biopipen 0.23.5__py3-none-any.whl → 0.23.6__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.23.5"
+__version__ = "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/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/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/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/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)

biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R

@@ -38,6 +38,7 @@ gmt_pathways <- function(gmt_file) {
     pathways
 }
 
+gmtfile <- localizeGmtfile(gmtfile)
 pathways <- gmt_pathways(gmtfile)
 metabolics <- unique(as.vector(unname(unlist(pathways))))
 sobj <- readRDS(sobjfile)

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/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)

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/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,
@@ -100,6 +140,7 @@ runFGSEA = function(
         ranks = unlist(ranks)
     }
 
+    gmtfile = localizeGmtfile(gmtfile)
     envs$pathways = gmtPathways(gmtfile)
     envs$stats = ranks
     gsea_res = do.call(fgsea::fgsea, envs)
@@ -135,7 +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]],
@@ -191,7 +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-0.23.5.dist-info → biopipen-0.23.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.23.5
+Version: 0.23.6
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.23.5.dist-info → biopipen-0.23.6.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=NmV-LR0j--svKElD-cVKR1iKjk_Puucfm1d0VLr-Zto,23
+biopipen/__init__.py,sha256=9os9lpDN2FpOV8_or7nYXNev84mb1sZPOVtGXewiSXw,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=Rn7Cta7WsMtmQkKGC4h9d5dU_STaIVBgR8UliiGgL6o,1757
@@ -20,8 +20,8 @@ biopipen/ns/gsea.py,sha256=EsNRAPYsagaV2KYgr4Jv0KCnZGqayM209v4yOGGTIOI,7423
 biopipen/ns/misc.py,sha256=fzn0pXvdghMkQhu-e3MMapPNMyO6IAJbtTzVU3GbFa0,3246
 biopipen/ns/plot.py,sha256=yguxmErUOH-hOM10JfuI_sXw2p49XF8yGR_gXfbd5yQ,4066
 biopipen/ns/rnaseq.py,sha256=l4vFeRasGhkexopGTM_VfSyIFewOxg-9L5niFzhWUNA,565
-biopipen/ns/scrna.py,sha256=qunKNFrehZZvY1RO1eUYZLNVL3T1jxIo1UUtE2dLKLo,95314
-biopipen/ns/scrna_metabolic_landscape.py,sha256=dSL-y1Gx1fcgebX7vk3wcSbm9aBALfCZKz0vjcDxQ_8,28139
+biopipen/ns/scrna.py,sha256=42cM6n7rNy8sze9Lhl90RNkpxWT5w6LKPDrGsAK_Y7U,95808
+biopipen/ns/scrna_metabolic_landscape.py,sha256=9s1NvH3aMaNDXyfwy9TdzGcSP_lIW4JqhLgknNZcIKE,28313
 biopipen/ns/tcgamaf.py,sha256=AFbUJIxiMSvsVY3RcHgjRFuMnNh2DG3Mr5slLNEyz6o,1455
 biopipen/ns/tcr.py,sha256=IcP1uD8U9XD6UbOgdjA_Lk5PK6r4R84Gi7511uvXoy8,84411
 biopipen/ns/vcf.py,sha256=cdkKroii0_nl_bSP2cnO09qESUAhHqu6btOiTSKS79Y,15314
@@ -131,12 +131,12 @@ biopipen/scripts/scrna/SeuratClusterStats-hists.R,sha256=GTZfs1yOkuoMUM1Zb19i_My
 biopipen/scripts/scrna/SeuratClusterStats-ngenes.R,sha256=GVKIXFNS_syCuSN8oxoBkjxxAeI5LdSxh-qLVkUsbDA,2146
 biopipen/scripts/scrna/SeuratClusterStats-stats.R,sha256=CE9989SaO75_KYEEVqivEbUoTcUOtiTkRGWLNtWzxI8,6450
 biopipen/scripts/scrna/SeuratClusterStats.R,sha256=PeXa3r2VTo0Q1rdXpSfAOIbYSJAcA8WUNM-tJkNUcPg,1284
-biopipen/scripts/scrna/SeuratClustering.R,sha256=Awc_aryIRabmGiRXe5mwug7I98_yDz4atzF7EQbMBnY,5131
+biopipen/scripts/scrna/SeuratClustering.R,sha256=Q3XGg0Rq1xqswyQSsj8AmarmiT9ZFdoolXy2g9ibiTo,5185
 biopipen/scripts/scrna/SeuratFilter.R,sha256=BrYK0MLdaTtQvInMaQsmOt7oH_hlks0M1zykkJtg2lM,509
 biopipen/scripts/scrna/SeuratLoading.R,sha256=ekWKnHIqtQb3kHVQiVymAHXXqiUxs6KKefjZKjaykmk,900
 biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=tisYmoSaCX8Kl8y6euuuUroWdDsJ2NGI27J5AWr9Niw,4392
 biopipen/scripts/scrna/SeuratMetadataMutater.R,sha256=Pp4GsF3hZ6ZC2vroC3LSBmVa4B1p2L3hbh981yaAIeQ,1093
-biopipen/scripts/scrna/SeuratPreparing.R,sha256=O1aQHMn7xwwHCKt2tjN9vKRMyvHgW-GYmB6sTi5unrg,11597
+biopipen/scripts/scrna/SeuratPreparing.R,sha256=wdAjqD4tD0jTiiSlOHFVJHjPzJvNkQq4N2IxdjmDlcM,12213
 biopipen/scripts/scrna/SeuratSplit.R,sha256=vdK11V39_Uo_NaOh76QWCtxObGaEr5Ynxqq0hTiSvsU,754
 biopipen/scripts/scrna/SeuratSubClustering.R,sha256=6b1J98YYK2gwJ_qkpuvYIdlj6uWxJA8IpUXvaCjgC_U,6334
 biopipen/scripts/scrna/SeuratSubset.R,sha256=yVA11NVE2FSSw-DhxQcJRapns0tNNHdyDYi5epO6SKM,1776
@@ -144,10 +144,10 @@ biopipen/scripts/scrna/SeuratTo10X.R,sha256=T2nJBTwOe12AIKC2FZsMSv6xx3s-67CYZokp
 biopipen/scripts/scrna/TopExpressingGenes.R,sha256=m1BEpDfrzD9rJ2wEwA355GMqBq8Wfc_PzCjtLavB68Q,7754
 biopipen/scripts/scrna/Write10X.R,sha256=OMhXvJwvaH-aWsMpijKrvXQVabc1qUu5ZEwiLAhkDeY,285
 biopipen/scripts/scrna/sctype.R,sha256=NaUJkABwF5G1UVm1CCtcMbwLSj94Mo24mbYCKFqo1Bw,6524
-biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R,sha256=4KVbBlk2fKBXlrA31HUc3zHPEE74ixTYF6YX0CcomW8,4805
-biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R,sha256=nxsaTnK2zk98adUUtxInU_7mRuS21lAQP5nIE6vVDn4,5197
-biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R,sha256=pF7XJheGXgx1i4BXng5KMukmicgni_XilkWp6pnwgrY,16169
-biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R,sha256=t0QHXrlnursqyvGn6Bf8xualNnlA3EqaOWj68pq7qyY,9820
+biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R,sha256=UbNoyspFB8166VgbkkFyTS6tkA-7ybylfvO50eqNnBU,4841
+biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R,sha256=dpyzIZU78zLHPLIEg9mAz8mK4XazxVuUm2CN33HGPpw,5233
+biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R,sha256=hq4UroRpg4p5pvXMXs9uOJTY1r0M5KzNAwhCOTLYFVQ,16205
+biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R,sha256=0MIRrUjCtTDkUiL6GfKbtjC7bLlt50AGWFv4fl4e72k,9856
 biopipen/scripts/tcgamaf/Maf2Vcf.py,sha256=Cxh7fiSNCxWDTfIJqZDOOnaSrw-85S_fH2U-PWY03hc,704
 biopipen/scripts/tcgamaf/MafAddChr.py,sha256=V10HMisl12O3ZfXuRmFNdy5p-3mr43WCvy0GHxSpwfA,494
 biopipen/scripts/tcgamaf/maf2vcf.pl,sha256=hJKcH-NbgWK6fmK7f3qex7ozJJl-PqCNPXqpwfcHwJg,22707
@@ -161,7 +161,7 @@ biopipen/scripts/tcr/GIANA/Imgt_Human_TRBV.fasta,sha256=XUwDPXJxVH5O9Q0gCL6EILKX
 biopipen/scripts/tcr/GIANA/query.py,sha256=5NWSEDNrJomMt48tzLGpRwJTZB0zQxvMVTilyG8osX8,7298
 biopipen/scripts/tcr/Immunarch-basic.R,sha256=lPmh8Il3bEvOHEpb4FN4BokRsq6cS2h47cT15YBv6fg,3194
 biopipen/scripts/tcr/Immunarch-clonality.R,sha256=ZPOSPNAVamHyM6yskx2MVAMNw051yuTaZllj3mUwxEM,3927
-biopipen/scripts/tcr/Immunarch-diversity.R,sha256=dcV32A4yBxKcjAezk6UHfPX3mS79TrVq9ApxryWkRgA,27375
+biopipen/scripts/tcr/Immunarch-diversity.R,sha256=Wk7b7435r4y4g3ItReTEAleHHfRXZtabRi3nNtqfo4A,27597
 biopipen/scripts/tcr/Immunarch-geneusage.R,sha256=30gJdMfe36enjIsn-tJayrU8YAowS_4EtVm5cj6FxUQ,6885
 biopipen/scripts/tcr/Immunarch-kmer.R,sha256=VmuXKI9AplyAj2NUnGV7utjgyu-ZuKRnry2ghf-9eQ0,6302
 biopipen/scripts/tcr/Immunarch-overlap.R,sha256=6RxXTjGhWzUC_1BxojMFrbrTq2PI_EAo9vpWxxbIs_o,7536
@@ -208,7 +208,7 @@ biopipen/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/utils/common_docstrs.py,sha256=ro9dUXeHMXBaqb-hTafwrG6xW5IOBEeiUM2_REjFoCo,5842
 biopipen/utils/gene.R,sha256=BzAwlLA8hO12vF-3t6IwEuTEeLa_jBll4zm_5qe3qoE,1243
 biopipen/utils/gene.py,sha256=qE_BqTayrJWxRdniffhcz6OhZcw9GUoOrj2EtFWH9Gw,2246
-biopipen/utils/gsea.R,sha256=FPH9H7V8mrZmqj30rBac5xBR7gu7UIKqLOT4W7lpA8E,5936
+biopipen/utils/gsea.R,sha256=rB_wHUBrn9SihMy_ICSRSgj-e48SGm_ZYs1oZtFgroA,7284
 biopipen/utils/io.R,sha256=jIYdqdn0iRWfQYAZa5CjXi3fikqmYvPPLIXhobRe8sw,537
 biopipen/utils/misc.R,sha256=nkjiAsEsilq0AeiKRDNqrhTx-1Grqg-rFlkjOEOEDYg,5224
 biopipen/utils/misc.py,sha256=Pmh3CBiKJ3vC_RqorfOfRAvTVKXrGDJT8DMLfYbTivs,3055
@@ -218,7 +218,7 @@ biopipen/utils/reference.py,sha256=6bPSwQa-GiDfr7xLR9a5T64Ey40y24yn3QfQ5wDFZkU,4
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=bKduqOQjSC8BtZJuwfUShR49omoEMbB57n3Gi6dYlqA,4147
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.23.5.dist-info/METADATA,sha256=R_O6RD_bSRRJZhYGObJS-zwXQfzU3HEnaGro0RoCXxQ,886
-biopipen-0.23.5.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-biopipen-0.23.5.dist-info/entry_points.txt,sha256=16Apdku3RFwghe1nb0JR7eVo4IzLae6hCWjU1VxYUn0,525
-biopipen-0.23.5.dist-info/RECORD,,
+biopipen-0.23.6.dist-info/METADATA,sha256=TMEpW8CrUWJfOaZufAWkrBwktO2uvWa-nbmAT_5FnOU,886
+biopipen-0.23.6.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+biopipen-0.23.6.dist-info/entry_points.txt,sha256=16Apdku3RFwghe1nb0JR7eVo4IzLae6hCWjU1VxYUn0,525
+biopipen-0.23.6.dist-info/RECORD,,