biopipen 0.34.0__tar.gz → 0.34.2__tar.gz

{biopipen-0.34.0 → biopipen-0.34.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: biopipen
-Version: 0.34.0
+Version: 0.34.2
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.34.2/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.34.2"

{biopipen-0.34.0 → biopipen-0.34.2}/biopipen/ns/scrna.py

@@ -61,7 +61,8 @@ class SeuratPreparing(Proc):
     Those paths should be either paths to directoies containing `matrix.mtx`,
     `barcodes.tsv` and `features.tsv` files that can be loaded by
     [`Seurat::Read10X()`](https://satijalab.org/seurat/reference/read10x),
-    or paths to `h5` files that can be loaded by
+    or paths of loom files that can be loaded by `SeuratDisk::LoadLoom()`, or paths to
+    `h5` files that can be loaded by
     [`Seurat::Read10X_h5()`](https://satijalab.org/seurat/reference/read10x_h5).
 
     Each sample will be loaded individually and then merged into one `Seurat` object, and then perform QC.
@@ -110,9 +111,11 @@ class SeuratPreparing(Proc):
         min_cells (type=int): The minimum number of cells that a gene must be
             expressed in to be kept. This is used in `Seurat::CreateSeuratObject()`.
             Futher QC (`envs.cell_qc`, `envs.gene_qc`) will be performed after this.
+            It doesn't work when data is loaded from loom files.
         min_features (type=int): The minimum number of features that a cell must
             express to be kept. This is used in `Seurat::CreateSeuratObject()`.
             Futher QC (`envs.cell_qc`, `envs.gene_qc`) will be performed after this.
+            It doesn't work when data is loaded from loom files.
         cell_qc: Filter expression to filter cells, using
             `tidyrseurat::filter()`.
             Available QC keys include `nFeature_RNA`, `nCount_RNA`,
@@ -194,8 +197,8 @@ class SeuratPreparing(Proc):
 
         SCTransform (ns): Arguments for [`SCTransform()`](https://satijalab.org/seurat/reference/sctransform).
             `object` is specified internally, and `-` in the key will be replaced with `.`.
-            - `return-only-var-genes`: Whether to return only variable genes.
-            - `min_cells`: The minimum number of cells that a gene must be expressed in to be kept.
+            - return-only-var-genes: Whether to return only variable genes.
+            - min_cells: The minimum number of cells that a gene must be expressed in to be kept.
                 A hidden argument of `SCTransform` to filter genes.
                 If you try to keep all genes in the `RNA` assay, you can set `min_cells` to `0` and
                 `return-only-var-genes` to `False`.
@@ -488,7 +491,7 @@ class SeuratClusterStats(Proc):
 
         ```toml
         [SeuratClusterStats.envs.stats]
-        nCells_Sample = { group-by = "Sample" }
+        nCells_Sample = { group_by = "Sample" }
         ```
 
         ![nCells_Sample](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_nCells_Sample.png){: width="80%" }
@@ -512,8 +515,6 @@ class SeuratClusterStats(Proc):
         ```toml
         [SeuratClusterStats.envs.dimplots.Idents]
         label = true
-        label-box = true
-        repel = true
         ```
 
         ![dimplots](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_dimplots.png){: width="80%" }
@@ -587,9 +588,11 @@ class SeuratClusterStats(Proc):
         ngenes (type=json): The number of genes expressed in each cell.
             Keys are the names of the plots and values are the dicts inherited from `env.ngenes_defaults`.
         features_defaults (ns): The default parameters for `features`.
-            - features: The features to plot.
+            - features (type=auto): The features to plot.
                 It can be either a string with comma separated features, a list of features, a file path with `file://` prefix with features
                 (one per line), or an integer to use the top N features from `VariantFeatures(srtobj)`.
+                It can also be a dict with the keys as the feature group names and the values as the features, which
+                is used for heatmap to group the features.
             - order_by (type=auto): The order of the clusters to show on the plot.
                 An expression passed to `dplyr::arrange()` on the grouped meta data frame (by `ident`).
                 For example, you can order the clusters by the activation score of
@@ -1002,11 +1005,11 @@ class DimPlots(Proc):
 class MarkersFinder(Proc):
     """Find markers between different groups of cells
 
-    When only `group-by` is specified as `"seurat_clusters"` in
+    When only `group_by` is specified as `"seurat_clusters"` in
     `envs.cases`, the markers will be found for all the clusters.
 
     You can also find the differentially expressed genes between
-    any two groups of cells by setting `group-by` to a different
+    any two groups of cells by setting `group_by` to a different
     column name in metadata. Follow `envs.cases` for more details.
 
     Input:
@@ -1023,16 +1026,16 @@ class MarkersFinder(Proc):
             * Used in `future::plan(strategy = "multicore", workers = <ncores>)` to parallelize some Seurat procedures.
             * See also: <https://satijalab.org/seurat/articles/future_vignette.html>
         mutaters (type=json): The mutaters to mutate the metadata
-        group-by: The column name in metadata to group the cells.
-            If only `group-by` is specified, and `ident-1` and `ident-2` are
+        group_by: The column name in metadata to group the cells.
+            If only `group_by` is specified, and `ident-1` and `ident-2` are
             not specified, markers will be found for all groups in this column
             in the manner of "group vs rest" comparison.
             `NA` group will be ignored.
             If `None`, `Seurat::Idents(srtobj)` will be used, which is usually
             `"seurat_clusters"` after unsupervised clustering.
-        ident-1: The first group of cells to compare
-            When this is empty, the comparisons will be expanded to each group v.s. the rest of the cells in `group-by`.
-        ident-2: The second group of cells to compare
+        ident_1: The first group of cells to compare
+            When this is empty, the comparisons will be expanded to each group v.s. the rest of the cells in `group_by`.
+        ident_2: The second group of cells to compare
             If not provided, the rest of the cells are used for `ident-2`.
         each: The column name in metadata to separate the cells into different
             cases.
@@ -1082,6 +1085,16 @@ class MarkersFinder(Proc):
             - <more>: Other arguments passed to [`scplotter::FeatureStatPlot()`](https://pwwang.github.io/scplotter/reference/FeatureStatPlot.html).
         allmarker_plots (type=json): All marker plot cases.
             The keys are the names of the cases and the values are the dicts inherited from `allmarker_plots_defaults`.
+        allenrich_plots_defaults (ns): Default options for the plots to generate for the enrichment analysis.
+            - plot_type: The type of the plot.
+            - devpars (ns): The device parameters for the 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.
+            - <more>: See <https://pwwang.github.io/scplotter/reference/EnrichmentPlot.html>.
+        allenrich_plots (type=json): Cases of the plots to generate for the enrichment analysis.
+            The keys are the names of the cases and the values are the dicts inherited from `allenrich_plots_defaults`.
+            The cases under `envs.cases` can inherit this options.
         marker_plots_defaults (ns): Default options for the plots to generate for the markers.
             - plot_type: The type of the plot.
                 See <https://pwwang.github.io/scplotter/reference/FeatureStatPlot.html>.
@@ -1149,9 +1162,9 @@ class MarkersFinder(Proc):
     envs = {
         "ncores": config.misc.ncores,
         "mutaters": {},
-        "group-by": None,
-        "ident-1": None,
-        "ident-2": None,
+        "group_by": None,
+        "ident_1": None,
+        "ident_2": None,
         "each": None,
         "dbs": ["KEGG_2021_Human", "MSigDB_Hallmark_2020"],
         "sigmarkers": "p_val_adj < 0.05",
@@ -1170,6 +1183,11 @@ class MarkersFinder(Proc):
             "genes": 10,
         },
         "allmarker_plots": {},
+        "allenrich_plots_defaults": {
+            "plot_type": "heatmap",
+            "devpars": {"res": 100},
+        },
+        "allenrich_plots": {},
         "marker_plots_defaults": {
             "plot_type": None,
             "more_formats": [],
@@ -1221,11 +1239,11 @@ class TopExpressingGenes(Proc):
     Envs:
         mutaters (type=json): The mutaters to mutate the metadata
         ident: The group of cells to find the top expressing genes.
-            The cells will be selected by the `group-by` column with this
+            The cells will be selected by the `group_by` column with this
             `ident` value in metadata.
             If not provided, the top expressing genes will be found for all
-            groups of cells in the `group-by` column.
-        group-by: The column name in metadata to group the cells.
+            groups of cells in the `group_by` column.
+        group_by: The column name in metadata to group the cells.
         each: The column name in metadata to separate the cells into different
             cases.
         dbs (list): The dbs to do enrichment analysis for significant
@@ -1268,7 +1286,7 @@ class TopExpressingGenes(Proc):
     envs = {
         "mutaters": {},
         "ident": None,
-        "group-by": None,
+        "group_by": None,
         "each": None,
         "dbs": ["KEGG_2021_Human", "MSigDB_Hallmark_2020"],
         "n": 250,
@@ -1285,7 +1303,7 @@ class TopExpressingGenes(Proc):
         "cases": {},
     }
     plugin_opts = {
-        "report": "file://../reports/scrna/TopExpressingGenes.svelte",
+        "report": "file://../reports/common.svelte",
         "report_paging": 8,
     }
 
@@ -1589,9 +1607,9 @@ class ScFGSEA(Proc):
         mutaters (type=json): The mutaters to mutate the metadata.
             The key-value pairs will be passed the `dplyr::mutate()` to mutate the metadata.
 
-        group-by: The column name in metadata to group the cells.
-        ident-1: The first group of cells to compare
-        ident-2: The second group of cells to compare, if not provided, the rest of the cells that are not `NA`s in `group-by` column are used for `ident-2`.
+        group_by: The column name in metadata to group the cells.
+        ident_1: The first group of cells to compare
+        ident_2: The second group of cells to compare, if not provided, the rest of the cells that are not `NA`s in `group_by` column are used for `ident-2`.
         each: The column name in metadata to separate the cells into different subsets to do the analysis.
         subset: An expression to subset the cells.
         gmtfile: The pathways in GMT format, with the gene names/ids in the same format as the seurat object.
@@ -1617,6 +1635,15 @@ class ScFGSEA(Proc):
             If it is < 1, will apply it to `padj`, selecting pathways with `padj` < `top`.
         eps (type=float): This parameter sets the boundary for calculating the p value.
             See <https://rdrr.io/bioc/fgsea/man/fgseaMultilevel.html>
+        alleach_plots_defaults (ns): Default options for the plots to generate for all pathways.
+            - plot_type: The type of the plot, currently either dot or heatmap (default)
+            - devpars (ns): The device parameters for the 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.
+            - <more>: See <https://pwwang.github.io/biopipen.utils.R/reference/VizGSEA.html>.
+        alleach_plots (type=json): Cases of the plots to generate for all pathways.
+            The keys are the names of the cases and the values are the dicts inherited from `alleach_plots_defaults`.
         minsize (type=int): Minimal size of a gene set to test. All pathways below the threshold are excluded.
         maxsize (type=int): Maximal size of a gene set to test. All pathways above the threshold are excluded.
         rest (type=json;order=98): Rest arguments for [`fgsea()`](https://rdrr.io/bioc/fgsea/man/fgsea.html)
@@ -1639,23 +1666,28 @@ class ScFGSEA(Proc):
     envs = {
         "mutaters": {},
         "ncores": config.misc.ncores,
-        "group-by": None,
-        "ident-1": None,
-        "ident-2": None,
+        "group_by": None,
+        "ident_1": None,
+        "ident_2": None,
         "each": None,
         "subset": None,
-        "gmtfile": "",
+        "gmtfile": "KEGG_2021_Human",
         "method": "s2n",
         "top": 20,
         "minsize": 10,
         "maxsize": 100,
         "eps": 0,
+        "alleach_plots_defaults": {
+            "plot_type": "heatmap",
+            "devpars": {"res": 100},
+        },
+        "alleach_plots": {},
         "rest": {},
         "cases": {},
     }
     script = "file://../scripts/scrna/ScFGSEA.R"
     plugin_opts = {
-        "report": "file://../reports/scrna/ScFGSEA.svelte",
+        "report": "file://../reports/common.svelte",
         "report_paging": 8,
     }
 
@@ -2647,3 +2679,217 @@ class LoomTo10X(Proc):
     output = "outdir:dir:{{in.loomfile | stem}}.10X"
     lang = config.lang.rscript
     script = "file://../scripts/scrna/LoomTo10X.R"
+
+
+class PseudoBulkDEG(Proc):
+    """Pseduo-bulk differential gene expression analysis
+
+    This process performs differential gene expression analysis, instead of
+    on single-cell level, on the pseudo-bulk data, aggregated from the single-cell data.
+
+    Input:
+        sobjfile: The seurat object file in RDS or qs/qs2 format.
+
+    Output:
+        outdir: The output containing the results of the differential gene expression
+            analysis.
+
+    Envs:
+        mutaters (type=json): Mutaters to mutate the metadata of the
+            seurat object. Keys are the new column names and values are the
+            expressions to mutate the columns. These new columns can be
+            used to define your cases.
+        each: The column name in metadata to separate the cells into different cases.
+            When specified, the case will be expanded to multiple cases for
+            each value in the column.
+        subset: An expression in string to subset the cells.
+        aggregate_by: The column names in metadata to aggregate the cells.
+        layer: The layer to pull and aggregate the data.
+        assay: The assay to pull and aggregate the data.
+        error (flag): Error out if no/not enough markers are found or no pathways are enriched.
+            If `False`, empty results will be returned.
+        group_by: The column name in metadata to group the cells.
+        ident_1: The first identity to compare.
+        ident_2: The second identity to compare.
+            If not specified, the rest of the identities will be compared with `ident_1`.
+        paired_by: The column name in metadata to mark the paired samples.
+            For example, subject. If specified, the paired test will be performed.
+        dbs (list): The databases to use for enrichment analysis.
+            The databases are passed to `biopipen.utils::Enrichr()` to do the
+            enrichment analysis. The default databases are `KEGG_2021_Human` and
+            `MSigDB_Hallmark_2020`.
+            See <https://maayanlab.cloud/Enrichr/#libraries> for the available
+            libraries.
+        sigmarkers: An expression passed to `dplyr::filter()` to filter the
+            significant markers for enrichment analysis.
+            The default is `p_val_adj < 0.05`.
+            If `tool = 'DESeq2'`, the variables that can be used for filtering
+            are: `baseMean`, `log2FC`, `lfcSE`, `stat`, `p_val`, `p_val_adj`.
+            If `tool = 'edgeR'`, the variables that can be used for filtering
+            are: `logCPM`, `log2FC`, `LR`, `p_val`, `p_val_adj`.
+        enrich_style (choice): The style of the enrichment analysis.
+            - enrichr: Use `enrichr`-style for the enrichment analysis.
+            - clusterProfiler: Use `clusterProfiler`-style for the enrichment analysis.
+        allmarker_plots_defaults (ns): Default options for the plots for all markers when `ident-1` is not specified.
+            - plot_type: The type of the plot.
+                See <https://pwwang.github.io/scplotter/reference/FeatureStatPlot.html>.
+                Available types are `violin`, `box`, `bar`, `ridge`, `dim`, `heatmap` and `dot`.
+            - more_formats (type=list): The extra formats to save the plot in.
+            - save_code (flag): Whether to save the code to generate the plot.
+            - devpars (ns): The device parameters for the 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.
+            - order_by: an expression to order the markers, passed by `dplyr::arrange()`.
+            - genes: The number of top genes to show or an expression passed to `dplyr::filter()` to filter the genes.
+            - <more>: Other arguments passed to [`scplotter::FeatureStatPlot()`](https://pwwang.github.io/scplotter/reference/FeatureStatPlot.html).
+        allmarker_plots (type=json): All marker plot cases.
+            The keys are the names of the cases and the values are the dicts inherited from `allmarker_plots_defaults`.
+        allenrich_plots_defaults (ns): Default options for the plots to generate for the enrichment analysis.
+            - plot_type: The type of the plot.
+            - devpars (ns): The device parameters for the 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.
+            - <more>: See <https://pwwang.github.io/scplotter/reference/EnrichmentPlot.html>.
+        allenrich_plots (type=json): Cases of the plots to generate for the enrichment analysis.
+            The keys are the names of the cases and the values are the dicts inherited from `allenrich_plots_defaults`.
+            The cases under `envs.cases` can inherit this options.
+        marker_plots_defaults (ns): Default options for the plots to generate for the markers.
+            - plot_type: The type of the plot.
+                See <https://pwwang.github.io/scplotter/reference/FeatureStatPlot.html>.
+                Available types are `violin`, `box`, `bar`, `ridge`, `dim`, `heatmap` and `dot`.
+                There are two additional types available - `volcano_pct` and `volcano_log2fc`.
+            - more_formats (type=list): The extra formats to save the plot in.
+            - save_code (flag): Whether to save the code to generate the plot.
+            - devpars (ns): The device parameters for the 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.
+            - order_by: an expression to order the markers, passed by `dplyr::arrange()`.
+            - genes: The number of top genes to show or an expression passed to `dplyr::filter()` to filter the genes.
+            - <more>: Other arguments passed to [`scplotter::FeatureStatPlot()`](https://pwwang.github.io/scplotter/reference/FeatureStatPlot.html).
+                If `plot_type` is `volcano_pct` or `volcano_log2fc`, they will be passed to
+                [`scplotter::VolcanoPlot()`](https://pwwang.github.io/plotthis/reference/VolcanoPlot.html).
+        marker_plots (type=json): Cases of the plots to generate for the markers.
+            Plot cases. The keys are the names of the cases and the values are the dicts inherited from `marker_plots_defaults`.
+            The cases under `envs.cases` can inherit this options.
+        enrich_plots_defaults (ns): Default options for the plots to generate for the enrichment analysis.
+            - plot_type: The type of the plot.
+                See <https://pwwang.github.io/scplotter/reference/EnrichmentPlot.html>.
+                Available types are `bar`, `dot`, `lollipop`, `network`, `enrichmap` and `wordcloud`.
+            - more_formats (type=list): The extra formats to save the plot in.
+            - save_code (flag): Whether to save the code to generate the plot.
+            - devpars (ns): The device parameters for the 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.
+            - <more>: See <https://pwwang.github.io/scplotter/reference/EnrichmentPlot.htmll>.
+        enrich_plots (type=json): Cases of the plots to generate for the enrichment analysis.
+            The keys are the names of the cases and the values are the dicts inherited from `enrich_plots_defaults`.
+            The cases under `envs.cases` can inherit this options.
+        overlaps_defaults (ns): Default options for investigating the overlapping of significant markers between different cases or comparisons.
+            This means either `ident-1` should be empty, so that they can be expanded to multiple comparisons.
+            - sigmarkers: The expression to filter the significant markers for each case.
+                If not provided, `envs.sigmarkers` will be used.
+            - plot_type (choice): The type of the plot to generate for the overlaps.
+                - venn: Use `plotthis::VennDiagram()`.
+                - upset: Use `plotthis::UpsetPlot()`.
+            - more_formats (type=list): The extra formats to save the plot in.
+            - save_code (flag): Whether to save the code to generate the plot.
+            - devpars (ns): The device parameters for the 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.
+            - <more>: More arguments pased to `plotthis::VennDiagram()`
+                (<https://pwwang.github.io/plotthis/reference/venndiagram1.html>)
+                or `plotthis::UpsetPlot()`
+                (<https://pwwang.github.io/plotthis/reference/upsetplot1.html>)
+        overlaps (type=json): Cases for investigating the overlapping of significant markers between different cases or comparisons.
+            The keys are the names of the cases and the values are the dicts inherited from `overlaps_defaults`.
+            There are two situations that we can perform overlaps:
+            1. If `ident-1` is not specified, the overlaps can be performed between different comparisons.
+            2. If `each` is specified, the overlaps can be performed between different cases, where in each case, `ident-1` must be specified.
+        tool (choice): The method to use for the differential expression analysis.
+            - DESeq2: Use DESeq2 for the analysis.
+            - edgeR: Use edgeR for the analysis.
+        plots_defaults (ns): The default parameters for the plots.
+            - <more>: Parameters passed to `biopipen.utils::VizBulkDEGs()`.
+                See: <https://pwwang.github.io/biopipen.utils.R/reference/VizBulkDEGs.html>
+        plots (type=json): The parameters for the plots.
+            The keys are the names of the plots and the values are the parameters
+            for the plots. The parameters will override the defaults in `plots_defaults`.
+            If not specified, no plots will be generated.
+        cases (type=json): The cases for the analysis.
+            The keys are the names of the cases and the values are the arguments for
+            the analysis. The arguments include the ones inherited from `envs`.
+            If no cases are specified, a default case will be added with
+            the name `DEG Analysis` and the default values specified above.
+    """  # noqa: E501
+    input = "sobjfile:file"
+    output = "outdir:dir:{{in.sobjfile | stem}}.pseudobulk_deg"
+    lang = config.lang.rscript
+    script = "file://../scripts/scrna/PseudoBulkDEG.R"
+    envs = {
+        "mutaters": {},
+        "each": None,
+        "subset": None,
+        "aggregate_by": None,
+        "layer": "counts",
+        "assay": "RNA",
+        "error": True,
+        "group_by": None,
+        "ident_1": None,
+        "ident_2": None,
+        "paired_by": None,
+        "tool": "DESeq2",
+        "dbs": ["KEGG_2021_Human", "MSigDB_Hallmark_2020"],
+        "sigmarkers": "p_val_adj < 0.05",
+        "enrich_style": "enrichr",
+        "allmarker_plots_defaults": {
+            "plot_type": None,
+            "more_formats": [],
+            "save_code": False,
+            "devpars": {"res": 100},
+            "order_by": "desc(abs(log2FC))",
+            "genes": 10,
+        },
+        "allmarker_plots": {},
+        "allenrich_plots_defaults": {
+            "plot_type": "heatmap",
+            "devpars": {"res": 100},
+        },
+        "allenrich_plots": {},
+        "marker_plots_defaults": {
+            "plot_type": None,
+            "more_formats": [],
+            "save_code": False,
+            "devpars": {"res": 100},
+            "order_by": "desc(abs(log2FC))",
+            "genes": 10,
+        },
+        "marker_plots": {
+            "Volcano Plot": {"plot_type": "volcano"},
+        },
+        "enrich_plots_defaults": {
+            "more_formats": [],
+            "save_code": False,
+            "devpars": {"res": 100},
+        },
+        "enrich_plots": {
+            "Bar Plot": {"plot_type": "bar", "ncol": 1, "top_term": 10},
+        },
+        "overlaps_defaults": {
+            "sigmarkers": None,
+            "plot_type": "venn",
+            "more_formats": [],
+            "save_code": False,
+            "devpars": {"res": 100},
+        },
+        "overlaps": {},
+        "cases": {},
+    }
+    plugin_opts = {
+        "report": "file://../reports/common.svelte",
+        "report_paging": 8,
+    }

{biopipen-0.34.0 → biopipen-0.34.2}/biopipen/ns/tcr.py

@@ -1756,10 +1756,10 @@ class ScRepCombiningExpression(Proc):
             a custom variable in the data.
         chain: indicate if both or a specific chain should be used
             e.g. "both", "TRA", "TRG", "IGH", "IGL".
-        group-by: The column label in the combined clones in which clone frequency will
+        group_by: The column label in the combined clones in which clone frequency will
             be calculated. NULL or "none" will keep the format of input.data.
         proportion (flag): Whether to proportion (TRUE) or total frequency (FALSE) of
-            the clone based on the group.by variable.
+            the clone based on the group_by variable.
         filterNA (flag): Method to subset Seurat/SCE object of barcodes without clone
             information
         cloneSize (type=json): The bins for the grouping based on proportion or
@@ -1767,7 +1767,7 @@ class ScRepCombiningExpression(Proc):
             If proportion is FALSE and the cloneSizes are not set high enough based on
             frequency, the upper limit of cloneSizes will be automatically updated.
         addLabel (flag): This will add a label to the frequency header, allowing the
-            user to try multiple group.by variables or recalculate frequencies after
+            user to try multiple group_by variables or recalculate frequencies after
             subsetting the data.
     """
     input = "screpfile:file,srtobj:file"
@@ -1776,7 +1776,7 @@ class ScRepCombiningExpression(Proc):
     envs = {
         "cloneCall": "aa",
         "chain": "both",
-        "group-by": "Sample",
+        "group_by": "Sample",
         "proportion": True,
         "filterNA": False,
         "cloneSize": {