biopipen 0.23.4__tar.gz → 0.23.6__tar.gz

{biopipen-0.23.4 → biopipen-0.23.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.23.4
+Version: 0.23.6
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.23.6/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.23.6"

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/core/filters.py

@@ -326,37 +326,58 @@ def _render_enrichr(
     components = []
 
     for db in dbs:
-        components.append(
-            {
-                "title": db,
-                "ui": "tabs",
-                "contents": [
-                    {
-                        "title": "Plot",
-                        "ui": "flat",
-                        "contents": [
-                            {
-                                "kind": "image",
-                                "src": str(
-                                    Path(cont["dir"]).joinpath(f"Enrichr-{db}.png")
-                                ),
-                            }
-                        ],
-                    },
-                    {
-                        "title": "Table",
-                        "ui": "flat",
-                        "contents": [
-                            {
-                                "kind": "table",
-                                "src": str(
-                                    Path(cont["dir"]).joinpath(f"Enrichr-{db}.txt")
-                                ),
-                            }
-                        ],
-                    },
-                ],
-            }
-        )
+        enrichr_plot = Path(cont["dir"]).joinpath(f"Enrichr-{db}.png")
+        if enrichr_plot.exists():
+            components.append(
+                {
+                    "title": db,
+                    "ui": "tabs",
+                    "contents": [
+                        {
+                            "title": "Plot",
+                            "ui": "flat",
+                            "contents": [
+                                {
+                                    "kind": "image",
+                                    "src": str(
+                                        Path(cont["dir"]).joinpath(f"Enrichr-{db}.png")
+                                    ),
+                                }
+                            ],
+                        },
+                        {
+                            "title": "Table",
+                            "ui": "flat",
+                            "contents": [
+                                {
+                                    "kind": "table",
+                                    "src": str(
+                                        Path(cont["dir"]).joinpath(f"Enrichr-{db}.txt")
+                                    ),
+                                }
+                            ],
+                        },
+                    ],
+                }
+            )
+        else:
+            components.append(
+                {
+                    "title": db,
+                    "ui": "tabs",
+                    "contents": [
+                        {
+                            "title": "Error",
+                            "ui": "flat",
+                            "contents": [
+                                {
+                                    "kind": "error",
+                                    "content": "No enriched terms found.",
+                                }
+                            ],
+                        },
+                    ],
+                }
+            )
 
     return render_ui(components, "accordion", job, level)

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/ns/scrna.py

@@ -77,6 +77,7 @@ class SeuratPreparing(Proc):
 
     /// Note
     When using `SCTransform`, the default Assay will be set to `SCT` in output, rather than `RNA`.
+    If you are using `cca` or `rpca` interation, the default assay will be `integrated`.
     ///
 
     /// Note
@@ -771,6 +772,10 @@ class ModuleScoreCalculator(Proc):
             >>>     "Proliferation": {"features": "STMN1,TUBB"}
             >>> }
 
+            For `CellCycle`, the columns `S.Score`, `G2M.Score` and `Phase` will
+            be added to the metadata. `S.Score` and `G2M.Score` are the cell cycle
+            scores for each cell, and `Phase` is the cell cycle phase for each cell.
+
             You can also add Diffusion Components (DC) to the modules
             >>> {"DC": {"features": 2, "kind": "diffmap"}}
             will perform diffusion map as a reduction and add the first 2
@@ -1460,7 +1465,8 @@ class ScFGSEA(Proc):
         each: The column name in metadata to separate the cells into different subsets to do the analysis.
         section: The section name for the report. Worked only when `each` is not specified. Otherwise, the section name will be constructed from `each` and its value.
             This allows different cases to be put into the same section in the report.
-        gmtfile: The pathways in GMT format, with the gene names/ids in the same format as the seurat object
+        gmtfile: The pathways in GMT format, with the gene names/ids in the same format as the seurat object.
+            One could also use a URL to a GMT file. For example, from <https://download.baderlab.org/EM_Genesets/current_release/Human/symbol/Pathways/>.
         method (choice): The method to do the preranking.
             - signal_to_noise: Signal to noise.
                 The larger the differences of the means (scaled by the standard deviations);

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/ns/scrna_metabolic_landscape.py

@@ -402,7 +402,10 @@ class ScrnaMetabolicLandscape(ProcGroup):
             If False, the values will be left as is.
         gmtfile: The GMT file with the metabolic pathways. The gene names should
             match the gene names in the gene list in RNAData or
-            the Seurat object
+            the Seurat object.
+            You can also provide a URL to the GMT file.
+            For example, from
+            <https://download.baderlab.org/EM_Genesets/current_release/Human/symbol/>.
         grouping: defines the basic groups to investigate the metabolic activity
             Typically the clusters.
         grouping_prefix: Working as a prefix to group names

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna/MarkersFinder.R

@@ -306,6 +306,10 @@ do_enrich <- function(info, markers, sig, volgenes) {
                 col.names = TRUE,
                 quote = FALSE
             )
+            if (nrow(enriched[[db]]) == 0) {
+                log_warn("  No enrichment found for case: {info$casename} - {db}")
+                next
+            }
             png(
                 file.path(info$casedir, paste0("Enrichr-", db, ".png")),
                 res = 100, height = 1000, width = 1000

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna/MetaMarkers.R

@@ -183,6 +183,12 @@ do_enrich <- function(info, markers, sig) {
             col.names = TRUE,
             quote = FALSE
         )
+
+        if (nrow(enriched[[db]]) == 0) {
+            log_info(paste0("  No enriched terms for ", db))
+            next
+        }
+
         png(
             file.path(info$casedir, paste0("Enrichr-", db, ".png")),
             res = 100, height = 600, width = 800

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna/SeuratClusterStats-stats.R

@@ -69,6 +69,10 @@ do_one_stats = function(name) {
             select(all_of(select_cols)) %>%
             group_by(!!!syms(select_cols)) %>%
             summarise(.n = n(), .groups = "drop")
+
+        if (isTRUE(case$frac) || isTRUE(case$frac_ofall)) {
+            plot_df <- plot_df %>% mutate(.frac = .n / sum(.n))
+        }
     }
 
     write.table(plot_df, tablefile, sep="\t", quote=FALSE, row.names=FALSE)

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna/SeuratClustering.R

@@ -143,6 +143,7 @@ if (is.null(resolution) || length(resolution) == 1) {
 }
 
 if (DefaultAssay(sobj) == "SCT") {
+    # https://github.com/satijalab/seurat/issues/6968
     log_info("Running PrepSCTFindMarkers ...")
     sobj <- PrepSCTFindMarkers(sobj)
 }

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna/SeuratPreparing.R

@@ -101,7 +101,6 @@ load_sample = function(sample) {
     # filter the cells that don't have any gene expressions
     cell_exprs = colSums(obj@assays$RNA)
     obj = subset(obj, cells = names(cell_exprs[cell_exprs > 0]))
-    # obj = SCTransform(object=obj, return.only.var.genes=FALSE, verbose=FALSE)
     obj = RenameCells(obj, add.cell.id = sample)
     # Attach meta data
     for (mname in names(mdata)) {
@@ -110,9 +109,15 @@ load_sample = function(sample) {
         if (is.factor(mdt)) { mdt = levels(mdt)[mdt] }
         obj[[mname]] = mdt
     }
-    # obj_list[[sample]] = obj
 
-    # obj_list
+    if (isTRUE(envs$use_sct)) {
+        # so that we have data and scale.data layers on RNA assay
+        # useful for visualization in case some genes are not in
+        # the SCT assay
+        obj = NormalizeData(obj, verbose = FALSE)
+        obj = FindVariableFeatures(obj, verbose = FALSE)
+        obj = ScaleData(obj, verbose = FALSE)
+    }
     obj
 }
 
@@ -329,6 +334,11 @@ if (!envs$no_integration) {
     IntegrateLayersArgs <- envs$IntegrateLayers
     IntegrateLayersArgs$object <- sobj
     method <- IntegrateLayersArgs$method
+    if (!is.null(IntegrateLayersArgs$reference) && is.character(IntegrateLayersArgs$reference)) {
+        log_info("  Using reference samples: {paste(IntegrateLayersArgs$reference, collapse = ', ')}")
+        IntegrateLayersArgs$reference <- match(IntegrateLayersArgs$reference, samples)
+        log_info("  Transferred to indices: {paste(IntegrateLayersArgs$reference, collapse = ', ')}")
+    }
     if (method %in% c("CCA", "cca")) { method <- "CCAIntegration" } else
     if (method %in% c("RPCA", "rpca")) { method <- "RPCAIntegration" } else
     if (method %in% c("Harmony", "harmony")) { method <- "HarmonyIntegration" } else

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna/TopExpressingGenes.R

@@ -177,6 +177,12 @@ do_enrich <- function(expr, odir) {
             col.names = TRUE,
             quote = FALSE
         )
+
+        if (nrow(enriched[[db]]) == 0) {
+            log_info(paste0("  No enriched terms for ", db))
+            next
+        }
+
         png(
             file.path(odir, paste0("Enrichr-", db, ".png")),
             res = 100, height = 1000, width = 1000

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R

@@ -36,6 +36,7 @@ gmt_pathways <- function(gmt_file) {
     pathways
 }
 
+gmtfile <- localizeGmtfile(gmtfile)
 pathways <- gmt_pathways(gmtfile)
 metabolics <- unique(as.vector(unname(unlist(pathways))))
 sobj <- readRDS(sobjfile)
@@ -78,7 +79,8 @@ do_one_group <- function(obj, features, group, outputdir, h1) {
             )
         }
 
-        add_report(
+        # Can't add report directly, mclapply can't modify global variables.
+        report = list(
             list(kind = "fgsea", dir = odir),
             h1 = ifelse(is.null(h1), groupname, h1),
             h2 = ifelse(is.null(h1), "#", groupname)
@@ -88,7 +90,7 @@ do_one_group <- function(obj, features, group, outputdir, h1) {
         log_warn(paste("Unable to run for", group))
         log_warn(e$message)
 
-        add_report(
+        report = list(
             list(
                 kind = "error",
                 content = paste0("Error running GSEA for ", group, ": ", e$message)
@@ -98,6 +100,7 @@ do_one_group <- function(obj, features, group, outputdir, h1) {
         )
     })
 
+    report
 }
 
 do_one_subset <- function(s, subset_col, subset_prefix) {
@@ -126,6 +129,8 @@ do_one_subset <- function(s, subset_col, subset_prefix) {
     if (any(unlist(lapply(x, class)) == "try-error")) {
         stop("mclapply error")
     }
+
+    for (r in x) { do.call(add_report, r) }
 }
 
 do_one_subset_col <- function(subset_col, subset_prefix) {

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R

@@ -38,11 +38,11 @@ gmt_pathways <- function(gmt_file) {
     pathways
 }
 
+gmtfile <- localizeGmtfile(gmtfile)
 pathways <- gmt_pathways(gmtfile)
 metabolics <- unique(as.vector(unname(unlist(pathways))))
 sobj <- readRDS(sobjfile)
 
-
 do_one_comparison <- function(
     obj,
     compname,
@@ -111,7 +111,7 @@ do_one_comparison <- function(
             envs = list(nproc = 1)
         )
 
-        add_report(
+        report = list(
             list(kind = "fgsea", dir = odir),
             h1 = groupname,
             h2 = compname
@@ -123,7 +123,11 @@ do_one_comparison <- function(
             gmtfile,
             odir
         )
+
+        report = list()
     }
+
+    report
 }
 
 do_one_group <- function(group) {
@@ -138,12 +142,13 @@ do_one_group <- function(group) {
     groupdir = file.path(outdir, slugify(groupname, tolower = FALSE))
     dir.create(groupdir, showWarnings = FALSE)
 
+    report = list()
     for (i in seq_along(subsetting_comparison)) {
         sci = subsetting_comparison[[i]]
         if (is.null(sci) || length(sci) == 0) {
             next
         }
-        sapply(
+        rs = lapply(
             names(sci),
             function(compname) {
                 do_one_comparison(
@@ -159,17 +164,23 @@ do_one_group <- function(group) {
                 )
             }
         )
+        if (length(rs) > 0) {
+            report = c(report, rs)
+        }
     }
+    report
 }
 
 groups = sort(as.character(unique(sobj@meta.data[[grouping]])))
 if (ncores == 1) {
-    lapply(groups, do_one_group)
+    x = lapply(groups, do_one_group)
 } else {
     x = mclapply(groups, do_one_group, mc.cores = ncores)
     if (any(unlist(lapply(x, class)) == "try-error")) {
         stop("mclapply error")
     }
 }
+report = unlist(x, recursive = FALSE)
+for (r in report) { do.call(add_report, r) }
 
 save_report(joboutdir)

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R

@@ -39,6 +39,7 @@ gmt_pathways <- function(gmt_file) {
     pathways
 }
 
+gmtfile <- localizeGmtfile(gmtfile)
 pathways <- gmt_pathways(gmtfile)
 pathway_names <- names(pathways)
 metabolics <- unique(as.vector(unname(unlist(pathways))))

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R

@@ -41,6 +41,7 @@ gmt_pathways <- function(gmt_file) {
     pathways
 }
 
+gmtfile <- localizeGmtfile(gmtfile)
 pathways <- gmt_pathways(gmtfile)
 metabolics <- unique(as.vector(unname(unlist(pathways))))
 sobj <- readRDS(sobjfile)
@@ -216,7 +217,7 @@ do_one_subset <- function(s, subset_col, subset_prefix) {
 
     ggsave(file.path(subset_dir, "PC_variance_plot.pdf"), p, device = "pdf", useDingbats = FALSE)
 
-    add_report(
+    list(
         list(kind = "descr", content = "Metabolic pathways enriched in genes with highest contribution to the metabolic heterogeneities"),
         list(kind = "image", src = bubblefile),
         h1 = ifelse(is.null(s), "Metabolic pathway heterogeneity", paste0(subset_prefix, s))
@@ -226,17 +227,20 @@ do_one_subset <- function(s, subset_col, subset_prefix) {
 do_one_subset_col <- function(subset_col, subset_prefix) {
     log_info(paste0("- Handling subset column: ", subset_col, " ..."))
     if (is.null(subset_col)) {
-        do_one_subset(NULL, subset_col = NULL, subset_prefix = NULL)
-    }
-    subsets <- na.omit(unique(sobj@meta.data[[subset_col]]))
-
-    if (ncores == 1) {
-        lapply(subsets, do_one_subset, subset_col = subset_col, subset_prefix = subset_prefix)
+        x <- do_one_subset(NULL, subset_col = NULL, subset_prefix = NULL)
+        do.call(add_report, x)
     } else {
-        x <- mclapply(subsets, do_one_subset, subset_col = subset_col, subset_prefix = subset_prefix, mc.cores = ncores)
-        if (any(unlist(lapply(x, class)) == "try-error")) {
-            stop(paste0("\nmclapply error:", x))
+        subsets <- na.omit(unique(sobj@meta.data[[subset_col]]))
+
+        if (ncores == 1) {
+            x = lapply(subsets, do_one_subset, subset_col = subset_col, subset_prefix = subset_prefix)
+        } else {
+            x <- mclapply(subsets, do_one_subset, subset_col = subset_col, subset_prefix = subset_prefix, mc.cores = ncores)
+            if (any(unlist(lapply(x, class)) == "try-error")) {
+                stop(paste0("\nmclapply error:", x))
+            }
         }
+        for (r in x) { do.call(add_report, r) }
     }
 }
 

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/scripts/tcr/Immunarch-diversity.R

@@ -647,6 +647,12 @@ run_div_case = function(casename) {
     # Filter
     if (!is.null(case$subset)) {
         d = immdata_from_expanded(filter_expanded_immdata(exdata, case$subset))
+        if (nrow(d$meta) == 0) {
+            stop(paste0(
+                "No samples/cells left after filtering. ",
+                "Do you have the correct `subset` for case: ",
+                casename, "?"))
+        }
     } else {
         d = immdata
     }

{biopipen-0.23.4 → biopipen-0.23.6}/biopipen/utils/gsea.R

@@ -1,8 +1,48 @@
 library(ggplot2)
 library(dplyr)
 library(tibble)
+library(slugify)
 
-prerank = function(
+
+localizeGmtfile <- function(gmturl, cachedir = tempdir()) {
+    # Download the GMT file and save it to cachedir
+    # Return the path to the GMT file
+    if (!startsWith(gmturl, "http") && !startsWith(gmturl, "ftp")) {
+        return(gmturl)
+    }
+    gmtfile = file.path(cachedir, basename(gmturl))
+    if (!file.exists(gmtfile)) {
+        download.file(gmturl, gmtfile)
+        items <- read.delim(gmtfile, header = FALSE, stringsAsFactors = FALSE, sep = "\t")
+        if (ncol(items) < 3) {
+            stop(paste0("Invalid GMT file: ", gmtfile, ", from ", gmturl))
+        }
+        if (nrow(items) == 0) {
+            stop(paste0("Empty GMT file: ", gmtfile, ", from ", gmturl))
+        }
+        if (nchar(items$V2[1]) < nchar(items$V1[1]) && nchar(items$V2[1]) > 0) {
+            warning(paste0(
+                "The second column is shorter, switching the first and second columns in GMT file ",
+                gmtfile,
+                " from ",
+                gmturl
+            ))
+            items <- items[, c(2, 1, 3:ncol(items))]
+            write.table(
+                items,
+                gmtfile,
+                row.names = F,
+                col.names = F,
+                sep = "\t",
+                quote = F
+            )
+        }
+    }
+    return(gmtfile)
+}
+
+
+prerank <- function(
     exprdata,
     pos,
     neg,
@@ -63,6 +103,11 @@ runEnrichr = function(
         outfig = file.path(outdir, paste0("Enrichr_", db, ".png"))
         write.table(enr, outtable, row.names=T, col.names=F, sep="\t", quote=F)
 
+        if (nrow(enr) == 0) {
+            print(paste0("No enriched terms for ", db))
+            next
+        }
+
         png(outfig, res=100, height=1000, width=1400)
         print(
             plotEnrich(
@@ -95,6 +140,7 @@ runFGSEA = function(
         ranks = unlist(ranks)
     }
 
+    gmtfile = localizeGmtfile(gmtfile)
     envs$pathways = gmtPathways(gmtfile)
     envs$stats = ranks
     gsea_res = do.call(fgsea::fgsea, envs)
@@ -130,7 +176,7 @@ runFGSEA = function(
     dev.off()
 
     for (pathway in topPathways) {
-        enrfig = file.path(outdir, paste0("fgsea_", gsub("/", "-", pathway, fixed=T), ".png"))
+        enrfig = file.path(outdir, paste0("fgsea_", slugify(pathway), ".png"))
         png(enrfig, res=100, width=1000, height=800)
         print(plotEnrichment(
             envs$pathways[[pathway]],
@@ -186,7 +232,7 @@ runGSEA = function(
 
     envs$input.ds = gctfile
     envs$input.cls = clsfile
-    envs$gs.db = gmtfile
+    envs$gs.db = localizeGmtfile(gmtfile)
     envs$output.directory = outdir
 
     do.call(GSEA, envs)

{biopipen-0.23.4 → biopipen-0.23.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.23.4"
+version = "0.23.6"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

{biopipen-0.23.4 → biopipen-0.23.6}/setup.py

@@ -75,7 +75,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.23.4',
+    'version': '0.23.6',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.23.4/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.23.4"