Repository 'music_deconvolution'
hg clone https://toolshed.g2.bx.psu.edu/repos/bgruening/music_deconvolution

Changeset 3:fd7a16d073c5 (2022-01-29)
Previous changeset 2:1c4cf4b7debe (2021-11-30) Next changeset 4:56371b5a2da9 (2022-02-10)
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/music/ commit 20f8561478535013e111d982b99639f48f1bea79"
modified:
macros.xml
music-deconvolution.xml
scripts/dendrogram.R
scripts/estimateprops.R
added:
test-data/default_output_no_disease.pdf
test-data/mouse_scrna_exprs.tabular
test-data/mouse_scrna_pheno.tabular
removed:
scripts/inspect.R
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 macros.xml
--- a/macros.xml Tue Nov 30 13:07:36 2021 +0000
+++ b/macros.xml Sat Jan 29 12:51:49 2022 +0000
b
@@ -1,9 +1,14 @@
 <macros>
-    <token name="@VERSION_SUFFIX@">1</token>
+    <token name="@VERSION_SUFFIX@">2</token>
     <!-- The ESet inspector/constructor and MuSiC tool can have
          independent Galaxy versions but should reference the same
          package version always. -->
     <token name="@TOOL_VERSION@">0.1.1</token>
+    <token name="@RDATATYPE@">rdata</token>
+    <!-- Below is disabled until Galaxy supports it. Still not present
+         in 21.09
+         <token name="@RDATATYPE@">rdata.eset</token>
+    -->
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@" >music-deconvolution</requirement>
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 music-deconvolution.xml
--- a/music-deconvolution.xml Tue Nov 30 13:07:36 2021 +0000
+++ b/music-deconvolution.xml Sat Jan 29 12:51:49 2022 +0000
[
b'@@ -1,5 +1,5 @@\n <tool id="music_deconvolution" name="MuSiC" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"\n-      profile="20.09" license="GPL-3.0-or-later" >\n+      profile="21.09" license="GPL-3.0-or-later" >\n     <description>estimate cell type proportions in bulk RNA-seq data</description>\n     <macros>\n         <import>macros.xml</import>\n@@ -25,20 +25,27 @@\n \n bulk_eset = readRDS(\'$bulk_eset\')\n scrna_eset = readRDS(\'$scrna_eset\')\n+use_disease_factor = FALSE\n+maxyscale = NA\n \n #if str($do.method) == "estimateprops":\n \n+maxyscale = as.numeric(\'$do.maxyscale\')  ## yields "NA" if blank\n phenotype_factors = null_str_vec(\'$do.phenotype_factors\')\n phenotype_factors_always_exclude = null_str_vec(\'$do.phenotype_factors_always_exclude\')\n celltypes_label = null_str_vec(\'$do.celltypes_label\')\n samples_label = null_str_vec(\'$do.samples_label\')\n celltypes = null_str_vec(\'$do.celltypes\')\n methods = c("MuSiC", "NNLS")\n-phenotype_target = null_str_vec(\'$do.phenotype_target\')\n-phenotype_target_threshold = as.numeric(\'$do.phenotype_target_threshold\')\n-sample_disease_group = null_str_vec(\'$do.sample_disease_group\')\n-sample_disease_group_scale = as.integer(\'$do.sample_disease_group_scale\')\n-compare_title = null_str_vec(\'$do.compare_title\')\n+\n+    #if str($do.disease_factor.use) == "yes":\n+use_disease_factor = TRUE\n+phenotype_scrna_target = null_str_vec(\'$do.disease_factor.phenotype_scrna_target\')\n+phenotype_target = null_str_vec(\'$do.disease_factor.phenotype_target\')\n+phenotype_target_threshold = as.numeric(\'$do.disease_factor.phenotype_target_threshold\')\n+sample_disease_group = null_str_vec(\'$do.disease_factor.sample_disease_group\')\n+sample_disease_group_scale = as.integer(\'$do.disease_factor.sample_disease_group_scale\')\n+    #end if\n \n outfile_pdf=\'$out_pdf\'\n \n@@ -54,11 +61,11 @@\n         #if $i == 0:\n         $repeat.cluster_id = list(cell.types = null_str_vec(\'$repeat.celltypes\'),\n             marker.names = null_str_vec(\'$repeat.marker_name\'),\n-                     marker.list = read_list(\'$repeat.marker_list\'))\n+            marker.list = read_list(\'$repeat.marker_list\'))\n         #else\n         , $repeat.cluster_id = list(cell.types = null_str_vec(\'$repeat.celltypes\'),\n-                     marker.names = null_str_vec(\'$repeat.marker_name\'),\n-                     marker.list = read_list(\'$repeat.marker_list\'))\n+            marker.names = null_str_vec(\'$repeat.marker_name\'),\n+            marker.list = read_list(\'$repeat.marker_list\'))\n         #end if\n     #end for\n )\n@@ -73,8 +80,8 @@\n         </configfile>\n     </configfiles>\n     <inputs>\n-        <param name="scrna_eset" label="scRNA Dataset" type="data" format="rdata.eset" />\n-        <param name="bulk_eset" label="Bulk RNA Dataset" type="data" format="rdata.eset" />\n+        <param name="scrna_eset" label="scRNA Dataset" type="data" format="@RDATATYPE@" />\n+        <param name="bulk_eset" label="Bulk RNA Dataset" type="data" format="@RDATATYPE@" />\n         <conditional name="do" >\n             <param name="method" type="select" label="Purpose" >\n                 <!-- The values here correspond to script names in the scripts folder\n@@ -103,24 +110,36 @@\n                        value="sampleID,SubjectName" >\n                     <expand macro="validator_index_identifiers" />\n                 </param>\n-                <param name="phenotype_target" type="text" label="Phenotype Target"\n-                       help="MUST exist in the bulk RNA datasets phenotype factors, as above." >\n-                    <expand macro="validator_text" />\n-                </param>\n-                <param name="phenotype_target_threshold" type="float" label="Phenotype Target Threshold"\n-                       value="-99"\n-                       help="The (%) threshold at which the phenotype target manifests. Leave at -99 to select all." >\n-                </param>\n-                <param name="sample_disease_group" type="text" label="Sample Disease Group"\n-                       help="MUST exist in th'..b'llection name="props" type="list" label="${tool.name} on ${on_string}: Proportion Matrices" >\n             <filter>do["method"] == "estimateprops"</filter>\n             <discover_datasets pattern="prop_(?P&lt;designation&gt;.+)\\.tabular" format="tabular" directory="report_data" />\n         </collection>\n         <collection name="summaries" type="list" label="${tool.name} on ${on_string}: Summaries and Logs">\n-            <filter>do["method"] == "estimateprops"</filter>\n+            <filter>do["method"] == "estimateprops" and do["disease_factor"]["use"] == "yes"</filter>\n             <discover_datasets pattern="summ_(?P&lt;designation&gt;.+)\\.txt" format="txt" directory="report_data" />\n             <discover_datasets pattern="varprop_(?P&lt;designation&gt;.+)\\.tabular" format="tabular" directory="report_data" />\n             <discover_datasets pattern="rsquared_(?P&lt;designation&gt;.+)\\.tabular" format="tabular" directory="report_data" />\n@@ -221,6 +240,18 @@\n                 </assert_contents>\n             </output>\n         </test>\n+        <test expect_num_outputs="2" >\n+            <!-- Estimate Proportions: no disease factor, no fitting reports -->\n+            <param name="bulk_eset" value="GSE50244bulkeset.subset.rds" />\n+            <param name="scrna_eset" value="EMTABesethealthy.subset.rds" />\n+            <conditional name="do" >\n+                <param name="method" value="estimateprops" />\n+                <param name="celltypes_label" value="cellType" />\n+                <param name="samples_label" value="sampleID" />\n+                <param name="disease_factor" value="no" />\n+            </conditional>\n+            <output name="out_pdf" value="default_output_no_disease.pdf" compare="sim_size" />\n+        </test>\n         <test expect_num_outputs="3" >\n             <!-- Estimate Proportions test -->\n             <param name="bulk_eset" value="GSE50244bulkeset.subset.rds" />\n@@ -230,12 +261,15 @@\n                 <param name="celltypes_label" value="cellType" />\n                 <param name="samples_label" value="sampleID" />\n                 <param name="celltypes" value="alpha,beta,delta,gamma,acinar,ductal" />\n-                <param name="phenotype_factors" value="age,bmi,hba1c,gender" />\n-                <param name="phenotype_target" value="hba1c" />\n-                <param name="phenotype_target_threshold" value="6.5" />\n-                <param name="sample_disease_group" value="T2D" />\n-                <param name="sample_disease_group_scale" value="5" />\n-                <param name="compare_title" value="HbA1c vs Beta Cell Type Proportion" />\n+                <conditional name="disease_factor" >\n+                    <param name="use" value="yes" />\n+                    <param name="phenotype_scrna_target" value="beta" />\n+                    <param name="phenotype_factors" value="age,bmi,hba1c,gender" />\n+                    <param name="phenotype_target" value="hba1c" />\n+                    <param name="phenotype_target_threshold" value="6.5" />\n+                    <param name="sample_disease_group" value="T2D" />\n+                    <param name="sample_disease_group_scale" value="5" />\n+                </conditional>\n             </conditional>\n             <output name="out_pdf" value="default_output.pdf" compare="sim_size" />\n             <output_collection name="summaries" count="5">\n@@ -257,10 +291,8 @@\n \n Solid tissues often contain closely related cell types which leads to collinearity. To deal with collinearity, MuSiC employs a tree-guided procedure that recursively zooms in on closely related cell types. Briefly, we first group similar cell types into the same cluster and estimate cluster proportions, then recursively repeat this procedure within each cluster.\n \n-.. image:: $PATH_TO_IMAGES/FigureMethod.jpg\n-\n     ]]></help>\n     <citations>\n         <citation type="doi">https://doi.org/10.1038/s41467-018-08023-x</citation>\n     </citations>\n-</tool>\n+</tool>\n\\ No newline at end of file\n'
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 scripts/dendrogram.R
--- a/scripts/dendrogram.R Tue Nov 30 13:07:36 2021 +0000
+++ b/scripts/dendrogram.R Sat Jan 29 12:51:49 2022 +0000
b
@@ -10,7 +10,7 @@
     if (lfile == "None") {
         return(NULL)
     }
-    return(read.table(file = lfile, header = FALSE,
+    return(read.table(file = lfile, header = FALSE, check.names = FALSE,
                       stringsAsFactors = FALSE)$V1)
 }
 
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 scripts/estimateprops.R
--- a/scripts/estimateprops.R Tue Nov 30 13:07:36 2021 +0000
+++ b/scripts/estimateprops.R Sat Jan 29 12:51:49 2022 +0000
[
b'@@ -17,13 +17,21 @@\n estimated_music_props <- est_prop$Est.prop.weighted\n estimated_nnls_props <- est_prop$Est.prop.allgene\n \n+scale_yaxes <- function(gplot, value) {\n+    if (is.na(value)) {\n+        gplot\n+    } else {\n+        gplot + scale_y_continuous(lim = c(0, value))\n+    }\n+}\n+\n ## Show different in estimation methods\n ## Jitter plot of estimated cell type proportions\n-jitter_fig <- Jitter_Est(\n+jitter_fig <- scale_yaxes(Jitter_Est(\n     list(data.matrix(estimated_music_props),\n          data.matrix(estimated_nnls_props)),\n     method.name = methods, title = "Jitter plot of Est Proportions",\n-    size = 2, alpha = 0.7) + theme_minimal()\n+    size = 2, alpha = 0.7) + theme_minimal(), maxyscale)\n \n \n ## Make a Plot\n@@ -42,11 +50,6 @@\n     message(celltypes)\n }\n \n-if (phenotype_target_threshold == -99) {\n-    phenotype_target_threshold <- -Inf\n-    message("phenotype target threshold set to -Inf")\n-}\n-\n if (is.null(phenotype_factors)) {\n     phenotype_factors <- colnames(pData(bulk_eset))\n }\n@@ -54,67 +57,94 @@\n phenotype_factors <- phenotype_factors[\n     !(phenotype_factors %in% phenotype_factors_always_exclude)]\n message("Phenotype Factors to use:")\n-message(phenotype_factors)\n-\n+message(paste0(phenotype_factors, collapse = ", "))\n \n m_prop$CellType <- factor(m_prop$CellType, levels = celltypes) # nolint\n m_prop$Method <- factor(rep(methods, each = nrow(estimated_music_props_flat)), # nolint\n                         levels = methods)\n-m_prop$Disease_factor <- rep(bulk_eset[[phenotype_target]], 2 * length(celltypes)) # nolint\n-m_prop <- m_prop[!is.na(m_prop$Disease_factor), ]\n-## Generate a TRUE/FALSE table of Normal == 1 and Disease == 2\n-sample_groups <- c("Normal", sample_disease_group)\n-m_prop$Disease <- factor(sample_groups[(m_prop$Disease_factor > phenotype_target_threshold) + 1], # nolint\n-                         levels = sample_groups)\n+\n+if (use_disease_factor) {\n+\n+    if (phenotype_target_threshold == -99) {\n+        phenotype_target_threshold <- -Inf\n+        message("phenotype target threshold set to -Inf")\n+    }\n+\n+    m_prop$Disease_factor <- rep(bulk_eset[[phenotype_target]], 2 * length(celltypes)) # nolint\n+    m_prop <- m_prop[!is.na(m_prop$Disease_factor), ]\n+    ## Generate a TRUE/FALSE table of Normal == 1 and Disease == 2\n+    sample_groups <- c("Normal", sample_disease_group)\n+    m_prop$Disease <- factor(sample_groups[(m_prop$Disease_factor > phenotype_target_threshold) + 1], # nolint\n+                             levels = sample_groups)\n \n-## Binary to scale: e.g. TRUE / 5 = 0.2\n-m_prop$D <- (m_prop$Disease ==   # nolint\n-             sample_disease_group) / sample_disease_group_scale\n-## NA\'s are not included in the comparison below\n-m_prop <- rbind(subset(m_prop, Disease != sample_disease_group),\n-               subset(m_prop, Disease == sample_disease_group))\n+    ## Binary to scale: e.g. TRUE / 5 = 0.2\n+    m_prop$D <- (m_prop$Disease ==   # nolint\n+                 sample_disease_group) / sample_disease_group_scale\n+    ## NA\'s are not included in the comparison below\n+    m_prop <- rbind(subset(m_prop, Disease != sample_disease_group),\n+                    subset(m_prop, Disease == sample_disease_group))\n \n-jitter_new <- ggplot(m_prop, aes(Method, Prop)) +\n-    geom_point(aes(fill = Method, color = Disease, stroke = D, shape = Disease),\n-               size = 2, alpha = 0.7,\n-               position = position_jitter(width = 0.25, height = 0)) +\n-    facet_wrap(~ CellType, scales = "free") +\n-    scale_colour_manual(values = c("white", "gray20")) +\n-    scale_shape_manual(values = c(21, 24)) + theme_minimal()\n+    jitter_new <- scale_yaxes(ggplot(m_prop, aes(Method, Prop)) +\n+        geom_point(aes(fill = Method, color = Disease, stroke = D, shape = Disease),\n+                   size = 2, alpha = 0.7,\n+                   position = position_jitter(width = 0.25, height = 0)) +\n+        facet_wrap(~ CellType, scales = "free") +\n+        scale_colour_manual(values = c("white", "gray20")) '..b'type_target), " vs. ",\n+                       toupper(phenotype_scrna_target), " Cell Type Proportion")) +\n+        theme_minimal() +\n+        ylab(paste0("Proportion of ",\n+                    phenotype_scrna_target, " cells")) +\n+        xlab(paste0("Level of bulk factor (", phenotype_target, ")")) +\n+        scale_colour_manual(values = c("white", "gray20")) +\n+        scale_shape_manual(values = c(21, 24)), maxyscale)\n+}\n \n ## BoxPlot\n-plot_box <- Boxplot_Est(list(\n+plot_box <- scale_yaxes(Boxplot_Est(list(\n     data.matrix(estimated_music_props),\n     data.matrix(estimated_nnls_props)),\n     method.name = c("MuSiC", "NNLS")) +\n     theme(axis.text.x = element_text(angle = -90),\n           axis.text.y = element_text(size = 8)) +\n-    ggtitle(element_blank()) + theme_minimal()\n+    ggtitle(element_blank()) + theme_minimal(), maxyscale)\n \n ## Heatmap\n plot_hmap <- Prop_heat_Est(list(\n@@ -125,8 +155,15 @@\n           axis.text.y = element_text(size = 6))\n \n pdf(file = outfile_pdf, width = 8, height = 8)\n-plot_grid(jitter_fig, plot_box, labels = "auto", ncol = 1, nrow = 2)\n-plot_grid(jitter_new, jitt_compare, labels = "auto", ncol = 1, nrow = 2)\n+if (length(celltypes) <= 8) {\n+    plot_grid(jitter_fig, plot_box, labels = "auto", ncol = 1, nrow = 2)\n+} else {\n+    print(jitter_fig)\n+    plot_box\n+}\n+if (use_disease_factor) {\n+    plot_grid(jitter_new, jitt_compare, labels = "auto", ncol = 1, nrow = 2)\n+}\n plot_hmap\n message(dev.off())\n \n@@ -159,29 +196,32 @@\n             quote = F, sep = "\\t", col.names = NA)\n \n \n-## Summary table\n-for (meth in methods) {\n-    ##lm_beta_meth = lm(ct.prop ~ age + bmi + hba1c + gender, data =\n-    sub_data <- subset(m_prop_ana, Method == meth)\n-    ## We can only do regression where there are more than 1 factors\n-    ## so we must find and exclude the ones which are not\n-    gt1_facts <- sapply(phenotype_factors, function(facname) {\n-        return(length(unique(sort(sub_data[[facname]]))) == 1)\n-    })\n-    form_factors <- phenotype_factors\n-    exclude_facts <- names(gt1_facts)[gt1_facts]\n-    if (length(exclude_facts) > 0) {\n-        message("Factors with only one level will be excluded:")\n-        message(exclude_facts)\n-        form_factors <- phenotype_factors[\n-            !(phenotype_factors %in% exclude_facts)]\n+if (use_disease_factor) {\n+    ## Summary table of linear regressions of disease factors\n+    for (meth in methods) {\n+        ##lm_beta_meth = lm(ct.prop ~ age + bmi + hba1c + gender, data =\n+        sub_data <- subset(m_prop_ana, Method == meth)\n+\n+        ## We can only do regression where there are more than 1 factors\n+        ## so we must find and exclude the ones which are not\n+        gt1_facts <- sapply(phenotype_factors, function(facname) {\n+            return(length(unique(sort(sub_data[[facname]]))) == 1)\n+        })\n+        form_factors <- phenotype_factors\n+        exclude_facts <- names(gt1_facts)[gt1_facts]\n+        if (length(exclude_facts) > 0) {\n+            message("Factors with only one level will be excluded:")\n+            message(exclude_facts)\n+            form_factors <- phenotype_factors[\n+                !(phenotype_factors %in% exclude_facts)]\n+        }\n+        lm_beta_meth <- lm(as.formula(\n+            paste("ct.prop", paste(form_factors, collapse = " + "),\n+                  sep = " ~ ")), data = sub_data)\n+        message(paste0("Summary: ", meth))\n+        capture.output(summary(lm_beta_meth),\n+                       file = paste0("report_data/summ_Log of ",\n+                                     meth,\n+                                     " fitting.txt"))\n     }\n-    lm_beta_meth <- lm(as.formula(\n-        paste("ct.prop", paste(form_factors, collapse = " + "),\n-              sep = " ~ ")), data = sub_data)\n-    message(paste0("Summary: ", meth))\n-    capture.output(summary(lm_beta_meth),\n-                   file = paste0("report_data/summ_Log of ",\n-                                 meth,\n-                                 " fitting.txt"))\n }\n'
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 scripts/inspect.R
--- a/scripts/inspect.R Tue Nov 30 13:07:36 2021 +0000
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
[
@@ -1,27 +0,0 @@
-
-suppressWarnings(suppressPackageStartupMessages(library(xbioc)))
-suppressWarnings(suppressPackageStartupMessages(library(MuSiC)))
-
-args <- commandArgs(trailingOnly = TRUE)
-source(args[1])
-
-printout <- function(text) {
-    if (typeof(text) %in% c("list", "vector", "integer", "double", "numeric")) {
-        write.table(text, file = outfile_tab, quote = F, sep = "\t",
-                    col.names = NA)
-    } else {
-        ## text
-        print(typeof(text))
-        capture.output(text, file = outfile_tab)  # nolint
-    }
-}
-
-if (inspector %in% c("print", "pData", "fData", "dims",
-                     "experimentData", "protocolData", "exprs",
-                     "signature", "annotation", "abstract")) {
-    op <- get(inspector)
-    tab <- op(rds_eset)
-    printout(tab)
-} else {
-    stop(paste0("No such option:", inspector))
-}
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 test-data/default_output_no_disease.pdf
b
Binary file test-data/default_output_no_disease.pdf has changed
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 test-data/mouse_scrna_exprs.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mouse_scrna_exprs.tabular Sat Jan 29 12:51:49 2022 +0000
b
b'@@ -0,0 +1,101 @@\n+\tTGGTTCCGTCGGCTCA-2\tCGAGCCAAGCGTCAAG-4\tGAATGAAGTTTGGGCC-5\tCTCGTACGTTGCCTCT-7\tTTCTCAATCCACGCAG-5\tCCTTCCCCATACCATG-4\tACTTTCACAGCTGGCT-7\tTGGGAAGCAAAGTGCG-7\tTCTATTGAGTAGGCCA-7\tTCGGTAACATCACGTA-2\tGGGTTGCCAGCTGTAT-2\tTGCGGGTGTCATATCG-6\tACTTGTTTCATATCGG-5\tCCAATCCCACGGCGTT-2\tCTAAGACCACCAGGCT-7\tTTAACTCAGTAGGCCA-6\tGTACTCCGTAACGCGA-1\tGCCTCTAGTTGTACAC-2\tTTCGAAGTCCTGCAGG-3\tTTCTACAAGTTGTAGA-7\tCCGTTCAGTTGAACTC-7\tGTGTTAGTCAGCTCGG-1\tGGATTACGTGTGCGTC-6\tTACGGTATCCGTTGTC-6\tTTAGTTCGTATTAGCC-5\tCCCAATCGTAGCGATG-3\tACACCAATCTGCGTAA-7\tAATCCAGTCCAAACTG-7\tCAGAATCAGCAATATG-1\tGCACATAAGCCGGTAA-5\tCCTTCCCAGGAGTTTA-5\tCGGAGCTAGGACTGGT-5\tTACGGATGTAAATGTG-4\tGGCAATTCATTCACTT-2\tCTCGGGAGTCTGCGGT-4\tCATTCGCGTCCTCTTG-2\tCGCGTTTAGATCGATA-1\tGGGTTGCCACCAACCG-4\tTGTGTTTCATCGATGT-2\tAGAGTGGAGCTGTTCA-7\tCTCACACGTCTCACCT-3\tAGTTGGTTCCACGAAT-7\tATCTGCCAGACCACGA-6\tTGTATTCCATTGAGCT-7\tTGAAAGAGTAGCCTAT-7\tAAATGCCAGAACTGTA-7\tTTTGCGCTCTACCAGA-4\tACATACGGTTTCCACC-6\tGCCTCTAGTTCCACAA-7\tGGGAGATGTACTCTCC-6\tGAACGGATCTTGTACT-7\tTACCTTATCCTAGAAC-1\tGCGCGATAGATGCCAG-2\tGACAGAGCAAGTTGTC-7\tTGACTAGGTATGAATG-3\tCACACTCAGTCACGCC-6\tATTGGTGGTTAGGGTG-5\tAGCAGCCCAGCGTAAG-2\tCATTCGCAGCCTTGAT-6\tGCGAGAACATAGACTC-2\tAGTCTTTGTAATAGCA-7\tTCGCGAGCAGACACTT-7\tCGGAGTCCAGCAGTTT-2\tGGTGTTACACACATGT-7\tTTCTCAAGTAAGTGTA-2\tTGCTGCTAGTCAATAG-2\tGATGAGGTCTACCAGA-2\tACATACGGTTGTACAC-5\tACGAGGACAGCTATTG-7\tCGATGTATCGGCGGTT-2\tCTGCGGATCACAACGT-2\tCGAACATAGTTGAGTA-5\tTAGTTGGTCGCGATCG-6\tGCAGCCACAATGTAAG-4\tCTCACACCAATAACGA-7\tCCTTTCTCATGAAGTA-2\tAGTGTCAAGAGCAATT-7\tAGCATACGTAAAGGAG-1\tACACCAATCTCGCTTG-5\tGGGATGAGTATCAGTC-6\tTGACAACAGAAGCCCA-2\tCGAATGTTCACAATGC-1\tGCACTCTTCCGCATAA-1\tCACCAGGTCCCAAGAT-2\tGTTACAGCACCGCTAG-6\tTAGCCGGCAGTACACT-2\tACGATGTGTTAAAGAC-2\tCCTTCCCAGTCTCGGC-7\tTAGTGGTTCTCTGTCG-7\tTAGCCGGAGGCTAGCA-5\tTTGTAGGTCAGCACAT-1\tGAATAAGCAGCTTCGG-7\tTCGCGAGAGTCCGGTC-3\tTCAACGAAGAGTAAGG-2\tCAGGTGCCACGAAATA-5\tTGTGTTTCACTATCTT-2\tTGGCCAGAGTGAAGAG-6\tACCAGTAAGTAGCCGA-2\tGCGGGTTAGAAGGTTT-1\tCAGTCCTGTCATTAGC-2\n+Rp1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Sox17\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Mrpl15\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\n+Lypla1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t2\t0\t1\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t2\t0\t1\t1\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t2\t0\t0\t0\t6\t2\t0\t2\t0\t0\t2\t0\t2\t0\t1\t1\t0\t0\t0\t0\t0\n+Gm37988\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Tcea1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Atp6v1h\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t2\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t3\n+Rb1cc1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t1\t2\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t2\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+4732440D04Rik\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\n+Pcmtd1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t1\t0\t0\t1\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t1\t1\t0\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1'..b'\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t1\t0\t0\t1\t1\t0\n+Hs6st1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t2\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\n+Uggt1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Neurl3\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Arid5a\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+4930403P22Rik\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Kansl3\t0\t0\t0\t0\t1\t0\t1\t0\t1\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t1\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\n+Lman2l\t0\t0\t0\t2\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Cnnm4\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Cnnm3\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Ankrd23\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Ankrd39\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\n+Sema4c\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Fam178b\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Cox5b\t1\t4\t1\t1\t10\t0\t1\t1\t0\t2\t2\t0\t0\t2\t0\t1\t7\t3\t17\t0\t8\t5\t1\t0\t4\t1\t4\t5\t2\t12\t2\t21\t3\t5\t5\t6\t2\t2\t3\t3\t1\t2\t0\t4\t6\t2\t0\t1\t0\t5\t2\t7\t5\t2\t4\t0\t5\t1\t0\t0\t1\t4\t4\t1\t4\t1\t0\t5\t10\t1\t6\t4\t0\t1\t0\t5\t2\t1\t10\t4\t4\t0\t2\t11\t2\t0\t2\t1\t7\t11\t9\t4\t1\t14\t2\t3\t1\t5\t0\t12\n+Actr1b\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t1\t2\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\n+Zap70\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Tmem131\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Inpp4a\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Coa5\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\n'
b
diff -r 1c4cf4b7debe -r fd7a16d073c5 test-data/mouse_scrna_pheno.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mouse_scrna_pheno.tabular Sat Jan 29 12:51:49 2022 +0000
b
@@ -0,0 +1,101 @@
+ sampleID SubjectName cellTypeID cellType
+TGGTTCCGTCGGCTCA-2 2 Mouse2 3 PT
+CGAGCCAAGCGTCAAG-4 4 Mouse4 5 DCT
+GAATGAAGTTTGGGCC-5 5 Mouse5 3 PT
+CTCGTACGTTGCCTCT-7 7 Mouse7 3 PT
+TTCTCAATCCACGCAG-5 5 Mouse5 4 LOH
+CCTTCCCCATACCATG-4 4 Mouse4 14 T lymph
+ACTTTCACAGCTGGCT-7 7 Mouse7 3 PT
+TGGGAAGCAAAGTGCG-7 7 Mouse7 3 PT
+TCTATTGAGTAGGCCA-7 7 Mouse7 3 PT
+TCGGTAACATCACGTA-2 2 Mouse2 3 PT
+GGGTTGCCAGCTGTAT-2 2 Mouse2 2 Podo
+TGCGGGTGTCATATCG-6 6 Mouse6 3 PT
+ACTTGTTTCATATCGG-5 5 Mouse5 14 T lymph
+CCAATCCCACGGCGTT-2 2 Mouse2 5 DCT
+CTAAGACCACCAGGCT-7 7 Mouse7 3 PT
+TTAACTCAGTAGGCCA-6 6 Mouse6 3 PT
+GTACTCCGTAACGCGA-1 1 Mouse1 3 PT
+GCCTCTAGTTGTACAC-2 2 Mouse2 3 PT
+TTCGAAGTCCTGCAGG-3 3 Mouse3 3 PT
+TTCTACAAGTTGTAGA-7 7 Mouse7 3 PT
+CCGTTCAGTTGAACTC-7 7 Mouse7 7 CD-IC
+GTGTTAGTCAGCTCGG-1 1 Mouse1 4 LOH
+GGATTACGTGTGCGTC-6 6 Mouse6 3 PT
+TACGGTATCCGTTGTC-6 6 Mouse6 3 PT
+TTAGTTCGTATTAGCC-5 5 Mouse5 3 PT
+CCCAATCGTAGCGATG-3 3 Mouse3 3 PT
+ACACCAATCTGCGTAA-7 7 Mouse7 5 DCT
+AATCCAGTCCAAACTG-7 7 Mouse7 5 DCT
+CAGAATCAGCAATATG-1 1 Mouse1 3 PT
+GCACATAAGCCGGTAA-5 5 Mouse5 5 DCT
+CCTTCCCAGGAGTTTA-5 5 Mouse5 3 PT
+CGGAGCTAGGACTGGT-5 5 Mouse5 4 LOH
+TACGGATGTAAATGTG-4 4 Mouse4 3 PT
+GGCAATTCATTCACTT-2 2 Mouse2 3 PT
+CTCGGGAGTCTGCGGT-4 4 Mouse4 6 CD-PC
+CATTCGCGTCCTCTTG-2 2 Mouse2 8 CD-Trans
+CGCGTTTAGATCGATA-1 1 Mouse1 6 CD-PC
+GGGTTGCCACCAACCG-4 4 Mouse4 7 CD-IC
+TGTGTTTCATCGATGT-2 2 Mouse2 3 PT
+AGAGTGGAGCTGTTCA-7 7 Mouse7 3 PT
+CTCACACGTCTCACCT-3 3 Mouse3 3 PT
+AGTTGGTTCCACGAAT-7 7 Mouse7 3 PT
+ATCTGCCAGACCACGA-6 6 Mouse6 3 PT
+TGTATTCCATTGAGCT-7 7 Mouse7 3 PT
+TGAAAGAGTAGCCTAT-7 7 Mouse7 3 PT
+AAATGCCAGAACTGTA-7 7 Mouse7 5 DCT
+TTTGCGCTCTACCAGA-4 4 Mouse4 3 PT
+ACATACGGTTTCCACC-6 6 Mouse6 3 PT
+GCCTCTAGTTCCACAA-7 7 Mouse7 3 PT
+GGGAGATGTACTCTCC-6 6 Mouse6 1 Endo
+GAACGGATCTTGTACT-7 7 Mouse7 3 PT
+TACCTTATCCTAGAAC-1 1 Mouse1 3 PT
+GCGCGATAGATGCCAG-2 2 Mouse2 3 PT
+GACAGAGCAAGTTGTC-7 7 Mouse7 3 PT
+TGACTAGGTATGAATG-3 3 Mouse3 4 LOH
+CACACTCAGTCACGCC-6 6 Mouse6 3 PT
+ATTGGTGGTTAGGGTG-5 5 Mouse5 3 PT
+AGCAGCCCAGCGTAAG-2 2 Mouse2 1 Endo
+CATTCGCAGCCTTGAT-6 6 Mouse6 3 PT
+GCGAGAACATAGACTC-2 2 Mouse2 14 T lymph
+AGTCTTTGTAATAGCA-7 7 Mouse7 3 PT
+TCGCGAGCAGACACTT-7 7 Mouse7 3 PT
+CGGAGTCCAGCAGTTT-2 2 Mouse2 3 PT
+GGTGTTACACACATGT-7 7 Mouse7 3 PT
+TTCTCAAGTAAGTGTA-2 2 Mouse2 1 Endo
+TGCTGCTAGTCAATAG-2 2 Mouse2 3 PT
+GATGAGGTCTACCAGA-2 2 Mouse2 3 PT
+ACATACGGTTGTACAC-5 5 Mouse5 3 PT
+ACGAGGACAGCTATTG-7 7 Mouse7 4 LOH
+CGATGTATCGGCGGTT-2 2 Mouse2 3 PT
+CTGCGGATCACAACGT-2 2 Mouse2 13 B lymph
+CGAACATAGTTGAGTA-5 5 Mouse5 3 PT
+TAGTTGGTCGCGATCG-6 6 Mouse6 5 DCT
+GCAGCCACAATGTAAG-4 4 Mouse4 1 Endo
+CTCACACCAATAACGA-7 7 Mouse7 3 PT
+CCTTTCTCATGAAGTA-2 2 Mouse2 7 CD-IC
+AGTGTCAAGAGCAATT-7 7 Mouse7 3 PT
+AGCATACGTAAAGGAG-1 1 Mouse1 6 CD-PC
+ACACCAATCTCGCTTG-5 5 Mouse5 3 PT
+GGGATGAGTATCAGTC-6 6 Mouse6 3 PT
+TGACAACAGAAGCCCA-2 2 Mouse2 3 PT
+CGAATGTTCACAATGC-1 1 Mouse1 1 Endo
+GCACTCTTCCGCATAA-1 1 Mouse1 3 PT
+CACCAGGTCCCAAGAT-2 2 Mouse2 3 PT
+GTTACAGCACCGCTAG-6 6 Mouse6 3 PT
+TAGCCGGCAGTACACT-2 2 Mouse2 11 Macro
+ACGATGTGTTAAAGAC-2 2 Mouse2 9 Novel1
+CCTTCCCAGTCTCGGC-7 7 Mouse7 3 PT
+TAGTGGTTCTCTGTCG-7 7 Mouse7 7 CD-IC
+TAGCCGGAGGCTAGCA-5 5 Mouse5 7 CD-IC
+TTGTAGGTCAGCACAT-1 1 Mouse1 4 LOH
+GAATAAGCAGCTTCGG-7 7 Mouse7 3 PT
+TCGCGAGAGTCCGGTC-3 3 Mouse3 14 T lymph
+TCAACGAAGAGTAAGG-2 2 Mouse2 5 DCT
+CAGGTGCCACGAAATA-5 5 Mouse5 3 PT
+TGTGTTTCACTATCTT-2 2 Mouse2 3 PT
+TGGCCAGAGTGAAGAG-6 6 Mouse6 3 PT
+ACCAGTAAGTAGCCGA-2 2 Mouse2 6 CD-PC
+GCGGGTTAGAAGGTTT-1 1 Mouse1 3 PT
+CAGTCCTGTCATTAGC-2 2 Mouse2 7 CD-IC