugin_opts = {
         "report": "file://../reports/scrna/MetaMarkers.svelte",
         "report_paging": 8,
-        "poplog_max": 15,
     }
 
 
@@ -2225,3 +2265,52 @@ class AnnData2Seurat(Proc):
     lang = config.lang.rscript
     envs = {"outtype": "rds", "assay": "RNA", "dotplot_check": True}
     script = "file://../scripts/scrna/AnnData2Seurat.R"
+
+
+class ScSimulation(Proc):
+    """Simulate single-cell data using splatter.
+
+    See <https://www.bioconductor.org/packages/devel/bioc/vignettes/splatter/inst/doc/splatter.html#2_Quickstart>
+
+    Input:
+        seed: The seed for the simulation
+            You could also use string as the seed, and the seed will be
+            generated by `digest::digest2int()`.
+            So this could also work as a unique identifier for the simulation (ie. Sample ID).
+
+    Output:
+        outfile: The output Seurat object/SingleCellExperiment in RDS format
+
+    Envs:
+        ngenes (type=int): The number of genes to simulate
+        ncells (type=int): The number of cells to simulate
+        nspikes (type=int): The number of spike-ins to simulate
+            When `ngenes`, `ncells`, and `nspikes` are not specified, the default
+            params from `mockSCE()` will be used. By default, `ngenes = 2000`,
+            `ncells = 200`, and `nspikes = 100`.
+        outtype (choice): The output file type.
+            - seurat: Seurat object
+            - singlecellexperiment: SingleCellExperiment object
+            - sce: alias for `singlecellexperiment`
+        method (choice): which simulation method to use. Options are:
+            - single: produces a single population
+            - groups: produces distinct groups (eg. cell types), or
+            - paths: selects cells from continuous trajectories (eg. differentiation processes)
+        params (ns): Other parameters for simulation.
+            The parameters are initialized `splitEstimate(mockSCE())` and then
+            updated with the given parameters.
+            See <https://rdrr.io/bioc/splatter/man/SplatParams.html>.
+            Hyphens (`-`) will be transformed into dots (`.`) for the keys.
+    """  # noqa: E501
+    input = "seed:var"
+    output = "outfile:file:simulatied_{{in.seed}}.RDS"
+    lang = config.lang.rscript
+    envs = {
+        "ngenes": None,
+        "ncells": None,
+        "nspikes": None,
+        "outtype": "seurat",
+        "method": "single",
+        "params": {},
+    }
+    script = "file://../scripts/scrna/ScSimulation.R"

biopipen-0.31.0/biopipen/ns/web.py

@@ -0,0 +1,160 @@
+"""Get data from the web"""
+from ..core.proc import Proc
+from ..core.config import config
+
+
+class Download(Proc):
+    """Download data from URLs
+
+    Input:
+        url: The URL to download data from
+
+    Output:
+        outfile: The file downloaded
+
+    Envs:
+        tool (choice): Which tool to use to download the data
+            - wget: Use wget
+            - aria2c: Use aria2c
+            - urllib: Use python's urllib
+            - aria: Alias for aria2c
+        wget: Path to wget
+        aria2c: Path to aria2c
+        args: The arguments to pass to the tool
+        ncores: The number of cores to use
+
+    Requires:
+        wget: Only required when envs.tool == "wget"
+            - check: {{proc.envs.wget}} --version
+        aria2c: Only required when envs.tool == "aria2c"
+            - check: {{proc.envs.aria2c}} --version
+    """
+    input = "url"
+    output = (
+        "outfile:file:"
+        "{{in.url | basename | replace: '%2E', '.' | slugify: separator='.'}}"
+    )
+    lang = config.lang.python
+    envs = {
+        "tool": "wget",  # or aria2c, python
+        "wget": config.exe.wget,
+        "aria2c": config.exe.aria2c,
+        "args": {},
+        "ncores": config.misc.ncores,
+    }
+    script = "file://../scripts/web/Download.py"
+
+
+class DownloadList(Proc):
+    """Download data from URLs in a file.
+
+    This does not work by iterating over the URLs in the file. The whole file is
+    passed to `wget` or `aria2c` at once.
+
+    Input:
+        urlfile: The file containing the URLs to download data from
+
+    Output:
+        outdir: The directory containing the downloaded files
+
+    Envs:
+        tool (choice): Which tool to use to download the data
+            - wget: Use wget
+            - aria2c: Use aria2c
+            - urllib: Use python's urllib
+            - aria: Alias for aria2c
+        wget: Path to wget
+        aria2c: Path to aria2c
+        args: The arguments to pass to the tool
+        ncores: The number of cores to use
+
+    Requires:
+        wget: Only required when envs.tool == "wget"
+            - check: {{proc.envs.wget}} --version
+        aria2c: Only required when envs.tool == "aria2c"
+            - check: {{proc.envs.aria2c}} --version
+    """
+    input = "urlfile:file"
+    output = "outdir:dir:{{in.urlfile | stem}}.downloaded"
+    lang = config.lang.python
+    envs = {
+        "tool": "wget",  # or aria2c
+        "wget": config.exe.wget,
+        "aria2c": config.exe.aria2c,
+        "args": {},
+        "ncores": config.misc.ncores,
+    }
+    script = "file://../scripts/web/DownloadList.py"
+
+
+class GCloudStorageDownloadFile(Proc):
+    """Download file from Google Cloud Storage
+
+    Before using this, make sure you have the `gcloud` tool installed and
+    logged in with the appropriate credentials using `gcloud auth login`.
+
+    Also make sure you have [`google-crc32c`](https://pypi.org/project/google-crc32c/)
+    installed to verify the integrity of the downloaded files.
+
+    Input:
+        url: The URL to download data from.
+            It should be in the format gs://bucket/path/to/file
+
+    Output:
+        outfile: The file downloaded
+
+    Envs:
+        gcloud: Path to gcloud
+        args (ns): Other arguments to pass to the `gcloud storage cp` command
+            - do_not_decompress (flag): Do not decompress the file.
+            - <more>: More arguments to pass to the `gcloud storage cp` command
+                See `gcloud storage cp --help` for more information
+    """
+    input = "url:var"
+    output = "outfile:file:{{in.url | replace: 'gs://', '/' | basename}}"
+    lang = config.lang.python
+    envs = {
+        "gcloud": config.exe.gcloud,
+        "args": {"do_not_decompress": True},
+    }
+    script = "file://../scripts/web/GCloudStorageDownloadFile.py"
+
+
+class GCloudStorageDownloadBucket(Proc):
+    """Download all files from a Google Cloud Storage bucket
+
+    Before using this, make sure you have the `gcloud` tool installed and
+    logged in with the appropriate credentials using `gcloud auth login`.
+
+    Note that this will not use the `--recursive` flag of `gcloud storage cp`.
+    The files will be listed and downloaded one by one so that they can be parallelized.
+
+    Also make sure you have [`google-crc32c`](https://pypi.org/project/google-crc32c/)
+    installed to verify the integrity of the downloaded files.
+
+    Input:
+        url: The URL to download data from.
+            It should be in the format gs://bucket
+
+    Output:
+        outdir: The directory containing the downloaded files
+
+    Envs:
+        gcloud: Path to gcloud
+        keep_structure (flag): Keep the directory structure of the bucket
+        ncores (type=int): The number of cores to use to download the files in parallel
+        args (ns): Other arguments to pass to the `gcloud storage cp` command
+            - do_not_decompress (flag): Do not decompress the file.
+            - <more>: More arguments to pass to the `gcloud storage cp` command
+                See `gcloud storage cp --help` for more information
+    """
+    input = "url:var"
+    output = "outdir:dir:{{in.url | replace: 'gs://', ''}}"
+    lang = config.lang.python
+    envs = {
+        "gcloud": config.exe.gcloud,
+        "keep_structure": True,
+        "ncores": config.misc.ncores,
+        "args": {"do_not_decompress": True},
+    }
+    script = "file://../scripts/web/GCloudStorageDownloadBucket.py"

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/bam/CNAClinic.R

@@ -1,4 +1,5 @@
-source("{{biopipen_dir}}/utils/misc.R")
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+
 library(parallel)
 library(dplyr)
 library(CNAclinic)

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/cellranger/CellRangerCount.py

@@ -11,8 +11,8 @@ cellranger = {{envs.cellranger | quote}}  # pyright: ignore
 tmpdir = Path({{envs.tmpdir | quote}})  # pyright: ignore
 ref = {{envs.ref | quote}}  # pyright: ignore
 ncores = {{envs.ncores | int}}  # pyright: ignore
-include_introns = {{envs.include_introns | repr}}
-create_bam = {{envs.create_bam | repr}}
+include_introns = {{envs.include_introns | repr}}  # pyright: ignore
+create_bam = {{envs.create_bam | repr}}  # pyright: ignore
 
 include_introns = str(include_introns).lower()
 create_bam = str(create_bam).lower()
@@ -54,7 +54,7 @@ version = version.replace("cellranger", "").replace("-", "").strip()
 version = list(map(int, version.split(".")))
 if version[0] >= 8:
     command += ["--create-bam", create_bam]
-elif not create_bam:
+elif create_bam != "true":
     command += ["--no-bam"]
 
 run_command(command, fg=True, cwd=str(Path(outdir).parent))

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/cellranger/CellRangerSummary.R

@@ -1,4 +1,5 @@
-source("{{biopipen_dir}}/utils/misc.R")
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+
 library(rlang)
 library(dplyr)
 library(ggplot2)

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/cnv/AneuploidyScore.R

@@ -1,4 +1,4 @@
-source("{{biopipen_dir}}/utils/misc.R")
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
 
 library(AneuploidyScore)
 library(dplyr)

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/cnv/AneuploidyScoreSummary.R

@@ -1,5 +1,5 @@
-source("{{biopipen_dir}}/utils/misc.R")
-source("{{biopipen_dir}}/utils/plot.R")
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+{{ biopipen_dir | joinpaths: "utils", "plot.R" | source_r }}
 
 library(ggplot2)
 library(ggprism)

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/delim/RowsBinder.R

@@ -1,4 +1,4 @@
-source("{{biopipen_dir}}/utils/misc.R")
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
 
 infiles <- {{in.infiles | r}}
 outfile <- {{out.outfile | r}}

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/delim/SampleInfo.R

@@ -1,5 +1,6 @@
-source("{{biopipen_dir}}/utils/misc.R")
-source("{{biopipen_dir}}/utils/mutate_helpers.R")
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+{{ biopipen_dir | joinpaths: "utils", "mutate_helpers.R" | source_r }}
+
 library(rlang)
 library(dplyr)
 library(ggplot2)

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/gene/GeneNameConversion.R

@@ -1,5 +1,5 @@
-source("{{biopipen_dir}}/utils/misc.R")
-source("{{biopipen_dir}}/utils/gene.R")
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+{{ biopipen_dir | joinpaths: "utils", "gene.R" | source_r }}
 
 infile <- {{in.infile | quote}}
 outfile <- {{out.outfile | quote}}

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/gsea/Enrichr.R

@@ -1,6 +1,6 @@
-source("{{biopipen_dir}}/utils/io.R")
-source("{{biopipen_dir}}/utils/gene.R")
-source("{{biopipen_dir}}/utils/gsea.R")
+{{ biopipen_dir | joinpaths: "utils", "io.R" | source_r }}
+{{ biopipen_dir | joinpaths: "utils", "gene.R" | source_r }}
+{{ biopipen_dir | joinpaths: "utils", "gsea.R" | source_r }}
 
 infile = {{in.infile | quote}}
 outdir = {{out.outdir | quote}}

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/gsea/FGSEA.R

@@ -1,7 +1,7 @@
 # PreRank the genes for GSEA analysis
 # See: https://gseapy.readthedocs.io/en/latest/_modules/gseapy/algorithm.html#ranking_metric
-source("{{biopipen_dir}}/utils/io.R")
-source("{{biopipen_dir}}/utils/gsea.R")
+{{ biopipen_dir | joinpaths: "utils", "io.R" | source_r }}
+{{ biopipen_dir | joinpaths: "utils", "gsea.R" | source_r }}
 
 infile = {{in.infile | quote}}
 metafile = {{in.metafile | quote}}

{biopipen-0.29.2 → biopipen-0.31.0}/biopipen/scripts/gsea/GSEA.R

@@ -1,7 +1,7 @@
 # devtools::install_github("GSEA-MSigDB/GSEA_R")
 
-source("{{biopipen_dir}}/utils/io.R")
-source("{{biopipen_dir}}/utils/gsea.R")
+{{ biopipen_dir | joinpaths: "utils", "io.R" | source_r }}
+{{ biopipen_dir | joinpaths: "utils", "gsea.R" | source_r }}
 
 library(dplyr)
 library(tibble)