biopipen 0.7.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

biopipen/ns/csv.py

@@ -1,6 +1,4 @@
 """Tools to deal with csv/tsv files"""
-
-
 from ..core.proc import Proc
 
 

biopipen/ns/gene.py

@@ -38,7 +38,6 @@ class GeneNameConversion(Proc):
             Supported: human, mouse, rat, fruitfly, nematode, zebrafish,
             thale-cress, frog and pig
     """  # noqa: E501
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | basename}}"
     lang = config.lang.python

biopipen/ns/gsea.py

@@ -1,5 +1,4 @@
 """Gene set enrichment analysis"""
-
 from ..core.proc import Proc
 from ..core.config import config
 
@@ -35,9 +34,8 @@ class GSEA(Proc):
             Other configs passed to `GSEA()` directly
 
     Requires:
-        - name: GSEA-MSigDB/GSEA_R
-          check: |
-            {{proc.lang}} <(echo "library(GSEA)")
+        GSEA-MSigDB/GSEA_R:
+            - check: {{proc.lang}} <(echo "library(GSEA)")
     """
 
     input = "infile:file, metafile:file, gmtfile:file, configfile:file"
@@ -86,7 +84,6 @@ class PreRank(Proc):
             the first one is pos and second is neg. Or you can have multiple
             pairs of labels (e.g. `[["CASE1", "CNTRL"], ["CASE2", "CNTRL"]]`)
     """
-
     input = "infile:file, metafile:file, configfile:file"
     output = "outfile:file:{{in.infile | stem}}.rank"
     lang = config.lang.rscript
@@ -139,11 +136,9 @@ class FGSEA(Proc):
         `<rest>`: Rest arguments for `fgsea()`
 
     Requires:
-        - name: bioconductor-fgsea
-          check: |
-            {{proc.lang}} -e "library(fgsea)"
+        bioconductor-fgsea:
+            - check: {{proc.lang}} -e "library(fgsea)"
     """
-
     input = "infile:file, metafile:file, gmtfile:file, configfile:file"
     output = "outdir:dir:{{in.infile | stem}}.fgsea"
     lang = config.lang.rscript
@@ -183,7 +178,6 @@ class Enrichr(Proc):
             See https://maayanlab.cloud/Enrichr/#libraries for all available
             databases/libaries
     """
-
     input = "infile:file"
     output = "outdir:dir:{{in.infile | stem}}.enrichr"
     lang = config.lang.rscript

biopipen/ns/misc.py

@@ -12,7 +12,6 @@ class File2Proc(Proc):
     Output:
         outfile: The output symbolic link to the input file
     """
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | basename}}"
     script = """
@@ -25,7 +24,6 @@ class File2Proc(Proc):
 class Glob2Dir(Proc):
     """Create symbolic links in output directory for the files given
     by the glob pattern"""
-
     input = "pattern:var"
     output = "outdir:dir:from_glob"
     script = """
@@ -54,7 +52,6 @@ class Config2File(Proc):
         infmt: The input format. `json` or `toml`.
         outfmt: The output format. `json` or `toml`.
     """
-
     input = "config:var, name:var"
     output = "outfile:file:{{(in.name or 'config') | slugify}}.{{envs.outfmt}}"
     envs = {"infmt": "toml", "outfmt": "toml"}
@@ -76,7 +73,6 @@ class Str2File(Proc):
     Envs:
         name: The name of the output file
     """
-
     input = "str, name"
     output = "outfile:file:{{in.name}}"
     lang = config.lang.python
@@ -99,7 +95,6 @@ class Shell(Proc):
         outdir: Whether the `out.outfile` should be a directory.
             If so a directory will be created before running the command.
     """
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | basename}}"
     envs = {"cmd": "", "outdir": False}

biopipen/ns/plot.py

@@ -94,11 +94,9 @@ class Heatmap(Proc):
         globals: Some globals for the expression in `args` to be evaluated
 
     Requires:
-        - name: bioconductor-complexheatmap
-          check: |
-            {{proc.lang}} <(echo "library(ComplexHeatmap)")
+        bioconductor-complexheatmap:
+            - check: {{proc.lang}} <(echo "library(ComplexHeatmap)")
     """
-
     input = "infile:file, annofiles:files"
     output = """
         {%- set outdir = in.infile | stem0 | append: ".heatmap" -%}

biopipen/ns/rnaseq.py

@@ -6,7 +6,6 @@ from ..core.config import config
 
 class UnitConversion(Proc):
     """Convert expression value units back and forth"""
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | basename}}"
     lang = config.lang.rscript

biopipen/ns/scrna.py

@@ -71,17 +71,13 @@ class SeuratPreparing(Proc):
             `gene_qc` is applied after `cell_qc`.
 
     Requires:
-        - name: r-seurat
-          check: |
-            {{proc.lang}} <(echo "library(Seurat)")
-        - name: r-future
-          check: |
-            {{proc.lang}} <(echo "library(future)")
-        - name: r-bracer
-          check: |
-            {{proc.lang}} <(echo "library(bracer)")
+        r-seurat:
+            - check: {{proc.lang}} <(echo "library(Seurat)")
+        r-future:
+            - check: {{proc.lang}} <(echo "library(future)")
+        r-bracer:
+            - check: {{proc.lang}} <(echo "library(bracer)")
     """
-
     input = "metafile:file"
     output = "rdsfile:file:{{in.metafile | stem}}.seurat.RDS"
     lang = config.lang.rscript
@@ -113,17 +109,13 @@ class SeuratClustering(Proc):
             Note that `dims = 30` will be expanded as `dims = 1:30`
 
     Requires:
-        - name: r-seurat
-          check: |
-            {{proc.lang}} <(echo "library(Seurat)")
-        - name: r-tidyr
-          check: |
-            {{proc.lang}} <(echo "library(tidyr)")
-        - name: r-dplyr
-          check: |
-            {{proc.lang}} <(echo "library(dplyr)")
+        r-seurat:
+            - check: {{proc.lang}} <(echo "library(Seurat)")
+        r-tidyr:
+            - check: {{proc.lang}} <(echo "library(tidyr)")
+        r-dplyr:
+            - check: {{proc.lang}} <(echo "library(dplyr)")
     """
-
     input = "srtobj:file"
     output = "rdsfile:file:{{in.srtobj | stem}}.RDS"
     lang = config.lang.rscript
@@ -196,9 +188,8 @@ class SeuratClusterStats(Proc):
             `Seurat::Dimplot()`, add `devpars`.
 
     Requires:
-        - name: r-seurat
-          check: |
-            {{proc.lang}} -e "library(Seurat)"
+        r-seurat:
+            - check: {{proc.lang}} -e "library(Seurat)"
     """
 
     input = "srtobj:file"
@@ -235,7 +226,6 @@ class CellsDistribution(Proc):
     Input:
         srtobj: The seurat object generated by SeuratClustering
         casefile: The file with the cases
-
             >>> # The name of the job, used in report, optional
             >>> # If not given, will use `{{in.srtobj | stem}}`, ...
             >>> name = ""
@@ -284,17 +274,13 @@ class CellsDistribution(Proc):
             will be used.
 
     Requires:
-        - name: r-seurat
-          check: |
-              {{proc.lang}} -e "library(Seurat)"
-        - name: r-dplyr
-          check: |
-              {{proc.lang}} -e "library(dplyr)"
-        - name: r-tidyr
-          check: |
-              {{proc.lang}} -e "library(tidyr)"
+        r-seurat:
+            - check: {{proc.lang}} -e "library(Seurat)"
+        r-dplyr:
+            - check: {{proc.lang}} -e "library(dplyr)"
+        r-tidyr:
+            - check: {{proc.lang}} -e "library(tidyr)"
     """
-
     input = "srtobj:file, casefile:file"
     output = "outdir:dir:{{in.srtobj | stem}}.cells_distribution"
     lang = config.lang.rscript
@@ -320,17 +306,13 @@ class SeuratMetadataMutater(Proc):
         rdsfile: The seurat object with the additional metadata
 
     Requires:
-        - name: r-seurat
-          check: |
-            {{proc.lang}} <(echo "library(Seurat)")
-        - name: r-tibble
-          check: |
-            {{proc.lang}} <(echo "library(tibble)")
-        - name: r-dplyr
-          check: |
-            {{proc.lang}} <(echo "library(dplyr)")
+        r-seurat:
+            - check: {{proc.lang}} <(echo "library(Seurat)")
+        r-tibble:
+            - check: {{proc.lang}} <(echo "library(tibble)")
+        r-dplyr:
+            - check: {{proc.lang}} <(echo "library(dplyr)")
     """
-
     input = "srtobj:file, metafile:file, mutaters:var"
     output = "rdsfile:file:{{in.srtobj | stem}}.RDS"
     lang = config.lang.rscript
@@ -372,7 +354,6 @@ class GeneExpressionInvestigation(Proc):
                 - `res`, `height` and `width` the parameters for `png()`
                 - other arguments for `ComplexHeatmap::Heatmap()`
     """
-
     input = "srtobj:file, genefile:file, configfile:file"
     output = "outdir:dir:{{in.configfile | stem0}}.gei"
     lang = config.lang.rscript
@@ -409,7 +390,6 @@ class DimPlots(Proc):
             Keys are the names and values are the arguments to
             `Seurat::Dimplots`
     """
-
     input = "srtobj:file, configfile:file, name:var"
     output = "outdir:dir:{{in.srtobj | stem}}.dimplots"
     lang = config.lang.rscript
@@ -444,6 +424,8 @@ class MarkersFinder(Proc):
             >>> "ident.1" = "Case"
             >>> "ident.2" = "Control"
             >>> "group.by" = "Group"
+            >>> # Do the comparison in each cluster
+            >>> each = "seurat_clusters"
             >>> # other arguments for Seruat::FindMarkers()
             >>> # Filter after mutaters
             >>> filter2 = "SampleType != 'Control'"
@@ -473,13 +455,11 @@ class MarkersFinder(Proc):
             `p_val_adj`
             Example - `"p_val_adj < 0.05 & abs(avg_log2FC) > 1"`
     """
-
     input = "srtobj:file, casefile:file"
     output = "outdir:dir:{{(in.casefile or in.srtobj) | stem0}}.markers"
     lang = config.lang.rscript
     envs = {
         "ncores": config.misc.ncores,
-        "name": "Markers for all clusters",
         "cases": {
             "Cluster": {"group.by": "seurat_clusters"},
         },
@@ -519,39 +499,33 @@ class ExprImpute(Proc):
             python: The python path where magic-impute is installed.
 
     Requires:
-        - name: r-scimpute
-          if: {{proc.envs.tool == "scimpute"}}
-          check: |
-            {{proc.lang}} <(echo "library(scImpute)")
-        - name: r-rmagic
-          if: {{proc.envs.tool == "rmagic"}}
-          check: |
-            {{proc.lang}} <(\
-                echo "\
-                    tryCatch(\
-                        { setwd(dirname(Sys.getenv('CONDA_PREFIX'))) }, \
-                        error = function(e) NULL \
-                    ); \
-                    library(Rmagic)\
-                "\
-            )
-        - name: magic-impute
-          if: {{proc.envs.tool == "rmagic"}}
-          check: |
-            {{proc.envs.rmagic_args.python}} -c "import magic")
-        - name: r-dplyr
-          if: {{proc.envs.tool == "scimpute"}}
-          check: |
-            {{proc.lang}} <(echo "library(dplyr)")
-        - name: r-seurat
-          check: |
-            {{proc.lang}} <(echo "library(Seurat)")
-        - name: r-seuratwrappers
-          if: {{proc.envs.tool == "alra"}}
-          check: |
-            {{proc.lang}} <(echo "library(SeuratWrappers)")
+        r-scimpute:
+            - if: {{proc.envs.tool == "scimpute"}}
+            - check: {{proc.lang}} <(echo "library(scImpute)")
+        r-rmagic:
+            - if: {{proc.envs.tool == "rmagic"}}
+            - check: |
+                {{proc.lang}} <(\
+                    echo "\
+                        tryCatch(\
+                            { setwd(dirname(Sys.getenv('CONDA_PREFIX'))) }, \
+                            error = function(e) NULL \
+                        ); \
+                        library(Rmagic)\
+                    "\
+                )
+        magic-impute:
+            - if: {{proc.envs.tool == "rmagic"}}
+            - check: {{proc.envs.rmagic_args.python}} -c "import magic")
+        r-dplyr:
+            - if: {{proc.envs.tool == "scimpute"}}
+            - check: {{proc.lang}} <(echo "library(dplyr)")
+        r-seurat:
+            - check: {{proc.lang}} <(echo "library(Seurat)")
+        r-seuratwrappers:
+            - if: {{proc.envs.tool == "alra"}}
+            - check: {{proc.lang}} <(echo "library(SeuratWrappers)")
     """
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | stem}}.imputed.RDS"
     lang = config.lang.rscript
@@ -587,7 +561,6 @@ class SCImpute(Proc):
         infmt: The input format.
             Either `seurat` or `matrix`
     """
-
     input = "infile:file, groupfile:file"
     output = [
         "outfile:file:{{in.infile | stem | replace: '.seurat', ''}}."
@@ -624,14 +597,11 @@ class SeuratFilter(Proc):
         invert: Invert the selection?
 
     Requires:
-        - name: r-seurat
-          check: |
-            {{proc.lang}} <(echo "library('Seurat')")
-        - name: r-dplyr
-          check: |
-            {{proc.lang}} <(echo "library('dplyr')")
+        r-seurat:
+            - check: {{proc.lang}} <(echo "library('Seurat')")
+        r-dplyr:
+            - check: {{proc.lang}} <(echo "library('dplyr')")
     """
-
     input = "srtobj:file, filters:var"
     output = "outfile:file:{{in.srtobj | stem}}.filtered.RDS"
     lang = config.lang.rscript
@@ -661,14 +631,11 @@ class SeuratSubset(Proc):
         ignore_nas: Ignore NA values?
 
     Requires:
-        - name: r-seurat
-          check: |
-            {{proc.lang}} <(echo "library('Seurat')")
-        - name: r-dplyr
-          check: |
-            {{proc.lang}} <(echo "library('dplyr')")
+        r-seurat:
+            - check: {{proc.lang}} <(echo "library('Seurat')")
+        r-dplyr:
+            - check: {{proc.lang}} <(echo "library('dplyr')")
     """
-
     input = "srtobj:file, subsets:var"
     output = "outdir:dir:{{in.srtobj | stem}}.subsets"
     envs = {"ignore_nas": True}
@@ -722,7 +689,6 @@ class Subset10X(Proc):
         feats_to_keep: The features/genes to keep.
             The final features list will be `feats_to_keep` + `nfeats`
     """
-
     input = "indir:dir"
     output = "outdir:dir:{{in.indir | stem}}"
     envs = {
@@ -749,7 +715,6 @@ class Write10X(Proc):
     Envs:
         version: The version of 10X format
     """
-
     input = "srtobj:file"
     output = "outdir:dir:{{in.srtobj | stem}}"
     envs = {"version": "3"}
@@ -789,14 +754,11 @@ class ScFGSEA(Proc):
 
 
     Requires:
-        - name: bioconductor-fgsea
-          check: |
-            {{proc.lang}} -e "library(fgsea)"
-        - name: r-seurat
-          check: |
-            {{proc.lang}} -e "library(seurat)"
+        bioconductor-fgsea:
+            - check: {{proc.lang}} -e "library(fgsea)"
+        r-seurat:
+            - check: {{proc.lang}} -e "library(seurat)"
     """
-
     input = "srtobj:file, casefile:file"
     output = "outdir:dir:{{(in.casefile or in.srtobj) | stem0}}.fgsea"
     lang = config.lang.rscript
@@ -836,22 +798,18 @@ class CellTypeAnnotate(Proc):
             identity and values as the new cell type.
 
     Requires:
-        - name: r-HGNChelper
-          if: {{proc.envs.tool == 'sctype'}}
-          check: |
-            {{proc.lang}} -e "library(HGNChelper)"
-        - name: r-seurat
-          if: {{proc.envs.tool == 'sctype'}}
-          check: |
-            {{proc.lang}} -e "library(Seurat)"
-        - name: r-dplyr
-          if: {{proc.envs.tool == 'sctype'}}
-          check: |
-            {{proc.lang}} -e "library(dplyr)"
-        - name: r-openxlsx
-          if: {{proc.envs.tool == 'sctype'}}
-          check: |
-            {{proc.lang}} -e "library(openxlsx)"
+        r-HGNChelper:
+            - if: {{proc.envs.tool == 'sctype'}}
+            - check: {{proc.lang}} -e "library(HGNChelper)"
+        r-seurat:
+            - if: {{proc.envs.tool == 'sctype'}}
+            - check: {{proc.lang}} -e "library(Seurat)"
+        r-dplyr:
+            - if: {{proc.envs.tool == 'sctype'}}
+            - check: {{proc.lang}} -e "library(dplyr)"
+        r-openxlsx:
+            - if: {{proc.envs.tool == 'sctype'}}
+            - check: {{proc.lang}} -e "library(openxlsx)"
     """
     input = "sobjfile:file"
     output = "outfile:file:{{in.sobjfile | stem}}.annotated.RDS"