biopipen 0.22.0__py3-none-any.whl → 0.22.1__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.22.0"
+__version__ = "0.22.1"

biopipen/ns/tcr.py

@@ -40,11 +40,13 @@ class ImmunarchLoading(Proc):
 
     Output:
         rdsfile: The RDS file with the data and metadata
-        metatxt: The meta data of the cells, used to attach to the Seurat object
+        metatxt: The meta data at cell level, which can be used to attach to the Seurat object
 
     Envs:
         prefix: The prefix to the barcodes. You can use placeholder like `{Sample}_`
-            to use the meta data from the `immunarch` object.
+            to use the meta data from the `immunarch` object. The prefixed barcodes will
+            be saved in `out.metatxt`. The `immunarch` object keeps the original barcodes, but
+            the prefix is saved at `immdata$prefix`.
 
             /// Note
             This option is useful because the barcodes for the cells from scRNA-seq
@@ -65,10 +67,16 @@ class ImmunarchLoading(Proc):
             paired chain data. For `single`, only TRB chain will be kept
             at `immdata$data`, information for other chains will be
             saved at `immdata$tra` and `immdata$multi`.
-        metacols (list): The columns to be exported to the text file.
+        extracols (list): The extra columns to be exported to the text file.
             You can refer to the
             [immunarch documentation](https://immunarch.com/articles/v2_data.html#immunarch-data-format)
-            for the full list of the columns.
+            to get a sense for the full list of the columns.
+            The columns may vary depending on the data source.
+            The columns from `immdata$meta` and some core columns, including
+            `Barcode`, `CDR3.aa`, `Clones`, `Proportion`, `V.name`, `J.name`, and
+            `D.name` will be exported by default. You can use this option to
+            specify the extra columns to be exported.
+
     """  # noqa: E501
     input = "metafile:file"
     output = [
@@ -80,7 +88,7 @@ class ImmunarchLoading(Proc):
         "tmpdir": config.path.tmpdir,
         "prefix": "{Sample}_",
         "mode": "single",
-        "metacols": ["Clones", "Proportion", "CDR3.aa"],
+        "extracols": [],
     }
     script = "file://../scripts/tcr/ImmunarchLoading.R"
 
@@ -322,6 +330,7 @@ class Immunarch(Proc):
         prefix: The prefix to the barcodes. You can use placeholder like `{Sample}_`
             The prefixed barcodes will be used to match the barcodes in `in.metafile`.
             Not used if `in.metafile` is not specified.
+            If `None` (default), `immdata$prefix` will be used.
         volumes (ns): Explore clonotype volume (sizes).
             - by: Groupings when visualize clonotype volumes, passed to the `.by` argument of `vis(imm_vol, .by = <values>)`.
                 Multiple columns should be separated by `,`.
@@ -682,7 +691,7 @@ class Immunarch(Proc):
     lang = config.lang.rscript
     envs = {
         "mutaters": {},
-        "prefix": "{Sample}_",
+        "prefix": None,
         # basic statistics
         "volumes": {
             "by": None,
@@ -1179,6 +1188,10 @@ class TCRClustering(Proc):
             For GIANA, using TRBV mutations is not supported
             - GIANA: by Li lab at UT Southwestern Medical Center
             - ClusTCR: by Sebastiaan Valkiers, etc
+        prefix: The prefix to the barcodes. You can use placeholder like `{Sample}_`
+            The prefixed barcodes will be used to match the barcodes in `in.metafile`.
+            Not used if `in.metafile` is not specified.
+            If `None` (default), `immdata$prefix` will be used.
         python: The path of python with `GIANA`'s dependencies installed
             or with `clusTCR` installed. Depending on the `tool` you choose.
         args (type=json): The arguments for the clustering tool
@@ -1202,6 +1215,7 @@ class TCRClustering(Proc):
     lang = config.lang.rscript
     envs = {
         "tool": "GIANA",  # or ClusTCR
+        "prefix": None,
         "on_multi": False,
         "python": config.lang.python,
         "args": {},
@@ -1507,7 +1521,8 @@ class TESSA(Proc):
             [link](https://www.nature.com/articles/s42256-021-00383-2)
 
     Input:
-        immdata: The data loaded by `immunarch::repLoad()`, saved in RDS format
+        immdata: The immunarch object in RDS file or text file of TCR data loaded by
+            [`ImmunarchLoading`](!!#biopipennstcrimmunarchloading)
         srtobj: The `Seurat` object, saved in RDS format, with dimension
             reduction performed if you want to use them to represent the
             transcriptome of T cells.
@@ -1522,8 +1537,13 @@ class TESSA(Proc):
 
     Envs:
         python: The path of python with `TESSA`'s dependencies installed
-        prefix: The prefix to the barcodes of TCR data. You can use placeholder
-            like `{Sample}_` to use the meta data from the immunarch object.
+        prefix: The prefix of the cell barcodes in the `Seurat` object.
+            Once could use a fixed prefix, or a placeholder with the column
+            name in meta data. For example, `"{Sample}_"` will replace the
+            placeholder with the value of the column `Sample` in meta data.
+            If `in.immdata` is text file, the prefix will be ignored and the
+            barcode should be already prefixed.
+            If `None` and `in.immdata` is RDS file, `immdata$prefix` will be used.
         within_sample (flag): Whether the TCR networks are constructed only
             within TCRs from the same sample/patient (True) or with all the
             TCRs in the meta data matrix (False).
@@ -1548,7 +1568,7 @@ class TESSA(Proc):
     lang = config.lang.rscript
     envs = {
         "python": config.lang.python,
-        "prefix": "{Sample}_",
+        "prefix": None,
         "assay": "RNA",
         "within_sample": False,
         "predefined_b": False,

biopipen/scripts/scrna/CellsDistribution.R

@@ -229,10 +229,16 @@ do_case <- function(name, case) {
         meta %>% select(
             !!sym(cells_by),
             !!sym(case$group_by),
+            seurat_clusters,
             CloneSize,
             CloneGroupSize,
             CloneClusterSize,
             CloneGroupClusterSize,
+        ) %>% distinct(
+            !!sym(cells_by),
+            !!sym(case$group_by),
+            seurat_clusters,
+            .keep_all = TRUE
         ),
         txtfile,
         sep = "\t",

biopipen/scripts/scrna/SeuratMetadataMutater.R

@@ -1,4 +1,6 @@
+source("{{biopipen_dir}}/utils/misc.R")
 source("{{biopipen_dir}}/utils/mutate_helpers.R")
+
 library(rlang)
 library(tibble)
 library(dplyr)
@@ -14,7 +16,17 @@ metadata = srt@meta.data
 
 if (!is.null(metafile)) {
     mdata = read.table(metafile, header=TRUE, row.names=1, sep="\t", check.names=FALSE)
-    metadata = cbind(metadata, mdata[rownames(metadata),,drop=FALSE])
+    ov_cols = intersect(colnames(metadata), colnames(mdata))
+    if (length(ov_cols) > 0) {
+        log_warn(paste0(
+            "The following columns are already present in Seurat object and will be ignored: ",
+            paste(ov_cols, collapse=', ')
+        ))
+    }
+    metadata = cbind(
+        metadata,
+        mdata[rownames(metadata), setdiff(colnames(mdata), ov_cols), drop=FALSE]
+    )
 }
 
 expr = list()

biopipen/scripts/tcr/Attach2Seurat.R

@@ -11,6 +11,7 @@ immfile = {{in.immfile | r}}
 sobjfile = {{in.sobjfile | r}}
 outfile = {{out.outfile | r}}
 metacols = {{envs.metacols | r}}
+prefix = {{envs.prefix | r}}
 
 immdata = readRDS(immfile)
 sobj = readRDS(sobjfile)
@@ -31,7 +32,7 @@ metadf = do_call(rbind, lapply(seq_len(nrow(immdata$meta)), function(i) {
 
     cldata %>%
         separate_rows(Barcode, sep=";") %>%
-        mutate(Barcode = glue("{{envs.prefix}}{Barcode}"))
+        mutate(Barcode = glue(paste0(prefix, "{Barcode}")))
 
 }))
 

biopipen/scripts/tcr/CDR3AAPhyschem.R

@@ -193,7 +193,7 @@ merge_data = function(sam) {
     if (!is.null(prefix) && nchar(prefix) > 0) {
         # Replace the placeholder like {Sample} with the data in other columns
         # in the same row
-        sdata = sdata %>% mutate(.prefix_len = nchar(glue("{{envs.prefix}}")))
+        sdata = sdata %>% mutate(.prefix_len = nchar(glue(prefix)))
         # Remove the prefix in the rownames of sdata
         rownames(sdata) = substring(rownames(sdata), sdata$.prefix_len + 1)
         sdata = sdata %>% select(-.prefix_len)

biopipen/scripts/tcr/Immunarch.R

@@ -27,6 +27,9 @@ prefix = {{ envs.prefix | r }}
 log_info("Loading immdata ...")
 immdata = readRDS(immfile)
 
+if (is.null(prefix)) { prefix = immdata$prefix }
+if (is.null(prefix)) { prefix = "" }
+
 log_info("Expanding immdata ...")
 exdata = expand_immdata(immdata)
 

biopipen/scripts/tcr/ImmunarchLoading.R

@@ -1,4 +1,5 @@
 source("{{biopipen_dir}}/utils/misc.R")
+source("{{biopipen_dir}}/utils/single_cell.R")
 
 # Loading 10x data into immunarch
 library(immunarch)
@@ -13,7 +14,8 @@ rdsfile = {{ out.rdsfile | quote }}
 metatxt = {{ out.metatxt | quote }}
 tmpdir = {{ envs.tmpdir | quote }}
 mode = {{ envs.mode | quote }}
-metacols = {{ envs.metacols | r}}
+extracols = {{ envs.extracols | r}}
+prefix = {{ envs.prefix | r }}
 
 metadata = read.table(
     metafile,
@@ -164,27 +166,24 @@ immdata$meta = left_join(
     by = "Sample"
 )
 
-saveRDS(immdata, file=rdsfile)
-
-metadf = do_call(rbind, lapply(seq_len(nrow(immdata$meta)), function(i) {
-    # Clones  Proportion   CDR3.aa                       Barcode
-    # 5      4 0.008583691 CAVRDTGNTPLVF;CASSEYSNQPQHF   GTTCGGGCACTTACGA-1;TCTCTAAGTACCAGTT-1
-    # 6      4 0.008583691 CALTQAAGNKLTF;CASRPEDLRGQPQHF GCTTGAAGTCGGCACT-1;TACTCGCTCCTAAGTG-1
-    cldata = immdata$data[[i]][, unique(c(metacols, "Barcode"))]
-    # # A tibble: 4 × 5
-    # Sample                  Patient     Timepoint Tissue
-    # <chr>                   <chr>       <chr>     <chr>
-    # 1 MC1685Pt011-Baseline-PB MC1685Pt011 Baseline  PB
-    mdata = as.list(immdata$meta[i, , drop=FALSE])
-    for (mname in names(mdata)) {
-        assign(mname, mdata[[mname]])
-    }
+immdata$prefix = prefix
 
-    cldata %>%
-        separate_rows(Barcode, sep=";") %>%
-        distinct(Barcode, .keep_all = TRUE) %>%
-        mutate(Barcode = glue("{{envs.prefix}}{Barcode}")) %>%
-        column_to_rownames("Barcode")
+saveRDS(immdata, file=rdsfile)
 
-}))
-write.table(metadf, metatxt, sep="\t", quote=FALSE, row.names=TRUE, col.names=TRUE)
+exdata <- expand_immdata(immdata, cell_id = "Barcode") %>%
+    distinct(Sample, Barcode, .keep_all = TRUE) %>%
+    mutate(Barcode = glue(paste0(prefix, "{Barcode}"))) %>%
+    select(any_of(c(
+        colnames(immdata$meta),
+        "Barcode",
+        "CDR3.aa",
+        "Clones",
+        "Proportion",
+        "V.name",
+        "D.name",
+        "J.name",
+        extracols
+    ))) %>%
+    column_to_rownames("Barcode")
+
+write.table(exdata, metatxt, sep="\t", quote=FALSE, row.names=TRUE, col.names=TRUE)

biopipen/scripts/tcr/TCRClustering.R

@@ -3,11 +3,13 @@
 # python = Sys.which({{envs.python | r}})
 # Sys.setenv(RETICULATE_PYTHON = python)
 # library(reticulate)
+source("{{biopipen_dir}}/utils/single_cell.R")
 
 library(immunarch)
 library(dplyr)
 library(tidyr)
 library(tibble)
+library(glue)
 
 immfile = {{in.immfile | r}}
 outdir = normalizePath({{job.outdir | r}})
@@ -17,6 +19,7 @@ tool = {{envs.tool | r}}
 python = {{envs.python | r}}
 on_multi = {{envs.on_multi | r}}
 args = {{envs.args | r}}
+prefix = {{envs.prefix | r}}
 
 setwd(outdir)
 
@@ -26,17 +29,13 @@ if (on_multi) {
 } else {
     seqdata = immdata$data
 }
+if (is.null(prefix)) { prefix = immdata$prefix }
+if (is.null(prefix)) { prefix = "" }
 
 get_cdr3aa_df = function() {
-    out = NULL
-    for (sample in names(immdata$data)) {
-        tmpdf = immdata$data[[sample]] %>%
-            select(Barcode, CDR3.aa) %>%
-            separate_rows(Barcode, sep = ";") %>%
-            mutate(Barcode = paste0(sample, "_", Barcode))
-        out = bind_rows(out, tmpdf)
-    }
-    out
+    expand_immdata(immdata, cell_id = "Barcode") %>%
+        mutate(Barcode = glue(paste0(prefix, "{Barcode}"))) %>%
+        select(Barcode, CDR3.aa)
 }
 cdr3aa_df = get_cdr3aa_df()
 

biopipen/scripts/tcr/TESSA.R

@@ -1,8 +1,10 @@
 source("{{biopipen_dir}}/utils/misc.R")
+source("{{biopipen_dir}}/utils/single_cell.R")
 
 library(glue)
 library(dplyr)
 library(tidyr)
+library(tibble)
 library(immunarch)
 library(Seurat)
 library(ggplot2)
@@ -13,6 +15,7 @@ exprfile <- {{in.srtobj | r}}
 outfile <- {{out.outfile | r}}
 joboutdir <- {{job.outdir | r}}
 python <- {{envs.python | r}}
+prefix <- {{envs.prefix | r}}
 within_sample <- {{envs.within_sample | r}}
 assay <- {{envs.assay | r}}
 predefined_b <- {{envs.predefined_b | r}}
@@ -29,34 +32,21 @@ if (!dir.exists(tessa_dir)) dir.create(tessa_dir)
 ### Start preparing input files for TESSA
 # Prepare input files
 log_info("Preparing TCR input file ...")
-immdata <- readRDS(immfile)
-
-has_VJ <- "V.name" %in% colnames(immdata$data[[1]]) && "J.name" %in% colnames(immdata$data[[1]])
-# Merge all samples
-tcrdata <- do_call(rbind, lapply(seq_len(nrow(immdata$meta)), function(i) {
-    # Clones  Proportion   CDR3.aa                       Barcode
-    # 5      4 0.008583691 CAVRDTGNTPLVF;CASSEYSNQPQHF   GTTCGGGCACTTACGA-1;TCTCTAAGTACCAGTT-1
-    # 6      4 0.008583691 CALTQAAGNKLTF;CASRPEDLRGQPQHF GCTTGAAGTCGGCACT-1;TACTCGCTCCTAAGTG-1
-    if (has_VJ) {
-        cldata = immdata$data[[i]][, c("Barcode", "CDR3.aa", "V.name", "J.name")]
-    } else {
-        cldata = immdata$data[[i]][, c("Barcode", "CDR3.aa")]
-    }
-    # # A tibble: 4 × 5
-    # Sample                  Patient     Timepoint Tissue
-    # <chr>                   <chr>       <chr>     <chr>
-    # 1 MC1685Pt011-Baseline-PB MC1685Pt011 Baseline  PB
-    mdata = as.list(immdata$meta[i, , drop=FALSE])
-    for (mname in names(mdata)) {
-        assign(mname, mdata[[mname]])
-    }
+# If immfile endswith .rds, then it is an immunarch object
+if (endsWith(tolower(immfile), ".rds")) {
+    immdata <- readRDS(immfile)
+    if (is.null(prefix)) { prefix = immdata$prefix }
+    if (is.null(prefix)) { prefix = "" }
+    tcrdata <- expand_immdata(immdata) %>%
+        mutate(Barcode = glue(paste0(prefix, "{Barcode}")))
+    rm(immdata)
+} else {
+    tcrdata <- read.table(immfile, sep="\t", header=TRUE, row.names=1) %>%
+        rownames_to_column("Barcode")
+}
+
+has_VJ <- "V.name" %in% colnames(tcrdata) && "J.name" %in% colnames(tcrdata)
 
-    cldata %>%
-        separate_rows(Barcode, sep=";") %>%
-        # Just in case there are duplicated barcodes
-        distinct(Barcode, .keep_all = TRUE) %>%
-        mutate(Barcode = glue("{{envs.prefix}}{Barcode}"), sample = Sample)
-}))
 if (has_VJ) {
     tcrdata <- tcrdata %>% dplyr::mutate(
         v_gene = sub("-\\d+$", "", V.name),
@@ -66,13 +56,13 @@ if (has_VJ) {
         cdr3 = CDR3.aa,
         v_gene,
         j_gene,
-        sample
+        sample = Sample
     )
 } else {
     tcrdata <- tcrdata %>% dplyr::select(
         contig_id = Barcode,
         cdr3 = CDR3.aa,
-        sample
+        sample = Sample
     )
 }
 
@@ -101,7 +91,10 @@ if (length(unused_expr_cells) > 0) {
     log_warn(glue("{length(unused_expr_cells)}/{ncol(expr)} expression cells are not used."))
 }
 if (length(cell_ids) == 0) {
-    stop("No common cells between TCR and expression data. Are you using the correct prefix?")
+    stop(paste0(
+        "No common cells between TCR and expression data. ",
+        "Are you using the correct `envs.prefix` here or in `ImmunarchLoading`?"
+    ))
 }
 tcrdata <- tcrdata[tcrdata$contig_id %in% cell_ids, , drop=FALSE]
 expr <- as.matrix(expr)[, tcrdata$contig_id, drop=FALSE]

{biopipen-0.22.0.dist-info → biopipen-0.22.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.22.0
+Version: 0.22.1
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.22.0.dist-info → biopipen-0.22.1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=0kk8efeJF41FZIYweGTJylbizaWrp9W3qN78RClCWIU,23
+biopipen/__init__.py,sha256=mjWPUw5WSKjOdLE532eMicR6Gvc0AStLxFjzYGRWcns,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=JALO2S7TfmV3gIRPJ0cLTFWncPXXheQJS3vYQlyX6wQ,1600
@@ -23,7 +23,7 @@ biopipen/ns/scrna.py,sha256=F5j1TmjsS2swwm-uDyT6sTys5pldIJ_M2hNITAQdflc,82728
 biopipen/ns/scrna_basic.py,sha256=Py90IveDI5Alm6FUeC89xp3W79VPRvAQctQpc5JtO2M,8639
 biopipen/ns/scrna_metabolic_landscape.py,sha256=dSL-y1Gx1fcgebX7vk3wcSbm9aBALfCZKz0vjcDxQ_8,28139
 biopipen/ns/tcgamaf.py,sha256=AFbUJIxiMSvsVY3RcHgjRFuMnNh2DG3Mr5slLNEyz6o,1455
-biopipen/ns/tcr.py,sha256=-cHx2VjfcYUIwWh1OpEfjHDe3RPH-GDlLnpS4pljUs8,82417
+biopipen/ns/tcr.py,sha256=ZCwL_1Of-F5xVJ0hgdVLAjHwwwfegqkW_SO66oYULqM,83738
 biopipen/ns/vcf.py,sha256=cdkKroii0_nl_bSP2cnO09qESUAhHqu6btOiTSKS79Y,15314
 biopipen/ns/web.py,sha256=3zucrDo-IVsSnIvlw-deoScuxqWa6OMTm8Vo-R4E44Q,2224
 biopipen/reports/bam/CNAClinic.svelte,sha256=D4IxQcgDCPQZMbXog-aZP5iJEQTK2N4i0C60e_iXyfs,213
@@ -110,7 +110,7 @@ biopipen/scripts/scrna/CellTypeAnnotation-hitype.R,sha256=6_DBAlLKcHqaMyWGZWvTd4
 biopipen/scripts/scrna/CellTypeAnnotation-sccatch.R,sha256=1ejye0hs-EOwzzdP9gFWSLPcF6dOAA6VmNKXEjmS11E,1654
 biopipen/scripts/scrna/CellTypeAnnotation-sctype.R,sha256=u1eQsBWv1GKTbkwp6OFyiPuMFFcgwoa4-VI-d4q8nM4,3877
 biopipen/scripts/scrna/CellTypeAnnotation.R,sha256=6Le1SvZcKI8D0SLkFZ5SibGsW9ZWqirnBl3Q1BNZOuU,513
-biopipen/scripts/scrna/CellsDistribution.R,sha256=iuDGlfHNzenACW2y4KGRtwDQAI650XJ4SSMts7UDXS0,12734
+biopipen/scripts/scrna/CellsDistribution.R,sha256=8bDwA1xQHCHnGRBW5XfW35BOpNLydxbWX93TId9vRa8,12908
 biopipen/scripts/scrna/DimPlots.R,sha256=-mXOTMnpPxvR30XLjwcohFfFx7xTqWKKiICwJiD6yEo,1554
 biopipen/scripts/scrna/ExprImpution-alra.R,sha256=8wcyZk1Whf45SXsYOM_ykl8m-iBxr27KEjtslbl2JQQ,782
 biopipen/scripts/scrna/ExprImpution-rmagic.R,sha256=yYnkyVfqIaNynsbaZZLGS6DrAJ_XhVQj1Ox598w8yOY,651
@@ -131,7 +131,7 @@ biopipen/scripts/scrna/SeuratClustering.R,sha256=JBJkwZmdjMsWzHaa_WvYCN1tXQimgcl
 biopipen/scripts/scrna/SeuratFilter.R,sha256=BrYK0MLdaTtQvInMaQsmOt7oH_hlks0M1zykkJtg2lM,509
 biopipen/scripts/scrna/SeuratLoading.R,sha256=ekWKnHIqtQb3kHVQiVymAHXXqiUxs6KKefjZKjaykmk,900
 biopipen/scripts/scrna/SeuratMap2Ref.R,sha256=TkDSDc5do6BOtkAq3fS5HpjyqWUwsu8YqRC5in62oz8,3750
-biopipen/scripts/scrna/SeuratMetadataMutater.R,sha256=YvuhTKTWT7Se3hTqkgD3Ag_PKqKXiyDi6HcGCNIIKiM,723
+biopipen/scripts/scrna/SeuratMetadataMutater.R,sha256=Pp4GsF3hZ6ZC2vroC3LSBmVa4B1p2L3hbh981yaAIeQ,1093
 biopipen/scripts/scrna/SeuratPreparing.R,sha256=j_t8EbPoNNRFPquerYd6BjtbIgdHCt8h2XXZax8_tXM,8453
 biopipen/scripts/scrna/SeuratSplit.R,sha256=vdK11V39_Uo_NaOh76QWCtxObGaEr5Ynxqq0hTiSvsU,754
 biopipen/scripts/scrna/SeuratSubset.R,sha256=yVA11NVE2FSSw-DhxQcJRapns0tNNHdyDYi5epO6SKM,1776
@@ -146,8 +146,8 @@ biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R,sha25
 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
-biopipen/scripts/tcr/Attach2Seurat.R,sha256=kJck_jpjpLhUx1_9vjBeKWCrzI8Gb09nGwUOtp1Ztnk,1315
-biopipen/scripts/tcr/CDR3AAPhyschem.R,sha256=p5vBspsd0H3xgk2iptjbGlxfJZlW16BIy3lVcwiMfEI,16656
+biopipen/scripts/tcr/Attach2Seurat.R,sha256=C91TAh1cLSxWkdFPf84pbxlpTYMuWq_rduG4eiIkXZI,1345
+biopipen/scripts/tcr/CDR3AAPhyschem.R,sha256=rvXa9z7EY745Su0bzz0WpBd6QxXMGrzV_Eq7Ur9xb_g,16645
 biopipen/scripts/tcr/CloneResidency.R,sha256=sH76jRg_5q0THsIlgcHMCucdQyeLsc4jixbF938ennI,21421
 biopipen/scripts/tcr/CloneSizeQQPlot.R,sha256=5FPfWQjxTsv59KSDQaDWj3C95zPQMngKG7qOf95NEzI,4527
 biopipen/scripts/tcr/GIANA/GIANA.py,sha256=0qLhgCWxT8K-4JvORA03CzBPTT5pd4Di5B_DgrHXbFA,47198
@@ -163,15 +163,15 @@ biopipen/scripts/tcr/Immunarch-overlap.R,sha256=6RxXTjGhWzUC_1BxojMFrbrTq2PI_EAo
 biopipen/scripts/tcr/Immunarch-spectratyping.R,sha256=ICmCbsUDvwYjwL9kTiTEqQ7Fpmy7t7_GAJ5VTU9IeOU,2977
 biopipen/scripts/tcr/Immunarch-tracking.R,sha256=j1w36v1YuzohW1Nd14m90wRtjzpJSD6OM5KbF_wVxcY,4443
 biopipen/scripts/tcr/Immunarch-vjjunc.R,sha256=nOueF9l4_KVrKSZ1Sl0yObmjbd-5Hms2-RON6K23idg,3736
-biopipen/scripts/tcr/Immunarch.R,sha256=wddxHA4mGAdlQ_P7IXEiovVFYDTb9buGyFQ1MwwEHjI,2943
+biopipen/scripts/tcr/Immunarch.R,sha256=L8rGJ4GODQ-anB8aIVmlPqRK01FBLhw6_ANT_4L6jhU,3030
 biopipen/scripts/tcr/Immunarch2VDJtools.R,sha256=QB9ILGbnsfoWaRANK6ceb14wpSWy8F1V1EdEmfIqiks,706
 biopipen/scripts/tcr/ImmunarchFilter.R,sha256=o25O36FwH_0w6F8DFQ0SfpcwDzlzaGefXqr9ESrvb4k,3974
-biopipen/scripts/tcr/ImmunarchLoading.R,sha256=vg3Pg_5JvcOiT3gOrWn98EpjGi8r7SYh52hhvfSyyzk,5836
+biopipen/scripts/tcr/ImmunarchLoading.R,sha256=BNUJorjfF2R-j2ApUFKrAgqAJxzhzsDN9RUqzpkrfDY,5426
 biopipen/scripts/tcr/ImmunarchSplitIdents.R,sha256=FGCeGV0uSmFU91lKkldUAeV4A2m3hHw5X4GNi8ffGzI,1873
 biopipen/scripts/tcr/SampleDiversity.R,sha256=jQ1OU3b8vswD8tZhLt3fkcqJKrl2bhQX0giHM2rXz3Y,2643
 biopipen/scripts/tcr/TCRClusterStats.R,sha256=3YxIfsTBbFFI6fBTU3gM60bGuVv52PmL7bs16_WciGw,12089
-biopipen/scripts/tcr/TCRClustering.R,sha256=yfIiCMQuywjoJnAXwRJjlJsoYIA8swUMKIt_AsGvHQY,8566
-biopipen/scripts/tcr/TESSA.R,sha256=math-ZvkxYlZvXuHB0dNz3sv8hkx7p87EFW2PmEvJ60,7294
+biopipen/scripts/tcr/TCRClustering.R,sha256=bW9cwVZCRlFIqO03LsUKu6qk6xZ_WxarHDUcnl_diT8,8592
+biopipen/scripts/tcr/TESSA.R,sha256=nvzkhJHziTOjgZvAuU0L6qqCNgSp9f90P0i4tEMivwA,6798
 biopipen/scripts/tcr/TESSA_source/Atchley_factors.csv,sha256=SumqDOqP67P54uM7Cuc5_O_rySTWcGo7eX3psMSPX9s,763
 biopipen/scripts/tcr/TESSA_source/BriseisEncoder.py,sha256=z4_Q_6StymffuUGGjHP1-B3aTsXtamKao5Q1-Kg9has,6831
 biopipen/scripts/tcr/TESSA_source/MCMC_control.R,sha256=93Nnz0IG8KfFnVscZDvmBp1qccZoSoG_jIVpOWBQLHE,2911
@@ -213,7 +213,7 @@ 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-0.22.0.dist-info/METADATA,sha256=Qc13J8hjCs_d1_nhm5emj93Knx889HqPT7ciqRVlKjQ,886
-biopipen-0.22.0.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-biopipen-0.22.0.dist-info/entry_points.txt,sha256=sfI6oDEEuMvAg0KNujE9uu-c29y7IwQQA1_A2sUjPhc,527
-biopipen-0.22.0.dist-info/RECORD,,
+biopipen-0.22.1.dist-info/METADATA,sha256=0PvmDBQ2Ffe1tvlcVMcEz5AdFbhLhPrswGpxHYXB5KM,886
+biopipen-0.22.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+biopipen-0.22.1.dist-info/entry_points.txt,sha256=sfI6oDEEuMvAg0KNujE9uu-c29y7IwQQA1_A2sUjPhc,527
+biopipen-0.22.1.dist-info/RECORD,,