biopipen 0.26.0__tar.gz → 0.26.1__tar.gz

{biopipen-0.26.0 → biopipen-0.26.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.26.0
+Version: 0.26.1
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.26.1/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.26.1"

{biopipen-0.26.0 → biopipen-0.26.1}/biopipen/ns/scrna.py

@@ -483,14 +483,18 @@ class SeuratClusterStats(Proc):
             The parameters from the cases can overwrite the default parameters.
             - frac (flag): Whether to output the fraction of cells instead of number.
             - pie (flag): Also output a pie chart?
+            - circos (flag): Also output a circos plot?
             - table (flag): Whether to output a table (in tab-delimited format) and in the report.
             - frac_ofall(flag): Whether to output the fraction against all cells,
                 instead of the fraction in each group.
+                Does not work for circos plot.
                 Only works when `frac` is `True` and `group-by` is specified.
             - transpose (flag): Whether to transpose the cluster and group, that is,
                 using group as the x-axis and cluster to fill the plot.
+                For circos plot, when transposed, the arrows will be drawn from the idents (by `ident`) to the
+                the groups (by `group-by`).
                 Only works when `group-by` is specified.
-            - position (choice): The position of the bars.
+            - position (choice): The position of the bars. Does not work for pie and circos plots.
                 - stack: Use `position_stack()`.
                 - fill: Use `position_fill()`.
                 - dodge: Use `position_dodge()`.
@@ -499,8 +503,13 @@ class SeuratClusterStats(Proc):
             - group-by: The column name in metadata to group the cells.
                 Does NOT support for pie charts.
             - split-by: The column name in metadata to split the cells into different plots.
+                Does NOT support for circos plots.
             - subset: An expression to subset the cells, will be passed to
                 `dplyr::filter()` on metadata.
+            - circos_devpars (ns): The device parameters for the circos 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.
             - pie_devpars (ns): The device parameters for the pie charts.
                 - res (type=int): The resolution of the plots.
                 - height (type=int): The height of the plots.
@@ -634,6 +643,7 @@ class SeuratClusterStats(Proc):
         "stats_defaults": {
             "frac": False,
             "pie": False,
+            "circos": False,
             "table": False,
             "position": "auto",
             "frac_ofall": False,
@@ -644,6 +654,7 @@ class SeuratClusterStats(Proc):
             "subset": None,
             "devpars": {"res": 100, "height": 600, "width": 800},
             "pie_devpars": {"res": 100, "height": 600, "width": 800},
+            "circos_devpars": {"res": 100, "height": 600, "width": 600},
         },
         "stats": {
             "Number of cells in each cluster": {
@@ -1142,6 +1153,7 @@ class TopExpressingGenes(Proc):
             markers See below for all libraries.
             <https://maayanlab.cloud/Enrichr/#libraries>
         n (type=int): The number of top expressing genes to find.
+        subset: An expression to subset the cells for each case.
         cases (type=json): If you have multiple cases, you can specify them
             here. The keys are the names of the cases and the values are the
             above options except `mutaters`. If some options are
@@ -1162,6 +1174,7 @@ class TopExpressingGenes(Proc):
         "section": "DEFAULT",
         "dbs": ["KEGG_2021_Human", "MSigDB_Hallmark_2020"],
         "n": 250,
+        "subset": None,
         "cases": {},
     }
     plugin_opts = {

{biopipen-0.26.0 → biopipen-0.26.1}/biopipen/scripts/scrna/CellsDistribution.R

@@ -372,6 +372,7 @@ do_case <- function(name, case) {
         # heatmaps
         log_debug("  Preparing pie charts ...")
         hmd <- m %>%
+            arrange(!!sym(case$group_by), !!sym(cby)) %>%
             mutate(!!sym(cby) := paste0("[", !!sym(case$group_by), "] ", !!sym(cby))) %>%
             select(!!sym(cby), CloneGroupClusterSize, seurat_clusters) %>%
             distinct(!!sym(cby), seurat_clusters, .keep_all = TRUE) %>%
@@ -426,6 +427,9 @@ do_case <- function(name, case) {
     if (length(cells_by) == 1) {
         hmsplits <- NULL
         extra_width <- extra_width - 15
+    } else {
+        # keep the row order
+        hmrowlbls <- factor(hmrowlbls, levels = unique(hmrowlbls))
     }
 
     col_fun <- colorRamp2(c(0, max(hmdata, na.rm = T)), c("lightyellow", "purple"))

{biopipen-0.26.0 → biopipen-0.26.1}/biopipen/scripts/scrna/SeuratClusterStats-stats.R

@@ -1,4 +1,5 @@
 # Loaded variables: srtfile, outdir, srtobj
+library(circlize)
 
 stats_defaults = {{envs.stats_defaults | r: todot="-"}}
 stats = {{envs.stats | r: todot="-", skip=1}}
@@ -12,6 +13,7 @@ do_one_stats = function(name) {
     case = list_update(stats_defaults, stats[[name]])
     case$devpars = list_update(stats_defaults$devpars, case$devpars)
     case$pie_devpars = list_update(stats_defaults$pie_devpars, case$pie_devpars)
+    case$circos_devpars = list_update(stats_defaults$circos_devpars, case$circos_devpars)
     if (isTRUE(case$pie) && !is.null(case$group.by)) {
         stop(paste0(name, ": pie charts are not supported for group-by"))
     }
@@ -27,6 +29,7 @@ do_one_stats = function(name) {
 
     figfile = file.path(odir, paste0(slugify(name), ".bar.png"))
     piefile = file.path(odir, paste0(slugify(name), ".pie.png"))
+    circosfile = file.path(odir, paste0(slugify(name), ".circos.png"))
     samtablefile = file.path(odir, paste0(slugify(name), ".bysample.txt"))
     tablefile = file.path(odir, paste0(slugify(name), ".txt"))
 
@@ -172,6 +175,40 @@ do_one_stats = function(name) {
             ui = "tabs"
         )
     }
+
+    if (isTRUE(case$circos)) {
+        if (isTRUE(case$transpose)) {
+            circos_df <- plot_df %>%
+                select(from=!!sym(case$ident), to=!!sym(case$group.by), value=.n)
+        } else {
+            circos_df <- plot_df %>%
+                select(from=!!sym(case$group.by), to=!!sym(case$ident), value=.n)
+        }
+
+        png(
+            circosfile,
+            width=case$circos_devpars$width,
+            height=case$circos_devpars$height,
+            res=case$circos_devpars$res
+        )
+        circos.clear()
+        chordDiagram(
+            circos_df,
+            direction = 1,
+            direction.type = c("diffHeight", "arrows"),
+            link.arr.type = "big.arrow"
+        )
+        dev.off()
+
+        add_report(
+            list(
+                name = "Circos plot",
+                contents = list(list(kind = "image", src = circosfile))
+            ),
+            h1 = name,
+            ui = "tabs"
+        )
+    }
 }
 
 sapply(names(stats), do_one_stats)

{biopipen-0.26.0 → biopipen-0.26.1}/biopipen/scripts/scrna/TopExpressingGenes.R

@@ -20,6 +20,7 @@ prefix_each <- {{ envs.prefix_each | r }}
 section <- {{ envs.section | r }}
 dbs <- {{ envs.dbs | r }}
 n <- {{ envs.n | r }}
+sset <- {{ envs.subset | r }}
 cases <- {{ envs.cases | r: todot = "-" }}  # nolint
 
 set.seed(8525)
@@ -43,7 +44,8 @@ if (is.null(cases) || length(cases) == 0) {
             prefix_each = prefix_each,
             section = section,
             dbs = dbs,
-            n = n
+            n = n,
+            subset = sset
         )
     )
 } else {
@@ -56,7 +58,8 @@ if (is.null(cases) || length(cases) == 0) {
             prefix_each = prefix_each,
             section = section,
             dbs = dbs,
-            n = n
+            n = n,
+            subset = sset
         )
     })
 }
@@ -144,7 +147,7 @@ casename_info <- function(casename, create = FALSE) {
 }
 
 do_enrich <- function(expr, odir) {
-    log_info("  Saving expressions ...")
+    log_debug("  Saving expressions ...")
     expr <- expr %>% as.data.frame()
     colnames(expr) <- c("Expression")
     expr <- expr %>% rownames_to_column("Gene") %>% select(Gene, Expression)
@@ -165,7 +168,7 @@ do_enrich <- function(expr, odir) {
         quote = FALSE
     )
 
-    log_info("  Running enrichment ...")
+    log_debug("  Running enrichment ...")
     enriched <- enrichr(head(expr$Gene, n), dbs)  # nolint
     for (db in dbs) {
         write.table(
@@ -178,7 +181,7 @@ do_enrich <- function(expr, odir) {
         )
 
         if (nrow(enriched[[db]]) == 0) {
-            log_info(paste0("  No enriched terms for ", db))
+            log_warn(paste0("  No enriched terms for ", db))
             next
         }
 
@@ -199,15 +202,24 @@ do_case <- function(casename) {
     case <- cases[[casename]]
     info <- casename_info(casename, create = TRUE)
 
-    log_info("  Calculating average expression ...")
-    assay <- DefaultAssay(srtobj)
+    log_debug("  Calculating average expression ...")
+    if (!is.null(case$subset)) {
+        tryCatch({
+            sobj <- subset(srtobj, !!parse_expr(case$subset))
+        }, error = function(e) {
+            log_warn("  No cells found for the subset, skipping ...")
+        })
+    } else {
+        sobj <- srtobj
+    }
+    assay <- DefaultAssay(sobj)
     avgexpr <- AverageExpression(
-        srtobj,
+        sobj,
         group.by = case$group.by,
         assays = assay
     )[[assay]]
     # https://github.com/satijalab/seurat/issues/7893
-    colnames(avgexpr) <- as.character(unique(srtobj@meta.data[[case$group.by]]))
+    colnames(avgexpr) <- as.character(unique(sobj@meta.data[[case$group.by]]))
     avgexpr <- avgexpr[, case$ident, drop = FALSE]
     avgexpr <- avgexpr[order(-avgexpr), , drop = FALSE]
 
@@ -217,7 +229,7 @@ do_case <- function(casename) {
 }
 
 add_case_report <- function(info) {
-    log_info("  Adding case report ...")
+    log_debug("  Adding case report ...")
     h1 = ifelse(
         info$section == "DEFAULT",
         info$case,
@@ -237,30 +249,43 @@ add_case_report <- function(info) {
         ifelse(single_section, "#", info$case)
     )
 
-    add_report(
-        list(
-            kind = "descr",
-            content = paste0("Top ", n, " expressing genes")
-        ),
-        list(
-            kind = "table",
-            src = file.path(info$casedir, "exprn.txt")
-        ),
-        h1 = h1,
-        h2 = ifelse(h2 == "#", "Top Expressing Genes", h2),
-        h3 = ifelse(h2 == "#", "#", "Top Expressing Genes")
-    )
+    if (!is.null(info$error)) {
+        add_report(
+            list(
+                kind = "descr",
+                content = paste0("Top ", n, " expressing genes")
+            ),
+            list(kind = "error", content = info$error),
+            h1 = h1,
+            h2 = ifelse(h2 == "#", "Top Expressing Genes", h2),
+            h3 = ifelse(h2 == "#", "#", "Top Expressing Genes")
+        )
+    } else {
+        add_report(
+            list(
+                kind = "descr",
+                content = paste0("Top ", n, " expressing genes")
+            ),
+            list(
+                kind = "table",
+                src = file.path(info$casedir, "exprn.txt")
+            ),
+            h1 = h1,
+            h2 = ifelse(h2 == "#", "Top Expressing Genes", h2),
+            h3 = ifelse(h2 == "#", "#", "Top Expressing Genes")
+        )
 
-    add_report(
-        list(
-            kind = "descr",
-            content = paste0("Enrichment analysis for the top ", n, " expressing genes")
-        ),
-        list(kind = "enrichr", dir = info$casedir),
-        h1 = h1,
-        h2 = ifelse(h2 == "#", "Enrichment Analysis", h2),
-        h3 = ifelse(h2 == "#", "#", "Enrichment Analysis")
-    )
+        add_report(
+            list(
+                kind = "descr",
+                content = paste0("Enrichment analysis for the top ", n, " expressing genes")
+            ),
+            list(kind = "enrichr", dir = info$casedir),
+            h1 = h1,
+            h2 = ifelse(h2 == "#", "Enrichment Analysis", h2),
+            h3 = ifelse(h2 == "#", "#", "Enrichment Analysis")
+        )
+    }
 }
 
 sapply(sort(names(cases)), do_case)

{biopipen-0.26.0 → biopipen-0.26.1}/biopipen/scripts/tcr/CloneResidency.R

@@ -329,6 +329,7 @@ plot_venndg <- function(counts, groups, singletons) {
 
 plot_upset <- function(counts, singletons) {
     query_singleton <- function(row) { row["Singletons"] == "true" }
+    query_multiplet <- function(row) { rep(TRUE, length(row)) }
 
     cnts <- column_to_rownames(counts, "CDR3.aa") %>%
         mutate(across(everything(), ~ as.integer(as.logical(.x))))
@@ -342,6 +343,14 @@ plot_upset <- function(counts, singletons) {
     sets <- make.names(sets)
 
     upset(cnts, sets = sets, query.legend = "top", sets.x.label = "# clones", queries = list(
+        list(
+            # in order to add legend
+            # actually mark all, but singleton will override
+            query = query_multiplet,
+            color = "#3b3b3b",
+            active = TRUE,
+            query.name = "Multiplets"
+        ),
         list(
             query = query_singleton,
             color = "orange",

{biopipen-0.26.0 → biopipen-0.26.1}/biopipen/utils/misc.R

@@ -29,6 +29,25 @@ bQuote <- function(x) {
 #' @param tolower Convert to lowercase
 #' @return A slugified string
 slugify <- function(x, non_alphanum_replace="-", collapse_replace=TRUE, tolower=FALSE) {
+    subs <- list(
+        "š"="s", "œ"="oe", "ž"="z", "ß"="ss", "þ"="y", "à"="a", "á"="a", "â"="a",
+        "ã"="a", "ä"="a", "å"="a", "æ"="ae", "ç"="c", "è"="e", "é"="e", "ê"="e",
+        "ë"="e", "ì"="i", "í"="i", "î"="i", "ï"="i", "ð"="d", "ñ"="n", "ò"="o",
+        "ó"="o", "ô"="o", "õ"="o", "ö"="o", "ø"="oe", "ù"="u", "ú"="u", "û"="u",
+        "ü"="u", "ý"="y", "ÿ"="y", "ğ"="g", "ı"="i", "ij"="ij", "ľ"="l", "ň"="n",
+        "ř"="r", "ş"="s", "ť"="t", "ų"="u", "ů"="u", "ý"="y", "ź"="z", "ż"="z",
+        "ſ"="s", "α"="a", "β"="b", "γ"="g", "δ"="d", "ε"="e", "ζ"="z", "η"="h",
+        "θ"="th", "ι"="i", "κ"="k", "λ"="l", "μ"="m", "ν"="n", "ξ"="x", "ο"="o",
+        "π"="p", "ρ"="r", "σ"="s", "τ"="t", "υ"="u", "φ"="ph", "χ"="ch", "ψ"="ps",
+        "ω"="o", "ά"="a", "έ"="e", "ή"="h", "ί"="i", "ό"="o", "ύ"="u", "ώ"="o",
+        "ϐ"="b", "ϑ"="th", "ϒ"="y", "ϕ"="ph", "ϖ"="p", "Ϛ"="st", "ϛ"="st", "Ϝ"="f",
+        "ϝ"="f", "Ϟ"="k", "ϟ"="k", "Ϡ"="k", "ϡ"="k", "ϰ"="k", "ϱ"="r", "ϲ"="s",
+        "ϳ"="j", "ϴ"="th", "ϵ"="e", "϶"="p"
+    )
+    # replace latin and greek characters to the closest english character
+    for (k in names(subs)) {
+        x <- gsub(k, subs[[k]], x)
+    }
     x <- gsub("[^[:alnum:]_]", non_alphanum_replace, x)
     if(collapse_replace) x <- gsub(paste0(non_alphanum_replace, "+"), non_alphanum_replace, x)
     if(tolower) x <- tolower(x)

{biopipen-0.26.0 → biopipen-0.26.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.26.0"
+version = "0.26.1"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"
@@ -38,11 +38,11 @@ delim = "biopipen.ns.delim"
 gene = "biopipen.ns.gene"
 gsea = "biopipen.ns.gsea"
 misc = "biopipen.ns.misc"
-plink = "biopipen.ns.plink"
 plot = "biopipen.ns.plot"
 rnaseq = "biopipen.ns.rnaseq"
 scrna = "biopipen.ns.scrna"
 scrna_metabolic_landscape = "biopipen.ns.scrna_metabolic_landscape"
+snp = "biopipen.ns.snp"
 stats = "biopipen.ns.stats"
 tcgamaf = "biopipen.ns.tcgamaf"
 tcr = "biopipen.ns.tcr"

{biopipen-0.26.0 → biopipen-0.26.1}/setup.py

@@ -67,12 +67,12 @@ entry_points = \
                    'gene = biopipen.ns.gene',
                    'gsea = biopipen.ns.gsea',
                    'misc = biopipen.ns.misc',
-                   'plink = biopipen.ns.plink',
                    'plot = biopipen.ns.plot',
                    'rnaseq = biopipen.ns.rnaseq',
                    'scrna = biopipen.ns.scrna',
                    'scrna_metabolic_landscape = '
                    'biopipen.ns.scrna_metabolic_landscape',
+                   'snp = biopipen.ns.snp',
                    'stats = biopipen.ns.stats',
                    'tcgamaf = biopipen.ns.tcgamaf',
                    'tcr = biopipen.ns.tcr',
@@ -81,7 +81,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.26.0',
+    'version': '0.26.1',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.26.0/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.26.0"