biopipen 0.34.14__py3-none-any.whl → 0.34.16__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.34.14"
+__version__ = "0.34.16"

biopipen/ns/scrna.py

@@ -96,6 +96,8 @@ class SeuratPreparing(Proc):
             `RNAData` to assign the path of the data to the samples
             The path will be read by `Read10X()` from `Seurat`, or the path
             to the h5 file that can be read by `Read10X_h5()` from `Seurat`.
+            It can also be an RDS or qs2 file containing a `Seurat` object.
+            Note that it must has a column named `Sample` in the meta.data to specify the sample names.
 
     Output:
         outfile: The qs2 file with the Seurat object with all samples integrated.
@@ -111,11 +113,11 @@ class SeuratPreparing(Proc):
         min_cells (type=int): The minimum number of cells that a gene must be
             expressed in to be kept. This is used in `Seurat::CreateSeuratObject()`.
             Futher QC (`envs.cell_qc`, `envs.gene_qc`) will be performed after this.
-            It doesn't work when data is loaded from loom files.
+            It doesn't work when data is loaded from loom files or RDS/qs2 files.
         min_features (type=int): The minimum number of features that a cell must
             express to be kept. This is used in `Seurat::CreateSeuratObject()`.
             Futher QC (`envs.cell_qc`, `envs.gene_qc`) will be performed after this.
-            It doesn't work when data is loaded from loom files.
+            It doesn't work when data is loaded from loom files or RDS/qs2 files.
         cell_qc: Filter expression to filter cells, using
             `tidyrseurat::filter()`.
             It can also be a dictionary of expressions, where the names of the list are
@@ -607,7 +609,7 @@ class SeuratClusterStats(Proc):
                 `ActivationScore` in the metadata.
                 You may also specify the literal order of the clusters by a list of strings (at least two).
             - subset: An expression to subset the cells, will be passed to `tidyrseurat::filter()`.
-            - devpars (ns): The device parameters for the plots. Does not work for `table`.
+            - devpars (ns): The device parameters for the 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.

biopipen/scripts/scrna/MarkersFinder.R

@@ -600,6 +600,28 @@ run_case <- function(name) {
 
             if (length(allenrich_plots) > 0 && !is.null(enriches) && nrow(enriches) > 0) {
                 log$info("- Visualizing all enrichments together ...")
+                # add other metadata columns if any by mapping groupname
+                # only add the metadata columns from object if there is a single value mapped
+                metacols <- srtobj@meta.data %>% group_by(!!sym(each)) %>%
+                    summarize(across(everything(), ~ n_distinct(.) == 1), .groups = "keep") %>%
+                    select(where(~ all(. == TRUE))) %>%
+                    colnames()
+
+                if (length(metacols) > 1) {
+                    metadf <- srtobj@meta.data[, metacols, drop = FALSE]  %>%
+                        distinct(!!sym(each), .keep_all = TRUE)
+
+                    for (col in setdiff(metacols, each)) {
+                        if (col %in% colnames(enriches)) {
+                            warning("Column name conflict: {col}, adding with suffix '_meta'", immediate. = TRUE)
+                            metadf[[paste0(col, "_meta")]] <- metadf[[col]]
+                            metadf[[col]] <- NULL
+                        }
+                    }
+
+                    enriches <- left_join(enriches, metadf, by = each)
+                }
+
                 process_allenriches(enriches, allenrich_plots, name, each)
             }
         }
@@ -659,6 +681,29 @@ run_case <- function(name) {
 
         if (length(allenrich_plots) > 0) {
             log$info("- Visualizing all enrichments together ...")
+            # add other metadata columns if any by mapping groupname
+            # only add the metadata columns from object if there is a single value mapped
+            metacols <- subobj@meta.data %>% group_by(!!sym(case$group_by)) %>%
+                summarize(across(everything(), ~ n_distinct(.) == 1), .groups = "keep") %>%
+                select(where(~ all(. == TRUE))) %>%
+                colnames()
+
+            if (length(metacols) > 1) {
+                metadf <- subobj@meta.data[, metacols, drop = FALSE]  %>%
+                    distinct(!!sym(case$group_by), .keep_all = TRUE)
+
+                for (col in setdiff(metacols, case$group_by)) {
+                    if (col %in% colnames(enriches[[1]])) {
+                        warning("Column name conflict: {col}, adding with suffix '_meta'", immediate. = TRUE)
+                        metadf[[paste0(col, "_meta")]] <- metadf[[col]]
+                        metadf[[col]] <- NULL
+                    }
+                }
+
+                for (ne in names(enriches)) {
+                    enriches[[ne]] <- left_join(enriches[[ne]], metadf, by = case$group_by)
+                }
+            }
             process_allenriches(enriches, allenrich_plots, name, case$group_by)
         }
     } else {

biopipen/scripts/scrna/SeuratPreparing.R

@@ -38,19 +38,27 @@ reporter$add(
     h1 = "Filters and QC"
 )
 
-metadata <- read.table(
-    metafile,
-    header = TRUE,
-    row.names = NULL,
-    sep = "\t",
-    check.names = FALSE
-)
+metadata <- tryCatch({
+    log$debug("Trying to read Seurat object from metafile ...")
+    read_obj(metafile)
+}, error = function(e) {
+    log$debug("Failed to read Seurat object from metafile: {e$message}")
+    log$debug("Reading metafile as a table (sample info) ...")
+    read.table(
+        metafile,
+        header = TRUE,
+        row.names = NULL,
+        sep = "\t",
+        check.names = FALSE
+    )
+})
+is_seurat <- inherits(metadata, "Seurat")
 
-meta_cols = colnames(metadata)
+meta_cols <- if (is_seurat) colnames(metadata@meta.data) else colnames(metadata)
 if (!"Sample" %in% meta_cols) {
-    stop("Error: Column `Sample` is not found in metafile.")
+    stop("Error: Column `Sample` is not found in ", ifelse(is_seurat, "Seurat object's meta.data.", "metafile."))
 }
-if (!"RNAData" %in% meta_cols) {
+if (!"RNAData" %in% meta_cols && !is_seurat) {
     stop("Error: Column `RNAData` is not found in metafile.")
 }
 

{biopipen-0.34.14.dist-info → biopipen-0.34.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: biopipen
-Version: 0.34.14
+Version: 0.34.16
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.34.14.dist-info → biopipen-0.34.16.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=EumHAzPCe3UipaK_9iqfQf47_8LP5jWSnXBVUZmzQTA,24
+biopipen/__init__.py,sha256=Ej0aenQBQvcrsqY3gHfGZPfKtKcKEskpGj0mMmPo81k,24
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=lZV_vbYWk6uqm19ZWJcsZCcSNqAdIfN2fOfamzxZpg4,2148
@@ -22,7 +22,7 @@ biopipen/ns/plot.py,sha256=N41_izb6zi-XArUly5WhLebapNXbTNSgGlOCCwtrDlY,18282
 biopipen/ns/protein.py,sha256=YJtlKoHI2p5yHdxKeQnNtm5QrbxDGOq1UXOdt_7tlTs,6391
 biopipen/ns/regulatory.py,sha256=WlnX_R8jEFyxCjk8mru5Qu5iCQJLzjMWiWGoc3gygzc,16221
 biopipen/ns/rnaseq.py,sha256=bKAa6friFWof4yDTWZQahm1MS-lrdetO1GqDKdfxXYc,7708
-biopipen/ns/scrna.py,sha256=yWG6oQ1XXzhr-GYOouiC_4aEwmi7XS8RW265XWsoqhw,145722
+biopipen/ns/scrna.py,sha256=HlR0eGaOOKXVIk9fcQYduMfdK1ith7OHfq38s9C55z8,145909
 biopipen/ns/scrna_metabolic_landscape.py,sha256=EwLMrsj_pTqvyAgtHLoishjQxCg_j8n5OofuTofUph0,22096
 biopipen/ns/snp.py,sha256=iXWrw7Lmhf4_ct57HGT7JGTClCXUD4sZ2FzOgsC2pTg,28123
 biopipen/ns/stats.py,sha256=DlPyK5Vsg6ZEkV9SDS3aAw21eXzvOHgqeZDkXPhg7go,20509
@@ -155,7 +155,7 @@ 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=nz18T_70ni9sfoFYp8weQMCiojphF61l5yHe9f_gOSM,26320
+biopipen/scripts/scrna/MarkersFinder.R,sha256=SBh3cA2WZQIlZTysAlU-U9knzO9gU0XW-yi8mk2iJG4,28588
 biopipen/scripts/scrna/MetaMarkers.R,sha256=BgYaWYEj6obwqaZaDWqNPtxb1IEEAnXAeBE0Ji9PvBA,12426
 biopipen/scripts/scrna/ModuleScoreCalculator.R,sha256=_mvo35a-wk5miUb_kMIVwvKK0b6InRa1NKtN8zznGwk,4457
 biopipen/scripts/scrna/PseudoBulkDEG.R,sha256=IuM4hl-KHZ5aaaTqZeylw4b1ZenMZaY4qobD5qxAlHs,25199
@@ -176,7 +176,7 @@ biopipen/scripts/scrna/SeuratFilter.R,sha256=BrYK0MLdaTtQvInMaQsmOt7oH_hlks0M1zy
 biopipen/scripts/scrna/SeuratLoading.R,sha256=23KAgsj0-XZhOOdUlLrb3r17St4LzZq230UlfIjLn_E,892
 biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=bSk-GPe5jZl6QGiNN7VrD7oAlbLjg9Vo5-t6ua28dyM,3631
 biopipen/scripts/scrna/SeuratMetadataMutater.R,sha256=22Kh9G3awSOvyeFZk5I8Sgg-fbu4gClAvHf_wJOxWnU,1020
-biopipen/scripts/scrna/SeuratPreparing.R,sha256=5mWDYwVBCncj_z3U8LGZ9xCQnax0gQJpEyGPZ7NykXk,8313
+biopipen/scripts/scrna/SeuratPreparing.R,sha256=T5BwpSLUnGDuUQsIBv9G8e9OBAODuJu8o1ZkvFO8p6k,8762
 biopipen/scripts/scrna/SeuratSplit.R,sha256=vdK11V39_Uo_NaOh76QWCtxObGaEr5Ynxqq0hTiSvsU,754
 biopipen/scripts/scrna/SeuratSubClustering.R,sha256=bsBzhzSsdqOy3aqNu_Cbx7qtRI7PDLnWRhUpoo8uvSw,1628
 biopipen/scripts/scrna/SeuratSubset.R,sha256=yVA11NVE2FSSw-DhxQcJRapns0tNNHdyDYi5epO6SKM,1776
@@ -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-0.34.14.dist-info/METADATA,sha256=uIS3ZdJr3bVM1TspZIe2NmoVavOa_XGKe4qsuRk7gdw,1027
-biopipen-0.34.14.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-biopipen-0.34.14.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
-biopipen-0.34.14.dist-info/RECORD,,
+biopipen-0.34.16.dist-info/METADATA,sha256=01g2zsm_S0SAqFkTHB5oIFDYxSc1WkBLH4zdBr0FNcA,1027
+biopipen-0.34.16.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+biopipen-0.34.16.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
+biopipen-0.34.16.dist-info/RECORD,,