biopipen 0.27.2__tar.gz → 0.27.8__tar.gz

{biopipen-0.27.2 → biopipen-0.27.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.2
+Version: 0.27.8
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang
@@ -17,6 +17,6 @@ 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 (>=0.12,<0.13)
-Requires-Dist: pipen-poplog (>=0.1,<0.2)
+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)

biopipen-0.27.8/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.27.8"

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/core/filters.py

@@ -235,8 +235,8 @@ def _render_fgsea(
     with Path(cont["dir"]).joinpath("fgsea.txt").open() as f:
         next(f)  # skip header
         for line in f:
-            pathway, _ = line.split("\t", 1)
-            pathways.append(pathway)
+            items = line.strip().split("\t")
+            pathways.append((items[0], items[-1]))
             if len(pathways) >= n_pathways:
                 break
 
@@ -263,6 +263,7 @@ def _render_fgsea(
                         {
                             "kind": "table",
                             "src": str(Path(cont["dir"]).joinpath("fgsea.txt")),
+                            "data": {"excluded": {"slug"}},
                         }
                     ],
                 },
@@ -274,10 +275,10 @@ def _render_fgsea(
             "ui": "table_of_images",
             "contents": [
                 {
-                    "src": str(Path(cont["dir"]) / f"fgsea_{pw.replace('/', '-')}.png"),
+                    "src": str(Path(cont["dir"]) / f"fgsea_{slug}.png"),
                     "title": pw,
                 }
-                for pw in pathways
+                for pw, slug in pathways
             ]
         },
     ]

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/core/testing.py

@@ -3,7 +3,7 @@ import tempfile
 from functools import wraps
 from pathlib import Path
 
-from pipen import Pipen, plugin
+from pipen import Pipen
 
 TESTING_INDEX_INIT = 1
 TESTING_PARENT_DIR = Path(tempfile.gettempdir())
@@ -40,26 +40,16 @@ def _get_test_dirs(testfile, new):
     return name, workdir, outdir
 
 
-class PipelineSucceeded:
-    """A plugin to check if the pipeline succeeded"""
-
-    name = "succeeded"
-    version = "0.1.0"
-
-    @plugin.impl
-    async def on_complete(pipen, succeeded):
-        pipen._succeeded = succeeded
-
-
-def get_pipeline(testfile, loglevel="debug", **kwargs):
+def get_pipeline(testfile, loglevel="debug", enable_report=False, **kwargs):
     """Get a pipeline for a test file"""
     name, workdir, outdir = _get_test_dirs(testfile, False)
+    report_plugin_prefix = "+" if enable_report else "-"
     kws = {
         "name": name,
         "workdir": workdir,
         "outdir": outdir,
         "loglevel": loglevel,
-        "plugins": [PipelineSucceeded, "-report"],
+        "plugins": [f"{report_plugin_prefix}report"],
     }
     kws.update(kwargs)
     return Pipen(**kws)

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/ns/delim.py

@@ -113,7 +113,7 @@ class SampleInfo(Proc):
         "exclude_cols": None,
         "defaults": {
             "on": "Sample",
-            "distinct": None,
+            # "distinct": None,
             "group": None,
             "na_group": False,
             "each": None,

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/ns/plot.py

@@ -114,3 +114,39 @@ class Heatmap(Proc):
         "globals": "",
     }
     script = "file://../scripts/plot/Heatmap.R"
+
+
+class ROC(Proc):
+    """Plot ROC curve using [`plotROC`](https://cran.r-project.org/web/packages/plotROC/vignettes/examples.html).
+
+    Input:
+        infile: The input file for data, tab-separated.
+            The first column should be ids of the records (this is optional if `envs.noids` is True).
+            The second column should be the labels of the records (1 for positive, 0 for negative).
+            If they are not binary, you can specify the positive label by `envs.pos_label`.
+            From the third column, it should be the scores of the different models.
+
+    Output:
+        outfile: The output figure file
+
+    Envs:
+        noids: Whether the input file has ids (first column) or not.
+        pos_label: The positive label.
+        ci: Whether to use `geom_rocci()` instead of `geom_roc()`.
+        devpars: The parameters for `png()`
+        args: Additional arguments for `geom_roc()` or `geom_rocci()` if `envs.ci` is True.
+        style_roc: Arguments for `style_roc()`
+    """  # noqa: E501
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}.roc.png"
+    lang = config.lang.rscript
+    envs = {
+        "noids": False,
+        "pos_label": 1,
+        "ci": False,
+        "devpars": {"res": 100, "width": 750, "height": 600},
+        "args": {"labels": False},
+        "style_roc": {},
+        "show_auc": True,
+    }
+    script = "file://../scripts/plot/ROC.R"

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/ns/scrna.py

@@ -122,6 +122,9 @@ class SeuratPreparing(Proc):
             genes.
             ///
 
+        cell_qc_per_sample (flag): Whether to perform cell QC per sample or not.
+            If `True`, the cell QC will be performed per sample, and the QC will be
+            applied to each sample before merging.
         gene_qc (ns): Filter genes.
             `gene_qc` is applied after `cell_qc`.
             - min_cells: The minimum number of cells that a gene must be
@@ -201,6 +204,13 @@ class SeuratPreparing(Proc):
                 - scvi: Same as `scVIIntegration`.
             - <more>: See <https://satijalab.org/seurat/reference/integratelayers>
 
+        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.
+
     Requires:
         r-seurat:
             - check: {{proc.lang}} <(echo "library(Seurat)")
@@ -215,6 +225,7 @@ class SeuratPreparing(Proc):
     envs = {
         "ncores": config.misc.ncores,
         "cell_qc": None,  # "nFeature_RNA > 200 & percent.mt < 5",
+        "cell_qc_per_sample": False,
         "gene_qc": {"min_cells": 0, "excludes": []},
         "use_sct": False,
         "no_integration": False,
@@ -227,6 +238,7 @@ class SeuratPreparing(Proc):
             "min_cells": 5,
         },
         "IntegrateLayers": {"method": "harmony"},
+        "DoubletFinder": {"PCs": 0, "pN": 0.25, "doublets": 0.075},
     }
     script = "file://../scripts/scrna/SeuratPreparing.R"
     plugin_opts = {
@@ -405,7 +417,7 @@ class SeuratClusterStats(Proc):
         nCells_All = { }
         ```
 
-        ![nCells_All](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_nCells_All.png){: width="80%" }
+        ![nCells_All](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_nCells_All.png){: width="80%" }
 
         ### Number of cells in each cluster by groups
 
@@ -414,7 +426,7 @@ class SeuratClusterStats(Proc):
         nCells_Sample = { group-by = "Sample" }
         ```
 
-        ![nCells_Sample](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_nCells_Sample.png){: width="80%" }
+        ![nCells_Sample](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_nCells_Sample.png){: width="80%" }
 
         ### Violin plots for the gene expressions
 
@@ -427,8 +439,8 @@ class SeuratClusterStats(Proc):
         vlnplots_1 = { features = ["FOXP3", "IL2RA"], pt-size = 0, kind = "vln" }
         ```
 
-        ![vlnplots](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_vlnplots.png){: width="80%" }
-        ![vlnplots_1](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_vlnplots_1.png){: width="80%" }
+        ![vlnplots](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_vlnplots.png){: width="80%" }
+        ![vlnplots_1](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_vlnplots_1.png){: width="80%" }
 
         ### Dimension reduction plot with labels
 
@@ -439,7 +451,7 @@ class SeuratClusterStats(Proc):
         repel = true
         ```
 
-        ![dimplots](https://pwwang.github.io/immunopipe/processes/images/SeuratClusterStats_dimplots.png){: width="80%" }
+        ![dimplots](https://pwwang.github.io/immunopipe/latest/processes/images/SeuratClusterStats_dimplots.png){: width="80%" }
 
     Input:
         srtobj: The seurat object loaded by `SeuratClustering`
@@ -849,7 +861,7 @@ class CellsDistribution(Proc):
         group_order = [ "Tumor", "Normal" ]
         ```
 
-        ![CellsDistribution_example](https://pwwang.github.io/immunopipe/processes/images/CellsDistribution_example.png)
+        ![CellsDistribution_example](https://pwwang.github.io/immunopipe/latest/processes/images/CellsDistribution_example.png)
 
     Input:
         srtobj: The seurat object in RDS format
@@ -1229,7 +1241,7 @@ class TopExpressingGenes(Proc):
     }
 
 
-class ExprImpution(Proc):
+class ExprImputation(Proc):
     """This process imputes the dropout values in scRNA-seq data.
 
     It takes the Seurat object as input and outputs the Seurat object with
@@ -1305,13 +1317,13 @@ class ExprImpution(Proc):
         },
         "alra_args": {},
     }
-    script = "file://../scripts/scrna/ExprImpution.R"
+    script = "file://../scripts/scrna/ExprImputation.R"
 
 
 class SCImpute(Proc):
     """Impute the dropout values in scRNA-seq data.
 
-    Deprecated. Use `ExprImpution` instead.
+    Deprecated. Use `ExprImputation` instead.
 
     Input:
         infile: The input file for imputation
@@ -1475,14 +1487,17 @@ class SeuratTo10X(Proc):
         srtobj: The seurat object in RDS
 
     Output:
-        outdir: The output directory
+        outdir: The output directory.
+            When `envs.split_by` is specified, the subdirectories will be
+            created for each distinct value of the column.
+            Otherwise, the matrices will be written to the output directory.
 
     Envs:
         version: The version of 10X format
     """
     input = "srtobj:file"
     output = "outdir:dir:{{in.srtobj | stem}}"
-    envs = {"version": "3"}
+    envs = {"version": "3", "split_by": None}
     lang = config.lang.rscript
     script = "file://../scripts/scrna/SeuratTo10X.R"
 
@@ -1754,13 +1769,18 @@ class SeuratMap2Ref(Proc):
         sobjfile: The seurat object
 
     Output:
-        outfile: The rds file of seurat object with cell type annotated
+        outfile: The rds file of seurat object with cell type annotated.
+            Note that the reduction name will be `ref.umap` for the mapping.
+            To visualize the mapping, you should use `ref.umap` as the reduction name.
 
     Envs:
         ncores (type=int;order=-100): Number of cores to use.
-            Used in `future::plan(strategy = "multicore", workers = <ncores>)`
+            When `split_by` is used, this will be the number of cores for each object to map to the reference.
+            When `split_by` is not used, this is used in `future::plan(strategy = "multicore", workers = <ncores>)`
             to parallelize some Seurat procedures.
-            See also: <https://satijalab.org/seurat/articles/future_vignette.html>
+            See also: <https://satijalab.org/seurat/archive/v3.0/future_vignette.html>
+        mutaters (type=json): The mutaters to mutate the metadata.
+            This is helpful when we want to create new columns for `split_by`.
         use: A column name of metadata from the reference
             (e.g. `celltype.l1`, `celltype.l2`) to transfer to the query as the
             cell types (ident) for downstream analysis. This field is required.
@@ -1772,16 +1792,29 @@ class SeuratMap2Ref(Proc):
             `Seurat::LoadH5Seurat()`.
             The file type is determined by the extension. `.rds` or `.RDS` for
             RDS file, `.h5seurat` or `.h5` for h5seurat file.
+        refnorm (choice): Normalization method the reference used. The same method will be used for the query.
+            - NormalizeData: Using [`NormalizeData`](https://satijalab.org/seurat/reference/normalizedata).
+            - SCTransform: Using [`SCTransform`](https://satijalab.org/seurat/reference/sctransform).
+            - auto: Automatically detect the normalization method.
+                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.
         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?
             - do-center (flag): Whether to center residuals to have mean zero?
             - <more>: See <https://satijalab.org/seurat/reference/sctransform>.
                 Note that the hyphen (`-`) will be transformed into `.` for the keys.
+        NormalizeData (ns): Arguments for [`NormalizeData()`](https://satijalab.org/seurat/reference/normalizedata)
+            - normalization-method: Normalization method.
+            - <more>: See <https://satijalab.org/seurat/reference/normalizedata>.
+                Note that the hyphen (`-`) will be transformed into `.` for the keys.
         FindTransferAnchors (ns): Arguments for [`FindTransferAnchors()`](https://satijalab.org/seurat/reference/findtransferanchors)
             - normalization-method (choice): Name of normalization method used.
                 - LogNormalize: Log-normalize the data matrix
                 - SCT: Scale data using the SCTransform method
+                - auto: Automatically detect the normalization method.
+                    See `envs.refnorm`.
             - reference-reduction: Name of dimensional reduction to use from the reference if running the pcaproject workflow.
                 Optionally enables reuse of precomputed reference dimensional reduction.
             - <more>: See <https://satijalab.org/seurat/reference/findtransferanchors>.
@@ -1807,14 +1840,19 @@ class SeuratMap2Ref(Proc):
         "ncores": config.misc.ncores,
         "use": None,
         "ident": "seurat_clusters",
+        "mutaters": {},
         "ref": None,
+        "refnorm": "auto",
+        "split_by": None,
         "SCTransform": {
             "do-correct-umi": False,
             "do-scale": False,
             "do-center": True,
         },
+        "NormalizeData": {
+            "normalization-method": "LogNormalize",
+        },
         "FindTransferAnchors": {
-            "normalization-method": "SCT",
             "reference-reduction": "spca",
         },
         "MapQuery": {
@@ -1862,7 +1900,7 @@ class RadarPlots(Proc):
 
         Then we will have a radar plots like this:
 
-        ![Radar plots](https://pwwang.github.io/immunopipe/processes/images/RadarPlots-default.png)
+        ![Radar plots](https://pwwang.github.io/immunopipe/latest/processes/images/RadarPlots-default.png)
 
         We can use `each` to separate the cells into different cases:
 
@@ -1874,7 +1912,7 @@ class RadarPlots(Proc):
 
         Then we will have two radar plots, one for `Pre` and one for `Post`:
 
-        ![Radar plots](https://pwwang.github.io/immunopipe/processes/images/RadarPlots-each.png)
+        ![Radar plots](https://pwwang.github.io/immunopipe/latest/processes/images/RadarPlots-each.png)
 
         Using `cluster_order` to change the order of the clusters and show only the first 3 clusters:
 
@@ -1885,7 +1923,7 @@ class RadarPlots(Proc):
         breaks = [0, 50, 100]  # also change the breaks
         ```
 
-        ![Radar plots cluster_order](https://pwwang.github.io/immunopipe/processes/images/RadarPlots-cluster_order.png)
+        ![Radar plots cluster_order](https://pwwang.github.io/immunopipe/latest/processes/images/RadarPlots-cluster_order.png)
 
 
         /// Attention

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/ns/scrna_metabolic_landscape.py

@@ -22,11 +22,11 @@ class MetabolicPathwayActivity(Proc):
     For each subset, a heatmap and a violin plot will be generated.
     The heatmap shows the pathway activities for each group and each metabolic pathway
 
-    ![MetabolicPathwayActivity_heatmap](https://pwwang.github.io/immunopipe/processes/images/MetabolicPathwayActivity_heatmap.png){: width="80%"}
+    ![MetabolicPathwayActivity_heatmap](https://pwwang.github.io/immunopipe/latest/processes/images/MetabolicPathwayActivity_heatmap.png){: width="80%"}
 
     The violin plot shows the distribution of the pathway activities for each group
 
-    ![MetabolicPathwayActivity_violin](https://pwwang.github.io/immunopipe/processes/images/MetabolicPathwayActivity_violin.png){: width="45%"}
+    ![MetabolicPathwayActivity_violin](https://pwwang.github.io/immunopipe/latest/processes/images/MetabolicPathwayActivity_violin.png){: width="45%"}
 
     Envs:
         ntimes (type=int): Number of times to do the permutation
@@ -294,7 +294,7 @@ class MetabolicPathwayHeterogeneity(Proc):
     The heterogeneity can be reflected by the NES values and the p-values in
     different groups for the metabolic pathways.
 
-    ![MetabolicPathwayHeterogeneity](https://pwwang.github.io/immunopipe/processes/images/MetabolicPathwayHeterogeneity.png)
+    ![MetabolicPathwayHeterogeneity](https://pwwang.github.io/immunopipe/latest/processes/images/MetabolicPathwayHeterogeneity.png)
 
 
     Envs:
@@ -566,8 +566,8 @@ class ScrnaMetabolicLandscape(ProcGroup):
             input_data = lambda ch: tibble(
                 srtobj=ch.iloc[:, 0],
                 metafile=[None],
-                mutaters=[self.opts.mutaters],
             )
+            envs = {"mutaters": self.opts.mutaters}
 
         return MetabolicSeuratMetadataMutater
 
@@ -577,10 +577,10 @@ class ScrnaMetabolicLandscape(ProcGroup):
         if self.opts.noimpute:
             return self.p_mutater
 
-        from .scrna import ExprImpution
+        from .scrna import ExprImputation
 
         @annotate.format_doc(indent=3)
-        class MetabolicExprImpution(ExprImpution):
+        class MetabolicExprImputation(ExprImputation):
             """{{Summary}}
 
             You can turn off the imputation by setting the `noimpute` option
@@ -588,7 +588,7 @@ class ScrnaMetabolicLandscape(ProcGroup):
             """
             requires = self.p_mutater
 
-        return MetabolicExprImpution
+        return MetabolicExprImputation
 
     @ProcGroup.add_proc
     def p_pathway_activity(self) -> Type[Proc]:

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/ns/snp.py

@@ -71,3 +71,68 @@ class PlinkSimulation(Proc):
         "sample_prefix": None,
     }
     script = "file://../scripts/snp/PlinkSimulation.py"
+
+
+class MatrixEQTL(Proc):
+    """Run Matrix eQTL
+
+    See also <https://www.bios.unc.edu/research/genomic_software/Matrix_eQTL/>
+
+    Input:
+        geno: Genotype matrix file with rows representing SNPs and columns
+            representing samples.
+        expr: Expression matrix file with rows representing genes and columns
+            representing samples.
+        cov: Covariate matrix file with rows representing covariates and columns
+            representing samples.
+
+    Output:
+        alleqtls: Matrix eQTL output file
+        cisqtls: The cis-eQTL file if `snppos` and `genepos` are provided.
+            Otherwise it'll be empty.
+
+    Envs:
+        model (choice): The model to use.
+            - `linear`: Linear model
+            - `modelLINEAR`: Same as `linear`
+            - `anova`: ANOVA model
+            - `modelANOVA`: Same as `anova`
+        pval (type=float): P-value threshold for eQTLs
+        transp (type=float): P-value threshold for trans-eQTLs.
+            If cis-eQTLs are not enabled (`snppos` and `genepos` are not set),
+            this defaults to 1e-5.
+            If cis-eQTLs are enabled, this defaults to `None`, which will disable
+            trans-eQTL analysis.
+        fdr (flag): Do FDR calculation or not (save memory if not).
+        snppos: The path of the SNP position file.
+            It could be a BED, GFF, VCF or a tab-delimited file with
+            `snp`, `chr`, `pos` as the first 3 columns.
+        genepos: The path of the gene position file.
+            It could be a BED or GFF file.
+        dist (type=int): Distance threshold for cis-eQTLs.
+        transpose_geno (flag): If set, the genotype matrix (`in.geno`)
+            will be transposed.
+        transpose_expr (flag): If set, the expression matrix (`in.expr`)
+            will be transposed.
+        transpose_cov (flag): If set, the covariate matrix (`in.cov`)
+            will be transposed.
+    """
+    input = "geno:file, expr:file, cov:file"
+    output = [
+        "alleqtls:file:{{in.geno | stem}}.alleqtls.txt",
+        "cisqtls:file:{{in.geno | stem}}.cisqtls.txt",
+    ]
+    lang = config.lang.rscript
+    envs = {
+        "model": "linear",
+        "pval": 1e-3,
+        "transp": None,
+        "fdr": False,
+        "snppos": None,
+        "genepos": config.ref.refgene,
+        "dist": 250000,
+        "transpose_geno": False,
+        "transpose_expr": False,
+        "transpose_cov": False,
+    }
+    script = "file://../scripts/snp/MatrixEQTL.R"

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/ns/tcr.py

@@ -923,7 +923,7 @@ class CloneResidency(Proc):
 
     - Residency plots showing the residency of clones in the two groups
 
-        ![CloneResidency_residency](https://pwwang.github.io/immunopipe/processes/images/CloneResidency.png)
+        ![CloneResidency_residency](https://pwwang.github.io/immunopipe/latest/processes/images/CloneResidency.png)
 
         The points in the plot are jittered to avoid overplotting. The x-axis is the residency in the first group and
         the y-axis is the residency in the second group. The size of the points are relative to the normalized size of
@@ -943,7 +943,7 @@ class CloneResidency(Proc):
 
     - Venn diagrams showing the overlap of the clones in the two groups
 
-        ![CloneResidency_venn](https://pwwang.github.io/immunopipe/processes/images/CloneResidency_venn.png){: width="60%"}
+        ![CloneResidency_venn](https://pwwang.github.io/immunopipe/latest/processes/images/CloneResidency_venn.png){: width="60%"}
 
     Input:
         immdata: The data loaded by `immunarch::repLoad()`
@@ -1259,7 +1259,7 @@ class TCRClusterStats(Proc):
         by = "Sample"
         ```
 
-        ![Cluster_size](https://pwwang.github.io/immunopipe/processes/images/TCRClusteringStats_cluster_size.png){: width="80%"}
+        ![Cluster_size](https://pwwang.github.io/immunopipe/latest/processes/images/TCRClusteringStats_cluster_size.png){: width="80%"}
 
         ### Shared clusters
 
@@ -1269,7 +1269,7 @@ class TCRClusterStats(Proc):
         heatmap_meta = ["region"]
         ```
 
-        ![Shared_clusters](https://pwwang.github.io/immunopipe/processes/images/TCRClusteringStats_shared_clusters.png){: width="80%"}
+        ![Shared_clusters](https://pwwang.github.io/immunopipe/latest/processes/images/TCRClusteringStats_shared_clusters.png){: width="80%"}
 
         ### Sample diversity
 
@@ -1278,11 +1278,11 @@ class TCRClusterStats(Proc):
         method = "gini"
         ```
 
-        ![Sample_diversity](https://pwwang.github.io/immunopipe/processes/images/TCRClusteringStats_sample_diversity.png){: width="80%"}
+        ![Sample_diversity](https://pwwang.github.io/immunopipe/latest/processes/images/TCRClusteringStats_sample_diversity.png){: width="80%"}
 
         Compared to the sample diversity using TCR clones:
 
-        ![Sample_diversity](https://pwwang.github.io/immunopipe/processes/images/Immunarch_sample_diversity.png){: width="80%"}
+        ![Sample_diversity](https://pwwang.github.io/immunopipe/latest/processes/images/Immunarch_sample_diversity.png){: width="80%"}
 
     Input:
         immfile: The immunarch object with TCR clusters attached

{biopipen-0.27.2 → biopipen-0.27.8}/biopipen/scripts/delim/SampleInfo.R

@@ -113,14 +113,14 @@ for (name in names(stats)) {
     if (stat$plot == "boxplot" || stat$plot == "box") {
         p <- ggplot(data, aes(x=!!group, y=!!sym(stat$on), fill=!!group)) +
             geom_boxplot(position = "dodge") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             xlab("")
     } else if (stat$plot == "violin" ||
                stat$plot == "violinplot" ||
                stat$plot == "vlnplot") {
         p <- ggplot(data, aes(x = !!group, y = !!sym(stat$on), fill=!!group)) +
             geom_violin(position = "dodge") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             xlab("")
     } else if (
         (grepl("violin", stat$plot) || grepl("vln", stat$plot)) &&
@@ -129,12 +129,12 @@ for (name in names(stats)) {
         p <- ggplot(data, aes(x = !!group, y = !!sym(stat$on), fill = !!group)) +
             geom_violin(position = "dodge") +
             geom_boxplot(width = 0.1, position = position_dodge(0.9), fill="white") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             xlab("")
     } else if (stat$plot == "histogram" || stat$plot == "hist") {
         p <- ggplot(data, aes(x = !!sym(stat$on), fill = !!group)) +
             geom_histogram(bins = 10, position = "dodge", alpha = 0.8, color = "white") +
-            scale_fill_biopipen()
+            scale_fill_biopipen(alpha = .6)
     } else if (stat$plot == "pie" || stat$plot == "piechart") {
         if (is.null(stat$each)) {
             data <- data %>% distinct(!!group, .keep_all = TRUE)
@@ -157,7 +157,7 @@ for (name in names(stats)) {
                 fill="#EEEEEE",
                 size=4
             ) +
-            scale_fill_biopipen(name = group) +
+            scale_fill_biopipen(alpha = .6, name = group) +
             ggtitle(paste0("# ", stat$on))
     } else if (stat$plot == "bar" || stat$plot == "barplot") {
         if (is.null(stat$each)) {
@@ -169,7 +169,7 @@ for (name in names(stats)) {
             data,
             aes(x = !!group, y = !!sym(count_on), fill = !!group)) +
             geom_bar(stat = "identity") +
-            scale_fill_biopipen() +
+            scale_fill_biopipen(alpha = .6) +
             ylab(paste0("# ", stat$on))
     } else {
         stop("Unknown plot type: ", stat$plot)