biopipen 0.30.0__py3-none-any.whl → 0.31.1__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.30.0"
+__version__ = "0.31.1"

biopipen/ns/scrna.py

@@ -541,14 +541,19 @@ class SeuratClusterStats(Proc):
             This is to do some basic statistics on the clusters. For more comprehensive analysis,
             see `RadarPlots` and `CellsDistribution`.
             The parameters from the cases can overwrite the default parameters.
-            - frac (flag): Whether to output the fraction of cells instead of number.
+            - frac (choice): How to calculate the fraction of cells.
+                - group: calculate the fraction in each group.
+                    The total fraction of the cells of idents in each group will be 1.
+                    When `group-by` is not specified, it will be the same as `all`.
+                - ident: calculate the fraction in each ident.
+                    The total fraction of the cells of groups in each ident will be 1.
+                    Only works when `group-by` is specified.
+                - cluster: alias of `ident`.
+                - all: calculate the fraction against all cells.
+                - none: do not calculate the fraction, use the number of cells instead.
             - 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
@@ -708,12 +713,11 @@ class SeuratClusterStats(Proc):
         },
         "hists": {},
         "stats_defaults": {
-            "frac": False,
+            "frac": "none",
             "pie": False,
             "circos": False,
             "table": False,
             "position": "auto",
-            "frac_ofall": False,
             "transpose": False,
             "ident": "seurat_clusters",
             "group-by": None,
@@ -731,7 +735,7 @@ class SeuratClusterStats(Proc):
             "Number of cells in each cluster by Sample": {
                 "group-by": "Sample",
                 "table": True,
-                "frac": True,
+                "frac": "group",
             },
         },
         "ngenes_defaults": {
@@ -2261,3 +2265,52 @@ class AnnData2Seurat(Proc):
     lang = config.lang.rscript
     envs = {"outtype": "rds", "assay": "RNA", "dotplot_check": True}
     script = "file://../scripts/scrna/AnnData2Seurat.R"
+
+
+class ScSimulation(Proc):
+    """Simulate single-cell data using splatter.
+
+    See <https://www.bioconductor.org/packages/devel/bioc/vignettes/splatter/inst/doc/splatter.html#2_Quickstart>
+
+    Input:
+        seed: The seed for the simulation
+            You could also use string as the seed, and the seed will be
+            generated by `digest::digest2int()`.
+            So this could also work as a unique identifier for the simulation (ie. Sample ID).
+
+    Output:
+        outfile: The output Seurat object/SingleCellExperiment in RDS format
+
+    Envs:
+        ngenes (type=int): The number of genes to simulate
+        ncells (type=int): The number of cells to simulate
+        nspikes (type=int): The number of spike-ins to simulate
+            When `ngenes`, `ncells`, and `nspikes` are not specified, the default
+            params from `mockSCE()` will be used. By default, `ngenes = 2000`,
+            `ncells = 200`, and `nspikes = 100`.
+        outtype (choice): The output file type.
+            - seurat: Seurat object
+            - singlecellexperiment: SingleCellExperiment object
+            - sce: alias for `singlecellexperiment`
+        method (choice): which simulation method to use. Options are:
+            - single: produces a single population
+            - groups: produces distinct groups (eg. cell types), or
+            - paths: selects cells from continuous trajectories (eg. differentiation processes)
+        params (ns): Other parameters for simulation.
+            The parameters are initialized `splitEstimate(mockSCE())` and then
+            updated with the given parameters.
+            See <https://rdrr.io/bioc/splatter/man/SplatParams.html>.
+            Hyphens (`-`) will be transformed into dots (`.`) for the keys.
+    """  # noqa: E501
+    input = "seed:var"
+    output = "outfile:file:simulatied_{{in.seed}}.RDS"
+    lang = config.lang.rscript
+    envs = {
+        "ngenes": None,
+        "ncells": None,
+        "nspikes": None,
+        "outtype": "seurat",
+        "method": "single",
+        "params": {},
+    }
+    script = "file://../scripts/scrna/ScSimulation.R"

biopipen/scripts/scrna/CellsDistribution.R

@@ -325,7 +325,7 @@ do_case <- function(name, case) {
             geom_col(width=.01, position="fill", color = "#888888") +
             geom_bar(stat = "identity", position = position_fill(reverse = TRUE)) +
             coord_polar("y", start = 0) +
-            scale_fill_biopipen(name = "Cluster", limits = levels(all_clusters)) +
+            scale_fill_manual(name = "Cluster", values = pal_biopipen()(length(levels(all_clusters)))) +
             theme_void() +
             theme(
                 plot.margin = plot.margin,

biopipen/scripts/scrna/ScSimulation.R

@@ -0,0 +1,64 @@
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+
+library(rlang)
+library(splatter)
+library(scater)
+
+# Load template variables
+seed <- {{ in.seed | r }}
+outfile <- {{ out.outfile | r }}
+ngenes <- {{ envs.ngenes | r }}
+ncells <- {{ envs.ncells | r }}
+nspikes <- {{ envs.nspikes | r }}
+outtype <- {{ envs.outtype | r }}
+method <- {{ envs.method | r }}
+user_params <- {{ envs.params | r: todot="-" }}
+
+log_info("Generating simulation parameters ...")
+
+seed <- seed %||% 1
+if (length(seed) > 1) {
+    log_warn("- multiple seeds provided, using the first one")
+    seed <- seed[1]
+}
+if (is.character(seed)) {
+    library(digest)
+    proj <- seed
+    seed <- digest2int(seed)
+} else {
+    proj <- paste0("S", seed)
+}
+
+set.seed(seed)
+mock_sce_params <- list()
+if (!is.null(ngenes)) mock_sce_params$ngenes <- ngenes
+if (!is.null(ncells)) mock_sce_params$ncells <- ncells
+if (!is.null(nspikes)) mock_sce_params$nspikes <- nspikes
+sce <- do.call(mockSCE, mock_sce_params)
+params <- splatEstimate(sce)
+user_params$seed <- seed
+user_params$object = params
+do_call(setParams, user_params)
+
+
+log_info("Saving simulation parameters to file ...")
+
+sim <- splatSimulate(params, method = method, verbose = TRUE)
+
+outtype <- tolower(outtype)
+if (outtype == "sce") outtype <- "singlecellexperiment"
+
+if (outtype == "singlecellexperiment") {
+    log_info("Saving simulation to file ...")
+    saveRDS(sim, file = outfile)
+} else {
+    log_info("Converting simulation to Seurat object ...")
+    cnts <- SingleCellExperiment::counts(sim)
+    sobj <- Seurat::CreateSeuratObject(counts = cnts, project = proj)
+    rm(sim)
+    rm(cnts)
+    gc()
+
+    log_info("Saving simulation to file ...")
+    saveRDS(sobj, file = outfile)
+}

biopipen/scripts/scrna/SeuratClusterStats-stats.R

@@ -18,12 +18,6 @@ do_one_stats = function(name) {
     if (isTRUE(case$pie) && !is.null(case$group.by)) {
         stop(paste0(name, ": pie charts are not supported for group-by"))
     }
-    if (!isTRUE(case$frac) && isTRUE(case$frac_ofall)) {
-        stop(paste0(name, ": frac_ofall is only supported when frac is true"))
-    }
-    if (isTRUE(case$frac_ofall) && is.null(case$group.by)) {
-        stop(paste0(name, ": frac_ofall is only supported for group-by"))
-    }
     if (isTRUE(case$transpose) && is.null(case$group.by)) {
         stop(paste0(name, ": transpose is only supported for group-by"))
     }
@@ -46,28 +40,28 @@ do_one_stats = function(name) {
             !!!syms(case$split.by)
         ), function(df) {
             out <- df %>% group_by(!!!syms(select_cols)) %>% summarise(.n = n(), .groups = "drop")
-            if (!is.null(case$group.by) && isTRUE(case$frac)) {
-                if (isTRUE(case$frac_ofall)) {
+            if (!is.null(case$group.by) && case$frac != "none") {
+                if (case$frac == "all") {
                     out <- out %>% mutate(.frac = .n / sum(.n))
-                } else if (isTRUE(case$transpose)) {
-                    out <- out %>% group_by(!!sym(case$ident)) %>% mutate(.frac = .n / sum(.n))
-                } else {
+                } else if (case$frac == "group") {
                     out <- out %>% group_by(!!sym(case$group.by)) %>% mutate(.frac = .n / sum(.n))
+                } else {  # case$frac == "ident" or "cluster"
+                    out <- out %>% group_by(!!sym(case$ident)) %>% mutate(.frac = .n / sum(.n))
                 }
             }
             out
         }))
-    } else if (!is.null(case$group.by) && isTRUE(case$frac)) {
+    } else if (!is.null(case$group.by) && case$frac != "none") {  # no split.by
         plot_df <- df_cells %>%
             select(all_of(select_cols)) %>%
             group_by(!!!syms(select_cols)) %>%
             summarise(.n = n(), .groups = "drop")
-        if (isTRUE(case$frac_ofall)) {
+        if (case$frac == "all") {
             plot_df = plot_df %>% mutate(.frac = .n / sum(.n))
-        } else {
-            plot_df = plot_df %>%
-                group_by(!!sym(ifelse(isTRUE(case$transpose), case$group.by, case$ident))) %>%
-                mutate(.frac = .n / sum(.n))
+        } else if (case$frac == "group") {
+            plot_df = plot_df %>% group_by(!!sym(case$group.by)) %>% mutate(.frac = .n / sum(.n))
+        } else {  # case$frac == "ident" or "cluster"
+            plot_df = plot_df %>% group_by(!!sym(case$ident)) %>% mutate(.frac = .n / sum(.n))
         }
     } else {
         plot_df <- df_cells %>%
@@ -75,7 +69,7 @@ do_one_stats = function(name) {
             group_by(!!!syms(select_cols)) %>%
             summarise(.n = n(), .groups = "drop")
 
-        if (isTRUE(case$frac) || isTRUE(case$frac_ofall)) {
+        if (case$frac != "none") {
             plot_df <- plot_df %>% mutate(.frac = .n / sum(.n))
         }
     }
@@ -88,13 +82,13 @@ do_one_stats = function(name) {
     p = plot_df %>%
         ggplot(aes(
             x=!!sym(ifelse(case$transpose, case$group.by, case$ident)),
-            y=if (isTRUE(case$frac)) .frac else .n,
+            y=if (case$frac != "none") .frac else .n,
             fill=!!sym(ifelse(is.null(case$group.by) || isTRUE(case$transpose), case$ident, case$group.by))
         )) +
         geom_bar(stat="identity", position=bar_position, alpha=.8) +
         theme_prism(axis_text_angle = 90) +
         scale_fill_biopipen() +
-        ylab(ifelse(isTRUE(case$frac), "Fraction of cells", "Number of cells"))
+        ylab(ifelse(case$frac != "none", "Fraction of cells", "Number of cells"))
 
     if (!is.null(case$split.by)) {
         p = p + facet_wrap(case$split.by)
@@ -109,7 +103,7 @@ do_one_stats = function(name) {
             kind = "descr",
             content = paste0(
                 "Plots showing the ",
-                ifelse(isTRUE(case$frac), "number/faction", "number"),
+                ifelse(case$frac != "none", "number/faction", "number"),
                 " of cells per cluster",
                 ifelse(
                     is.null(case$group.by),
@@ -150,7 +144,7 @@ do_one_stats = function(name) {
             guides(fill = guide_legend(title = case$ident)) +
             theme_void() +
             geom_label(
-                if (isTRUE(case$frac))
+                if (case$frac != "none")
                     aes(label=sprintf("%.1f%%", .frac * 100))
                 else
                     aes(label=.n),

biopipen/scripts/scrna/SeuratMap2Ref.R

@@ -45,6 +45,10 @@ if (is.null(split_by)) {
     future::plan(strategy = "multicore", workers = ncores)
 }
 
+.is_sct <- function(x) {
+    return(Seurat:::IsSCT(assay = x@assays[[DefaultAssay(x)]]))
+}
+
 .expand_dims = function(args, name = "dims") {
     # Expand dims from 30 to 1:30
     if (is.numeric(args[[name]]) && length(args[[name]] == 1)) {
@@ -63,6 +67,8 @@ if (endsWith(ref, ".rds") || endsWith(ref, ".RDS")) {
 } else {
     reference = LoadH5Seurat(ref)
 }
+reference = UpdateSeuratObject(reference)
+reference = UpdateSCTAssays(reference)
 
 # check if refdata exists in the reference
 for (rname in names(mapquery_args$refdata)) {
@@ -84,9 +90,20 @@ for (rname in names(mapquery_args$refdata)) {
     }
 }
 
-if (refnorm == "auto" && DefaultAssay(reference) == "SCT") {
+if (refnorm == "auto" && .is_sct(reference)) {
     refnorm = "SCTransform"
 }
+if (refnorm == "SCTransform") {
+    # Check if the reference is SCTransform'ed
+    if (!.is_sct(reference)) {
+        stop("Reference is not SCTransform'ed")
+    }
+    n_models = length(x = slot(object = reference[[DefaultAssay(reference)]], name = "SCTModel.list"))
+    if (n_models == 0) {
+        stop("Reference doesn't contain SCTModel.")
+    }
+}
+
 log_info("  Normalization method used: {refnorm}")
 if (refnorm == "SCTransform") {
     findtransferanchors_args$normalization.method = "SCT"
@@ -130,18 +147,17 @@ log_info("- Normalizing data")
 if (refnorm == "SCTransform") {
     if (defassay == "SCT" && skip_if_normalized) {
         log_warn("  Skipping normalization as the object is already SCTransform'ed")
-        query = sobj
     } else {
         log_info("  Using SCTransform normalization")
         sctransform_args$residual.features = rownames(x = reference)
         if (is.null(split_by)) {
             sctransform_args$object = sobj
-            query = do_call(SCTransform, sctransform_args)
+            sobj = do_call(SCTransform, sctransform_args)
             sctransform_args$object <- NULL
             rm(sctransform_args)
             gc()
         } else {
-            query = mclapply(
+            sobj = mclapply(
                 X = sobj,
                 FUN = function(x) {
                     sctransform_args$object = x
@@ -149,22 +165,21 @@ if (refnorm == "SCTransform") {
                 },
                 mc.cores = ncores
             )
-            if (any(unlist(lapply(query, class)) == "try-error")) {
-                stop(paste0("\nmclapply (SCTransform) error:", query))
+            if (any(unlist(lapply(sobj, class)) == "try-error")) {
+                stop(paste0("\nmclapply (SCTransform) error:", sobj))
             }
         }
     }
 } else {
     if (defassay == "RNA" && skip_if_normalized) {
         log_warn("  Skipping normalization as the object is already LogNormalize'd")
-        query = sobj
     } else {
         log_info("  Using NormalizeData normalization")
         if (is.null(split_by)) {
             normalizedata_args$object = sobj
-            query = do_call(NormalizeData, normalizedata_args)
+            sobj = do_call(NormalizeData, normalizedata_args)
         } else {
-            query = mclapply(
+            sobj = mclapply(
                 X = sobj,
                 FUN = function(x) {
                     normalizedata_args$object = x
@@ -172,8 +187,8 @@ if (refnorm == "SCTransform") {
                 },
                 mc.cores = ncores
             )
-            if (any(unlist(lapply(query, class)) == "try-error")) {
-                stop(paste0("\nmclapply (NormalizeData) error:", query))
+            if (any(unlist(lapply(sobj, class)) == "try-error")) {
+                stop(paste0("\nmclapply (NormalizeData) error:", sobj))
             }
         }
         normalizedata_args$object <- NULL
@@ -181,14 +196,12 @@ if (refnorm == "SCTransform") {
         gc()
     }
 }
-rm(sobj)
-gc()
 
 # Find anchors between query and reference
 log_info("- Finding anchors")
 findtransferanchors_args$reference = reference
 if (is.null(split_by)) {
-    findtransferanchors_args$query = query
+    findtransferanchors_args$query = sobj
     anchors = do_call(FindTransferAnchors, findtransferanchors_args)
     findtransferanchors_args$reference = NULL
     findtransferanchors_args$query = NULL
@@ -196,7 +209,7 @@ if (is.null(split_by)) {
     gc()
 } else {
     anchors = mclapply(
-        X = query,
+        X = sobj,
         FUN = function(x) {
             findtransferanchors_args$query = x
             do_call(FindTransferAnchors, findtransferanchors_args)
@@ -212,25 +225,25 @@ if (is.null(split_by)) {
 log_info("- Mapping query to reference")
 mapquery_args$reference = reference
 if (is.null(split_by)) {
-    mapquery_args$query = query
+    mapquery_args$query = sobj
     mapquery_args$anchorset = anchors
-    query = do_call(MapQuery, mapquery_args)
+    sobj = do_call(MapQuery, mapquery_args)
     mapquery_args$reference = NULL
     mapquery_args$query = NULL
     mapquery_args$anchorset = NULL
     gc()
 } else {
-    query = mclapply(
-        X = seq_along(query),
+    sobj = mclapply(
+        X = seq_along(sobj),
         FUN = function(i) {
-            mapquery_args$query = query[[i]]
+            mapquery_args$query = sobj[[i]]
             mapquery_args$anchorset = anchors[[i]]
             do_call(MapQuery, mapquery_args)
         },
         mc.cores = ncores
     )
-    if (any(unlist(lapply(query, class)) == "try-error")) {
-        stop(paste0("\nmclapply (MapQuery) error:", query))
+    if (any(unlist(lapply(sobj, class)) == "try-error")) {
+        stop(paste0("\nmclapply (MapQuery) error:", sobj))
     }
 }
 
@@ -254,7 +267,7 @@ if (is.null(split_by)) {
     gc()
 } else {
     mappingscore = mclapply(
-        X = seq_along(query),
+        X = seq_along(sobj),
         FUN = function(i) {
             mappingscore_args$anchors = anchors[[i]]
             tryCatch({
@@ -274,25 +287,25 @@ if (is.null(split_by)) {
 # Calculate mapping score and add to metadata
 log_info("- Adding mapping score to metadata")
 if (is.null(split_by)) {
-    query = AddMetaData(
-        object = query,
+    sobj = AddMetaData(
+        object = sobj,
         metadata = mappingscore,
         col.name = "mapping.score"
     )
 } else {
-    query = mclapply(
-        X = seq_along(query),
+    sobj = mclapply(
+        X = seq_along(sobj),
         FUN = function(i) {
             AddMetaData(
-                object = query[[i]],
+                object = sobj[[i]],
                 metadata = mappingscore[[i]],
                 col.name = "mapping.score"
             )
         },
         mc.cores = ncores
     )
-    if (any(unlist(lapply(query, class)) == "try-error")) {
-        stop(paste0("\nmclapply (AddMetaData) error:", query))
+    if (any(unlist(lapply(sobj, class)) == "try-error")) {
+        stop(paste0("\nmclapply (AddMetaData) error:", sobj))
     }
 
     # Combine the results
@@ -300,19 +313,33 @@ if (is.null(split_by)) {
     gc()
     # Memory efficient way to merge the results
     # query = Reduce(function(x, y) merge(x, y, merge.dr = "ref.umap"), query)
-    query = merge(query[[1]], query[2:length(query)], merge.dr = "ref.umap")
+    sobj = merge(sobj[[1]], sobj[2:length(sobj)], merge.dr = "ref.umap")
 }
 
 # Add the alias to the metadata for the clusters
 log_info("- Adding ident to metadata and set as ident")
-query@meta.data = query@meta.data %>% mutate(
+sobj@meta.data = sobj@meta.data %>% mutate(
     !!sym(ident) := as.factor(!!parse_expr(paste0("predicted.", use)))
 )
-Idents(query) = ident
+Idents(sobj) = ident
+
+# Check if PrepSCTFindMarkers is done
+if (.is_sct(sobj) && is.null(sobj@commands$PrepSCTFindMarkers)) {
+    log_info("- Running PrepSCTFindMarkers ...")
+    sobj <- PrepSCTFindMarkers(sobj)
+    # compose a new SeuratCommand to record it to sobj@commands
+    commands <- names(pbmc_small@commands)
+    scommand <- pbmc_small@commands[[commands[length(commands)]]]
+    scommand@time.stamp <- Sys.time()
+    scommand@assay.used <- DefaultAssay(sobj)
+    scommand@call.string <- "PrepSCTFindMarkers(object = sobj)"
+    scommand@params <- list()
+    sobj@commands$PrepSCTFindMarkers <- scommand
+}
 
 # Save
 log_info("- Saving result ...")
-saveRDS(query, file = outfile)
+saveRDS(sobj, file = outfile)
 
 
 # ############################
@@ -325,7 +352,7 @@ ref.reduction = mapquery_args$reduction.model %||% "wnn.umap"
 for (qname in names(mapquery_args$refdata)) {
     rname <- mapquery_args$refdata[[qname]]
 
-    if (grepl("Array", class(reference[[rname]])) && grepl("Array", class(query[[qname]]))) {
+    if (grepl("Array", class(reference[[rname]])) && grepl("Array", class(sobj[[qname]]))) {
         log_warn("  Skipping transferred array: {qname} -> {rname}")
         next
     }
@@ -342,7 +369,7 @@ for (qname in names(mapquery_args$refdata)) {
     ) + NoLegend()
 
     query_p <- DimPlot(
-        object = query,
+        object = sobj,
         reduction = "ref.umap",
         group.by = paste0("predicted.", qname),
         label = TRUE,

{biopipen-0.30.0.dist-info → biopipen-0.31.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.30.0
+Version: 0.31.1
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang
@@ -14,9 +14,9 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Provides-Extra: runinfo
 Requires-Dist: datar[pandas] (>=0.15.6,<0.16.0)
-Requires-Dist: pipen-board[report] (>=0.15,<0.16)
-Requires-Dist: pipen-cli-run (>=0.13,<0.14)
-Requires-Dist: pipen-filters (>=0.13,<0.14)
-Requires-Dist: pipen-poplog (>=0.1.2,<0.2.0)
-Requires-Dist: pipen-runinfo (>=0.6,<0.7) ; extra == "runinfo"
-Requires-Dist: pipen-verbose (>=0.11,<0.12)
+Requires-Dist: pipen-board[report] (>=0.16,<0.17)
+Requires-Dist: pipen-cli-run (>=0.14,<0.15)
+Requires-Dist: pipen-filters (>=0.14,<0.15)
+Requires-Dist: pipen-poplog (>=0.2.0,<0.3.0)
+Requires-Dist: pipen-runinfo (>=0.7,<0.8) ; extra == "runinfo"
+Requires-Dist: pipen-verbose (>=0.12,<0.13)

{biopipen-0.30.0.dist-info → biopipen-0.31.1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=OlatFEFA4ttqSSIiV8jdE-sq3KG5zu2hnC4B4mzWF3s,23
+biopipen/__init__.py,sha256=PB3hjnlSwoWLBLl2ge7lsrSRubKXRdIanr_Hg2t3ViA,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=7IXvviRicZ2D1h6x3BVgbLJ96nsh-ikvZ0sVlQepqFE,1944
@@ -21,7 +21,7 @@ biopipen/ns/misc.py,sha256=qXcm0RdR6W-xpYGgQn3v7JBeYRWwVm5gtgSj2tdVxx4,2935
 biopipen/ns/plot.py,sha256=_dGLKpyHiJqLIIQu5tqCk8H5BkgGBh_qRUZHkjnOgtE,18080
 biopipen/ns/regulatory.py,sha256=qvc9QrwgwCI_lg0DQ2QOZbAhC8BAD1qnQXSGtAGlVcY,11750
 biopipen/ns/rnaseq.py,sha256=bKAa6friFWof4yDTWZQahm1MS-lrdetO1GqDKdfxXYc,7708
-biopipen/ns/scrna.py,sha256=UNX1v_nMM3tzxbj6ecyZuI1aW9vyy4P2Xv3yia7fQ2w,110412
+biopipen/ns/scrna.py,sha256=fXP_h7gchcuk_Jwos0IgY_P8ON6Q995OgKHgdrxfvAY,112868
 biopipen/ns/scrna_metabolic_landscape.py,sha256=6AhaynGG3lNRi96N2tReVT46BJMuEwooSSd2irBoN80,28347
 biopipen/ns/snp.py,sha256=-Jx5Hsv_7KV7TqLU0nHCaPkMEN0CFdi4tNVlyq0rUZ4,27259
 biopipen/ns/stats.py,sha256=DlPyK5Vsg6ZEkV9SDS3aAw21eXzvOHgqeZDkXPhg7go,20509
@@ -139,7 +139,7 @@ biopipen/scripts/scrna/CellTypeAnnotation-hitype.R,sha256=zol-IF0jd3DTzw9I1UVUMY
 biopipen/scripts/scrna/CellTypeAnnotation-sccatch.R,sha256=LTvFzGzP0nmQLkJIxn6H7L8xkP2Z3q52DknXtBkkmcA,1822
 biopipen/scripts/scrna/CellTypeAnnotation-sctype.R,sha256=RhFHy1E4b3Y7pw6feKEhPx5GTbNdaQMDXHzvRlPk34Q,4544
 biopipen/scripts/scrna/CellTypeAnnotation.R,sha256=X_LR0LZ6UQjLA-SCCcQ8CBFZGG_J8CUNx--qwBS8Oh8,773
-biopipen/scripts/scrna/CellsDistribution.R,sha256=KOmo8rZBl2-xojyO1TaxE7JXLwIwArq-WdIR_JZxvcE,18958
+biopipen/scripts/scrna/CellsDistribution.R,sha256=QOkQhpendXMmgen99wn0Pl3XKnMJQzvLVb0hPdR49NQ,18980
 biopipen/scripts/scrna/DimPlots.R,sha256=oKhygoWQOCck8OlpnOrNJg0CS2q-r8Com1dfjTvQzvU,1575
 biopipen/scripts/scrna/ExprImputation-alra.R,sha256=xNdQiXgY13-iF16o2KgCJWfPIy4P-lOiO1bl9PfXI4U,864
 biopipen/scripts/scrna/ExprImputation-rmagic.R,sha256=jYIfqZpnvjKJkvItLnemPVtUApHBYQi1_L8rHVbEe1M,735
@@ -151,19 +151,20 @@ biopipen/scripts/scrna/ModuleScoreCalculator.R,sha256=QJ_E6qjRC8GazoopcxZfT5cKxl
 biopipen/scripts/scrna/RadarPlots.R,sha256=4zs0hAm7yq1Ls62f_29koPLqAKCeKbYiztNM-HR7j3U,13041
 biopipen/scripts/scrna/SCImpute.R,sha256=dSJOHhmJ3x_72LBRXT72dbCti5oiB85CJ-OjWtqONbk,2958
 biopipen/scripts/scrna/ScFGSEA.R,sha256=MFoJ3i3LFBfsPCxwLPnTh141ZJyrzwnrTuCZIFwvYjU,6318
+biopipen/scripts/scrna/ScSimulation.R,sha256=b2LtL68ucxLoI57tSEDD0hOSbVHUA_x88Y96eK07N-s,1712
 biopipen/scripts/scrna/Seurat2AnnData.R,sha256=G7bcHGffdNlz6Uuy98tQdlahXiPkTDokflp1yTUgcSQ,1578
 biopipen/scripts/scrna/SeuratClusterStats-clustree.R,sha256=FkbniQMHiZGrFAIuS8nUfPVJKFofSL-ZnpxTqIhTa54,3058
 biopipen/scripts/scrna/SeuratClusterStats-dimplots.R,sha256=NEdlJHNXnJZfF7YkefYVWTPO8Z_KAppRAs9rNvB8TXs,2360
 biopipen/scripts/scrna/SeuratClusterStats-features.R,sha256=DeGo7AkBRq0V3Y3JDaifId6rrr5dwawTzcSAJ3W1lxE,15614
 biopipen/scripts/scrna/SeuratClusterStats-hists.R,sha256=PXyDKww8HcloCU8r4IqRwRrm6Ly0cpmpvRcP30xxBa4,5038
 biopipen/scripts/scrna/SeuratClusterStats-ngenes.R,sha256=ihZLB27iEhgICKj-ZTnxTvRAYIgg9rzWr9Oyh1YmOYM,2160
-biopipen/scripts/scrna/SeuratClusterStats-stats.R,sha256=j4ZrmzwBYKIR0WGQaYxXOxangTZPxKwzmb1KDgP_jY4,9277
+biopipen/scripts/scrna/SeuratClusterStats-stats.R,sha256=jufs99zxNyUaTCDiWzO0yt76ncc73Yn_SpPa5igbJyA,9120
 biopipen/scripts/scrna/SeuratClusterStats.R,sha256=fywRBVjaFIJBxdgsZxLXEheUZI4l5VUoNIcJnhPIdPQ,2193
 biopipen/scripts/scrna/SeuratClustering-common.R,sha256=JX4Cn2FC6GOcBqaVyGDD3MM5zGpm3TpKJlfo2oOQ4Uk,8195
 biopipen/scripts/scrna/SeuratClustering.R,sha256=0OKRBQ5rFuupK7c03_sSt2HMwMdMnCYFqTvkRXFKchs,1706
 biopipen/scripts/scrna/SeuratFilter.R,sha256=BrYK0MLdaTtQvInMaQsmOt7oH_hlks0M1zykkJtg2lM,509
 biopipen/scripts/scrna/SeuratLoading.R,sha256=ekWKnHIqtQb3kHVQiVymAHXXqiUxs6KKefjZKjaykmk,900
-biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=s4LlwVGIXgxivOOMEMoOPDKVxShrJX1q8AIICiFu7zo,10994
+biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=KARt5IVBDYpNhLZ7_j0FEi1u5S8PxU_mB4THH26s7AM,12008
 biopipen/scripts/scrna/SeuratMetadataMutater.R,sha256=PMwG0Xvl_EEVKkicfrIi4arEqpY948PkYLkb59kTAXI,1135
 biopipen/scripts/scrna/SeuratPreparing-common.R,sha256=WuD7lGS17eAUQWSiIdAoV0EIeqS3Tnkkx-7PbP6Q3tc,16279
 biopipen/scripts/scrna/SeuratPreparing-doublet_detection.R,sha256=TNN2lfFjpnnO0rguMsG38JYCP1nFUhcPLJ1LqGj-Sc8,6674
@@ -278,7 +279,7 @@ biopipen/utils/reference.py,sha256=oi5evicLwHxF0KAIPNZohBeHJLJQNWFJH0cr2y5pgcg,5
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=pJjYP8bIZpNAtTQ32rOXhZxaM1Y-6D-xUcK3pql9tbk,4316
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.30.0.dist-info/METADATA,sha256=hX1BYgYwes-v9P9pgYQ-7iJO2D6LmdfJ0B9z3JZgeEk,882
-biopipen-0.30.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.30.0.dist-info/entry_points.txt,sha256=69SbeMaF47Z2DS40yo-qDyoBKmMmumrNnsjEZMOioCE,625
-biopipen-0.30.0.dist-info/RECORD,,
+biopipen-0.31.1.dist-info/METADATA,sha256=uPOVUaGxNgT5ZJwJWBDXqmnxaBUxaMvyErjqFCRsV60,882
+biopipen-0.31.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+biopipen-0.31.1.dist-info/entry_points.txt,sha256=69SbeMaF47Z2DS40yo-qDyoBKmMmumrNnsjEZMOioCE,625
+biopipen-0.31.1.dist-info/RECORD,,