biopipen 0.27.7__py3-none-any.whl → 0.27.8__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.27.7"
+__version__ = "0.27.8"

biopipen/ns/scrna.py

@@ -1769,13 +1769,18 @@ class SeuratMap2Ref(Proc):
         sobjfile: The seurat object
 
     Output:
-        outfile: The rds file of seurat object with cell type annotated
+        outfile: The rds file of seurat object with cell type annotated.
+            Note that the reduction name will be `ref.umap` for the mapping.
+            To visualize the mapping, you should use `ref.umap` as the reduction name.
 
     Envs:
         ncores (type=int;order=-100): Number of cores to use.
-            Used in `future::plan(strategy = "multicore", workers = <ncores>)`
+            When `split_by` is used, this will be the number of cores for each object to map to the reference.
+            When `split_by` is not used, this is used in `future::plan(strategy = "multicore", workers = <ncores>)`
             to parallelize some Seurat procedures.
-            See also: <https://satijalab.org/seurat/articles/future_vignette.html>
+            See also: <https://satijalab.org/seurat/archive/v3.0/future_vignette.html>
+        mutaters (type=json): The mutaters to mutate the metadata.
+            This is helpful when we want to create new columns for `split_by`.
         use: A column name of metadata from the reference
             (e.g. `celltype.l1`, `celltype.l2`) to transfer to the query as the
             cell types (ident) for downstream analysis. This field is required.
@@ -1787,16 +1792,29 @@ class SeuratMap2Ref(Proc):
             `Seurat::LoadH5Seurat()`.
             The file type is determined by the extension. `.rds` or `.RDS` for
             RDS file, `.h5seurat` or `.h5` for h5seurat file.
+        refnorm (choice): Normalization method the reference used. The same method will be used for the query.
+            - NormalizeData: Using [`NormalizeData`](https://satijalab.org/seurat/reference/normalizedata).
+            - SCTransform: Using [`SCTransform`](https://satijalab.org/seurat/reference/sctransform).
+            - auto: Automatically detect the normalization method.
+                If the default assay of reference is `SCT`, then `SCTransform` will be used.
+        split_by: The column name in metadata to split the query into multiple objects.
+            This helps when the original query is too large to process.
         SCTransform (ns): Arguments for [`SCTransform()`](https://satijalab.org/seurat/reference/sctransform)
             - do-correct-umi (flag): Place corrected UMI matrix in assay counts layer?
             - do-scale (flag): Whether to scale residuals to have unit variance?
             - do-center (flag): Whether to center residuals to have mean zero?
             - <more>: See <https://satijalab.org/seurat/reference/sctransform>.
                 Note that the hyphen (`-`) will be transformed into `.` for the keys.
+        NormalizeData (ns): Arguments for [`NormalizeData()`](https://satijalab.org/seurat/reference/normalizedata)
+            - normalization-method: Normalization method.
+            - <more>: See <https://satijalab.org/seurat/reference/normalizedata>.
+                Note that the hyphen (`-`) will be transformed into `.` for the keys.
         FindTransferAnchors (ns): Arguments for [`FindTransferAnchors()`](https://satijalab.org/seurat/reference/findtransferanchors)
             - normalization-method (choice): Name of normalization method used.
                 - LogNormalize: Log-normalize the data matrix
                 - SCT: Scale data using the SCTransform method
+                - auto: Automatically detect the normalization method.
+                    See `envs.refnorm`.
             - reference-reduction: Name of dimensional reduction to use from the reference if running the pcaproject workflow.
                 Optionally enables reuse of precomputed reference dimensional reduction.
             - <more>: See <https://satijalab.org/seurat/reference/findtransferanchors>.
@@ -1822,14 +1840,19 @@ class SeuratMap2Ref(Proc):
         "ncores": config.misc.ncores,
         "use": None,
         "ident": "seurat_clusters",
+        "mutaters": {},
         "ref": None,
+        "refnorm": "auto",
+        "split_by": None,
         "SCTransform": {
             "do-correct-umi": False,
             "do-scale": False,
             "do-center": True,
         },
+        "NormalizeData": {
+            "normalization-method": "LogNormalize",
+        },
         "FindTransferAnchors": {
-            "normalization-method": "SCT",
             "reference-reduction": "spca",
         },
         "MapQuery": {

biopipen/scripts/scrna/SeuratClusterStats-stats.R

@@ -38,7 +38,7 @@ do_one_stats = function(name) {
         df_cells = df_cells %>% filter(!!rlang::parse_expr(case$subset))
     }
 
-    select_cols = c(case$ident, case$group.by, case$split.by)
+    select_cols = unique(c(case$ident, case$group.by, case$split.by))
     if (!is.null(case$split.by)) {
         plot_df = do_call(rbind, lapply(group_split(
             df_cells %>% select(all_of(select_cols)),

biopipen/scripts/scrna/SeuratMap2Ref.R

@@ -1,5 +1,6 @@
 source("{{biopipen_dir}}/utils/misc.R")
 
+library(parallel)
 library(Seurat)
 library(SeuratDisk)
 library(rlang)
@@ -12,8 +13,12 @@ outfile = {{out.outfile | r}}
 use = {{envs.use | r}}
 ident = {{envs.ident | r}}
 ref = {{envs.ref | r}}
+refnorm = {{envs.refnorm | r}}
 ncores = {{envs.ncores | r}}
+split_by = {{envs.split_by | r}}
+mutaters = {{envs.mutaters | r}}
 sctransform_args = {{envs.SCTransform | r: todot="-"}}
+normalizedata_args = {{envs.NormalizeData | r: todot="-"}}
 findtransferanchors_args = {{envs.FindTransferAnchors | r: todot="-"}}
 mappingscore_args = {{envs.MappingScore | r: todot="-"}}
 mapquery_args = {{envs.MapQuery | r: todot="-"}}
@@ -34,8 +39,10 @@ if (is.null(mapquery_args$refdata) || length(mapquery_args$refdata) == 0) {
 mapquery_args$refdata[[use]] = use
 
 outdir = dirname(outfile)
-options(future.globals.maxSize = 80000 * 1024^2)
-plan(strategy = "multicore", workers = ncores)
+if (is.null(split_by)) {
+    options(future.globals.maxSize = 80000 * 1024^2)
+    future::plan(strategy = "multicore", workers = ncores)
+}
 
 .expand_dims = function(args, name = "dims") {
     # Expand dims from 30 to 1:30
@@ -56,52 +63,191 @@ if (endsWith(ref, ".rds") || endsWith(ref, ".RDS")) {
     reference = LoadH5Seurat(ref)
 }
 
+if (refnorm == "auto" && DefaultAssay(reference) == "SCT") {
+    refnorm = "SCTransform"
+}
+log_info("  Normalization method used: {refnorm}")
+if (refnorm == "SCTransform") {
+    findtransferanchors_args$normalization.method = "SCT"
+} else if (refnorm == "NormalizeData") {
+    findtransferanchors_args$normalization.method = "LogNormalize"
+} else {
+    stop("Unknown normalization method: {refnorm}")
+}
+
 # Load Seurat object
 log_info("- Loading Seurat object")
 sobj = readRDS(sobjfile)
 
+if (!is.null(mutaters) && length(mutaters) > 0) {
+    log_info("- Applying mutaters")
+    sobj@meta.data <- sobj@meta.data %>% mutate(!!!lapply(mutaters, parse_expr))
+}
+
+if (!is.null(split_by)) {
+    # check if each split has more than 100 cells
+    cellno = table(sobj@meta.data[[split_by]])
+    cellno = cellno[cellno < 100]
+    if (length(cellno) > 0) {
+        # stop and print the splits with # cells
+        stop(paste0(
+            "The following splits have less than 100 cells: \n",
+            paste0("- ", names(cellno), ": ", cellno, collapse = "\n"),
+            "\n\n",
+            "You can use `envs.mutaters` to merge these splits and use `newsplit` as `envs.split_by`: \n",
+            "> mutaters = {\n",
+            ">   newsplit = \"if_else(oldsplit %in% c('split1', 'split2'), 'mergedsplit', oldsplit)\"\n",
+            "> }\n"
+        ))
+    }
+    sobj = SplitObject(sobj, split.by = split_by)
+}
+
 # Normalize data
 log_info("- Normalizing data")
-sctransform_args$object = sobj
-sctransform_args$residual.features = rownames(x = reference)
-query = do_call(SCTransform, sctransform_args)
+if (refnorm == "SCTransform") {
+    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)
+    } else {
+        query = mclapply(
+            X = sobj,
+            FUN = function(x) {
+                sctransform_args$object = x
+                do_call(SCTransform, sctransform_args)
+            },
+            mc.cores = ncores
+        )
+        if (any(unlist(lapply(query, class)) == "try-error")) {
+            stop(paste0("\nmclapply (SCTransform) error:", query))
+        }
+    }
+} else {
+    log_info("  Using NormalizeData normalization")
+    if (is.null(split_by)) {
+        normalizedata_args$object = sobj
+        query = do_call(NormalizeData, normalizedata_args)
+    } else {
+        query = mclapply(
+            X = sobj,
+            FUN = function(x) {
+                normalizedata_args$object = x
+                do_call(NormalizeData, normalizedata_args)
+            },
+            mc.cores = ncores
+        )
+        if (any(unlist(lapply(query, class)) == "try-error")) {
+            stop(paste0("\nmclapply (NormalizeData) error:", query))
+        }
+    }
+}
 
 # Find anchors between query and reference
 log_info("- Finding anchors")
 findtransferanchors_args$reference = reference
-findtransferanchors_args$query = query
-anchors = do_call(FindTransferAnchors, findtransferanchors_args)
+if (is.null(split_by)) {
+    findtransferanchors_args$query = query
+    anchors = do_call(FindTransferAnchors, findtransferanchors_args)
+} else {
+    anchors = mclapply(
+        X = query,
+        FUN = function(x) {
+            findtransferanchors_args$query = x
+            do_call(FindTransferAnchors, findtransferanchors_args)
+        },
+        mc.cores = ncores
+    )
+    if (any(unlist(lapply(anchors, class)) == "try-error")) {
+        stop(paste0("\nmclapply (FindTransferAnchors) error:", anchors))
+    }
+}
 
 # Map query to reference
 log_info("- Mapping query to reference")
 mapquery_args$reference = reference
-mapquery_args$query = query
-mapquery_args$anchorset = anchors
-query = do_call(MapQuery, mapquery_args)
+if (is.null(split_by)) {
+    mapquery_args$query = query
+    mapquery_args$anchorset = anchors
+    query = do_call(MapQuery, mapquery_args)
+} else {
+    query = mclapply(
+        X = seq_along(query),
+        FUN = function(i) {
+            mapquery_args$query = query[[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))
+    }
+}
 
 # Calculating mapping score
 log_info("- Calculating mapping score")
-mappingscore_args$anchors = anchors
-mappingscore = tryCatch({
-    do_call(MappingScore, mappingscore_args)
-}, error = function(e) {
-    if (e$message == "subscript out of bounds") {
-        stop(paste0(
-            "While calculating mapping score, the following error was encountered: \n",
-            "subscript out of bounds.  \n\n",
-            "You may want to try a smaller `ndim` (default: 50) in `envs.MappingScore`."
-        ))
+mappingscore_sob_msg = paste0(
+    "While calculating mapping score, the following error was encountered: \n",
+    "subscript out of bounds.  \n\n",
+    "You may want to try a smaller `ndim` (default: 50) in `envs.MappingScore`."
+)
+if (is.null(split_by)) {
+    mappingscore_args$anchors = anchors
+    mappingscore = tryCatch({
+        do_call(MappingScore, mappingscore_args)
+    }, error = function(e) {
+        if (e$message == "subscript out of bounds") stop(mappingscore_sob_msg)
+        stop(e)
+    })
+} else {
+    mappingscore = mclapply(
+        X = seq_along(query),
+        FUN = function(i) {
+            mappingscore_args$anchors = anchors[[i]]
+            tryCatch({
+                do_call(MappingScore, mappingscore_args)
+            }, error = function(e) {
+                if (e$message == "subscript out of bounds") stop(mappingscore_sob_msg)
+                stop(e)
+            })
+        },
+        mc.cores = ncores
+    )
+    if (any(unlist(lapply(mappingscore, class)) == "try-error")) {
+        stop(paste0("\nmclapply (MappingScore) error:", mappingscore))
     }
-    stop(e)
-})
+}
 
 # Calculate mapping score and add to metadata
-log_info("- Calculating mapping score")
-query = AddMetaData(
-  object = query,
-  metadata = mappingscore,
-  col.name = "mapping.score"
-)
+log_info("- Adding mapping score to metadata")
+if (is.null(split_by)) {
+    query = AddMetaData(
+        object = query,
+        metadata = mappingscore,
+        col.name = "mapping.score"
+    )
+} else {
+    query = mclapply(
+        X = seq_along(query),
+        FUN = function(i) {
+            AddMetaData(
+                object = query[[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))
+    }
+
+    # Combine the results
+    log_info("- Merging the results")
+    query = merge(query[[1]], query[2:length(query)], merge.dr = "ref.umap")
+}
 
 # Add the alias to the metadata for the clusters
 log_info("- Adding ident to metadata and set as ident")

{biopipen-0.27.7.dist-info → biopipen-0.27.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.7
+Version: 0.27.8
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.27.7.dist-info → biopipen-0.27.8.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=2q8A1v0my4JKqq2Mun4r1CJc3a3hPBoWgXjeUKWcOpQ,23
+biopipen/__init__.py,sha256=tTYofCNMPRiC5Qs7KVRV32NVPrdQ2HjfgoMDf4fChsQ,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=20RCI30Peee1EQdfb_UbV3Hf74XUPndJnYZlUThytsw,1781
@@ -21,7 +21,7 @@ biopipen/ns/gsea.py,sha256=EsNRAPYsagaV2KYgr4Jv0KCnZGqayM209v4yOGGTIOI,7423
 biopipen/ns/misc.py,sha256=fzn0pXvdghMkQhu-e3MMapPNMyO6IAJbtTzVU3GbFa0,3246
 biopipen/ns/plot.py,sha256=fzJAKKl4a_tsVkLREGCQTFVHP049m33LdWgeYRb6v7M,5483
 biopipen/ns/rnaseq.py,sha256=bKAa6friFWof4yDTWZQahm1MS-lrdetO1GqDKdfxXYc,7708
-biopipen/ns/scrna.py,sha256=qpMBKqkn_Cx6clpiNUpZjxGZIBzL3zPvO4m_Lxt4O0o,103952
+biopipen/ns/scrna.py,sha256=KL5Eu0mnIITLLSHAIz_sgr4ssmEU6AuBDXwedqYU7BI,105633
 biopipen/ns/scrna_metabolic_landscape.py,sha256=6AhaynGG3lNRi96N2tReVT46BJMuEwooSSd2irBoN80,28347
 biopipen/ns/snp.py,sha256=EQ2FS0trQ7YThPmBVTpS66lc2OSfgQ6lCh6WnyP-C2g,5499
 biopipen/ns/stats.py,sha256=yJ6C1CXF84T7DDs9mgufqUOr89Rl6kybE5ji8Vnx6cw,13693
@@ -141,12 +141,12 @@ biopipen/scripts/scrna/SeuratClusterStats-dimplots.R,sha256=gViDgQ8NorYD64iK0Fgc
 biopipen/scripts/scrna/SeuratClusterStats-features.R,sha256=W7iYhaFsC5EMZLO50QukYPLYGK4bq9kQc1VT5FwvI68,15496
 biopipen/scripts/scrna/SeuratClusterStats-hists.R,sha256=YhuD-GePjJPSkR0iLRgV_hiGHD_bnOIKp-LB6GCwquo,5037
 biopipen/scripts/scrna/SeuratClusterStats-ngenes.R,sha256=GVKIXFNS_syCuSN8oxoBkjxxAeI5LdSxh-qLVkUsbDA,2146
-biopipen/scripts/scrna/SeuratClusterStats-stats.R,sha256=TxQ0OcLwXwIgwL1mTLArboK0ATJIJhxWiv9DV_jBlhE,9255
+biopipen/scripts/scrna/SeuratClusterStats-stats.R,sha256=bBbvNCvV6dZLg9zvhh2nR48_53md5A5UEqrPXD00MZU,9263
 biopipen/scripts/scrna/SeuratClusterStats.R,sha256=ouWoj7Q644uG3MUlT23AES8f74g38-jPtPhINSvoUas,1267
 biopipen/scripts/scrna/SeuratClustering.R,sha256=kAvQq3RV86_KSv9NlUtUeQrPKkbhSsnv6Q4DoiTu8M0,6403
 biopipen/scripts/scrna/SeuratFilter.R,sha256=BrYK0MLdaTtQvInMaQsmOt7oH_hlks0M1zykkJtg2lM,509
 biopipen/scripts/scrna/SeuratLoading.R,sha256=ekWKnHIqtQb3kHVQiVymAHXXqiUxs6KKefjZKjaykmk,900
-biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=Xn3VnvKqShuC0Ju05380wjuLVSdW0uWVzntdxjme244,4359
+biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=_G8pG7NRV2GOFDzKBLY1nkXR0DO1c-6NkX990_hC8mk,9127
 biopipen/scripts/scrna/SeuratMetadataMutater.R,sha256=Pp4GsF3hZ6ZC2vroC3LSBmVa4B1p2L3hbh981yaAIeQ,1093
 biopipen/scripts/scrna/SeuratPreparing.R,sha256=t6GOcc9ZNwpRLeES7uBWja9RF6u6k5I_TXcdK4Ve7d0,18683
 biopipen/scripts/scrna/SeuratSplit.R,sha256=vdK11V39_Uo_NaOh76QWCtxObGaEr5Ynxqq0hTiSvsU,754
@@ -240,7 +240,7 @@ biopipen/utils/reference.py,sha256=6bPSwQa-GiDfr7xLR9a5T64Ey40y24yn3QfQ5wDFZkU,4
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=pJjYP8bIZpNAtTQ32rOXhZxaM1Y-6D-xUcK3pql9tbk,4316
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.27.7.dist-info/METADATA,sha256=uIwtisFh-OLK9tI5oR7psOVDH_lSUIT8Dy6iWzgmyyE,882
-biopipen-0.27.7.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.27.7.dist-info/entry_points.txt,sha256=wu70aoBcv1UahVbB_5237MY-9M9_mzqmWjDD-oi3yz0,621
-biopipen-0.27.7.dist-info/RECORD,,
+biopipen-0.27.8.dist-info/METADATA,sha256=3rTtE5ECOr8Y67BOOCAfleIqkVabeEstjmhzKwxUI-w,882
+biopipen-0.27.8.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+biopipen-0.27.8.dist-info/entry_points.txt,sha256=wu70aoBcv1UahVbB_5237MY-9M9_mzqmWjDD-oi3yz0,621
+biopipen-0.27.8.dist-info/RECORD,,