biopipen 0.34.5__py3-none-any.whl → 0.34.7__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.34.5"
+__version__ = "0.34.7"

biopipen/ns/tcr.py

@@ -1682,6 +1682,10 @@ class ScRepLoading(Proc):
         type (choice): The type of the data to load.
             - TCR: T cell receptor data
             - BCR: B cell receptor data
+            - auto: Automatically detect the type from the metadata.
+                If `auto` is selected, the type will be determined by the presence of
+                `TCRData` or `BCRData` columns in the metadata. If both columns are
+                present, `TCR` will be selected by default.
         combineTCR (type=json): The extra arguments for `scRepertoire::combineTCR`
             function.
             See also <https://www.borch.dev/uploads/screpertoire/reference/combinetcr>
@@ -1721,13 +1725,12 @@ class ScRepLoading(Proc):
     output = "outfile:file:{{in.metafile | stem}}.scRep.qs"
     lang = config.lang.rscript
     envs = {
-        "type": "TCR",  # or BCR
+        "type": "auto",  # or TCR/BCR
         "combineTCR": {"samples": True},
         "combineBCR": {"samples": True},
         "exclude": ["BCRData", "TCRData", "RNAData"],
         "format": None,
         "tmpdir": config.path.tmpdir,
-
     }
     script = "file://../scripts/tcr/ScRepLoading.R"
 
@@ -1750,7 +1753,7 @@ 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
+            `scRepertoire::combineExpression()`, a new column `VDJ_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.

biopipen/scripts/scrna/CellTypeAnnotation-celltypist.R

@@ -111,7 +111,7 @@ if (file.exists(celltypist_outfile) &&
         command <- paste(command, "-v")
     }
     log$info("Running celltypist:")
-    log$debug("- {command}")
+    print("- {command}")
     rc <- system(command)
     if (rc != 0) {
         stop("Failed to run celltypist. Check the job.stderr file to see the error message.")

biopipen/scripts/scrna/MarkersFinder.R

@@ -165,10 +165,12 @@ post_casing <- function(name, case) {
 
         if (length(cases) == 0 && name == "Marker Discovery") {
             name <- case$each
+        } else {
+            name <- paste0(name, " (", case$each, ")")
         }
 
         for (each in eachs) {
-            newname <- paste0(name, " - ", each)
+            newname <- paste0(name, "::", each)
             newcase <- case
 
             newcase$original_case <- name

biopipen/scripts/scrna/PseudoBulkDEG.R

@@ -131,12 +131,14 @@ expand_each <- function(name, case) {
 
         if (length(cases) == 0 && name == "DEG Analysis") {
             name <- case$each
+        } else {
+            name <- paste0(name, " (", case$each, ")")
         }
 
         case$aggregate_by <- unique(c(case$aggregate_by, case$group_by, case$paired_by, case$each))
 
         for (each in eachs) {
-            newname <- paste0(case$each, "::", each)
+            newname <- paste0(name, "::", each)
             newcase <- case
 
             newcase$original_case <- name
@@ -212,7 +214,52 @@ process_markers <- function(markers, info, case) {
     # markers <- markers %>%
     #     mutate(gene = as.character(gene)) %>%
     #     arrange(p_val_adj, desc(abs(avg_log2FC)))
+
+    empty <- if (case$enrich_style == "enrichr") {
+        data.frame(
+            Database = character(0),
+            Term = character(0),
+            Overlap = character(0),
+            P.value = numeric(0),
+            Adjusted.P.value = numeric(0),
+            Odds.Ratio = numeric(0),
+            Combined.Score = numeric(0),
+            Genes = character(0),
+            Rank = numeric(0)
+        )
+    } else {  # clusterProfiler
+        data.frame(
+            ID = character(0),
+            Description = character(0),
+            GeneRatio = character(0),
+            BgRatio = character(0),
+            Count = integer(0),
+            pvalue = numeric(0),
+            p.adjust = numeric(0),
+            qvalue = numeric(0),
+            geneID = character(0),
+            Database = character(0)
+        )
+    }
+    if (is.null(markers) || nrow(markers) == 0) {
+        if (case$error) {
+            stop("Error: No markers found in case '", info$name, "'.")
+        } else {
+            log$warn("! Warning: No markers found in case '", info$name, "'.")
+            reporter$add2(
+                list(
+                    name = "Warning",
+                    contents = list(list(kind = "error", content = "No markers found.", kind_ = "warning"))),
+                hs = c(info$section, info$name),
+                hs2 = "DEG Analysis",
+                ui = "tabs"
+            )
+            return(empty)
+        }
+    }
     markers$gene <- as.character(markers$gene)
+    markers$p_val_adj <- as.numeric(markers$p_val_adj)
+    markers$log2FC <- as.numeric(markers$log2FC)
     markers <- markers[order(markers$p_val_adj, -abs(markers$log2FC)), ]
 
     # Save markers
@@ -287,7 +334,7 @@ process_markers <- function(markers, info, case) {
             stop("Error: Not enough significant DEGs with '", case$sigmarkers, "' in case '", info$name, "' found (< 5) for enrichment analysis.")
         } else {
             message <- paste0("Not enough significant DEGs with '", case$sigmarkers, "' found (< 5) for enrichment analysis.")
-            log$warn("  ! Error: {message}")
+            log$warn("! Error: {message}")
             reporter$add2(
                 list(
                     name = "Warning",
@@ -345,7 +392,7 @@ process_markers <- function(markers, info, case) {
             if (case$error) {
                 stop("Error: ", e$message)
             } else {
-                log$warn("  ! Error: {e$message}")
+                log$warn("! Error: {e$message}")
                 reporter$add2(
                     list(
                         name = "Warning",
@@ -478,6 +525,7 @@ process_overlaps <- function(markers, ovcases, casename, groupname) {
 
 run_case <- function(name) {
     case <- cases[[name]]
+    log$info("----------------------------------------")
     log$info("Case: {name} ...")
 
     case <- extract_vars(
@@ -558,16 +606,35 @@ run_case <- function(name) {
         return(invisible())
     }
 
+    info <- case_info(name, outdir, create = TRUE)
     exprs <- AggregateExpressionPseudobulk(
         srtobj, aggregate_by = aggregate_by, layer = layer, assay = assay,
         subset = subset, log = log
     )
-    markers <- RunDEGAnalysis(
-        exprs, group_by = group_by, ident_1 = ident_1, ident_2 = ident_2,
-        paired_by = paired_by, tool = tool, log = log
+    markers <- tryCatch(
+        {
+            RunDEGAnalysis(
+                exprs, group_by = group_by, ident_1 = ident_1, ident_2 = ident_2,
+                paired_by = paired_by, tool = tool, log = log
+            )
+        }, error = function(e) {
+            if (error) {
+                stop("Error: ", e$message)
+            } else {
+                log$warn("! Error: {e$message}")
+                reporter$add2(
+                    list(
+                        name = "Warning",
+                        contents = list(list(kind = "error", content = e$message, kind_ = "warning"))),
+                    hs = c(info$section, info$name),
+                    hs2 = "DEG Analysis",
+                    ui = "tabs"
+                )
+                return(invisible())
+            }
+        }
     )
 
-    info <- case_info(name, outdir, create = TRUE)
     enrich <- process_markers(markers, info = info, case = list(
         dbs = dbs,
         sigmarkers = sigmarkers,

biopipen/scripts/scrna/ScFGSEA.R

@@ -83,10 +83,12 @@ expand_each <- function(name, case) {
 
         if (length(cases) == 0 && name == "GSEA") {
             name <- case$each
+        } else {
+            name <- paste0(name, " (", case$each, ")")
         }
 
         for (each in eachs) {
-            newname <- paste0(case$each, "::", each)
+            newname <- paste0(name, "::", each)
             newcase <- case
 
             newcase$original_case <- paste0(name, " (all ", case$each,")")

biopipen/scripts/tcr/ScRepCombiningExpression.R

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

biopipen/scripts/tcr/ScRepLoading.R

@@ -21,6 +21,18 @@ log <- get_logger()
 
 log$info("Loading metadata ...")
 metadata <- read.table(metafile, header = TRUE, sep = "\t", row.names = NULL, check.names = FALSE)
+if (type == "AUTO") {
+    if ("TCRData" %in% colnames(metadata) && "BCRData" %in% colnames(metadata)) {
+        log$warn("Both TCRData and BCRData columns found in metadata. Defaulting to TCR.")
+        type <- "TCR"
+    } else if ("TCRData" %in% colnames(metadata)) {
+        type <- "TCR"
+    } else if ("BCRData" %in% colnames(metadata)) {
+        type <- "BCR"
+    } else {
+        stop("Error: Neither TCRData nor BCRData column found in metadata.")
+    }
+}
 
 data_column <- ifelse(type == "TCR", "TCRData", "BCRData")
 combine_fn <- ifelse(type == "TCR", combineTCR, combineBCR)

{biopipen-0.34.5.dist-info → biopipen-0.34.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: biopipen
-Version: 0.34.5
+Version: 0.34.7
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.34.5.dist-info → biopipen-0.34.7.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=h8CbBrHmMIAi56YuHk8Y6QbCUJtGFC7bwBFj8VtTAR8,23
+biopipen/__init__.py,sha256=vVRUKRt0zUNKxfGQQE5WrQiVWQ-bg4UrgyEGX7LclcA,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=lZV_vbYWk6uqm19ZWJcsZCcSNqAdIfN2fOfamzxZpg4,2148
@@ -27,7 +27,7 @@ biopipen/ns/scrna_metabolic_landscape.py,sha256=EwLMrsj_pTqvyAgtHLoishjQxCg_j8n5
 biopipen/ns/snp.py,sha256=iXWrw7Lmhf4_ct57HGT7JGTClCXUD4sZ2FzOgsC2pTg,28123
 biopipen/ns/stats.py,sha256=DlPyK5Vsg6ZEkV9SDS3aAw21eXzvOHgqeZDkXPhg7go,20509
 biopipen/ns/tcgamaf.py,sha256=AFbUJIxiMSvsVY3RcHgjRFuMnNh2DG3Mr5slLNEyz6o,1455
-biopipen/ns/tcr.py,sha256=urx0RomtzhyEtE0V8r3mpNUEMSZCXJ8T6C_I1TSShSY,99373
+biopipen/ns/tcr.py,sha256=XvhbZcVzdJYCjGe61G_EitdRpZyDnyDsaMNPlyH5590,99676
 biopipen/ns/vcf.py,sha256=zjOH2qiSJsHACLmBqV-Tew-mn-peZgvYLAWjTLh7uTI,23823
 biopipen/ns/web.py,sha256=8VY4Xsb8UrzS4IkGUX_84GQP1JG6NcTZrV7f9tA1tUI,5458
 biopipen/reports/bam/CNAClinic.svelte,sha256=D4IxQcgDCPQZMbXog-aZP5iJEQTK2N4i0C60e_iXyfs,213
@@ -142,7 +142,7 @@ biopipen/scripts/scrna/AnnData2Seurat.R,sha256=wc5PDbK9TkuJtoXXxF4W1ODylWhyfKWd3
 biopipen/scripts/scrna/CCPlotR-patch.R,sha256=KpB8fwacBaWaUNjIidcLUkMShLjS4Gq9UY8LUgIITB0,8369
 biopipen/scripts/scrna/CellCellCommunication.py,sha256=Wg0uFSo0Yt0wq6UT1TBodyK8GtWQXGv7hXRfM665paU,4354
 biopipen/scripts/scrna/CellCellCommunicationPlots.R,sha256=4l2EJVd1y94Nfry8fuRL9OSF6AhS8PGBekimpRUu3s8,1919
-biopipen/scripts/scrna/CellTypeAnnotation-celltypist.R,sha256=AlNx0vBKqvpQ83yfNUbU4taJ8CUyz63iXzumZcw-PBc,6968
+biopipen/scripts/scrna/CellTypeAnnotation-celltypist.R,sha256=CwYR8WWQMf8r7V2CTalG4kxdKnYMtyhpJBe9zP2sQWA,6964
 biopipen/scripts/scrna/CellTypeAnnotation-direct.R,sha256=w3CKRUA9NZfC3TFbU8I35L4XJ6MtVaWX-VnV7ScZlBI,2196
 biopipen/scripts/scrna/CellTypeAnnotation-hitype.R,sha256=vvjhxin4aoA9heecey0dpr6ofirybygY3ApjgtQW89Y,2094
 biopipen/scripts/scrna/CellTypeAnnotation-sccatch.R,sha256=xxB4K1MzBSNQnDxa44s5ExeU67MbncOBf8lGFr7RvwQ,1870
@@ -155,13 +155,13 @@ biopipen/scripts/scrna/ExprImputation-rmagic.R,sha256=ePgbMZ_3bKbeUrjsMdkdtBM_MS
 biopipen/scripts/scrna/ExprImputation-scimpute.R,sha256=MI_bYfvCDKJsuGntUxfx_-NdrssBoQgL95-DGwJVE5s,1191
 biopipen/scripts/scrna/ExprImputation.R,sha256=GcdZJpkDpq88hRQjtLZY5-byp8V43stEFm5T-pQbU6A,319
 biopipen/scripts/scrna/LoomTo10X.R,sha256=c6F0p1udsL5UOlb84-53K5BsjSDWkdFyYTt5NQmlIec,1059
-biopipen/scripts/scrna/MarkersFinder.R,sha256=P6BgseCrXTeJR8X52hzD16qBUuCeHmPc96h5pKE_-qY,24207
+biopipen/scripts/scrna/MarkersFinder.R,sha256=A-YCJ2WogU2QR8PqVn71lXCP63Vq1sMyAAIhqZYYawg,24278
 biopipen/scripts/scrna/MetaMarkers.R,sha256=BgYaWYEj6obwqaZaDWqNPtxb1IEEAnXAeBE0Ji9PvBA,12426
 biopipen/scripts/scrna/ModuleScoreCalculator.R,sha256=-tByCPk7i070LynAb0z2ANeRxr1QqiKP0dfrJm52jH4,4198
-biopipen/scripts/scrna/PseudoBulkDEG.R,sha256=32Hd3x2WyTFv175Os4bxf6goAcIq7QN8m1i7i7emnMI,22308
+biopipen/scripts/scrna/PseudoBulkDEG.R,sha256=Y5OuVCaIIppBqMxxXM3HpJQk5kA42wSgbBBIC1Rr1s0,24608
 biopipen/scripts/scrna/RadarPlots.R,sha256=Kn1E-hpczuujpgNjR8MqeIIVN-S3PbpmfcKWGKcNCVY,14546
 biopipen/scripts/scrna/SCImpute.R,sha256=dSJOHhmJ3x_72LBRXT72dbCti5oiB85CJ-OjWtqONbk,2958
-biopipen/scripts/scrna/ScFGSEA.R,sha256=Cbr1RE4jD3CbR7K4Y1XWKfcqiqhZmzATCKEd3ysCnCc,11517
+biopipen/scripts/scrna/ScFGSEA.R,sha256=EyRbsH5d1daIxtOHjYz24Udmv1PhV0nUC9HqEtzRnpE,11584
 biopipen/scripts/scrna/ScSimulation.R,sha256=q0-dXD9px1cApc_TxGmR-OdNHE8W1VSVWfSI57B96bo,1697
 biopipen/scripts/scrna/ScVelo.py,sha256=SPUZFgZW1Zhw-bnjJo98RK0vpuNFODQ8Q3eTguNc84k,21359
 biopipen/scripts/scrna/Seurat2AnnData.R,sha256=F8g5n2CqX4-KBggxd8ittz8TejYuqqNLMudAHdFt1QM,184
@@ -234,8 +234,8 @@ biopipen/scripts/tcr/ImmunarchFilter.R,sha256=-en-zi0ZB1JjuqhPlaEAN8YvHrELZNJ1V7
 biopipen/scripts/tcr/ImmunarchLoading.R,sha256=u3o2aag_7cZ17HA8RxpN58wvrII0Uh-q6FY6dA8MWeQ,5756
 biopipen/scripts/tcr/ImmunarchSplitIdents.R,sha256=FGCeGV0uSmFU91lKkldUAeV4A2m3hHw5X4GNi8ffGzI,1873
 biopipen/scripts/tcr/SampleDiversity.R,sha256=oipN4-2nQZe8bYjI0lZ0SvZ7T8GZ_FWkpkobi1cwmWE,2664
-biopipen/scripts/tcr/ScRepCombiningExpression.R,sha256=TwnlUWG9isSl7H1VqhFLbWlVSdDwFRVSszqbnShH_E0,1011
-biopipen/scripts/tcr/ScRepLoading.R,sha256=FORXYfeTitFr9EtfJrv2A-2GeWG-WKDBBANeeT9ejds,5269
+biopipen/scripts/tcr/ScRepCombiningExpression.R,sha256=sYn6BEUB53Z3pF7IAjYpewGYBvVBwzJqoAOPpcAxzQo,1011
+biopipen/scripts/tcr/ScRepLoading.R,sha256=COdY7KotlYemq4LDJT3d08NlzOzRwrDUTrNUdt4P66A,5732
 biopipen/scripts/tcr/TCRClusterStats.R,sha256=ns3S95DVDBuhSe1YgTZ1OksbfBgREO2Tnp1d4QzbTw0,13530
 biopipen/scripts/tcr/TCRClustering.R,sha256=K01qYLNhXrMmPb3TJE504lpRXnfizUNZ5q75nL7dxBg,9152
 biopipen/scripts/tcr/TCRDock.py,sha256=Oyw27k6vr0pnJ0w1-lrk5b6sZ_IOf6TmbhSxQae-3Q8,3148
@@ -284,7 +284,7 @@ biopipen/utils/misc.py,sha256=pDZ-INWVNqHuXYvcjmu8KqNAigkh2lsHy0BxX44CPvc,4048
 biopipen/utils/reference.py,sha256=Oc6IlA1giLxymAuI7DO-IQLHQ7-DbsWzOQE86oTDfMU,5955
 biopipen/utils/reporter.py,sha256=VwLl6xyVDWnGY7NEXyqBlkW8expKJoNQ5iTyZSELf5c,4922
 biopipen/utils/vcf.py,sha256=MmMbAtLUcKPp02jUdk9TzuET2gWSeoWn7xgoOXFysK0,9393
-biopipen-0.34.5.dist-info/METADATA,sha256=WmREdhe4-vouw0NWeH63QRdWDg_I8lWvhhcxK0QoKeA,975
-biopipen-0.34.5.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-biopipen-0.34.5.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
-biopipen-0.34.5.dist-info/RECORD,,
+biopipen-0.34.7.dist-info/METADATA,sha256=uR3Q2oygeFSoT96Lp0wQGCcigCJGaIyzbYzdJ2wlWVw,975
+biopipen-0.34.7.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+biopipen-0.34.7.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
+biopipen-0.34.7.dist-info/RECORD,,