biopipen 0.34.6__py3-none-any.whl → 0.34.26__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.34.6"
+__version__ = "0.34.26"

biopipen/core/config.toml

@@ -10,6 +10,8 @@ bcftools = "bcftools"
 calculate_rmsd = "calculate_rmsd"
 # cellranger
 cellranger = "cellranger"
+# cellsnp-lite
+cellsnp_lite = "cellsnp-lite"
 # Control-FREEC to call cnvs
 freec = "freec"
 # liftover coordinates across genomes
@@ -33,6 +35,8 @@ convert = "convert"
 fimo = "fimo"
 # MAXIT: https://sw-tools.rcsb.org/apps/MAXIT/
 maxit = "maxit"
+# MQuad: https://github.com/single-cell-genetics/MQuad
+mquad = "mquad"
 # wget
 wget = "wget"
 # aria2c

biopipen/core/filters.py

@@ -32,7 +32,7 @@ def dict_to_cli_args(
 
     Args:
         dic: The dict to convert
-        exclude: The keys to exclude
+        exclude: The keys to exclude before conversion (e.g. dashify)
         prefix: The prefix of the keys after conversion
             Defaults to `None`, mean `-` for short keys and `--` for long keys
         sep: The separator between key and value

biopipen/core/testing.py

@@ -6,7 +6,8 @@ from pathlib import Path
 from pipen import Pipen
 
 TESTING_INDEX_INIT = 1
-TESTING_PARENT_DIR = Path(tempfile.gettempdir())
+TESTING_PARENT_DIR = Path(__file__).parent.parent.parent.joinpath("tests", "running")
+TESTING_PARENT_DIR.mkdir(parents=True, exist_ok=True)
 TESTING_DIR = str(TESTING_PARENT_DIR.joinpath("biopipen-tests-%(index)s"))
 RSCRIPT_DIR = TESTING_PARENT_DIR.joinpath("biopipen-tests-rscripts")
 RSCRIPT_DIR.mkdir(exist_ok=True)

biopipen/ns/cellranger.py

@@ -30,13 +30,26 @@ class CellRangerCount(Proc):
         ref: Path of folder containing 10x-compatible transcriptome reference
         tmpdir: Path to temporary directory, used to save the soft-lined fastq files
             to pass to cellranger
+        outdir_is_mounted (flag): A flag indicating whether the output directory is
+            on a mounted filesystem. As of `cellranger` v9.0.1, `cellranger vdj` will
+            fail when trying to copy/operate files to a mounted filesystem.
+            See <https://github.com/10XGenomics/cellranger/issues/210> and
+            <https://github.com/10XGenomics/cellranger/issues/250> for similar issues.
+            If that is the case, set this flag to `True` to use `envs.tmpdir` as
+            the output directory for `cellranger vdj`, and then move the results
+            to the final output directory after `cellranger vdj` finishes.
+            In this case, make sure that `envs.tmpdir` must have enough space and
+            it must be a local filesystem.
+        copy_outs_only (flag): If `outdir_is_mounted` is `True`, set this flag to `True`
+            to only copy the `outs` folder from the temporary output directory
+            to the final output directory, instead of the whole output directory.
         include_introns (flag): Set to false to exclude intronic reads in count.
         create_bam (flag): Enable or disable BAM file generation.
             This is required by cellrange v8+. When using cellrange v8-, it will be
             transformed to `--no-bam`.
         <more>: Other environment variables required by `cellranger count`
             See `cellranger count --help` for more details or
-            https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#count
+            <https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#count>
     """  # noqa: E501
     input = "fastqs:files, id"
     output = """outdir:dir:
@@ -59,6 +72,8 @@ class CellRangerCount(Proc):
         "cellranger": config.exe.cellranger,
         "ref": config.ref.ref_cellranger_gex,
         "tmpdir": config.path.tmpdir,
+        "outdir_is_mounted": False,
+        "copy_outs_only": True,
         "include_introns": True,
         "create_bam": False,
     }
@@ -91,10 +106,23 @@ class CellRangerVdj(Proc):
         cellranger: Path to cellranger
         ref: Path of folder containing 10x-compatible transcriptome reference
         tmpdir: Path to temporary directory, used to save the soft-lined fastq files
-            to pass to cellranger
+            to pass to cellranger.
+        outdir_is_mounted (flag): A flag indicating whether the output directory is
+            on a mounted filesystem. As of `cellranger` v9.0.1, `cellranger vdj` will
+            fail when trying to copy the VDJ reference files to a mounted filesystem.
+            See <https://github.com/10XGenomics/cellranger/issues/210> and
+            <https://github.com/10XGenomics/cellranger/issues/250> for similar issues.
+            If that is the case, set this flag to `True` to use `envs.tmpdir` as
+            the output directory for `cellranger vdj`, and then move the results
+            to the final output directory after `cellranger vdj` finishes.
+            In this case, make sure that `envs.tmpdir` must have enough space and
+            it must be a local filesystem.
+        copy_outs_only (flag): If `outdir_is_mounted` is `True`, set this flag to `True`
+            to only copy the `outs` folder from the temporary output directory
+            to the final output directory, instead of the whole output directory.
         <more>: Other environment variables required by `cellranger vdj`
             See `cellranger vdj --help` for more details or
-            https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#vdj
+            <https://www.10xgenomics.com/support/software/cell-ranger/advanced/cr-command-line-arguments#vdj>
     """  # noqa: E501
     input = "fastqs:files, id"
     output = """outdir:dir:
@@ -116,6 +144,8 @@ class CellRangerVdj(Proc):
         "ncores": config.misc.ncores,
         "cellranger": config.exe.cellranger,
         "ref": config.ref.ref_cellranger_vdj,
+        "outdir_is_mounted": False,
+        "copy_outs_only": True,
         "tmpdir": config.path.tmpdir,
     }
     script = "file://../scripts/cellranger/CellRangerVdj.py"

biopipen/ns/regulatory.py

@@ -132,6 +132,9 @@ class MotifAffinityTest(Proc):
             If no `regulator_col` is provided, no regulator information is written in
             the output. Otherwise, the regulator information is written in the output in
             the `Regulator` column.
+        var_col: The column names in the `in.motiffile` containing the variant information.
+            It has to be matching the names in the `in.varfile`. This is helpful when
+            we only need to test the pairs of variants and motifs in the `in.motiffile`.
         notfound (choice): What to do if a motif is not found in the database,
             or a regulator is not found in the regulator-motif mapping (envs.regmotifs)
             file.
@@ -200,6 +203,7 @@ class MotifAffinityTest(Proc):
         "bcftools": config.exe.bcftools,
         "motif_col": None,
         "regulator_col": None,
+        "var_col": None,
         "notfound": "error",
         "motifdb": config.ref.tf_motifdb,
         "regmotifs": config.ref.tf_motifs,