biopipen 0.7.1__tar.gz → 0.8.0__tar.gz

{biopipen-0.7.1 → biopipen-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.7.1
+Version: 0.8.0
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang
@@ -12,12 +12,11 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Provides-Extra: test
 Requires-Dist: cmdy (>=0.5,<0.6)
 Requires-Dist: datar[pandas] (>=0.11,<0.12)
-Requires-Dist: pipen (>=0.3,<0.4)
-Requires-Dist: pipen-args (>=0.3,<0.4) ; extra == "test"
-Requires-Dist: pipen-cli-run (>=0.4,<0.5)
-Requires-Dist: pipen-filters (>=0.2,<0.3)
-Requires-Dist: pipen-report (>=0.4,<0.5)
-Requires-Dist: pipen-verbose (>=0.1,<0.2) ; extra == "test"
+Requires-Dist: pipen (>=0.5,<0.6)
+Requires-Dist: pipen-args (>=0.6,<0.7)
+Requires-Dist: pipen-cli-run (>=0.5,<0.6)
+Requires-Dist: pipen-filters (>=0.4,<0.5)
+Requires-Dist: pipen-report (>=0.6,<0.7)
+Requires-Dist: pipen-verbose (>=0.3,<0.4)

biopipen-0.8.0/biopipen/__init__.py

@@ -0,0 +1,2 @@
+
+__version__ = "0.8.0"

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/core/config.py

@@ -1,6 +1,5 @@
 """Provides the envs from configuration files"""
 
-import sys
 from typing import Any
 from pathlib import Path
 from tempfile import gettempdir
@@ -38,9 +37,5 @@ config_profiles = [
     USER_CONFIG_FILE,
     PROJ_CONFIG_FILE,
 ]
-# scan sys.argv to see if +config <config file> passed in
-if "+config" in sys.argv:
-    cindex = sys.argv.index("+config")
-    config_profiles.append(sys.argv[cindex + 1])
 
 config = ConfigItems(Config.load(*config_profiles, ignore_nonexist=True))

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/core/config.toml

@@ -36,6 +36,8 @@ samtools = "samtools"
 magic_python = "python"
 # truvari
 truvari = "truvari"
+# vcfanno
+vcfanno = "vcfanno"
 
 # Interpreters
 [lang]
@@ -80,7 +82,3 @@ sctype_db = ""
 [misc]
 # Number of cores used for each job
 ncores = 1
-
-[pipeline.scrna_metabolic_landscape]
-
-[pipeline.cnvkit_pipeline]

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/core/defaults.py

@@ -1,8 +1,8 @@
 """Provide default variables
 
-- `BIOPIPEN_DIR`: the root directory of the biopipen source
-- `REPORT_DIR`: the root directory of the report
-- `SCRIPTS_DIR`: the root directory of the scripts
+- BIOPIPEN_DIR: the root directory of the biopipen source
+- REPORT_DIR: the root directory of the report
+- SCRIPTS_DIR: the root directory of the scripts
 """
 from pathlib import Path
 

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/core/filters.py

@@ -1,3 +1,4 @@
+"""Additional filters for pipen"""
 from pathlib import Path
 from typing import Any, Mapping
 

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/core/proc.py

@@ -10,9 +10,7 @@ class Proc(PipenProc):
     """Base class for all processes in biopipen to subclass"""
 
     template_opts = {
-        "globals": {
-            "biopipen_dir": str(BIOPIPEN_DIR),
-        },
+        "globals": {"biopipen_dir": str(BIOPIPEN_DIR)},
         "filters": filtermanager.filters.copy(),
         "search_paths": SEARCH_PATHS + [str(REPORT_DIR)],
     }

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/core/testing.py

@@ -51,5 +51,4 @@ def get_pipeline(testfile, loglevel="debug", **kwargs):
         "loglevel": loglevel,
     }
     kws.update(kwargs)
-    pipen = Pipen(**kws)
-    return pipen
+    return Pipen(**kws)

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/ns/bam.py

@@ -33,11 +33,9 @@ class CNVpytor(Proc):
         baf_nomask: Do not use P mask in BAF histograms
 
     Requires:
-        - name: cnvpytor
-          check: |
-            {{proc.envs.cnvpytor}} --version
+        cnvpytor:
+           - check: {{proc.envs.cnvpytor}} --version
     """
-
     input = "bamfile:file, snpfile:file"
     output = "outdir:dir:{{in.bamfile | stem}}.cnvpytor"
     lang = config.lang.python
@@ -93,9 +91,7 @@ class ControlFREEC(Proc):
         freec: Path to Control-FREEC executable
         ncores: Number of cores to use
         arggs: Other arguments for Control-FREEC
-
     """
-
     input = "bamfile:file, snpfile:file"
     output = "outdir:dir:{{in.bamfile | stem}}.freec"
     lang = config.lang.python
@@ -132,14 +128,14 @@ class CNAClinic(Proc):
     Input:
         metafile: The meta file, header included, tab-delimited, including
             following columns:
-            "Bam": The path to bam file
-            "Sample": Optional. The sample names,
+            - Bam: The path to bam file
+            - Sample: Optional. The sample names,
                 if you don't want filename of bam file to be used
-            "Group": Optional. The group names, either "Case" or "Control"
-            "Patient": Optional. The patient names. Since CNAClinic only
+            - Group: Optional. The group names, either "Case" or "Control"
+            - Patient: Optional. The patient names. Since CNAClinic only
                 supports paired samples, you need to provide the patient names
                 for each sample. Required if "Group" is provided.
-            "Binsizer": Optional. Samples used to estimate the bin size
+            - Binsizer: Optional. Samples used to estimate the bin size
                 "Y", "Yes", "T", "True", will be treated as True
                 If not provided, will use `envs.binsizer` to get the samples
                 to use. Either this column or `envs.binsizer` should be
@@ -153,9 +149,9 @@ class CNAClinic(Proc):
         seed: The seed for random number generator for choosing samples
             for estimating bin size
         binsizer: The samples used to estimate the bin size, it could be:
-            - A list of sample names
-            - A float number (0 < x <= 1), the fraction of samples to use
-            - A integer number (x > 1), the number of samples to use
+            A list of sample names
+            A float number (0 < x <= 1), the fraction of samples to use
+            A integer number (x > 1), the number of samples to use
         binsize: Directly use this binsize for CNAClinic, in kbp.
         genome: The genome assembly
         run_args: The arguments for CNAClinic::runSegmentation

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/ns/bcftools.py

@@ -23,7 +23,6 @@ class BcftoolsAnnotate(Proc):
         header: Headers to be added
         args: Other arguments for `bcftools annotate`
     """
-
     input = "infile:file, annfile:file"
     output = "outfile:file:{{in.infile | basename}}"
     lang = config.lang.python
@@ -59,13 +58,11 @@ class BcftoolsFilter(Proc):
             Since the filters need to be applied one by one by bcftools
         includes: and
         excludes: include/exclude only sites for which EXPRESSION is true.
-            - See: https://samtools.github.io/bcftools/bcftools.html#expressions
-            - If provided, `envs.args.include/exclude` will be ignored.
-            - If `str`/`list` used, The filter names will be `Filter%d`
-            - A dict is used when keys are filter names and values are
-              expressions
+            See: https://samtools.github.io/bcftools/bcftools.html#expressions
+            If provided, `envs.args.include/exclude` will be ignored.
+            If `str`/`list` used, The filter names will be `Filter%d`
+            A dict is used when keys are filter names and values are expressions
     """
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | basename}}"
     lang = config.lang.python

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/ns/bed.py

@@ -17,11 +17,9 @@ class BedLiftOver(Proc):
         chain: The map chain file for liftover
 
     Requires:
-        - name: liftOver
-          check: |
-            {{proc.envs.liftover}} 2>&1 | grep "usage"
+        liftOver:
+            - check: {{proc.envs.liftover}} 2>&1 | grep "usage"
     """
-
     input = "inbed:file"
     output = "outbed:file:{{in.inbed | basename}}"
     envs = {
@@ -64,18 +62,14 @@ class Bed2Vcf(Proc):
         index: Sort and index output file
 
     Requires:
-        - name: cyvcf2
-          check: |
-            {{proc.lang}} -c "import cyvcf2"
-        - name: pysam
-          check: |
-            {{proc.lang}} -c "import pysam"
-        - name: bcftools
-          if: {{proc.envs.index}}
-          check: |
-            {{proc.envs.bcftools}} --version
+        cyvcf2:
+            - check: {{proc.lang}} -c "import cyvcf2"
+        pysam:
+            - check: {{proc.lang}} -c "import pysam"
+        bcftools:
+            - if: {{proc.envs.index}}
+            - check: {{proc.envs.bcftools}} --version
     """
-
     input = "inbed:file"
     output = (
         "outvcf:file:{{in.inbed | stem}}.vcf{{'.gz' if envs.index else ''}}"
@@ -141,7 +135,6 @@ class BedConsensus(Proc):
         ncores: Number of cores to use to calculate the weights for
             each bed file
     """
-
     input = "bedfiles:files"
     output = (
         "outbed:file:{{in.bedfiles | first | stem | append: '_consensus'}}.bed"

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/ns/cnv.py

@@ -19,17 +19,14 @@ class AneuploidyScore(Proc):
             plot to show the CAAs for each chromosome arm
 
     Requires:
-        - name: AneuploidyScore
-          check: |
-            {{proc.lang}} <(echo "library(AneuploidyScore)")
-        - name: ucsc.hg19.cytoband
-          if: {{ proc.envs.genome == 'hg19' }}
-          check: |
-            {{proc.lang}} <(echo "library(ucsc.hg19.cytoband)")
-        - name: ucsc.hg38.cytoband
-          if: {{ proc.envs.genome == 'hg38' }}
-          check: |
-            {{proc.lang}} <(echo "library(ucsc.hg38.cytoband)")
+        AneuploidyScore:
+            - check: {{proc.lang}} <(echo "library(AneuploidyScore)")
+        ucsc.hg19.cytoband:
+            - if: {{ proc.envs.genome == 'hg19' }}
+            - check: {{proc.lang}} <(echo "library(ucsc.hg19.cytoband)")
+        ucsc.hg38.cytoband:
+            - if: {{ proc.envs.genome == 'hg38' }}
+            - check: {{proc.lang}} <(echo "library(ucsc.hg38.cytoband)")
     """
     input = "segfile:file"
     output = "outdir:dir:{{in.segfile | stem}}.aneuploidy_score"

{biopipen-0.7.1 → biopipen-0.8.0}/biopipen/ns/cnvkit.py

@@ -19,11 +19,9 @@ class CNVkitAccess(Proc):
         ref: The reference genome fasta file
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
     """
-
     input = "excfiles:files"
     output = (
         "outfile:file:{{envs.ref | stem0}}.access.{{envs.min_gap_size}}.bed"
@@ -71,11 +69,9 @@ class CNVkitAutobin(Proc):
         ref: The reference genome fasta file
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
     """
-
     input = "bamfiles:files, accfile:file, baitfile:file"
     output = [
         "target_file:file:{{in.bamfiles | first | stem0}}-etc.target.bed",
@@ -117,11 +113,9 @@ class CNVkitCoverage(Proc):
         ref: The reference genome fasta file
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
     """
-
     input = "bamfile:file, target_file:file"
     output = """
         {%- if "antitarget" in basename(in.target_file) -%}
@@ -174,11 +168,9 @@ class CNVkitReference(Proc):
         ref: The reference genome fasta file
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
     """
-
     input = (
         "covfiles:files, target_file:file, antitarget_file:file, sample_sex:var"
     )
@@ -221,11 +213,9 @@ class CNVkitFix(Proc):
         no_rmask: Skip RepeatMasker correction.
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
     """
-
     input = (
         "target_file:file, antitarget_file:file, reference:file, sample_id:var"
     )
@@ -286,14 +276,11 @@ class CNVkitSegment(Proc):
             zygosity from allele frequencies.
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
-        - name: r-DNAcopy
-          check: |
-            {{proc.envs.rscript}} <(echo "library(DNAcopy)")
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
+        r-DNAcopy:
+            - check: {{proc.envs.rscript}} <(echo "library(DNAcopy)")
     """
-
     input = "cnrfile:file, vcf:file, sample_id:var, normal_id:var"
     output = "outfile:file:{{in.cnrfile | stem0}}.cns"
     lang = config.lang.python
@@ -366,14 +353,11 @@ class CNVkitScatter(Proc):
             if no case specified
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
-        - name: convert
-          check: |
-            {{proc.envs.convert}} -version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
+        convert:
+            - check: {{proc.envs.convert}} -version
     """
-
     input = (
         "cnrfile:file, cnsfile:file, config:var, "
         "vcf:file, sample_id:var, normal_id:var"
@@ -439,14 +423,11 @@ class CNVkitDiagram(Proc):
             and `title`
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
-        - name: convert
-          check: |
-            {{proc.envs.convert}} -version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
+        convert:
+            - check: {{proc.envs.convert}} -version
     """
-
     input = "cnrfile:file, cnsfile:file, sample_sex:var"
     output = "outdir:dir:{{in.cnrfile | stem0}}.diagram"
     lang = config.lang.python
@@ -510,14 +491,11 @@ class CNVkitHeatmap(Proc):
             if no case specified
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
-        - name: convert
-          check: |
-            {{proc.envs.convert}} -version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
+        convert:
+            - check: {{proc.envs.convert}} -version
     """
-
     input = "segfiles:files, sample_sex: var"
     output = "outdir:dir:{{in.segfiles | first | stem0}}-etc.heatmap"
     lang = config.lang.python
@@ -587,11 +565,9 @@ class CNVkitCall(Proc):
             zygosity from allele frequencies.
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
     """
-
     input = [
         "cnrfile:file",
         "cnsfile:file",
@@ -691,14 +667,11 @@ class CNVkitBatch(Proc):
             `in.metafile`
 
     Requires:
-        - name: cnvkit
-          check: |
-            {{proc.envs.cnvkit}} version
-        - name: r-DNAcopy
-          check: |
-            {{proc.envs.rscript}} <(echo "library(DNAcopy)")
+        cnvkit:
+            - check: {{proc.envs.cnvkit}} version
+        r-DNAcopy:
+            - check: {{proc.envs.rscript}} <(echo "library(DNAcopy)")
     """
-
     input = "metafile:file"
     output = "outdir:dir:{{in.metafile | stem0}}.cnvkit"
     lang = config.lang.python