biopipen 0.34.2__py3-none-any.whl → 0.34.3__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.34.2"
+__version__ = "0.34.3"

biopipen/ns/scrna.py

@@ -531,6 +531,8 @@ class SeuratClusterStats(Proc):
     Envs:
         mutaters (type=json): The mutaters to mutate the metadata to subset the cells.
             The mutaters will be applied in the order specified.
+            You can also use the clone selectors to select the TCR clones/clusters.
+            See <https://pwwang.github.io/scplotter/reference/clone_selectors.html>.
         cache (type=auto): Whether to cache the plots.
             Currently only plots for features are supported, since creating the those
             plots can be time consuming.
@@ -564,6 +566,7 @@ class SeuratClusterStats(Proc):
                 - res (type=int): The resolution of the plots.
                 - height (type=int): The height of the plots.
                 - width (type=int): The width of the plots.
+            - descr: The description of the plot, showing in the report.
             - more_formats (type=list): The formats to save the plots other than `png`.
             - save_code (flag): Whether to save the code to reproduce the plot.
             - save_data (flag): Whether to save the data used to generate the plot.
@@ -655,6 +658,7 @@ class SeuratClusterStats(Proc):
         "clustrees": {},
         "stats_defaults": {
             "subset": None,
+            "descr": None,
             "devpars": {"res": 100},
             "more_formats": [],
             "save_code": False,
@@ -663,10 +667,12 @@ class SeuratClusterStats(Proc):
         "stats": {
             "Number of cells in each cluster (Bar Chart)": {
                 "plot_type": "bar",
+                "x_text_angle": 90,
             },
             "Number of cells in each cluster by Sample (Bar Chart)": {
                 "plot_type": "bar",
                 "group_by": "Sample",
+                "x_text_angle": 90,
             },
         },
         "ngenes_defaults": {
@@ -698,7 +704,6 @@ class SeuratClusterStats(Proc):
         "dimplots": {
             "Dimensional reduction plot": {
                 "label": True,
-                "label_insitu": True,
             },
         },
     }
@@ -1025,7 +1030,9 @@ class MarkersFinder(Proc):
         ncores (type=int): Number of cores to use for parallel computing for some `Seurat` procedures.
             * 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
+        mutaters (type=json): The mutaters to mutate the metadata.
+            You can also use the clone selectors to select the TCR clones/clusters.
+            See <https://pwwang.github.io/scplotter/reference/clone_selectors.html>.
         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
@@ -1237,7 +1244,9 @@ class TopExpressingGenes(Proc):
         outdir: The output directory for the tables and plots
 
     Envs:
-        mutaters (type=json): The mutaters to mutate the metadata
+        mutaters (type=json): The mutaters to mutate the metadata.
+            You can also use the clone selectors to select the TCR clones/clusters.
+            See <https://pwwang.github.io/scplotter/reference/clone_selectors.html>.
         ident: The group of cells to find the top expressing genes.
             The cells will be selected by the `group_by` column with this
             `ident` value in metadata.
@@ -1606,6 +1615,8 @@ class ScFGSEA(Proc):
             Passed to `nproc` of `fgseaMultilevel()`.
         mutaters (type=json): The mutaters to mutate the metadata.
             The key-value pairs will be passed the `dplyr::mutate()` to mutate the metadata.
+            You can also use the clone selectors to select the TCR clones/clusters.
+            See <https://pwwang.github.io/scplotter/reference/clone_selectors.html>.
 
         group_by: The column name in metadata to group the cells.
         ident_1: The first group of cells to compare
@@ -2699,6 +2710,8 @@ class PseudoBulkDEG(Proc):
             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.
+            You can also use the clone selectors to select the TCR clones/clusters.
+            See <https://pwwang.github.io/scplotter/reference/clone_selectors.html>.
         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.

biopipen/ns/scrna_metabolic_landscape.py

@@ -165,7 +165,7 @@ class MetabolicFeatures(Proc):
             `1`, `2` and `3` in the `group_by` column, we could have
             `comparisons = ["1", "2"]`, which will compare the group `1` with groups
             `2` and `3`, and the group `2` with groups `1` and `3`. We could also
-            have `comparisons = ["1,2", "1,3"]`, which will compare the group `1` with
+            have `comparisons = ["1:2", "1:3"]`, which will compare the group `1` with
             group `2` and group `1` with group `3`.
         fgsea_args (type=json): Other arguments for the `fgsea::fgsea()` function.
             For example, `{"minSize": 15, "maxSize": 500}`.

biopipen/ns/tcr.py

@@ -1749,6 +1749,11 @@ class ScRepCombiningExpression(Proc):
 
     Output:
         outfile: The `Seurat` object with the TCR/BCR data combined
+            In addition to the meta columns added by
+            `scRepertoire::combineExpression()`, a new column `TCR_Presence` will be
+            added to the metadata. It indicates whether the cell has a TCR/BCR
+            sequence or not. The value is `TRUE` if the cell has a TCR/BCR sequence,
+            and `FALSE` otherwise.
 
     Envs:
         cloneCall: How to call the clone - VDJC gene (gene), CDR3 nucleotide (nt),

biopipen/reports/scrna_metabolic_landscape/MetabolicFeatures.svelte

@@ -34,15 +34,15 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
 
 <UnorderedList>
 <ListItem>
-    <a href="../MetabolicPathwayActivity/index.html">MetabolicPathwayActivity</a>
+    <a href="?proc=MetabolicPathwayActivity" class="listitem">MetabolicPathwayActivity</a>
     <Tile><p>Investigating the metabolic pathways of the cells in different subsets and groups.</p></Tile>
 </ListItem>
 <ListItem>
-    <a href="../MetabolicPathwayHeterogeneity/index.html">MetabolicPathwayHeterogeneity</a>
+    <a href="?proc=MetabolicPathwayHeterogeneity" class="listitem">MetabolicPathwayHeterogeneity</a>
     <Tile><p>Showing metabolic pathways enriched in genes with highest contribution to the metabolic heterogeneities</p></Tile>
 </ListItem>
 <ListItem>
-    MetabolicFeatures (this page)
+    <span class="listitem">MetabolicFeatures (this page)</span>
     <Tile>
     <p>Gene set enrichment analysis against the metabolic pathways for comparisons by different groups in different subsets.</p>
     <p>The metabolic features are actual gene set enrichment analysis (GSEA) results for the metabolic pathways with given comparisons.</p>
@@ -59,3 +59,12 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
 {%- endmacro -%}
 
 {{ report_jobs(jobs, head_job, report_job) }}
+
+<style>
+.listitem {
+    font-size: large;
+    font-weight: bold;
+    margin: 1rem 0 0.5rem 0;
+    display: inline-block;
+}
+</style>

biopipen/reports/scrna_metabolic_landscape/MetabolicPathwayActivity.svelte

@@ -34,7 +34,7 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
 
 <UnorderedList>
 <ListItem>
-    MetabolicPathwayActivity (this page)
+    <span class="listitem">MetabolicPathwayActivity (this page)</span>
     <Tile>
         <p>Investigating the metabolic pathways of the cells in different subsets and groups.</p>
         <p>The cells are first subset by subsets and then the metabolic activities are examined for each groups in different subsets.</p>
@@ -69,13 +69,13 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
     </Tile>
 </ListItem>
 <ListItem>
-    <a href="../MetabolicPathwayHeterogeneity/index.html">MetabolicPathwayHeterogeneity</a>
+    <a href="?proc=MetabolicPathwayHeterogeneity" class="listitem">MetabolicPathwayHeterogeneity</a>
     <Tile>
         <p>Showing metabolic pathways enriched in genes with highest contribution to the metabolic heterogeneities</p>
     </Tile>
 </ListItem>
 <ListItem>
-    <a href="../MetabolicFeatures/index.html">MetabolicFeatures</a>
+    <a href="?proc=MetabolicFeatures" class="listitem">MetabolicFeatures</a>
     <Tile>
         <p>Gene set enrichment analysis against the metabolic pathways for comparisons by different groups in different subsets.</p>
     </Tile>
@@ -91,3 +91,12 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
 {%- endmacro -%}
 
 {{ report_jobs(jobs, head_job, report_job) }}
+
+<style>
+.listitem {
+    font-size: large;
+    font-weight: bold;
+    margin: 1rem 0 0.5rem 0;
+    display: inline-block;
+}
+</style>

biopipen/reports/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.svelte

@@ -34,13 +34,13 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
 
 <UnorderedList>
 <ListItem>
-    <a href="../MetabolicPathwayActivity/index.html">MetabolicPathwayActivity</a>
+    <a href="?proc=MetabolicPathwayActivity" class="listitem">MetabolicPathwayActivity</a>
     <Tile>
     <p>Investigating the metabolic pathways of the cells in different subsets and groups.</p>
     </Tile>
 </ListItem>
 <ListItem>
-    MetabolicPathwayHeterogeneity (this page)
+    <span class="listitem">MetabolicPathwayHeterogeneity (this page)</span>
     <Tile>
     <p>Showing metabolic pathways enriched in genes with highest contribution to the metabolic heterogeneities</p>
     <p>
@@ -54,7 +54,7 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
     </Tile>
 </ListItem>
 <ListItem>
-    <a href="../MetabolicFeatures/index.html">MetabolicFeatures</a>
+    <a href="?proc=MetabolicFeatures" class="listitem">MetabolicFeatures</a>
     <Tile>
     <p>Gene set enrichment analysis against the metabolic pathways for comparisons by different groups in different subsets.</p>
     </Tile>
@@ -70,3 +70,12 @@ The cells are grouped at 2 dimensions: `subset_by`, usually the clinic groups th
 {%- endmacro -%}
 
 {{ report_jobs(jobs, head_job, report_job) }}
+
+<style>
+.listitem {
+    font-size: large;
+    font-weight: bold;
+    margin: 1rem 0 0.5rem 0;
+    display: inline-block;
+}
+</style>

biopipen/scripts/scrna/CellTypeAnnotation-celltypist.R

@@ -26,15 +26,8 @@ if (is.null(celltypist_args$model)) {
 }
 dir.create(file.path(outdir, "data", "models"), recursive = TRUE, showWarnings = FALSE)
 modelfile <- file.path(outdir, "data", "models", basename(celltypist_args$model))
-if (!file.exists(modelfile)) {
-    file.symlink(celltypist_args$model, modelfile)
-} else {
-    real_modelfile <- normalizePath(Sys.readlink(modelfile))
-    if (real_modelfile != normalizePath(celltypist_args$model)) {
-        file.remove(modelfile)
-        file.symlink(celltypist_args$model, modelfile)
-    }
-}
+suppressWarnings(file.remove(modelfile))
+file.symlink(normalizePath(celltypist_args$model), modelfile)
 
 sobj <- NULL
 if (!endsWith(sobjfile, ".h5ad")) {
@@ -43,7 +36,7 @@ if (!endsWith(sobjfile, ".h5ad")) {
         # find the default ident name in meta.data
         for (col in colnames(sobj@meta.data)) {
             if (!is.factor(sobj@meta.data[[col]])) { next }
-            if (isTRUE(all.equal(Idents(sobj), sobj@meta.data[[col]]))) {
+            if (isTRUE(all.equal(unname(Idents(sobj)), sobj@meta.data[[col]]))) {
                 celltypist_args$over_clustering <- col
                 break
             }

biopipen/scripts/scrna/SeuratClusterStats-clustree.R

@@ -26,6 +26,22 @@ if (
     if (length(clustrees) == 0) {
         log$warn("- no case found, skipping ...")
     } else {
+        reporter$add(
+            list(
+                kind = "descr",
+                content = 'The clustree plots displays clustering results from the Seurat object across different
+                resolutions of the clustering algorithm
+                (<a target="_blank" href="https://satijalab.org/seurat/reference/findclusters">Seurat::FindClusters</a>).
+                Each node represents a cluster, with the resolution levels labeled along the vertical (y) axis.
+                The size of each node reflects the number of cells in that cluster. Edges connect clusters between
+                adjacent resolutions and indicate how cells transition between clusters as resolution increases.
+                The thickness of the edges corresponds to the proportion of shared cells (in_prop) between clusters,
+                where darker lines signify a higher overlap (up to 100%). The color of the edges indicates the actual
+                number of cells that transitioned between clusters.'
+            ),
+            h1 = "Clustree plots"
+        )
+
         reports <- list()
         for (name in names(clustrees)) {
             if (is.null(clustrees[[name]]$prefix)) {

biopipen/scripts/scrna/SeuratClusterStats-dimplots.R

@@ -40,7 +40,7 @@ do_one_dimplot = function(name) {
     reporter$add(
         list(
             kind = "descr",
-            content = paste0("Dimensionality reduction plot for ", case$group.by)
+            content = paste0("Dimensionality reduction plot for ", case$group_by)
         ),
         reporter$image(prefix, "pdf", FALSE),
         h1 = name

biopipen/scripts/scrna/SeuratClusterStats-features.R

@@ -64,11 +64,11 @@ do_one_features <- function(name) {
     log$info("- Case: {name}")
 
     case <- list_update(features_defaults, features[[name]])
-    case$descr <- case$descr %||% ""
     case <- extract_vars(
         case,
         "devpars", "more_formats", "save_code", "save_data", "order_by",
-        "subset", "features", "descr")
+        "subset", "features", "descr",
+        allow_nonexisting = TRUE)
 
     if (!is.null(subset)) {
         case$object <- srtobj %>% filter(!!parse_expr(subset))
@@ -77,6 +77,7 @@ do_one_features <- function(name) {
     }
 
     if (exists("order_by") && !is.null(order_by)) {
+        case$ident <- case$ident %||% GetIdentityColumn(case$object)
         if (length(order_by) < 2) {
             clusters <- case$object@meta.data %>%
                 group_by(!!sym(case$ident)) %>%
@@ -126,12 +127,34 @@ do_one_features <- function(name) {
         caching$save(info$prefix)
     }
     # add reports
-    if (!is.null(descr) && nchar(descr) > 0) {
-        reporter$add2(
-            list(kind = "descr", content = descr),
-            hs = c(info$section, info$name)
+    default_descr <- glue(
+        "The plot shows the distribution or pattern of the specified features ({paste(case$features %||% features, collapse = ', ')}) ",
+        "across cells",
+        "{if (!is.null(case$ident)) glue(', identified by \"{case$ident}\"') else ''}",
+        "{if (!is.null(case$group_by)) glue(', grouped by \"{case$group_by}\"') else ''}",
+        "{if (!is.null(case$split_by)) glue(', and split by \"{case$split_by}\"') else ''}. ",
+        "The plot type is '{case$plot_type}', ",
+        "{if (case$plot_type == 'dim') 'displaying the features on a dimensional reduction embedding' ",
+        " else if (case$plot_type == 'heatmap') 'arranged as a heatmap by rows_name and other grouping variables' ",
+        " else if (case$plot_type %in% c('violin', 'box', 'ridge')) 'showing the distribution of feature values by the grouping variables' ",
+        " else if (case$plot_type == 'cor') 'showing the correlation between features' ",
+        " else 'showing aggregated feature values by the grouping variables'}. ",
+        "{if (!is.null(case$facet_by)) glue('Plots are further faceted by \"{case$facet_by}\". ') else ''}",
+        "{if (case$plot_type == 'dim') glue('The reduction used is \"{if (!is.null(case$reduction)) case$reduction else DefaultDimReduc(case$object)}\"') else ''}",
+        "{if (case$plot_type == 'dim' && !is.null(case$graph)) glue(', with graph \"{case$graph}\" drawn to show cell neighbor edges') else ''}",
+        "{if (case$plot_type == 'dim' && !is.null(case$bg_cutoff) && case$bg_cutoff > 0) glue(', and a background cutoff of {case$bg_cutoff}') else ''}",
+        "{if (case$plot_type == 'dim') glue(', using dimensions {paste(case$dims %||% 1:2, collapse = \",\")}') else ''}"
+    )
+    if (!is.null(case$comparisons)) {
+        default_descr <- paste0(
+            default_descr,
+            "Statistical comparisons were performed between groups using '{case$pairwise_method %||% 'wilcox.test'}' method."
         )
     }
+    reporter$add2(
+        list(kind = "descr", content = descr %||% default_descr),
+        hs = c(info$section, info$name)
+    )
 
     if (save_data) {
         reporter$add2(

biopipen/scripts/scrna/SeuratClusterStats-stats.R

@@ -5,17 +5,26 @@ log$info("stats:")
 odir <- file.path(outdir, "stats")
 dir.create(odir, recursive=TRUE, showWarnings=FALSE)
 
+
+
 do_one_stats <- function(name) {
     log$info("- Case: {name}")
 
     case <- list_update(stats_defaults, stats[[name]])
-    extract_vars(case, "devpars", "more_formats", "save_code", "save_data", "subset")
+    case <- extract_vars(case, "devpars", "more_formats", "save_code", "save_data", "subset", "descr")
 
     if (!is.null(subset)) {
         case$object <- srtobj %>% filter(!!parse_expr(subset))
     } else {
         case$object <- srtobj
     }
+    ident <- case$ident %||% GetIdentityColumn(case$object)
+    groupings <- unique(c(case$group_by, case$rows_by, case$columns_by, case$pie_group_by, ident))
+    if (length(groupings) > 0) {
+        for (g in groupings) {
+            case$object <- filter(case$object, !is.na(!!sym(g)))
+        }
+    }
 
     info <- case_info(name, odir, is_dir = FALSE, create = TRUE)
     p <- do_call(gglogger::register(CellStatPlot), case)
@@ -27,6 +36,20 @@ do_one_stats <- function(name) {
             auto_data_setup = FALSE)
     }
 
+    frac <- case$frac %||% "none"
+    default_descr <- glue(
+        "The {case$plot_type} plot shows the distribution of cells across categories defined by '{ident}'",
+        "{if (!is.null(case$group_by)) glue(', grouped by {case$group_by}') else ''}",
+        "{if (!is.null(case$split_by)) glue(', and split by {case$split_by}') else ''}. ",
+        "The values represent ",
+        "{if (frac == 'none') 'the number of cells' else glue('the fraction of cells calculated by \"{frac}\"')}. "
+    )
+    if (!is.null(case$comparisons)) {
+        default_descr <- paste0(
+            default_descr,
+            "Statistical comparisons were performed between groups using '{case$pairwise_method %||% 'wilcox.test'}' method."
+        )
+    }
     if (save_data) {
         pdata <- attr(p, "data") %||% p$data
         if (!inherits(pdata, "data.frame") && !inherits(pdata, "matrix")) {
@@ -37,6 +60,10 @@ do_one_stats <- function(name) {
             list(
                 name = "Plot",
                 contents = list(
+                    list(
+                        kind = "descr",
+                        content = case$descr %||% default_descr
+                    ),
                     reporter$image(
                         info$prefix, more_formats, save_code, kind = "image")
                 )
@@ -60,6 +87,7 @@ do_one_stats <- function(name) {
         )
     } else {
         reporter$add2(
+            list(kind = "descr", content = case$descr %||% default_descr),
             reporter$image(info$prefix, more_formats, save_code, kind = "image"),
             hs = c(info$section, info$name)
         )

biopipen/scripts/scrna/SeuratClusterStats.R

@@ -3,6 +3,7 @@ library(rlang)
 library(dplyr)
 library(tidyr)
 library(tibble)
+library(glue)
 library(forcats)
 library(tidyseurat)
 library(gglogger)

biopipen/scripts/scrna/celltypist-wrapper.py

@@ -29,6 +29,8 @@ if __name__ == "__main__":
         raise ValueError(
             f"Over clustering column '{over_clustering}' not found in AnnData object."
         )
+    if 'neighbors' in adata.uns and 'params' in adata.uns['neighbors']:
+        adata.uns['neighbors']['params'].setdefault('n_neighbors', 15)
 
     annotated = celltypist.annotate(
         adata,

biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R

@@ -98,7 +98,13 @@ do_comparison <- function(object, caseinfo, subset_by, subset_val, group_by, gro
     }
 
     classes <- as.character(object@meta.data[[group_by]])
-    classes[classes != group1] <- "_REST"
+    if (!group1 %in% classes) {
+        stop("Group '", group1, "' not found in '", group_by, "' column of the Seurat object.")
+    }
+    if (!is.null(group2) && !group2 %in% classes) {
+        stop("Group '", group2, "' not found in '", group_by, "' column of the Seurat object.")
+    }
+    classes[classes != group1] <- "Other"
     if (any(table(classes) < 5)) {
         msg <- paste0(
             "  ! skipped. Group has less than 5 cells: ",
@@ -266,8 +272,8 @@ do_subset <- function(object, caseinfo, subset_by, subset_val, group_by, compari
             rbind, lapply(
                 as.character(comparisons),
                 function(comparison) {
-                    if (grepl(",", comparison)) {
-                        group1 <- trimws(unlist(strsplit(comparison, ",")))
+                    if (grepl(":", comparison)) {
+                        group1 <- trimws(unlist(strsplit(comparison, ":")))
                         group2 <- group1[2]
                         group1 <- group1[1]
                     } else {

biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R

@@ -315,8 +315,8 @@ do_subset <- function(
             plotargs$keep_empty <- TRUE
 
             p <- do_call(plotfn, plotargs)
-            devpars$width <- devpars$width %||% (attr(p, "width") * devpars$res) %||% 1000
-            devpars$height <- devpars$height %||% (attr(p, "height") * devpars$res) %||% 1000
+            devpars$width <- devpars$width %||% (attr(p, "width") * 2 * devpars$res) %||% 1000
+            devpars$height <- devpars$height %||% (attr(p, "height") * 2 * devpars$res) %||% 1000
         } else {  # heatmap
             minval <- min(dat)
             maxval <- max(dat)

biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R

@@ -195,6 +195,7 @@ do_subset <- function(object, caseinfo, subset_by, subset_val, group_by, plots,
         plotprefix <- file.path(odir, slugify(plot))
         plotargs$devpars$width <- plotargs$devpars$width %||% (attr(p, "width") * plotargs$devpars$res) %||% 800
         plotargs$devpars$height <- plotargs$devpars$height %||% (attr(p, "height") * plotargs$devpars$res) %||% 600
+        plotargs$devpars$height <- max(plotargs$devpars$height, plotargs$devpars$width / 1.5)
         png(
             filename = paste0(plotprefix, ".png"),
             width = plotargs$devpars$width,

biopipen/scripts/tcr/GIANA/GIANA4.py

@@ -36,9 +36,6 @@ from sklearn.manifold import MDS
 import faiss
 from query import *
 try:
-    from Bio.SubsMat.MatrixInfo import blosum62
-    print(blosum62)
-except ModuleNotFoundError:
     from Bio.Align import substitution_matrices
     blosum62 = substitution_matrices.load("BLOSUM62")
     _tmp = {}
@@ -46,7 +43,8 @@ except ModuleNotFoundError:
         for ab2 in blosum62.alphabet:
             _tmp[(ab1, ab2)] = int(blosum62[(ab1, ab2)])
     blosum62 = _tmp
-    print(blosum62)
+except ModuleNotFoundError:
+    from Bio.SubsMat.MatrixInfo import blosum62
 
 AAstring = "ACDEFGHIKLMNPQRSTVWY"
 AAstringList = list(AAstring)

biopipen/scripts/tcr/ScRepCombiningExpression.R

@@ -34,6 +34,7 @@ obj <- combineExpression(
     cloneSize = unlist(cloneSize),
     addLabel = addLabel
 )
+obj$TCR_Presence <- !is.na(obj$CTaa)
 
 log$info("Saving combined object ...")
 save_obj(obj, outfile)

biopipen/scripts/tcr/ScRepLoading.R

@@ -118,8 +118,13 @@ load_contig <- function(input, sample, fmt) {
     fmt <- dirfmt[[2]]
     if (is.null(dir)) { return(NULL) }
     x <- loadContigs(dir, format = fmt %||% "10X")
-    x[[1]]$sample <- NULL
-    x[[1]]
+    x <- x[[1]]
+    x$sample <- NULL
+    if (identical(fmt %||% "10X", "10X") && colnames(x)[1] == "X") {
+        x$X <- NULL
+    }
+
+    x
 }
 
 

biopipen/scripts/tcr/TCRClustering.R

@@ -130,11 +130,10 @@ output.clusters_df.to_csv(clustcr_dir + "/clusters.txt", sep="\t", index=False)
     clustcr_file
 }
 
-clean_clustcr_output = function(clustcr_outfile, clustcr_input) {
+clean_clustcr_output = function(clustcr_outfile) {
     clustcr_out = read.delim2(clustcr_outfile, header=TRUE, row.names = NULL)
     colnames(clustcr_out) = c("CDR3.aa", "TCR_Cluster")
-    in_cdr3 = read.delim2(clustcr_input, header=TRUE, row.names = NULL)
-    out = left_join(in_cdr3, distinct(clustcr_out), by=c("CDR3.aa")) %>%
+    out = left_join(cdr3aa_df, distinct(clustcr_out), by=c(cdr3seq4clustering = "CDR3.aa")) %>%
         mutate(
             TCR_Cluster = if_else(
                 is.na(TCR_Cluster),
@@ -170,7 +169,7 @@ run_clustcr = function() {
         quit(status=rc)
     }
     clustcr_outfile = file.path(clustcr_dir, "clusters.txt")
-    clean_clustcr_output(clustcr_outfile, clustcr_input)
+    clean_clustcr_output(clustcr_outfile)
 }
 
 prepare_giana = function() {
@@ -193,21 +192,8 @@ prepare_giana = function() {
 }
 
 prepare_input = function() {
-    # prepare input file for GIANA
-    cdr3 = c()
-    # cdr3col = if (!on_multi) "cdr3" else "CDR3.aa"
-    cdr3col = "CDR3.aa"
-    for (sample in names(seqdata)) {
-        sdata = seqdata[[sample]]
-        if (on_multi) {
-            sdata[[cdr3col]] = sub(";", "", sdata[[cdr3col]])
-        } else if ("chain" %in% colnames(sdata)) {
-            sdata = sdata %>% separate_rows(chain, cdr3col, sep = ";") %>%
-                filter(chain == "TRB")
-        }
-        cdr3 = union(cdr3, unique(sdata[[cdr3col]]))
-    }
-    cdr3 = unique(cdr3)
+    cdr3aa_df$cdr3seq4clustering <<- gsub("[^A-Z]", "", cdr3aa_df$CDR3.aa)  # Remove non-amino acid characters
+    cdr3 <- unique(cdr3aa_df$cdr3seq4clustering)
 
     # cdr3 = distinct(cdr3, aminoAcid, vMaxResolved)
 
@@ -220,15 +206,14 @@ prepare_input = function() {
     cdr3file
 }
 
-clean_giana_output = function(giana_outfile, giana_infile) {
+clean_giana_output = function(giana_outfile) {
     # generate an output file with columns:
     # CDR3.aa, TCR_Cluster, V.name, Sample
     # If sequence doesn't exist in the input file,
     # Then a unique cluster id is assigned to it.
     giana_out = read.delim2(giana_outfile, header=FALSE, comment.char = "#", row.names = NULL)[, 1:2, drop=FALSE]
     colnames(giana_out) = c("CDR3.aa", "TCR_Cluster")
-    in_cdr3 = read.delim2(giana_infile, header=TRUE, row.names = NULL)
-    out = left_join(in_cdr3, distinct(giana_out), by=c("CDR3.aa")) %>%
+    out = left_join(cdr3aa_df, distinct(giana_out), by=c(cdr3seq4clustering = "CDR3.aa")) %>%
         mutate(
             TCR_Cluster = if_else(
                 is.na(TCR_Cluster),
@@ -283,10 +268,11 @@ run_giana = function() {
         quit(status=rc)
     }
     giana_outfile = file.path(giana_outdir, "cdr3--RotationEncodingBL62.txt")
-    clean_giana_output(giana_outfile, giana_input)
+    clean_giana_output(giana_outfile)
 }
 
 attach_to_obj = function(obj, out) {
+    out <- as.data.frame(out)
     rownames(out) <- out$Barcode
     if (is_seurat) {
         # Attach results to Seurat object

biopipen/scripts/tcr/TESSA.R

@@ -39,9 +39,11 @@ log$info("Preparing TCR input file ...")
 # If immfile endswith .rds, then it is an immunarch object
 tcrdata <- sobj@meta.data %>%
     rownames_to_column("contig_id") %>%
+    select(contig_id, CTaa, CTgene, sample = Sample) %>%
     filter(!is.na(CTaa) & !is.na(CTgene)) %>%
-    separate(CTaa, into = c(NA, "cdr3"), sep = "_", remove = FALSE) %>%
-    separate(CTgene, into = c(NA, "vjgene"), sep = "_", remove = FALSE) %>%
+    separate(CTaa, into = c(NA, "cdr3"), sep = "_", remove = TRUE) %>%
+    filter(!is.na(cdr3) & cdr3 != "NA" & cdr3 != "nan") %>%
+    separate(CTgene, into = c(NA, "vjgene"), sep = "_", remove = TRUE) %>%
     separate(vjgene, into = c("v_gene", NA, "j_gene", NA), sep = "\\.", remove = TRUE) %>%
     mutate(v_gene = sub("-\\d+$", "", v_gene), j_gene = sub("-\\d+$", "", j_gene))
 

{biopipen-0.34.2.dist-info → biopipen-0.34.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: biopipen
-Version: 0.34.2
+Version: 0.34.3
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang