lec_flow_push – preprocessing_n

# install.packages("dplyr")
# install.packages("ggplot2")
# install.packages("SingleCellExperiment") #failed
# install.packages("scater") #failed
# install.packages("scran") #failed
# install.packages("UpSetR")
# install.packages("googlesheets4")
# install.packages("cowplot")
# install.packages("BiocParallel") #failed
# install.packages("scDblFinder") #failed
# install.packages("tibble")
# install.packages("ggpubr") #failed
# install.packages("reshape2")
# install.packages("pheatmap")
# install.packages("RColorBrewer")
# install.packages("batchelor") #failed

# install.packages('BiocManager')

# BiocManager::install("SingleCellExperiment")
#BiocManager::install("scater")
# BiocManager::install("scran")
# BiocManager::install("BiocParallel")
# BiocManager::install("scDblFinder")
# BiocManager::install("ggpubr")
# BiocManager::install("batchelor")
# BiocManager::install("DropletUtils")

# install.packages("knitr")

require("knitr")
knitr::opts_chunk$set(fig.width=10, fig.height=12)

Caricamento del pacchetto richiesto: knitr

suppressPackageStartupMessages({
    library(dplyr)
    library(ggplot2)
    library(SingleCellExperiment)
    library(scater)
    library(scran)
    library(UpSetR)
    library(googlesheets4)
    library(cowplot)
    library(BiocParallel)
    library(scDblFinder)
    library(tibble)
    library(ggpubr)
    library(reshape2)
    library(pheatmap)
    library(RColorBrewer)
    library(batchelor)
    library(DropletUtils)
})

Warning message:
“il pacchetto ‘UpSetR’ è stato creato con R versione 4.3.0”
Warning message:
“il pacchetto ‘googlesheets4’ è stato creato con R versione 4.3.0”
Warning message:
“il pacchetto ‘batchelor’ è stato creato con R versione 4.3.0”
Warning message:
“il pacchetto ‘DropletUtils’ è stato creato con R versione 4.3.0”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__DummyArrayViewport’ con ‘DelayedArray::.__C__DummyArrayViewport’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::DummyArrayGrid’ con ‘DelayedArray::DummyArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::DummyArrayViewport’ con ‘DelayedArray::DummyArrayViewport’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::write_block’ con ‘DelayedArray::write_block’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::maxlength’ con ‘DelayedArray::maxlength’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::arbind’ con ‘DelayedArray::arbind’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::aperm.ArbitraryArrayGrid’ con ‘DelayedArray::aperm.ArbitraryArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::refdim’ con ‘DelayedArray::refdim’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::downsample’ con ‘DelayedArray::downsample’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.character.Array’ con ‘DelayedArray::as.character.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::mapToGrid’ con ‘DelayedArray::mapToGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.complex.Array’ con ‘DelayedArray::as.complex.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::Mindex2Lindex’ con ‘DelayedArray::Mindex2Lindex’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.matrix.Array’ con ‘DelayedArray::as.matrix.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::is_sparse’ con ‘DelayedArray::is_sparse’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__RegularArrayGrid’ con ‘DelayedArray::.__C__RegularArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__SafeArrayViewport’ con ‘DelayedArray::.__C__SafeArrayViewport’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__Array’ con ‘DelayedArray::.__C__Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__ArrayViewport’ con ‘DelayedArray::.__C__ArrayViewport’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::RegularArrayGrid’ con ‘DelayedArray::RegularArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::makeNindexFromArrayViewport’ con ‘DelayedArray::makeNindexFromArrayViewport’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::extract_array’ con ‘DelayedArray::extract_array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__ArbitraryArrayGrid’ con ‘DelayedArray::.__C__ArbitraryArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::aperm.DummyArrayGrid’ con ‘DelayedArray::aperm.DummyArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.array.Array’ con ‘DelayedArray::as.array.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.integer.Array’ con ‘DelayedArray::as.integer.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::is_sparse<-’ con ‘DelayedArray::is_sparse<-’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.raw.Array’ con ‘DelayedArray::as.raw.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__DummyArrayGrid’ con ‘DelayedArray::.__C__DummyArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::ArbitraryArrayGrid’ con ‘DelayedArray::ArbitraryArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.character.ArrayGrid’ con ‘DelayedArray::as.character.ArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.numeric.Array’ con ‘DelayedArray::as.numeric.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::ArrayViewport’ con ‘DelayedArray::ArrayViewport’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::acbind’ con ‘DelayedArray::acbind’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::t.Array’ con ‘DelayedArray::t.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::read_block’ con ‘DelayedArray::read_block’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::rowsum’ con ‘DelayedArray::rowsum’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::.__C__ArrayGrid’ con ‘DelayedArray::.__C__ArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::aperm.RegularArrayGrid’ con ‘DelayedArray::aperm.RegularArrayGrid’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.vector.Array’ con ‘DelayedArray::as.vector.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::Lindex2Mindex’ con ‘DelayedArray::Lindex2Mindex’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::colsum’ con ‘DelayedArray::colsum’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::mapToRef’ con ‘DelayedArray::mapToRef’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.data.frame.Array’ con ‘DelayedArray::as.data.frame.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“sostituzione dell'importazione precedente ‘S4Arrays::as.logical.Array’ con ‘DelayedArray::as.logical.Array’ durante il caricamento di ‘HDF5Array’”
Warning message:
“trovate tabelle metodi multiple per ‘extract_array’”
Warning message:
“trovate tabelle metodi multiple per ‘is_sparse’”
Warning message:
“trovate tabelle metodi multiple per ‘is_sparse<-’”
Warning message:
“trovate tabelle metodi multiple per ‘write_block’”

datadir <- dir("../data", "filtered_feature_bc_matrix$", 
               full.names = TRUE, recursive = TRUE,
               include.dirs = TRUE)
names(datadir) <- sapply(strsplit(datadir, "/"), .subset, 3)
datadir

donor1_fat: '../data/donor1_fat/count/sample_filtered_feature_bc_matrix'
donor1_skin: '../data/donor1_skin/count/sample_filtered_feature_bc_matrix'
donor2_fat: '../data/donor2_fat/count/sample_filtered_feature_bc_matrix'
donor3_fat: '../data/donor3_fat/count/sample_filtered_feature_bc_matrix'
donor3_skin: '../data/donor3_skin/count/sample_filtered_feature_bc_matrix'
donor4_fat: '../data/donor4_fat/count/sample_filtered_feature_bc_matrix'
donor4_skin: '../data/donor4_skin/count/sample_filtered_feature_bc_matrix'
donor5_fat: '../data/donor5_fat/count/sample_filtered_feature_bc_matrix'
donor5_recovery: '../data/donor5_recovery/filtered_feature_bc_matrix'
donor5_skin: '../data/donor5_skin/count/sample_filtered_feature_bc_matrix'
donor6_fat: '../data/donor6_fat/count/sample_filtered_feature_bc_matrix'
donor6_skin: '../data/donor6_skin/count/sample_filtered_feature_bc_matrix'
donor7_fat: '../data/donor7_fat/count/sample_filtered_feature_bc_matrix'
donor7_skin: '../data/donor7_skin/count/sample_filtered_feature_bc_matrix'

stub <- "https://docs.google.com/spreadsheets/d/"
md_sheet <- paste0(stub, "1yEqqOHX7TY1A-lmEQu3cPcFY60IconZWR6W349xH2pY")
md_sheet

'https://docs.google.com/spreadsheets/d/1yEqqOHX7TY1A-lmEQu3cPcFY60IconZWR6W349xH2pY'

googlesheets4::gs4_deauth()
md <- googlesheets4::read_sheet(md_sheet, sheet = "single-cell") %>%
    filter(keep == 1)
md

✔ Reading from halin-bauer-hLECs-metadata.

✔ Range ''single-cell''.

A tibble: 12 × 8
sample_name	donor	tissue	tissue_origin	sequencing_run	keep	sex	notes
<chr>	<dbl>	<chr>	<chr>	<dbl>	<dbl>	<chr>	<chr>
donor1_fat	1	fat	abdomen	1	1	F	NA
donor1_skin	1	skin	abdomen	1	1	F	NA
donor2_fat	2	fat	arm	1	1	F	NA
donor3_fat	3	fat	abdomen	2	1	F	has contamination
donor3_skin	3	skin	abdomen	2	1	F	NA
donor4_fat	4	fat	abdomen	2	1	F	NA
donor4_skin	4	skin	abdomen	2	1	F	NA
donor5_recovery	5	mixed	abdomen	4	1	?	recovered sample
donor6_fat	6	fat	abdomen	3	1	M	NA
donor6_skin	6	skin	abdomen	3	1	M	NA
donor7_fat	7	fat	thigh	3	1	?	has contamination
donor7_skin	7	skin	thigh	3	1	?	NA

datadir <- datadir[md$sample_name]
print(all(names(datadir)==md$sample_name))
datadir

[1] TRUE

donor1_fat: '../data/donor1_fat/count/sample_filtered_feature_bc_matrix'
donor1_skin: '../data/donor1_skin/count/sample_filtered_feature_bc_matrix'
donor2_fat: '../data/donor2_fat/count/sample_filtered_feature_bc_matrix'
donor3_fat: '../data/donor3_fat/count/sample_filtered_feature_bc_matrix'
donor3_skin: '../data/donor3_skin/count/sample_filtered_feature_bc_matrix'
donor4_fat: '../data/donor4_fat/count/sample_filtered_feature_bc_matrix'
donor4_skin: '../data/donor4_skin/count/sample_filtered_feature_bc_matrix'
donor5_recovery: '../data/donor5_recovery/filtered_feature_bc_matrix'
donor6_fat: '../data/donor6_fat/count/sample_filtered_feature_bc_matrix'
donor6_skin: '../data/donor6_skin/count/sample_filtered_feature_bc_matrix'
donor7_fat: '../data/donor7_fat/count/sample_filtered_feature_bc_matrix'
donor7_skin: '../data/donor7_skin/count/sample_filtered_feature_bc_matrix'

fs <- split(datadir, md$sequencing_run)
fs <- lapply(fs, function(u) {
    rc <- DropletUtils::read10xCounts(u)
    nr <- nrow(rc)
    if(any(grep("Multiplexing", rowData(rc)$Type))) {
        rc <- rc[rowData(rc)$Type != "Multiplexing Capture",]
        removed <- "barcodes"
    }
    else {
        rc <- rc[-grep("NA.[1-6]", rownames(rc)),]
        removed <- "features"
    }
    cat(sprintf(
        "%s: removing %d %s; %d features left.\n", paste0(names(u), collapse=","), 
        nr-nrow(rc), removed, nrow(rc)
    ))
    return(rc)
})

fs

donor1_fat,donor1_skin,donor2_fat: removing 3 barcodes; 21134 features left.
donor3_fat,donor3_skin,donor4_fat,donor4_skin: removing 4 barcodes; 21134 features left.
donor6_fat,donor6_skin,donor7_fat,donor7_skin: removing 6 barcodes; 21134 features left.
donor5_recovery: removing 6 features; 21134 features left.

$`1`
class: SingleCellExperiment 
dim: 21134 6891 
metadata(1): Samples
assays(1): counts
rownames(21134): ENSG00000186092 ENSG00000284733 ... ENSG00000278817
  ENSG00000277196
rowData names(3): ID Symbol Type
colnames: NULL
colData names(2): Sample Barcode
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

$`2`
class: SingleCellExperiment 
dim: 21134 2759 
metadata(1): Samples
assays(1): counts
rownames(21134): ENSG00000186092 ENSG00000284733 ... ENSG00000278817
  ENSG00000277196
rowData names(3): ID Symbol Type
colnames: NULL
colData names(2): Sample Barcode
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

$`3`
class: SingleCellExperiment 
dim: 21134 8336 
metadata(1): Samples
assays(1): counts
rownames(21134): ENSG00000186092 ENSG00000284733 ... ENSG00000278817
  ENSG00000277196
rowData names(3): ID Symbol Type
colnames: NULL
colData names(2): Sample Barcode
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

$`4`
class: SingleCellExperiment 
dim: 21134 4889 
metadata(1): Samples
assays(1): counts
rownames(21134): ENSG00000186092 ENSG00000284733 ... ENSG00000278817
  ENSG00000277196
rowData names(3): ID Symbol Type
colnames: NULL
colData names(2): Sample Barcode
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

sce <- SingleCellExperiment(
    assays = SimpleList(
        counts = do.call("cbind", lapply(fs, counts))
    ),
    rowData = rowData(fs[[1]]),
    colData = do.call("rbind", lapply(fs, colData))
)
table(sce$Sample)


     donor1_fat     donor1_skin      donor2_fat      donor3_fat     donor3_skin 
            162            3861            2868            1133             620 
     donor4_fat     donor4_skin donor5_recovery      donor6_fat     donor6_skin 
            131             875            4889            2001            1715 
     donor7_fat     donor7_skin 
           1713            2907

colData(sce) <- colData(sce) %>% as.data.frame %>%
                left_join(md %>% select(-keep,-notes), by = c("Sample"="sample_name")) %>% DataFrame
colData(sce)

DataFrame with 22875 rows and 7 columns
               Sample            Barcode     donor      tissue tissue_origin
          <character>        <character> <numeric> <character>   <character>
1          donor1_fat AAAGAACCACATACGT-1         1         fat       abdomen
2          donor1_fat AAAGGTAGTCCGGTCA-1         1         fat       abdomen
3          donor1_fat AAAGGTATCTCTCTTC-1         1         fat       abdomen
4          donor1_fat AACCACACAGTGGCTC-1         1         fat       abdomen
5          donor1_fat AACCCAAGTATGGGAC-1         1         fat       abdomen
...               ...                ...       ...         ...           ...
22871 donor5_recovery TTTGGTTTCGACCAAT-1         5       mixed       abdomen
22872 donor5_recovery TTTGTTGGTCCTACGG-1         5       mixed       abdomen
22873 donor5_recovery TTTGTTGGTCGCAGTC-1         5       mixed       abdomen
22874 donor5_recovery TTTGTTGGTGGCGTAA-1         5       mixed       abdomen
22875 donor5_recovery TTTGTTGTCGGCATTA-1         5       mixed       abdomen
      sequencing_run         sex
           <numeric> <character>
1                  1           F
2                  1           F
3                  1           F
4                  1           F
5                  1           F
...              ...         ...
22871              4           ?
22872              4           ?
22873              4           ?
22874              4           ?
22875              4           ?

colnames(sce) <- paste0(sce$Sample, ".", sce$Barcode)
rownames(sce) <- paste0(rowData(sce)$ID, ".", rowData(sce)$Symbol)
sce

class: SingleCellExperiment 
dim: 21134 22875 
metadata(0):
assays(1): counts
rownames(21134): ENSG00000186092.OR4F5 ENSG00000284733.OR4F29 ...
  ENSG00000278817.ENSG00000278817 ENSG00000277196.ENSG00000277196
rowData names(3): ID Symbol Type
colnames(22875): donor1_fat.AAAGAACCACATACGT-1
  donor1_fat.AAAGGTAGTCCGGTCA-1 ... donor5_recovery.TTTGTTGGTGGCGTAA-1
  donor5_recovery.TTTGTTGTCGGCATTA-1
colData names(7): Sample Barcode ... sequencing_run sex
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

# very basic filter
sce <- sce[rowSums(counts(sce))>0]
sce

class: SingleCellExperiment 
dim: 18664 22875 
metadata(0):
assays(1): counts
rownames(18664): ENSG00000187634.SAMD11 ENSG00000188976.NOC2L ...
  ENSG00000278817.ENSG00000278817 ENSG00000277196.ENSG00000277196
rowData names(3): ID Symbol Type
colnames(22875): donor1_fat.AAAGAACCACATACGT-1
  donor1_fat.AAAGGTAGTCCGGTCA-1 ... donor5_recovery.TTTGTTGGTGGCGTAA-1
  donor5_recovery.TTTGTTGTCGGCATTA-1
colData names(7): Sample Barcode ... sequencing_run sex
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

saveRDS(sce, file="../output/0.0-sce-unfiltered.rds")

is.mito <- grepl("\\.mt-", rownames(sce), ignore.case = TRUE)
rownames(sce)[is.mito]
sum(is.mito)

'ENSG00000210049.MT-TF'
'ENSG00000211459.MT-RNR1'
'ENSG00000210077.MT-TV'
'ENSG00000210082.MT-RNR2'
'ENSG00000209082.MT-TL1'
'ENSG00000198888.MT-ND1'
'ENSG00000210100.MT-TI'
'ENSG00000210107.MT-TQ'
'ENSG00000210112.MT-TM'
'ENSG00000198763.MT-ND2'
'ENSG00000210117.MT-TW'
'ENSG00000210127.MT-TA'
'ENSG00000210135.MT-TN'
'ENSG00000210140.MT-TC'
'ENSG00000210144.MT-TY'
'ENSG00000198804.MT-CO1'
'ENSG00000210151.MT-TS1'
'ENSG00000210154.MT-TD'
'ENSG00000198712.MT-CO2'
'ENSG00000210156.MT-TK'
'ENSG00000228253.MT-ATP8'
'ENSG00000198899.MT-ATP6'
'ENSG00000198938.MT-CO3'
'ENSG00000210164.MT-TG'
'ENSG00000198840.MT-ND3'
'ENSG00000210174.MT-TR'
'ENSG00000212907.MT-ND4L'
'ENSG00000198886.MT-ND4'
'ENSG00000210176.MT-TH'
'ENSG00000210184.MT-TS2'
'ENSG00000210191.MT-TL2'
'ENSG00000198786.MT-ND5'
'ENSG00000198695.MT-ND6'
'ENSG00000210194.MT-TE'
'ENSG00000198727.MT-CYB'
'ENSG00000210195.MT-TT'
'ENSG00000210196.MT-TP'

sce <- addPerCellQC(sce, subsets=list(Mito=is.mito), percent_top=c(50,100,200,500))
sce <- sce[!is.mito]
head(colData(sce),3)

DataFrame with 3 rows and 17 columns
                                   Sample            Barcode     donor
                              <character>        <character> <numeric>
donor1_fat.AAAGAACCACATACGT-1  donor1_fat AAAGAACCACATACGT-1         1
donor1_fat.AAAGGTAGTCCGGTCA-1  donor1_fat AAAGGTAGTCCGGTCA-1         1
donor1_fat.AAAGGTATCTCTCTTC-1  donor1_fat AAAGGTATCTCTCTTC-1         1
                                   tissue tissue_origin sequencing_run
                              <character>   <character>      <numeric>
donor1_fat.AAAGAACCACATACGT-1         fat       abdomen              1
donor1_fat.AAAGGTAGTCCGGTCA-1         fat       abdomen              1
donor1_fat.AAAGGTATCTCTCTTC-1         fat       abdomen              1
                                      sex       sum  detected percent.top_50
                              <character> <numeric> <integer>      <numeric>
donor1_fat.AAAGAACCACATACGT-1           F      4276      1721        33.8868
donor1_fat.AAAGGTAGTCCGGTCA-1           F      3023      1084        39.6626
donor1_fat.AAAGGTATCTCTCTTC-1           F      3892      1422        34.1213
                              percent.top_100 percent.top_200 percent.top_500
                                    <numeric>       <numeric>       <numeric>
donor1_fat.AAAGAACCACATACGT-1         42.7736         52.9935         69.3171
donor1_fat.AAAGGTAGTCCGGTCA-1         52.9937         65.0017         80.6814
donor1_fat.AAAGGTATCTCTCTTC-1         46.5570         58.3505         75.9250
                              subsets_Mito_sum subsets_Mito_detected
                                     <numeric>             <integer>
donor1_fat.AAAGAACCACATACGT-1              752                    16
donor1_fat.AAAGGTAGTCCGGTCA-1               52                    12
donor1_fat.AAAGGTATCTCTCTTC-1               48                    12
                              subsets_Mito_percent     total
                                         <numeric> <numeric>
donor1_fat.AAAGAACCACATACGT-1             17.58653      4276
donor1_fat.AAAGGTAGTCCGGTCA-1              1.72015      3023
donor1_fat.AAAGGTATCTCTCTTC-1              1.23330      3892

cd_df <- colData(sce) %>% as.data.frame
cd_df

A data.frame: 22875 × 17
	Sample	Barcode	donor	tissue	tissue_origin	sequencing_run	sex	sum	detected	percent.top_50	percent.top_100	percent.top_200	percent.top_500	subsets_Mito_sum	subsets_Mito_detected	subsets_Mito_percent	total
	<chr>	<chr>	<dbl>	<chr>	<chr>	<dbl>	<chr>	<dbl>	<int>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<int>	<dbl>	<dbl>
donor1_fat.AAAGAACCACATACGT-1	donor1_fat	AAAGAACCACATACGT-1	1	fat	abdomen	1	F	4276	1721	33.88681	42.77362	52.99345	69.31712	752	16	17.5865295	4276
donor1_fat.AAAGGTAGTCCGGTCA-1	donor1_fat	AAAGGTAGTCCGGTCA-1	1	fat	abdomen	1	F	3023	1084	39.66259	52.99371	65.00165	80.68144	52	12	1.7201456	3023
donor1_fat.AAAGGTATCTCTCTTC-1	donor1_fat	AAAGGTATCTCTCTTC-1	1	fat	abdomen	1	F	3892	1422	34.12127	46.55704	58.35046	75.92497	48	12	1.2332991	3892
donor1_fat.AACCACACAGTGGCTC-1	donor1_fat	AACCACACAGTGGCTC-1	1	fat	abdomen	1	F	7722	2633	26.89718	38.12484	48.67910	64.12846	103	13	1.3338513	7722
donor1_fat.AACCCAAGTATGGGAC-1	donor1_fat	AACCCAAGTATGGGAC-1	1	fat	abdomen	1	F	636	178	79.87421	87.73585	100.00000	100.00000	445	15	69.9685535	636
donor1_fat.AACGGGATCTGCTGAA-1	donor1_fat	AACGGGATCTGCTGAA-1	1	fat	abdomen	1	F	3256	1284	34.33661	46.80590	59.06020	75.92138	123	11	3.7776413	3256
donor1_fat.AAGAACATCTGTGCAA-1	donor1_fat	AAGAACATCTGTGCAA-1	1	fat	abdomen	1	F	6777	1989	32.86115	47.38085	60.01180	74.07407	224	14	3.3052973	6777
donor1_fat.AAGCATCTCGATCCCT-1	donor1_fat	AAGCATCTCGATCCCT-1	1	fat	abdomen	1	F	1746	839	34.07789	47.53723	61.45475	80.58419	63	11	3.6082474	1746
donor1_fat.AAGCGAGAGTATCCTG-1	donor1_fat	AAGCGAGAGTATCCTG-1	1	fat	abdomen	1	F	6750	2393	24.08889	35.12593	46.69630	63.71852	277	18	4.1037037	6750
donor1_fat.AAGTTCGAGGCAGGTT-1	donor1_fat	AAGTTCGAGGCAGGTT-1	1	fat	abdomen	1	F	5707	2041	31.20729	43.42036	54.17908	68.91537	188	12	3.2942001	5707
donor1_fat.AATCGACCAATTGCAC-1	donor1_fat	AATCGACCAATTGCAC-1	1	fat	abdomen	1	F	3401	1534	26.60982	37.37136	49.51485	68.92091	107	15	3.1461335	3401
donor1_fat.ACAAAGACAATGACCT-1	donor1_fat	ACAAAGACAATGACCT-1	1	fat	abdomen	1	F	5851	1802	32.49017	45.70159	58.43446	74.67100	106	16	1.8116561	5851
donor1_fat.ACAAAGACACTAACGT-1	donor1_fat	ACAAAGACACTAACGT-1	1	fat	abdomen	1	F	3602	1004	43.80900	59.35591	72.01555	86.00777	60	11	1.6657413	3602
donor1_fat.ACAACCAAGGGCTTCC-1	donor1_fat	ACAACCAAGGGCTTCC-1	1	fat	abdomen	1	F	10238	3273	22.24067	33.03380	44.50088	59.89451	168	12	1.6409455	10238
donor1_fat.ACAGGGACACACTTAG-1	donor1_fat	ACAGGGACACACTTAG-1	1	fat	abdomen	1	F	606	63	97.85479	100.00000	100.00000	100.00000	556	15	91.7491749	606
donor1_fat.ACAGGGATCTCATAGG-1	donor1_fat	ACAGGGATCTCATAGG-1	1	fat	abdomen	1	F	5210	1884	27.96545	40.07678	53.03263	69.17466	105	13	2.0153551	5210
donor1_fat.ACATTTCCACTCCACT-1	donor1_fat	ACATTTCCACTCCACT-1	1	fat	abdomen	1	F	3606	1305	36.30061	49.16805	61.53633	77.67610	33	11	0.9151414	3606
donor1_fat.ACATTTCTCGATGGAG-1	donor1_fat	ACATTTCTCGATGGAG-1	1	fat	abdomen	1	F	3853	1491	34.07734	47.31378	58.44796	74.27978	68	13	1.7648586	3853
donor1_fat.ACCCTTGTCACCATAG-1	donor1_fat	ACCCTTGTCACCATAG-1	1	fat	abdomen	1	F	4627	1604	34.92544	48.32505	59.39053	74.82170	84	12	1.8154312	4627
donor1_fat.ACCTACCAGACCTCCG-1	donor1_fat	ACCTACCAGACCTCCG-1	1	fat	abdomen	1	F	1732	651	46.76674	60.56582	73.78753	91.28176	41	12	2.3672055	1732
donor1_fat.ACGGAAGCACACCTAA-1	donor1_fat	ACGGAAGCACACCTAA-1	1	fat	abdomen	1	F	5069	2279	17.65634	25.42908	36.41744	56.77648	369	14	7.2795423	5069
donor1_fat.ACGTAACAGTCTAGCT-1	donor1_fat	ACGTAACAGTCTAGCT-1	1	fat	abdomen	1	F	1188	491	60.43771	67.08754	75.50505	100.00000	620	18	52.1885522	1188
donor1_fat.ACGTAGTTCCCGAAAT-1	donor1_fat	ACGTAGTTCCCGAAAT-1	1	fat	abdomen	1	F	3897	1246	36.23300	49.73056	62.63793	80.70310	39	11	1.0007698	3897
donor1_fat.ACGTTCCAGATGAATC-1	donor1_fat	ACGTTCCAGATGAATC-1	1	fat	abdomen	1	F	1884	1136	28.60934	36.57113	47.29299	66.24204	280	13	14.8619958	1884
donor1_fat.ACTCTCGAGCCGTTGC-1	donor1_fat	ACTCTCGAGCCGTTGC-1	1	fat	abdomen	1	F	1220	611	41.96721	53.77049	66.31148	90.90164	154	15	12.6229508	1220
donor1_fat.ACTTCCGTCAGGAACG-1	donor1_fat	ACTTCCGTCAGGAACG-1	1	fat	abdomen	1	F	4898	2364	17.29277	24.37730	34.29971	53.14414	367	16	7.4928542	4898
donor1_fat.AGACACTCAGGCGATA-1	donor1_fat	AGACACTCAGGCGATA-1	1	fat	abdomen	1	F	4601	1518	33.51445	46.70724	59.70441	76.26603	171	12	3.7165834	4601
donor1_fat.AGACCATTCAAAGGTA-1	donor1_fat	AGACCATTCAAAGGTA-1	1	fat	abdomen	1	F	7030	2375	27.28307	38.50640	50.54054	66.28734	27	10	0.3840683	7030
donor1_fat.AGAGAGCCAAGCCCAC-1	donor1_fat	AGAGAGCCAAGCCCAC-1	1	fat	abdomen	1	F	3437	1047	43.26447	57.81205	69.53739	84.08496	85	12	2.4730870	3437
donor1_fat.AGAGCCCAGTCTAGCT-1	donor1_fat	AGAGCCCAGTCTAGCT-1	1	fat	abdomen	1	F	4781	1680	33.44489	46.37105	58.12592	73.41560	110	14	2.3007739	4781
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
donor5_recovery.TTTCGATAGTGGAATT-1	donor5_recovery	TTTCGATAGTGGAATT-1	5	mixed	abdomen	4	?	3048	1575	21.42388	31.33202	42.84777	64.20604	139	16	4.5603675	3048
donor5_recovery.TTTCGATGTGCTGATT-1	donor5_recovery	TTTCGATGTGCTGATT-1	5	mixed	abdomen	4	?	2238	1400	17.20286	25.24576	36.90795	59.78552	57	15	2.5469169	2238
donor5_recovery.TTTGACTAGATGGGCT-1	donor5_recovery	TTTGACTAGATGGGCT-1	5	mixed	abdomen	4	?	2448	1208	27.69608	39.95098	53.10458	71.07843	95	16	3.8807190	2448
donor5_recovery.TTTGACTAGTGTTCAC-1	donor5_recovery	TTTGACTAGTGTTCAC-1	5	mixed	abdomen	4	?	6499	2564	24.23450	34.06678	44.72996	60.70165	78	13	1.2001846	6499
donor5_recovery.TTTGACTGTCCAAATC-1	donor5_recovery	TTTGACTGTCCAAATC-1	5	mixed	abdomen	4	?	958	673	24.32150	35.80376	50.62630	81.94154	8	4	0.8350731	958
donor5_recovery.TTTGACTGTGATTCTG-1	donor5_recovery	TTTGACTGTGATTCTG-1	5	mixed	abdomen	4	?	1568	955	26.97704	37.75510	50.70153	70.98214	71	14	4.5280612	1568
donor5_recovery.TTTGACTGTTGTCTAG-1	donor5_recovery	TTTGACTGTTGTCTAG-1	5	mixed	abdomen	4	?	936	593	29.70085	42.30769	58.01282	90.06410	38	11	4.0598291	936
donor5_recovery.TTTGATCAGATGACCG-1	donor5_recovery	TTTGATCAGATGACCG-1	5	mixed	abdomen	4	?	956	596	30.75314	43.61925	58.57741	89.95816	25	8	2.6150628	956
donor5_recovery.TTTGATCAGCAATAAC-1	donor5_recovery	TTTGATCAGCAATAAC-1	5	mixed	abdomen	4	?	2148	939	34.35754	48.51024	61.17318	79.56238	71	14	3.3054004	2148
donor5_recovery.TTTGATCAGTTACTCG-1	donor5_recovery	TTTGATCAGTTACTCG-1	5	mixed	abdomen	4	?	3145	1486	21.90779	32.84579	46.45469	67.59936	66	15	2.0985692	3145
donor5_recovery.TTTGATCGTTGGGCCT-1	donor5_recovery	TTTGATCGTTGGGCCT-1	5	mixed	abdomen	4	?	2897	1316	30.54884	42.18157	54.57370	71.83293	182	17	6.2823611	2897
donor5_recovery.TTTGATCTCAAAGGTA-1	donor5_recovery	TTTGATCTCAAAGGTA-1	5	mixed	abdomen	4	?	2155	1136	26.07889	36.98376	50.06961	70.48724	98	14	4.5475638	2155
donor5_recovery.TTTGGAGAGTGCAAAT-1	donor5_recovery	TTTGGAGAGTGCAAAT-1	5	mixed	abdomen	4	?	1054	601	34.91461	48.10247	61.95446	90.41746	43	14	4.0796964	1054
donor5_recovery.TTTGGAGCATAGGTAA-1	donor5_recovery	TTTGGAGCATAGGTAA-1	5	mixed	abdomen	4	?	1846	1050	23.34778	33.91116	47.50813	70.20585	89	14	4.8212351	1846
donor5_recovery.TTTGGAGGTCAGTTTG-1	donor5_recovery	TTTGGAGGTCAGTTTG-1	5	mixed	abdomen	4	?	1222	769	26.67758	38.21604	53.43699	77.98691	51	13	4.1734861	1222
donor5_recovery.TTTGGAGGTCCAAGAG-1	donor5_recovery	TTTGGAGGTCCAAGAG-1	5	mixed	abdomen	4	?	1829	1058	27.28267	37.88956	49.64461	69.49153	28	12	1.5308912	1829
donor5_recovery.TTTGGAGGTCGACTTA-1	donor5_recovery	TTTGGAGGTCGACTTA-1	5	mixed	abdomen	4	?	2389	1430	17.91545	26.28715	38.21683	61.07158	154	21	6.4462118	2389
donor5_recovery.TTTGGAGGTTGAGAGC-1	donor5_recovery	TTTGGAGGTTGAGAGC-1	5	mixed	abdomen	4	?	1618	993	21.69345	32.26205	46.66255	69.53028	38	11	2.3485785	1618
donor5_recovery.TTTGGAGTCCAAGAGG-1	donor5_recovery	TTTGGAGTCCAAGAGG-1	5	mixed	abdomen	4	?	1262	830	23.85103	34.62758	50.07924	73.85103	69	14	5.4675119	1262
donor5_recovery.TTTGGAGTCTCAACCC-1	donor5_recovery	TTTGGAGTCTCAACCC-1	5	mixed	abdomen	4	?	1135	717	29.51542	40.79295	54.44934	80.88106	18	10	1.5859031	1135
donor5_recovery.TTTGGTTAGCCTCTTC-1	donor5_recovery	TTTGGTTAGCCTCTTC-1	5	mixed	abdomen	4	?	763	584	24.90170	36.56619	49.67235	88.99083	24	8	3.1454784	763
donor5_recovery.TTTGGTTCACTCTAGA-1	donor5_recovery	TTTGGTTCACTCTAGA-1	5	mixed	abdomen	4	?	812	570	27.58621	40.14778	54.43350	91.37931	24	8	2.9556650	812
donor5_recovery.TTTGGTTGTACGTGAG-1	donor5_recovery	TTTGGTTGTACGTGAG-1	5	mixed	abdomen	4	?	755	494	30.99338	44.90066	61.05960	100.00000	34	9	4.5033113	755
donor5_recovery.TTTGGTTGTCCTACAA-1	donor5_recovery	TTTGGTTGTCCTACAA-1	5	mixed	abdomen	4	?	835	625	24.07186	36.04790	49.10180	85.02994	27	6	3.2335329	835
donor5_recovery.TTTGGTTGTGACTCTA-1	donor5_recovery	TTTGGTTGTGACTCTA-1	5	mixed	abdomen	4	?	938	572	29.63753	43.39019	60.34115	92.32409	2	2	0.2132196	938
donor5_recovery.TTTGGTTTCGACCAAT-1	donor5_recovery	TTTGGTTTCGACCAAT-1	5	mixed	abdomen	4	?	1328	670	34.33735	48.34337	64.30723	87.19880	67	10	5.0451807	1328
donor5_recovery.TTTGTTGGTCCTACGG-1	donor5_recovery	TTTGTTGGTCCTACGG-1	5	mixed	abdomen	4	?	795	552	28.30189	41.63522	55.72327	93.45912	44	12	5.5345912	795
donor5_recovery.TTTGTTGGTCGCAGTC-1	donor5_recovery	TTTGTTGGTCGCAGTC-1	5	mixed	abdomen	4	?	1872	1250	16.18590	24.73291	37.01923	59.93590	66	14	3.5256410	1872
donor5_recovery.TTTGTTGGTGGCGTAA-1	donor5_recovery	TTTGTTGGTGGCGTAA-1	5	mixed	abdomen	4	?	1928	931	33.14315	46.21369	58.97303	77.64523	51	13	2.6452282	1928
donor5_recovery.TTTGTTGTCGGCATTA-1	donor5_recovery	TTTGTTGTCGGCATTA-1	5	mixed	abdomen	4	?	2091	1206	21.95122	32.56815	45.28934	66.23625	53	14	2.5346724	2091

options(repr.plot.width=20, repr.plot.height=20)

ggplot(cd_df, aes(sum, detected)) +
    geom_point(size=.5) +
    scale_x_log10() +
    scale_y_log10() +
    geom_density_2d(contour_var = "ndensity") +
    facet_wrap(~Sample)

options(repr.plot.width=12, repr.plot.height=6)

ggplot(cd_df, aes(x=sum, color=Sample)) +
    geom_density(size=4) +
    scale_x_log10()

Warning message:
“Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.”

options(repr.plot.width=12, repr.plot.height=6)

ggplot(cd_df, aes(x=detected, color=Sample)) +
  geom_density(linewidth=4) +
  scale_x_log10()

options(repr.plot.width=12, repr.plot.height=12)

ggplot(cd_df, aes(x=Sample, y=sum)) +
    geom_violin() +
    geom_jitter() +
    scale_y_log10()

options(repr.plot.width=20, repr.plot.height=20)

ggplot(cd_df, aes(sum, percent.top_50)) +
    geom_point(size=.5) +
    scale_x_log10() +
    geom_density_2d(contour_var = "ndensity") +
    facet_wrap(~Sample)

options(repr.plot.width=20, repr.plot.height=20)

ggplot(cd_df, aes(sum, subsets_Mito_percent)) +
    geom_point(size=.5) +
    scale_x_log10() +
    scale_y_sqrt() +
    geom_density_2d(contour_var = "ndensity") +
    facet_wrap(~Sample)

mito_cutoff <- 30
detected_cutoff <- 200

with(cd_df, table(Sample, detected < detected_cutoff))
with(cd_df, table(Sample, subsets_Mito_percent > mito_cutoff))
with(cd_df, table(Sample, subsets_Mito_percent > mito_cutoff | detected < detected_cutoff))

                 
Sample            FALSE TRUE
  donor1_fat        159    3
  donor1_skin      3844   17
  donor2_fat       2852   16
  donor3_fat       1122   11
  donor3_skin       611    9
  donor4_fat        123    8
  donor4_skin       810   65
  donor5_recovery  4887    2
  donor6_fat       2000    1
  donor6_skin      1715    0
  donor7_fat       1713    0
  donor7_skin      2907    0

                 
Sample            FALSE TRUE
  donor1_fat        158    4
  donor1_skin      3804   57
  donor2_fat       2823   45
  donor3_fat       1063   70
  donor3_skin       573   47
  donor4_fat         89   42
  donor4_skin       638  237
  donor5_recovery  4880    9
  donor6_fat       1994    7
  donor6_skin      1710    5
  donor7_fat       1708    5
  donor7_skin      2898    9

                 
Sample            FALSE TRUE
  donor1_fat        158    4
  donor1_skin      3804   57
  donor2_fat       2823   45
  donor3_fat       1063   70
  donor3_skin       573   47
  donor4_fat         89   42
  donor4_skin       638  237
  donor5_recovery  4879   10
  donor6_fat       1994    7
  donor6_skin      1710    5
  donor7_fat       1708    5
  donor7_skin      2898    9

sce <- sce[, (sce$subsets_Mito_percent < mito_cutoff) & (sce$detected > detected_cutoff)]
sce

class: SingleCellExperiment 
dim: 18627 22337 
metadata(0):
assays(1): counts
rownames(18627): ENSG00000187634.SAMD11 ENSG00000188976.NOC2L ...
  ENSG00000278817.ENSG00000278817 ENSG00000277196.ENSG00000277196
rowData names(3): ID Symbol Type
colnames(22337): donor1_fat.AAAGAACCACATACGT-1
  donor1_fat.AAAGGTAGTCCGGTCA-1 ... donor5_recovery.TTTGTTGGTGGCGTAA-1
  donor5_recovery.TTTGTTGTCGGCATTA-1
colData names(17): Sample Barcode ... subsets_Mito_percent total
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

table(sce$tissue)


  fat mixed  skin 
 7835  4879  9623

cd_df <- colData(sce) %>% as.data.frame

cd_df <- cd_df %>% mutate(
    outlier_sum=isOutlier(
        sum, nmads=4, type="both", log=TRUE, batch=Sample
    ),
    outlier_detected=isOutlier(
        detected, nmads=4, type="both", log=TRUE, batch=Sample
    )
)

cd_df

A data.frame: 22337 × 19
	Sample	Barcode	donor	tissue	tissue_origin	sequencing_run	sex	sum	detected	percent.top_50	percent.top_100	percent.top_200	percent.top_500	subsets_Mito_sum	subsets_Mito_detected	subsets_Mito_percent	total	outlier_sum	outlier_detected
	<chr>	<chr>	<dbl>	<chr>	<chr>	<dbl>	<chr>	<dbl>	<int>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<int>	<dbl>	<dbl>	<otlr.flt>	<otlr.flt>
donor1_fat.AAAGAACCACATACGT-1	donor1_fat	AAAGAACCACATACGT-1	1	fat	abdomen	1	F	4276	1721	33.88681	42.77362	52.99345	69.31712	752	16	17.5865295	4276	FALSE	FALSE
donor1_fat.AAAGGTAGTCCGGTCA-1	donor1_fat	AAAGGTAGTCCGGTCA-1	1	fat	abdomen	1	F	3023	1084	39.66259	52.99371	65.00165	80.68144	52	12	1.7201456	3023	FALSE	FALSE
donor1_fat.AAAGGTATCTCTCTTC-1	donor1_fat	AAAGGTATCTCTCTTC-1	1	fat	abdomen	1	F	3892	1422	34.12127	46.55704	58.35046	75.92497	48	12	1.2332991	3892	FALSE	FALSE
donor1_fat.AACCACACAGTGGCTC-1	donor1_fat	AACCACACAGTGGCTC-1	1	fat	abdomen	1	F	7722	2633	26.89718	38.12484	48.67910	64.12846	103	13	1.3338513	7722	FALSE	FALSE
donor1_fat.AACGGGATCTGCTGAA-1	donor1_fat	AACGGGATCTGCTGAA-1	1	fat	abdomen	1	F	3256	1284	34.33661	46.80590	59.06020	75.92138	123	11	3.7776413	3256	FALSE	FALSE
donor1_fat.AAGAACATCTGTGCAA-1	donor1_fat	AAGAACATCTGTGCAA-1	1	fat	abdomen	1	F	6777	1989	32.86115	47.38085	60.01180	74.07407	224	14	3.3052973	6777	FALSE	FALSE
donor1_fat.AAGCATCTCGATCCCT-1	donor1_fat	AAGCATCTCGATCCCT-1	1	fat	abdomen	1	F	1746	839	34.07789	47.53723	61.45475	80.58419	63	11	3.6082474	1746	FALSE	FALSE
donor1_fat.AAGCGAGAGTATCCTG-1	donor1_fat	AAGCGAGAGTATCCTG-1	1	fat	abdomen	1	F	6750	2393	24.08889	35.12593	46.69630	63.71852	277	18	4.1037037	6750	FALSE	FALSE
donor1_fat.AAGTTCGAGGCAGGTT-1	donor1_fat	AAGTTCGAGGCAGGTT-1	1	fat	abdomen	1	F	5707	2041	31.20729	43.42036	54.17908	68.91537	188	12	3.2942001	5707	FALSE	FALSE
donor1_fat.AATCGACCAATTGCAC-1	donor1_fat	AATCGACCAATTGCAC-1	1	fat	abdomen	1	F	3401	1534	26.60982	37.37136	49.51485	68.92091	107	15	3.1461335	3401	FALSE	FALSE
donor1_fat.ACAAAGACAATGACCT-1	donor1_fat	ACAAAGACAATGACCT-1	1	fat	abdomen	1	F	5851	1802	32.49017	45.70159	58.43446	74.67100	106	16	1.8116561	5851	FALSE	FALSE
donor1_fat.ACAAAGACACTAACGT-1	donor1_fat	ACAAAGACACTAACGT-1	1	fat	abdomen	1	F	3602	1004	43.80900	59.35591	72.01555	86.00777	60	11	1.6657413	3602	FALSE	FALSE
donor1_fat.ACAACCAAGGGCTTCC-1	donor1_fat	ACAACCAAGGGCTTCC-1	1	fat	abdomen	1	F	10238	3273	22.24067	33.03380	44.50088	59.89451	168	12	1.6409455	10238	FALSE	FALSE
donor1_fat.ACAGGGATCTCATAGG-1	donor1_fat	ACAGGGATCTCATAGG-1	1	fat	abdomen	1	F	5210	1884	27.96545	40.07678	53.03263	69.17466	105	13	2.0153551	5210	FALSE	FALSE
donor1_fat.ACATTTCCACTCCACT-1	donor1_fat	ACATTTCCACTCCACT-1	1	fat	abdomen	1	F	3606	1305	36.30061	49.16805	61.53633	77.67610	33	11	0.9151414	3606	FALSE	FALSE
donor1_fat.ACATTTCTCGATGGAG-1	donor1_fat	ACATTTCTCGATGGAG-1	1	fat	abdomen	1	F	3853	1491	34.07734	47.31378	58.44796	74.27978	68	13	1.7648586	3853	FALSE	FALSE
donor1_fat.ACCCTTGTCACCATAG-1	donor1_fat	ACCCTTGTCACCATAG-1	1	fat	abdomen	1	F	4627	1604	34.92544	48.32505	59.39053	74.82170	84	12	1.8154312	4627	FALSE	FALSE
donor1_fat.ACCTACCAGACCTCCG-1	donor1_fat	ACCTACCAGACCTCCG-1	1	fat	abdomen	1	F	1732	651	46.76674	60.56582	73.78753	91.28176	41	12	2.3672055	1732	FALSE	FALSE
donor1_fat.ACGGAAGCACACCTAA-1	donor1_fat	ACGGAAGCACACCTAA-1	1	fat	abdomen	1	F	5069	2279	17.65634	25.42908	36.41744	56.77648	369	14	7.2795423	5069	FALSE	FALSE
donor1_fat.ACGTAGTTCCCGAAAT-1	donor1_fat	ACGTAGTTCCCGAAAT-1	1	fat	abdomen	1	F	3897	1246	36.23300	49.73056	62.63793	80.70310	39	11	1.0007698	3897	FALSE	FALSE
donor1_fat.ACGTTCCAGATGAATC-1	donor1_fat	ACGTTCCAGATGAATC-1	1	fat	abdomen	1	F	1884	1136	28.60934	36.57113	47.29299	66.24204	280	13	14.8619958	1884	FALSE	FALSE
donor1_fat.ACTCTCGAGCCGTTGC-1	donor1_fat	ACTCTCGAGCCGTTGC-1	1	fat	abdomen	1	F	1220	611	41.96721	53.77049	66.31148	90.90164	154	15	12.6229508	1220	FALSE	FALSE
donor1_fat.ACTTCCGTCAGGAACG-1	donor1_fat	ACTTCCGTCAGGAACG-1	1	fat	abdomen	1	F	4898	2364	17.29277	24.37730	34.29971	53.14414	367	16	7.4928542	4898	FALSE	FALSE
donor1_fat.AGACACTCAGGCGATA-1	donor1_fat	AGACACTCAGGCGATA-1	1	fat	abdomen	1	F	4601	1518	33.51445	46.70724	59.70441	76.26603	171	12	3.7165834	4601	FALSE	FALSE
donor1_fat.AGACCATTCAAAGGTA-1	donor1_fat	AGACCATTCAAAGGTA-1	1	fat	abdomen	1	F	7030	2375	27.28307	38.50640	50.54054	66.28734	27	10	0.3840683	7030	FALSE	FALSE
donor1_fat.AGAGAGCCAAGCCCAC-1	donor1_fat	AGAGAGCCAAGCCCAC-1	1	fat	abdomen	1	F	3437	1047	43.26447	57.81205	69.53739	84.08496	85	12	2.4730870	3437	FALSE	FALSE
donor1_fat.AGAGCCCAGTCTAGCT-1	donor1_fat	AGAGCCCAGTCTAGCT-1	1	fat	abdomen	1	F	4781	1680	33.44489	46.37105	58.12592	73.41560	110	14	2.3007739	4781	FALSE	FALSE
donor1_fat.AGATCCAGTGCAGTGA-1	donor1_fat	AGATCCAGTGCAGTGA-1	1	fat	abdomen	1	F	3119	1398	30.49054	42.70600	53.83136	71.20872	84	12	2.6931709	3119	FALSE	FALSE
donor1_fat.AGATCGTGTTGCGTAT-1	donor1_fat	AGATCGTGTTGCGTAT-1	1	fat	abdomen	1	F	4444	1616	32.06571	45.16202	56.79568	73.33483	7	5	0.1575158	4444	FALSE	FALSE
donor1_fat.AGGAGGTCAATACGAA-1	donor1_fat	AGGAGGTCAATACGAA-1	1	fat	abdomen	1	F	3179	1211	36.83548	49.82699	61.81189	77.63448	108	12	3.3972947	3179	FALSE	FALSE
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
donor5_recovery.TTTCGATAGTGGAATT-1	donor5_recovery	TTTCGATAGTGGAATT-1	5	mixed	abdomen	4	?	3048	1575	21.42388	31.33202	42.84777	64.20604	139	16	4.5603675	3048	FALSE	FALSE
donor5_recovery.TTTCGATGTGCTGATT-1	donor5_recovery	TTTCGATGTGCTGATT-1	5	mixed	abdomen	4	?	2238	1400	17.20286	25.24576	36.90795	59.78552	57	15	2.5469169	2238	FALSE	FALSE
donor5_recovery.TTTGACTAGATGGGCT-1	donor5_recovery	TTTGACTAGATGGGCT-1	5	mixed	abdomen	4	?	2448	1208	27.69608	39.95098	53.10458	71.07843	95	16	3.8807190	2448	FALSE	FALSE
donor5_recovery.TTTGACTAGTGTTCAC-1	donor5_recovery	TTTGACTAGTGTTCAC-1	5	mixed	abdomen	4	?	6499	2564	24.23450	34.06678	44.72996	60.70165	78	13	1.2001846	6499	FALSE	FALSE
donor5_recovery.TTTGACTGTCCAAATC-1	donor5_recovery	TTTGACTGTCCAAATC-1	5	mixed	abdomen	4	?	958	673	24.32150	35.80376	50.62630	81.94154	8	4	0.8350731	958	FALSE	FALSE
donor5_recovery.TTTGACTGTGATTCTG-1	donor5_recovery	TTTGACTGTGATTCTG-1	5	mixed	abdomen	4	?	1568	955	26.97704	37.75510	50.70153	70.98214	71	14	4.5280612	1568	FALSE	FALSE
donor5_recovery.TTTGACTGTTGTCTAG-1	donor5_recovery	TTTGACTGTTGTCTAG-1	5	mixed	abdomen	4	?	936	593	29.70085	42.30769	58.01282	90.06410	38	11	4.0598291	936	FALSE	FALSE
donor5_recovery.TTTGATCAGATGACCG-1	donor5_recovery	TTTGATCAGATGACCG-1	5	mixed	abdomen	4	?	956	596	30.75314	43.61925	58.57741	89.95816	25	8	2.6150628	956	FALSE	FALSE
donor5_recovery.TTTGATCAGCAATAAC-1	donor5_recovery	TTTGATCAGCAATAAC-1	5	mixed	abdomen	4	?	2148	939	34.35754	48.51024	61.17318	79.56238	71	14	3.3054004	2148	FALSE	FALSE
donor5_recovery.TTTGATCAGTTACTCG-1	donor5_recovery	TTTGATCAGTTACTCG-1	5	mixed	abdomen	4	?	3145	1486	21.90779	32.84579	46.45469	67.59936	66	15	2.0985692	3145	FALSE	FALSE
donor5_recovery.TTTGATCGTTGGGCCT-1	donor5_recovery	TTTGATCGTTGGGCCT-1	5	mixed	abdomen	4	?	2897	1316	30.54884	42.18157	54.57370	71.83293	182	17	6.2823611	2897	FALSE	FALSE
donor5_recovery.TTTGATCTCAAAGGTA-1	donor5_recovery	TTTGATCTCAAAGGTA-1	5	mixed	abdomen	4	?	2155	1136	26.07889	36.98376	50.06961	70.48724	98	14	4.5475638	2155	FALSE	FALSE
donor5_recovery.TTTGGAGAGTGCAAAT-1	donor5_recovery	TTTGGAGAGTGCAAAT-1	5	mixed	abdomen	4	?	1054	601	34.91461	48.10247	61.95446	90.41746	43	14	4.0796964	1054	FALSE	FALSE
donor5_recovery.TTTGGAGCATAGGTAA-1	donor5_recovery	TTTGGAGCATAGGTAA-1	5	mixed	abdomen	4	?	1846	1050	23.34778	33.91116	47.50813	70.20585	89	14	4.8212351	1846	FALSE	FALSE
donor5_recovery.TTTGGAGGTCAGTTTG-1	donor5_recovery	TTTGGAGGTCAGTTTG-1	5	mixed	abdomen	4	?	1222	769	26.67758	38.21604	53.43699	77.98691	51	13	4.1734861	1222	FALSE	FALSE
donor5_recovery.TTTGGAGGTCCAAGAG-1	donor5_recovery	TTTGGAGGTCCAAGAG-1	5	mixed	abdomen	4	?	1829	1058	27.28267	37.88956	49.64461	69.49153	28	12	1.5308912	1829	FALSE	FALSE
donor5_recovery.TTTGGAGGTCGACTTA-1	donor5_recovery	TTTGGAGGTCGACTTA-1	5	mixed	abdomen	4	?	2389	1430	17.91545	26.28715	38.21683	61.07158	154	21	6.4462118	2389	FALSE	FALSE
donor5_recovery.TTTGGAGGTTGAGAGC-1	donor5_recovery	TTTGGAGGTTGAGAGC-1	5	mixed	abdomen	4	?	1618	993	21.69345	32.26205	46.66255	69.53028	38	11	2.3485785	1618	FALSE	FALSE
donor5_recovery.TTTGGAGTCCAAGAGG-1	donor5_recovery	TTTGGAGTCCAAGAGG-1	5	mixed	abdomen	4	?	1262	830	23.85103	34.62758	50.07924	73.85103	69	14	5.4675119	1262	FALSE	FALSE
donor5_recovery.TTTGGAGTCTCAACCC-1	donor5_recovery	TTTGGAGTCTCAACCC-1	5	mixed	abdomen	4	?	1135	717	29.51542	40.79295	54.44934	80.88106	18	10	1.5859031	1135	FALSE	FALSE
donor5_recovery.TTTGGTTAGCCTCTTC-1	donor5_recovery	TTTGGTTAGCCTCTTC-1	5	mixed	abdomen	4	?	763	584	24.90170	36.56619	49.67235	88.99083	24	8	3.1454784	763	FALSE	FALSE
donor5_recovery.TTTGGTTCACTCTAGA-1	donor5_recovery	TTTGGTTCACTCTAGA-1	5	mixed	abdomen	4	?	812	570	27.58621	40.14778	54.43350	91.37931	24	8	2.9556650	812	FALSE	FALSE
donor5_recovery.TTTGGTTGTACGTGAG-1	donor5_recovery	TTTGGTTGTACGTGAG-1	5	mixed	abdomen	4	?	755	494	30.99338	44.90066	61.05960	100.00000	34	9	4.5033113	755	FALSE	FALSE
donor5_recovery.TTTGGTTGTCCTACAA-1	donor5_recovery	TTTGGTTGTCCTACAA-1	5	mixed	abdomen	4	?	835	625	24.07186	36.04790	49.10180	85.02994	27	6	3.2335329	835	FALSE	FALSE
donor5_recovery.TTTGGTTGTGACTCTA-1	donor5_recovery	TTTGGTTGTGACTCTA-1	5	mixed	abdomen	4	?	938	572	29.63753	43.39019	60.34115	92.32409	2	2	0.2132196	938	FALSE	FALSE
donor5_recovery.TTTGGTTTCGACCAAT-1	donor5_recovery	TTTGGTTTCGACCAAT-1	5	mixed	abdomen	4	?	1328	670	34.33735	48.34337	64.30723	87.19880	67	10	5.0451807	1328	FALSE	FALSE
donor5_recovery.TTTGTTGGTCCTACGG-1	donor5_recovery	TTTGTTGGTCCTACGG-1	5	mixed	abdomen	4	?	795	552	28.30189	41.63522	55.72327	93.45912	44	12	5.5345912	795	FALSE	FALSE
donor5_recovery.TTTGTTGGTCGCAGTC-1	donor5_recovery	TTTGTTGGTCGCAGTC-1	5	mixed	abdomen	4	?	1872	1250	16.18590	24.73291	37.01923	59.93590	66	14	3.5256410	1872	FALSE	FALSE
donor5_recovery.TTTGTTGGTGGCGTAA-1	donor5_recovery	TTTGTTGGTGGCGTAA-1	5	mixed	abdomen	4	?	1928	931	33.14315	46.21369	58.97303	77.64523	51	13	2.6452282	1928	FALSE	FALSE
donor5_recovery.TTTGTTGTCGGCATTA-1	donor5_recovery	TTTGTTGTCGGCATTA-1	5	mixed	abdomen	4	?	2091	1206	21.95122	32.56815	45.28934	66.23625	53	14	2.5346724	2091	FALSE	FALSE

with(cd_df, table(outlier_sum, outlier_detected))

           outlier_detected
outlier_sum FALSE  TRUE
      FALSE 22274    12
      TRUE     12    39

options(repr.plot.width=20, repr.plot.height=20)


ggplot(cd_df, aes(sum, detected, color=outlier_sum, shape=outlier_detected)) +
    geom_point(size=2) +
    scale_x_log10() +
    scale_y_log10() +
    facet_wrap(~Sample)

options(repr.plot.width=20, repr.plot.height=20)

ggplot(cd_df, aes(sum, subsets_Mito_percent, color=outlier_sum, shape=outlier_detected)) +
    geom_point(size=2) +
    scale_x_log10() +
    facet_wrap(~Sample)

colData(sce) <- cd_df %>% DataFrame
colData(sce)

DataFrame with 22337 rows and 19 columns
                                            Sample            Barcode     donor
                                       <character>        <character> <numeric>
donor1_fat.AAAGAACCACATACGT-1           donor1_fat AAAGAACCACATACGT-1         1
donor1_fat.AAAGGTAGTCCGGTCA-1           donor1_fat AAAGGTAGTCCGGTCA-1         1
donor1_fat.AAAGGTATCTCTCTTC-1           donor1_fat AAAGGTATCTCTCTTC-1         1
donor1_fat.AACCACACAGTGGCTC-1           donor1_fat AACCACACAGTGGCTC-1         1
donor1_fat.AACGGGATCTGCTGAA-1           donor1_fat AACGGGATCTGCTGAA-1         1
...                                            ...                ...       ...
donor5_recovery.TTTGGTTTCGACCAAT-1 donor5_recovery TTTGGTTTCGACCAAT-1         5
donor5_recovery.TTTGTTGGTCCTACGG-1 donor5_recovery TTTGTTGGTCCTACGG-1         5
donor5_recovery.TTTGTTGGTCGCAGTC-1 donor5_recovery TTTGTTGGTCGCAGTC-1         5
donor5_recovery.TTTGTTGGTGGCGTAA-1 donor5_recovery TTTGTTGGTGGCGTAA-1         5
donor5_recovery.TTTGTTGTCGGCATTA-1 donor5_recovery TTTGTTGTCGGCATTA-1         5
                                        tissue tissue_origin sequencing_run
                                   <character>   <character>      <numeric>
donor1_fat.AAAGAACCACATACGT-1              fat       abdomen              1
donor1_fat.AAAGGTAGTCCGGTCA-1              fat       abdomen              1
donor1_fat.AAAGGTATCTCTCTTC-1              fat       abdomen              1
donor1_fat.AACCACACAGTGGCTC-1              fat       abdomen              1
donor1_fat.AACGGGATCTGCTGAA-1              fat       abdomen              1
...                                        ...           ...            ...
donor5_recovery.TTTGGTTTCGACCAAT-1       mixed       abdomen              4
donor5_recovery.TTTGTTGGTCCTACGG-1       mixed       abdomen              4
donor5_recovery.TTTGTTGGTCGCAGTC-1       mixed       abdomen              4
donor5_recovery.TTTGTTGGTGGCGTAA-1       mixed       abdomen              4
donor5_recovery.TTTGTTGTCGGCATTA-1       mixed       abdomen              4
                                           sex       sum  detected
                                   <character> <numeric> <integer>
donor1_fat.AAAGAACCACATACGT-1                F      4276      1721
donor1_fat.AAAGGTAGTCCGGTCA-1                F      3023      1084
donor1_fat.AAAGGTATCTCTCTTC-1                F      3892      1422
donor1_fat.AACCACACAGTGGCTC-1                F      7722      2633
donor1_fat.AACGGGATCTGCTGAA-1                F      3256      1284
...                                        ...       ...       ...
donor5_recovery.TTTGGTTTCGACCAAT-1           ?      1328       670
donor5_recovery.TTTGTTGGTCCTACGG-1           ?       795       552
donor5_recovery.TTTGTTGGTCGCAGTC-1           ?      1872      1250
donor5_recovery.TTTGTTGGTGGCGTAA-1           ?      1928       931
donor5_recovery.TTTGTTGTCGGCATTA-1           ?      2091      1206
                                   percent.top_50 percent.top_100
                                        <numeric>       <numeric>
donor1_fat.AAAGAACCACATACGT-1             33.8868         42.7736
donor1_fat.AAAGGTAGTCCGGTCA-1             39.6626         52.9937
donor1_fat.AAAGGTATCTCTCTTC-1             34.1213         46.5570
donor1_fat.AACCACACAGTGGCTC-1             26.8972         38.1248
donor1_fat.AACGGGATCTGCTGAA-1             34.3366         46.8059
...                                           ...             ...
donor5_recovery.TTTGGTTTCGACCAAT-1        34.3373         48.3434
donor5_recovery.TTTGTTGGTCCTACGG-1        28.3019         41.6352
donor5_recovery.TTTGTTGGTCGCAGTC-1        16.1859         24.7329
donor5_recovery.TTTGTTGGTGGCGTAA-1        33.1432         46.2137
donor5_recovery.TTTGTTGTCGGCATTA-1        21.9512         32.5681
                                   percent.top_200 percent.top_500
                                         <numeric>       <numeric>
donor1_fat.AAAGAACCACATACGT-1              52.9935         69.3171
donor1_fat.AAAGGTAGTCCGGTCA-1              65.0017         80.6814
donor1_fat.AAAGGTATCTCTCTTC-1              58.3505         75.9250
donor1_fat.AACCACACAGTGGCTC-1              48.6791         64.1285
donor1_fat.AACGGGATCTGCTGAA-1              59.0602         75.9214
...                                            ...             ...
donor5_recovery.TTTGGTTTCGACCAAT-1         64.3072         87.1988
donor5_recovery.TTTGTTGGTCCTACGG-1         55.7233         93.4591
donor5_recovery.TTTGTTGGTCGCAGTC-1         37.0192         59.9359
donor5_recovery.TTTGTTGGTGGCGTAA-1         58.9730         77.6452
donor5_recovery.TTTGTTGTCGGCATTA-1         45.2893         66.2363
                                   subsets_Mito_sum subsets_Mito_detected
                                          <numeric>             <integer>
donor1_fat.AAAGAACCACATACGT-1                   752                    16
donor1_fat.AAAGGTAGTCCGGTCA-1                    52                    12
donor1_fat.AAAGGTATCTCTCTTC-1                    48                    12
donor1_fat.AACCACACAGTGGCTC-1                   103                    13
donor1_fat.AACGGGATCTGCTGAA-1                   123                    11
...                                             ...                   ...
donor5_recovery.TTTGGTTTCGACCAAT-1               67                    10
donor5_recovery.TTTGTTGGTCCTACGG-1               44                    12
donor5_recovery.TTTGTTGGTCGCAGTC-1               66                    14
donor5_recovery.TTTGTTGGTGGCGTAA-1               51                    13
donor5_recovery.TTTGTTGTCGGCATTA-1               53                    14
                                   subsets_Mito_percent     total
                                              <numeric> <numeric>
donor1_fat.AAAGAACCACATACGT-1                  17.58653      4276
donor1_fat.AAAGGTAGTCCGGTCA-1                   1.72015      3023
donor1_fat.AAAGGTATCTCTCTTC-1                   1.23330      3892
donor1_fat.AACCACACAGTGGCTC-1                   1.33385      7722
donor1_fat.AACGGGATCTGCTGAA-1                   3.77764      3256
...                                                 ...       ...
donor5_recovery.TTTGGTTTCGACCAAT-1              5.04518      1328
donor5_recovery.TTTGTTGGTCCTACGG-1              5.53459       795
donor5_recovery.TTTGTTGGTCGCAGTC-1              3.52564      1872
donor5_recovery.TTTGTTGGTGGCGTAA-1              2.64523      1928
donor5_recovery.TTTGTTGTCGGCATTA-1              2.53467      2091
                                        outlier_sum outlier_detected
                                   <outlier.filter> <outlier.filter>
donor1_fat.AAAGAACCACATACGT-1                 FALSE            FALSE
donor1_fat.AAAGGTAGTCCGGTCA-1                 FALSE            FALSE
donor1_fat.AAAGGTATCTCTCTTC-1                 FALSE            FALSE
donor1_fat.AACCACACAGTGGCTC-1                 FALSE            FALSE
donor1_fat.AACGGGATCTGCTGAA-1                 FALSE            FALSE
...                                             ...              ...
donor5_recovery.TTTGGTTTCGACCAAT-1            FALSE            FALSE
donor5_recovery.TTTGTTGGTCCTACGG-1            FALSE            FALSE
donor5_recovery.TTTGTTGGTCGCAGTC-1            FALSE            FALSE
donor5_recovery.TTTGTTGGTGGCGTAA-1            FALSE            FALSE
donor5_recovery.TTTGTTGTCGGCATTA-1            FALSE            FALSE

sce <- sce[,!colData(sce)$outlier_detected]
sce <- sce[,!colData(sce)$outlier_sum]
sce

class: SingleCellExperiment 
dim: 18627 22274 
metadata(0):
assays(1): counts
rownames(18627): ENSG00000187634.SAMD11 ENSG00000188976.NOC2L ...
  ENSG00000278817.ENSG00000278817 ENSG00000277196.ENSG00000277196
rowData names(3): ID Symbol Type
colnames(22274): donor1_fat.AAAGAACCACATACGT-1
  donor1_fat.AAAGGTAGTCCGGTCA-1 ... donor5_recovery.TTTGTTGGTGGCGTAA-1
  donor5_recovery.TTTGTTGTCGGCATTA-1
colData names(19): Sample Barcode ... outlier_sum outlier_detected
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

saveRDS(sce, file="../output/0.1-sce-after-filtering.rds")

markers <- googlesheets4::read_sheet(md_sheet, sheet = "markers")
markers

✔ Reading from halin-bauer-hLECs-metadata.

✔ Range ''markers''.

A tibble: 37 × 5
gene_name	subpopulation	subpopshort	direction	known
<chr>	<chr>	<chr>	<chr>	<chr>
ENSG00000117707.PROX1	LECs	LEC	positive	yes
ENSG00000162493.PDPN	LECs	LEC	positive	yes
ENSG00000133800.LYVE1	capillary-LEC	cpLEC	positive	yes
ENSG00000137077.CCL21	capillary-LEC	cpLEC	positive	yes
ENSG00000189056.RELN	capillary-LEC	cpLEC	positive	yes
ENSG00000129048.ACKR4	capillary-LEC	cpLEC	negative	yes
ENSG00000108691.CCL2	capillary-LEC	cpLEC	negative	no
ENSG00000081041.CXCL2	capillary-LEC	cpLEC	negative	no
ENSG00000133800.LYVE1	precollector-LEC	pcLEC	positive	yes
ENSG00000137077.CCL21	precollector-LEC	pcLEC	positive	yes
ENSG00000189056.RELN	precollector-LEC	pcLEC	positive	yes
ENSG00000129048.ACKR4	precollector-LEC	pcLEC	negative	yes
ENSG00000108691.CCL2	precollector-LEC	pcLEC	positive	no
ENSG00000081041.CXCL2	precollector-LEC	pcLEC	positive	no
ENSG00000133800.LYVE1	collector-LEC	clLEC	negative	yes
ENSG00000137077.CCL21	collector-LEC	clLEC	negative	yes
ENSG00000189056.RELN	collector-LEC	clLEC	negative	yes
ENSG00000129048.ACKR4	collector-LEC	clLEC	positive	yes
ENSG00000108691.CCL2	collector-LEC	clLEC	positive	no
ENSG00000081041.CXCL2	collector-LEC	clLEC	positive	no
ENSG00000137077.CCL21	valve-LEC	vLEC	negative	yes
ENSG00000133800.LYVE1	valve-LEC	vLEC	negative	yes
ENSG00000013297.CLDN11	valve-LEC	vLEC	positive	yes
ENSG00000272398.CD24	valve-LEC	vLEC	positive	no
ENSG00000149564.ESAM	valve-LEC	vLEC	positive	no
ENSG00000170017.ALCAM	valve-LEC	vLEC	positive	no
ENSG00000108821.COL1A1	contaminant-fibroblasts-smooth-muscle	CONT-FSM	positive	yes
ENSG00000113721.PDGFRB	contaminant-fibroblasts-smooth-muscle	CONT-FSM	positive	yes
ENSG00000107796.ACTA2	contaminant-fibroblasts-smooth-muscle	CONT-FSM	positive	yes
ENSG00000186081.KRT5	contaminant-keratinocytes	CONT-K	positive	yes
ENSG00000186847.KRT14	contaminant-keratinocytes	CONT-K	positive	yes
ENSG00000081237.PTPRC	contaminant-leukocytes	CONT-L	positive	yes
ENSG00000102755.FLT1	contaminant-blood-endothelial-cells	CONT-BEC	positive	yes
ENSG00000154721.JAM2	contaminant-blood-endothelial-cells	CONT-BEC	positive	yes
ENSG00000090339.ICAM1	LECs	LEC	positive	?
ENSG00000103335.PIEZO1	LECs	LEC	positive	?
ENSG00000154864.PIEZO2	LECs	LEC	positive	?

sce <- logNormCounts(sce)
sce

class: SingleCellExperiment 
dim: 18627 22274 
metadata(0):
assays(2): counts logcounts
rownames(18627): ENSG00000187634.SAMD11 ENSG00000188976.NOC2L ...
  ENSG00000278817.ENSG00000278817 ENSG00000277196.ENSG00000277196
rowData names(3): ID Symbol Type
colnames(22274): donor1_fat.AAAGAACCACATACGT-1
  donor1_fat.AAAGGTAGTCCGGTCA-1 ... donor5_recovery.TTTGTTGGTGGCGTAA-1
  donor5_recovery.TTTGTTGTCGGCATTA-1
colData names(20): Sample Barcode ... outlier_detected sizeFactor
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

mgv <- modelGeneVar(sce, block=sce$Sample)
per_block <- mgv$per.block
mgv$mgv$per.block <- NULL
per_block

DataFrame with 18627 rows and 12 columns
                                donor1_fat
                               <DataFrame>
1        0.0000000:0.0000000:0.0000000:...
2        0.0447544:0.0483622:0.0471062:...
3        0.0299111:0.0420068:0.0315344:...
4        0.0000000:0.0000000:0.0000000:...
5        0.0000000:0.0000000:0.0000000:...
...                                    ...
18623 0.00527968:0.00440426:0.00557591:...
18624 0.00000000:0.00000000:0.00000000:...
18625 0.00000000:0.00000000:0.00000000:...
18626 0.01379355:0.01574627:0.01456116:...
18627 0.00000000:0.00000000:0.00000000:...
                                  donor1_skin
                                  <DataFrame>
1     0.000192091:0.000140327:0.000210392:...
2     0.030096853:0.034786115:0.032963547:...
3     0.007230149:0.009100637:0.007918963:...
4     0.000673060:0.000577614:0.000737182:...
5     0.000000000:0.000000000:0.000000000:...
...                                       ...
18623 0.005793431:0.006536338:0.006345371:...
18624 0.000655845:0.000823243:0.000718328:...
18625 0.000000000:0.000000000:0.000000000:...
18626 0.015571469:0.017150311:0.017054905:...
18627 0.000000000:0.000000000:0.000000000:...
                                   donor2_fat
                                  <DataFrame>
1     0.000257818:9.52261e-05:0.000231155:...
2     0.030989651:2.27018e-02:0.027517226:...
3     0.000541784:4.51619e-04:0.000485743:...
4     0.001016535:7.51721e-04:0.000911335:...
5     0.000000000:0.00000e+00:0.000000000:...
...                                       ...
18623  0.006846574:0.00432770:0.006130807:...
18624  0.063328584:0.05779895:0.055368734:...
18625  0.000000000:0.00000000:0.000000000:...
18626  0.018603745:0.01511799:0.016598744:...
18627  0.000612517:0.00105725:0.000549155:...
                                   donor3_fat
                                  <DataFrame>
1     0.005251594:0.002826777:0.002720376:...
2     0.058227092:0.025883220:0.030161476:...
3     0.002911593:0.001252882:0.001508233:...
4     0.000463204:0.000109945:0.000239944:...
5     0.000768523:0.000603030:0.000398102:...
...                                       ...
18623  0.01701294:0.007165761:0.008812857:...
18624  0.04656016:0.019818419:0.024118293:...
18625  0.00047452:0.000119722:0.000245806:...
18626  0.02401902:0.009052763:0.012442053:...
18627  0.00000000:0.000000000:0.000000000:...
                                  donor3_skin
                                  <DataFrame>
1     0.000000000:0.000000000:0.000000000:...
2     0.077795605:0.048279909:0.058675308:...
3     0.004722309:0.005066520:0.003738193:...
4     0.000962391:0.000527005:0.000763779:...
5     0.000000000:0.000000000:0.000000000:...
...                                       ...
18623    0.03084809:0.02389855:0.02399428:...
18624    0.05316327:0.03602979:0.04074557:...
18625    0.00000000:0.00000000:0.00000000:...
18626    0.00585365:0.00409068:0.00463021:...
18627    0.00000000:0.00000000:0.00000000:...
                                  donor4_fat
                                 <DataFrame>
1     0.01069955:3.53034e-03:0.004835728:...
2     0.09387548:4.16551e-02:0.042425119:...
3     0.01530288:6.05392e-03:0.006916231:...
4     0.00104185:9.55201e-05:0.000470872:...
5     0.00000000:0.00000e+00:0.000000000:...
...                                      ...
18623    0.0202734:0.00534214:0.00916268:...
18624    0.0624849:0.02416214:0.02823992:...
18625    0.0000000:0.00000000:0.00000000:...
18626    0.0377530:0.01659354:0.01706262:...
18627    0.0000000:0.00000000:0.00000000:...
                                  donor4_skin
                                  <DataFrame>
1     0.001684255:0.000984743:0.000795111:...
2     0.099895592:0.041682785:0.047077413:...
3     0.018399329:0.011478903:0.008685330:...
4     0.002311079:0.000617455:0.001091023:...
5     0.000486684:0.000148986:0.000229756:...
...                                       ...
18623  0.03531342:0.017654658:0.016666491:...
18624  0.08061596:0.029509405:0.038012706:...
18625  0.00000000:0.000000000:0.000000000:...
18626  0.00619706:0.002728810:0.002925505:...
18627  0.00156129:0.000797139:0.000737061:...
                              donor5_recovery
                                  <DataFrame>
1     0.002386149:0.003595803:0.004200088:...
2     0.036177813:0.066393947:0.063676351:...
3     0.005542531:0.010860622:0.009755932:...
4     0.000470654:0.000546747:0.000828443:...
5     0.000000000:0.000000000:0.000000000:...
...                                       ...
18623    0.00385830:0.00629160:0.00679135:...
18624    0.00000000:0.00000000:0.00000000:...
18625    0.00000000:0.00000000:0.00000000:...
18626    0.00218717:0.00460785:0.00384985:...
18627    0.00000000:0.00000000:0.00000000:...
                                donor6_fat                          donor6_skin
                               <DataFrame>                          <DataFrame>
1     0.00000000:0.00000000:0.00000000:... 0.00116394:0.00130381:0.00192853:...
2     0.02855809:0.04743540:0.04610573:... 0.03484125:0.06236383:0.05771629:...
3     0.00443248:0.00746152:0.00715685:... 0.00171647:0.00298939:0.00284401:...
4     0.00105621:0.00222445:0.00170539:... 0.00000000:0.00000000:0.00000000:...
5     0.00000000:0.00000000:0.00000000:... 0.00000000:0.00000000:0.00000000:...
...                                    ...                                  ...
18623  0.00672034:0.0142582:0.01085087:...  0.01009389:0.0186100:0.01672428:...
18624  0.00000000:0.0000000:0.00000000:...  0.00000000:0.0000000:0.00000000:...
18625  0.00000000:0.0000000:0.00000000:...  0.00000000:0.0000000:0.00000000:...
18626  0.00103449:0.0021339:0.00167032:...  0.00490375:0.0084261:0.00812499:...
18627  0.00000000:0.0000000:0.00000000:...  0.00000000:0.0000000:0.00000000:...
                                  donor7_fat
                                 <DataFrame>
1       0.00162012:0.00274062:0.00245109:...
2       0.03856859:0.06085669:0.05814055:...
3       0.01021691:0.01666630:0.01544960:...
4       0.00108433:0.00200704:0.00164052:...
5       0.00000000:0.00000000:0.00000000:...
...                                      ...
18623 0.012511800:0.017865490:0.01891639:...
18624 0.000000000:0.000000000:0.00000000:...
18625 0.000000000:0.000000000:0.00000000:...
18626 0.000761895:0.000990887:0.00115271:...
18627 0.000000000:0.000000000:0.00000000:...
                                  donor7_skin
                                  <DataFrame>
1     0.000377092:0.000412090:0.000554036:...
2     0.029380808:0.047142481:0.043156883:...
3     0.004676678:0.007048741:0.006871096:...
4     0.002052253:0.002850248:0.003015239:...
5     0.000457449:0.000606435:0.000672101:...
...                                       ...
18623    0.00951234:0.01478812:0.01397550:...
18624    0.00000000:0.00000000:0.00000000:...
18625    0.00000000:0.00000000:0.00000000:...
18626    0.00246677:0.00309163:0.00362426:...
18627    0.00000000:0.00000000:0.00000000:...

mgv <- mgv %>% as.data.frame %>% rownames_to_column("gene_name") %>% left_join(markers, multiple = "first")
mgv

Joining with `by = join_by(gene_name)`

A data.frame: 18627 × 83
gene_name	mean	total	tech	bio	p.value	FDR	per.block.donor1_fat.mean	per.block.donor1_fat.total	per.block.donor1_fat.tech	⋯	per.block.donor7_skin.mean	per.block.donor7_skin.total	per.block.donor7_skin.tech	per.block.donor7_skin.bio	per.block.donor7_skin.p.value	per.block.donor7_skin.FDR	subpopulation	subpopshort	direction	known
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<chr>	<chr>	<chr>	<chr>
ENSG00000187634.SAMD11	0.0019693835	0.0013024782	0.0014938755	-1.913973e-04	8.737032e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0003770917	0.0004120903	0.0005540363	-1.419460e-04	9.994747e-01	1.000000e+00	NA	NA	NA	NA
ENSG00000188976.NOC2L	0.0502634315	0.0456286194	0.0462268405	-5.982211e-04	5.299364e-01	9.355400e-01	0.044754353	0.048362162	0.047106190	⋯	0.0293808083	0.0471424812	0.0431568827	3.985598e-03	1.187842e-01	5.326614e-01	NA	NA	NA	NA
ENSG00000187961.KLHL17	0.0088003534	0.0100364902	0.0085720454	1.464445e-03	1.356136e-02	5.041921e-02	0.029911128	0.042006834	0.031534370	⋯	0.0046766780	0.0070487413	0.0068710959	1.776454e-04	3.704551e-01	7.408704e-01	NA	NA	NA	NA
ENSG00000187583.PLEKHN1	0.0009276301	0.0008589782	0.0009503105	-9.133234e-05	7.086989e-02	2.073134e-01	0.000000000	0.000000000	0.000000000	⋯	0.0020522533	0.0028502483	0.0030152388	-1.649905e-04	7.579746e-01	8.954704e-01	NA	NA	NA	NA
ENSG00000187642.PERM1	0.0001427214	0.0001132043	0.0001083299	4.874395e-06	1.791375e-01	4.312149e-01	0.000000000	0.000000000	0.000000000	⋯	0.0004574494	0.0006064354	0.0006721007	-6.566524e-05	8.942605e-01	9.949778e-01	NA	NA	NA	NA
ENSG00000188290.HES4	0.4317683304	0.4744427877	0.4318170816	4.262571e-02	1.769217e-02	6.342516e-02	0.579772219	0.530487385	0.524572804	⋯	0.5032418551	0.7325884217	0.6744572788	5.813114e-02	1.351696e-01	5.618877e-01	NA	NA	NA	NA
ENSG00000187608.ISG15	0.1907224467	0.2125479814	0.1605618632	5.198612e-02	8.298437e-13	1.131179e-11	0.116807731	0.111024323	0.121563029	⋯	0.1162945309	0.1917556701	0.1700318967	2.172377e-02	5.113300e-02	3.398987e-01	NA	NA	NA	NA
ENSG00000188157.AGRN	0.1114768158	0.1148564437	0.1092542055	5.602238e-03	1.795969e-01	4.320410e-01	0.138418928	0.130595390	0.143518295	⋯	0.1001736813	0.1677008352	0.1467709611	2.092987e-02	3.409516e-02	2.628374e-01	NA	NA	NA	NA
ENSG00000131591.C1orf159	0.0313450869	0.0341074411	0.0326217764	1.485665e-03	1.950322e-01	4.590749e-01	0.014560216	0.016643509	0.015369731	⋯	0.0290359040	0.0439328414	0.0426504987	1.282343e-03	3.502968e-01	7.360048e-01	NA	NA	NA	NA
ENSG00000162571.TTLL10	0.0008546147	0.0005900526	0.0005168317	7.322091e-05	1.540465e-10	1.746455e-09	0.000000000	0.000000000	0.000000000	⋯	0.0008199698	0.0019484717	0.0012047281	7.437436e-04	1.447307e-15	1.961519e-13	NA	NA	NA	NA
ENSG00000186891.TNFRSF18	0.0058911157	0.0033663407	0.0034570205	-9.067979e-05	1.715891e-07	1.429371e-06	0.000000000	0.000000000	0.000000000	⋯	0.0006670706	0.0006459384	0.0009800834	-3.341450e-04	9.999935e-01	1.000000e+00	NA	NA	NA	NA
ENSG00000186827.TNFRSF4	0.1043514102	0.1025507891	0.0915769314	1.097386e-02	4.067668e-02	1.298149e-01	0.118148494	0.138295830	0.122931497	⋯	0.0535097343	0.0819809698	0.0785558824	3.425087e-03	2.885551e-01	7.098456e-01	NA	NA	NA	NA
ENSG00000078808.SDF4	0.2212428288	0.1731091994	0.1900223305	-1.691313e-02	9.752666e-01	1.000000e+00	0.125266097	0.109117598	0.130182344	⋯	0.1523546501	0.2205261063	0.2216055398	-1.079434e-03	5.248361e-01	7.857325e-01	NA	NA	NA	NA
ENSG00000176022.B3GALT6	0.0331810618	0.0290155465	0.0298696351	-8.540886e-04	2.808728e-01	6.080890e-01	0.033773789	0.043187394	0.035592796	⋯	0.0172146779	0.0291051117	0.0252902950	3.814817e-03	2.685835e-02	2.274809e-01	NA	NA	NA	NA
ENSG00000184163.C1QTNF12	0.0021494577	0.0015139299	0.0013974834	1.164465e-04	1.620399e-01	3.997888e-01	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000160087.UBE2J2	0.1039678327	0.0900077789	0.0929954030	-2.987624e-03	6.280412e-01	1.000000e+00	0.095448125	0.074176088	0.099676791	⋯	0.0682506326	0.1080415891	0.1001470086	7.894581e-03	1.566890e-01	5.931810e-01	NA	NA	NA	NA
ENSG00000162572.SCNN1D	0.0039239679	0.0045575486	0.0040416201	5.159285e-04	4.918952e-08	4.365540e-07	0.000000000	0.000000000	0.000000000	⋯	0.0057684617	0.0101547219	0.0084751452	1.679577e-03	5.630535e-03	7.276488e-02	NA	NA	NA	NA
ENSG00000131584.ACAP3	0.0229812853	0.0232988062	0.0211932916	2.105515e-03	1.937648e-05	1.234214e-04	0.011195668	0.019804193	0.011820538	⋯	0.0194500131	0.0379595830	0.0285735981	9.385985e-03	1.328671e-05	4.117809e-04	NA	NA	NA	NA
ENSG00000169972.PUSL1	0.0148668264	0.0123331169	0.0130527191	-7.196022e-04	8.753588e-01	1.000000e+00	0.022273057	0.021196167	0.023497957	⋯	0.0099100098	0.0157438677	0.0145597274	1.184140e-03	1.491395e-01	5.811430e-01	NA	NA	NA	NA
ENSG00000127054.INTS11	0.0863434745	0.0693228612	0.0735482434	-4.225382e-03	3.658966e-01	7.358698e-01	0.084655755	0.072026480	0.088577214	⋯	0.0394623773	0.0632514002	0.0579543345	5.297066e-03	1.212164e-01	5.363840e-01	NA	NA	NA	NA
ENSG00000224051.CPTP	0.0437399735	0.0345153310	0.0355729713	-1.057640e-03	2.192897e-01	5.029921e-01	0.028106629	0.021103972	0.029637060	⋯	0.0200511600	0.0345908846	0.0294565347	5.134350e-03	1.290151e-02	1.357971e-01	NA	NA	NA	NA
ENSG00000169962.TAS1R3	0.0004052785	0.0005136642	0.0004490183	6.464582e-05	6.063849e-10	6.566403e-09	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000107404.DVL1	0.0546596741	0.0559125190	0.0546148119	1.297707e-03	1.169168e-01	3.097954e-01	0.051992919	0.051285625	0.054674802	⋯	0.0494111753	0.0774444246	0.0725473686	4.897056e-03	1.939918e-01	6.394011e-01	NA	NA	NA	NA
ENSG00000162576.MXRA8	0.0733304526	0.0816338793	0.0424210381	3.921284e-02	8.369574e-10	8.943419e-09	0.041612054	0.048939431	0.043815198	⋯	0.0070240558	0.0104407885	0.0103198435	1.209450e-04	4.404284e-01	7.639509e-01	NA	NA	NA	NA
ENSG00000175756.AURKAIP1	0.2877332314	0.2267634099	0.2455746749	-1.881126e-02	9.404859e-01	1.000000e+00	0.358315318	0.322001177	0.351057560	⋯	0.1725839830	0.2569559693	0.2502336724	6.722297e-03	3.655864e-01	7.396080e-01	NA	NA	NA	NA
ENSG00000221978.CCNL2	0.1554273129	0.1607440768	0.1474084468	1.333563e-02	5.406649e-02	1.654175e-01	0.143807887	0.203728633	0.148957683	⋯	0.1123157102	0.1831533488	0.1643020608	1.885129e-02	7.113931e-02	4.110676e-01	NA	NA	NA	NA
ENSG00000242485.MRPL20	0.4041161319	0.3611990674	0.3758276205	-1.462855e-02	9.394156e-01	1.000000e+00	0.435379963	0.374452458	0.415710684	⋯	0.3693702802	0.5208705603	0.5140860481	6.784512e-03	4.329849e-01	7.621041e-01	NA	NA	NA	NA
ENSG00000235098.ANKRD65	0.0075721639	0.0037111374	0.0045934832	-8.823459e-04	7.679673e-01	1.000000e+00	0.005096231	0.004103508	0.005382204	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000205116.TMEM88B	0.0003453538	0.0001663211	0.0002435159	-7.719476e-05	9.989500e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0002774246	0.0002230429	0.0004076020	-1.845591e-04	1.000000e+00	1.000000e+00	NA	NA	NA	NA
ENSG00000179403.VWA1	0.0201312569	0.0184182043	0.0144274781	3.990726e-03	9.560126e-06	6.380166e-05	0.011154903	0.007099697	0.011777524	⋯	0.0078463236	0.0130163670	0.0115278913	1.488476e-03	4.933709e-02	3.325438e-01	NA	NA	NA	NA
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋱	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
ENSG00000182484.WASH6P	1.060511e-01	1.051630e-01	1.012401e-01	3.922887e-03	5.385302e-02	1.649027e-01	0.089568204	0.108006196	0.093636322	⋯	0.0983430607	0.1563313631	0.1441048272	1.222654e-02	1.389424e-01	0.567558120	NA	NA	NA	NA
ENSG00000129824.RPS4Y1	2.235694e-01	2.838755e-01	2.897254e-01	-5.849912e-03	1.472026e-03	6.816781e-03	0.002959566	0.001383926	0.003125851	⋯	0.0170548138	0.0324826172	0.0250554751	7.427142e-03	7.501188e-05	0.001922062	NA	NA	NA	NA
ENSG00000067646.ZFY	3.808236e-02	4.753073e-02	4.488257e-02	2.648161e-03	5.600530e-03	2.288586e-02	0.062956984	0.069570622	0.066102981	⋯	0.0111761192	0.0168789885	0.0164197643	4.592242e-04	3.602910e-01	0.738736203	NA	NA	NA	NA
ENSG00000099715.PCDH11Y	8.276551e-03	1.038031e-02	8.746170e-03	1.634137e-03	2.348474e-03	1.046374e-02	0.018789257	0.035260608	0.019828012	⋯	0.0056077484	0.0089139084	0.0082390261	6.748823e-04	1.474144e-01	0.578190854	NA	NA	NA	NA
ENSG00000099721.AMELY	3.799039e-04	3.942317e-04	3.744746e-04	1.975718e-05	2.299880e-04	1.239469e-03	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000092377.TBL1Y	6.918795e-04	7.768121e-04	8.532257e-04	-7.641360e-05	4.001967e-01	7.810283e-01	0.000000000	0.000000000	0.000000000	⋯	0.0009483741	0.0013166584	0.0013933841	-7.672566e-05	7.593519e-01	0.896580882	NA	NA	NA	NA
ENSG00000114374.USP9Y	3.812034e-02	6.343246e-02	6.151179e-02	1.920676e-03	8.991925e-01	1.000000e+00	0.004961967	0.003890137	0.005240431	⋯	0.0014691287	0.0021249447	0.0021584939	-3.354920e-05	5.787820e-01	0.804795343	NA	NA	NA	NA
ENSG00000067048.DDX3Y	9.987608e-02	1.538440e-01	1.521439e-01	1.700035e-03	3.401029e-04	1.767338e-03	0.000000000	0.000000000	0.000000000	⋯	0.0067399916	0.0129023438	0.0099025033	2.999841e-03	5.346960e-05	0.001428091	NA	NA	NA	NA
ENSG00000183878.UTY	6.276576e-02	1.035719e-01	9.944009e-02	4.131834e-03	2.371132e-05	1.491927e-04	0.000000000	0.000000000	0.000000000	⋯	0.0037955497	0.0055075356	0.0055765314	-6.899581e-05	5.628633e-01	0.797561478	NA	NA	NA	NA
ENSG00000154620.TMSB4Y	3.161534e-03	5.812091e-03	5.249932e-03	5.621585e-04	3.716597e-03	1.584561e-02	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000165246.NLGN4Y	2.889787e-02	4.648592e-02	4.439543e-02	2.090492e-03	2.261591e-05	1.426383e-04	0.007101396	0.007967912	0.007499287	⋯	0.0059726097	0.0094529158	0.0087750778	6.778379e-04	1.616008e-01	0.599288583	NA	NA	NA	NA
ENSG00000172468.HSFY1	1.774793e-04	1.349566e-04	1.911604e-04	-5.620376e-05	9.754492e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0002446283	0.0001734250	0.0003594165	-1.859914e-04	1.000000e+00	1.000000000	NA	NA	NA	NA
ENSG00000169953.HSFY2	2.195080e-04	2.132608e-04	2.215071e-04	-8.246239e-06	6.838196e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0002892259	0.0002424224	0.0004249408	-1.825184e-04	1.000000e+00	1.000000000	NA	NA	NA	NA
ENSG00000012817.KDM5D	1.168414e-02	2.019782e-02	1.928814e-02	9.096875e-04	2.116818e-03	9.515955e-03	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000198692.EIF1AY	4.603123e-02	7.533155e-02	7.455884e-02	7.727028e-04	9.981512e-02	2.736453e-01	0.000000000	0.000000000	0.000000000	⋯	0.0009624456	0.0009776989	0.0014140584	-4.363595e-04	9.999604e-01	1.000000000	NA	NA	NA	NA
ENSG00000280969.RPS4Y2	3.188270e-05	2.432296e-05	5.147908e-05	-2.715612e-05	1.000000e+00	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000169807.PRY2	6.112707e-05	5.399550e-05	8.281698e-05	-2.882148e-05	8.976356e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000187191.DAZ3	2.244223e-05	1.703156e-05	2.012135e-05	-3.089796e-06	8.264456e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000205916.DAZ4	1.205705e-04	2.539327e-04	1.831278e-04	7.080490e-05	7.884693e-07	6.082992e-06	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000278704.ENSG00000278704	6.738617e-03	7.672991e-03	7.311764e-03	3.612269e-04	3.103076e-01	6.540698e-01	0.007461762	0.008797108	0.007879719	⋯	0.0070398383	0.0101438386	0.0103430307	-1.991921e-04	5.972746e-01	0.811804880	NA	NA	NA	NA
ENSG00000277400.ENSG00000277400	3.346039e-03	3.604205e-03	3.321011e-03	2.831942e-04	6.867569e-01	1.000000e+00	0.009749444	0.015018162	0.010294400	⋯	0.0003640715	0.0003841243	0.0005349066	-1.507823e-04	9.998439e-01	1.000000000	NA	NA	NA	NA
ENSG00000274847.MAFIP	2.747836e-02	3.523302e-02	3.322526e-02	2.007761e-03	1.097189e-01	2.950113e-01	0.045624753	0.054548175	0.048017210	⋯	0.0266886287	0.0400806811	0.0392040406	8.766406e-04	3.874484e-01	0.746886890	NA	NA	NA	NA
ENSG00000276256.ENSG00000276256	1.456334e-01	1.587725e-01	1.663422e-01	-7.569715e-03	9.946371e-01	1.000000e+00	0.022176195	0.016113771	0.023395954	⋯	0.2252880825	0.3118314572	0.3236612085	-1.182975e-02	6.799064e-01	0.849895931	NA	NA	NA	NA
ENSG00000278384.ENSG00000278384	8.811104e-03	1.040108e-02	1.052278e-02	-1.217001e-04	5.977625e-01	9.991189e-01	0.003029215	0.001449831	0.003199408	⋯	0.0087212489	0.0138309448	0.0128132871	1.017658e-03	1.548784e-01	0.590868757	NA	NA	NA	NA
ENSG00000273748.ENSG00000273748	8.629686e-02	9.038450e-02	8.604669e-02	4.337806e-03	4.265947e-01	8.149871e-01	0.068696288	0.080482907	0.072066698	⋯	0.0876646108	0.1369676261	0.1285271979	8.440428e-03	2.004931e-01	0.646712417	NA	NA	NA	NA
ENSG00000271254.ENSG00000271254	1.367201e-02	1.176190e-02	1.199557e-02	-2.336686e-04	1.048407e-01	2.843984e-01	0.005279681	0.004404255	0.005575911	⋯	0.0095123359	0.0147881250	0.0139754977	8.126273e-04	2.285474e-01	0.674288547	NA	NA	NA	NA
ENSG00000276345.ENSG00000276345	2.556739e-02	1.401183e-02	1.560030e-02	-1.588466e-03	8.243541e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000276017.ENSG00000276017	3.954335e-05	9.976801e-06	2.048383e-05	-1.050703e-05	9.858771e-01	1.000000e+00	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA
ENSG00000278817.ENSG00000278817	1.109546e-02	8.310894e-03	8.641444e-03	-3.305493e-04	7.548021e-03	2.987236e-02	0.013793552	0.015746266	0.014561158	⋯	0.0024667705	0.0030916251	0.0036242592	-5.326341e-04	9.699135e-01	1.000000000	NA	NA	NA	NA
ENSG00000277196.ENSG00000277196	1.811506e-04	1.545324e-04	1.071847e-04	4.734772e-05	5.457040e-08	4.813223e-07	0.000000000	0.000000000	0.000000000	⋯	0.0000000000	0.0000000000	0.0000000000	0.000000e+00	NaN	NaN	NA	NA	NA	NA

options(repr.plot.width=10, repr.plot.height=10)

ggplot(mgv, aes(x=mean, y=bio, colour=subpopshort)) +
    geom_point(size=5)

ggplot(mgv, aes(x=subpopshort, y=bio, colour=subpopshort)) +
    geom_boxplot() +
    theme(axis.text.x = element_text(angle = 45, hjust=1))

nm <- names(per_block)
names(nm) <- nm
nm

donor1_fat: 'donor1_fat'
donor1_skin: 'donor1_skin'
donor2_fat: 'donor2_fat'
donor3_fat: 'donor3_fat'
donor3_skin: 'donor3_skin'
donor4_fat: 'donor4_fat'
donor4_skin: 'donor4_skin'
donor5_recovery: 'donor5_recovery'
donor6_fat: 'donor6_fat'
donor6_skin: 'donor6_skin'
donor7_fat: 'donor7_fat'
donor7_skin: 'donor7_skin'

options(repr.plot.width=6, repr.plot.height=6)

per_block_ggs <- lapply(nm, function(u) {
    z <- per_block[[u]] %>% as.data.frame %>% rownames_to_column("gene_name") %>%
        left_join(markers, multiple = "first")
    p <- ggplot(z, aes(x=subpopshort, y=-log10(FDR), colour=subpopshort)) +
        geom_boxplot() +
        theme(axis.text.x = element_text(angle = 45, hjust=1)) +
        ggtitle(u)
        print(p)
})

Joining with `by = join_by(gene_name)`
Warning message:
“Removed 5932 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 1984 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 2469 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 1555 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 3137 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 3732 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 2029 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 1699 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 2766 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 3088 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 2705 rows containing non-finite values (`stat_boxplot()`).”
Joining with `by = join_by(gene_name)`
Warning message:
“Removed 2229 rows containing non-finite values (`stat_boxplot()`).”

options(repr.plot.width=20, repr.plot.height=20)
ggarrange(plotlist = per_block_ggs, nrow = 3, ncol = 4)

Warning message:
“Removed 5932 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 1984 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 2469 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 1555 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 3137 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 3732 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 2029 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 1699 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 2766 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 3088 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 2705 rows containing non-finite values (`stat_boxplot()`).”
Warning message:
“Removed 2229 rows containing non-finite values (`stat_boxplot()`).”

uniq_markers <- unique(markers$gene_name)
uniq_markers

'ENSG00000117707.PROX1'
'ENSG00000162493.PDPN'
'ENSG00000133800.LYVE1'
'ENSG00000137077.CCL21'
'ENSG00000189056.RELN'
'ENSG00000129048.ACKR4'
'ENSG00000108691.CCL2'
'ENSG00000081041.CXCL2'
'ENSG00000013297.CLDN11'
'ENSG00000272398.CD24'
'ENSG00000149564.ESAM'
'ENSG00000170017.ALCAM'
'ENSG00000108821.COL1A1'
'ENSG00000113721.PDGFRB'
'ENSG00000107796.ACTA2'
'ENSG00000186081.KRT5'
'ENSG00000186847.KRT14'
'ENSG00000081237.PTPRC'
'ENSG00000102755.FLT1'
'ENSG00000154721.JAM2'
'ENSG00000090339.ICAM1'
'ENSG00000103335.PIEZO1'
'ENSG00000154864.PIEZO2'

per_block_umaps <- lapply(nm, function(u) {
    s <- sce[,sce$Sample==u]
    mgv <- modelGeneVar(s)
    hvgs <- mgv %>% as.data.frame %>% rownames_to_column("gene_name") %>%
        arrange(p.value) %>% head(500) %>% pull("gene_name")
    s <- runPCA(s, subset_row=hvgs)
    s <- runUMAP(s)
    exp <- as.matrix(logcounts(s)[uniq_markers,])
    data.frame(
        rowname = rownames(colData(s)), Sample = s$Sample,
        UMAP = reducedDim(s, "UMAP"), t(exp)
    ) %>% return()
})

Warning message in (function (A, nv = 5, nu = nv, maxit = 1000, work = nv + 7, reorth = TRUE, :
“You're computing too large a percentage of total singular values, use a standard svd instead.”

pdf("figures/umaps-markers-across-samples.pdf", width=10, height=8)
for(i in seq_len(length(uniq_markers))) {

  m <- markers %>% dplyr::filter(gene_name==uniq_markers[i]) %>% pull("subpopulation")

    print(ggplot(bind_rows(per_block_umaps), aes_string(x="UMAP.1", y="UMAP.2", colour = uniq_markers[i])) +
        geom_point() +
        scale_colour_gradient(low = "grey80", high = "blue") +
        facet_wrap(~Sample, scales = "free") +
        theme(legend.position="top") +
        ggtitle(m)
    )

}
dev.off()

Warning message:
“`aes_string()` was deprecated in ggplot2 3.0.0.
ℹ Please use tidy evaluation idioms with `aes()`.
ℹ See also `vignette("ggplot2-in-packages")` for more information.”

pdf: 2

ms <- bind_rows(per_block_umaps) %>% melt(id.vars = c("rowname", "Sample", "UMAP.1", "UMAP.2")) %>% split("Sample")
ms

$Sample =

A data.frame: 512302 × 6
	rowname	Sample	UMAP.1	UMAP.2	variable	value
	<chr>	<chr>	<dbl>	<dbl>	<fct>	<dbl>
1	donor1_fat.AAAGAACCACATACGT-1	donor1_fat	-2.0484646	-1.1637262	ENSG00000117707.PROX1	1.1180317
2	donor1_fat.AAAGGTAGTCCGGTCA-1	donor1_fat	2.8242526	-1.0391492	ENSG00000117707.PROX1	0.0000000
3	donor1_fat.AAAGGTATCTCTCTTC-1	donor1_fat	0.9381566	0.6268698	ENSG00000117707.PROX1	1.0517659
4	donor1_fat.AACCACACAGTGGCTC-1	donor1_fat	-0.6080225	-0.6364202	ENSG00000117707.PROX1	0.0000000
5	donor1_fat.AACGGGATCTGCTGAA-1	donor1_fat	-1.0524757	-1.6120028	ENSG00000117707.PROX1	0.0000000
6	donor1_fat.AAGAACATCTGTGCAA-1	donor1_fat	1.5718066	0.7489513	ENSG00000117707.PROX1	2.0521759
7	donor1_fat.AAGCATCTCGATCCCT-1	donor1_fat	1.7909548	0.8797356	ENSG00000117707.PROX1	1.7869727
8	donor1_fat.AAGCGAGAGTATCCTG-1	donor1_fat	-1.0558064	1.0522912	ENSG00000117707.PROX1	2.0656439
9	donor1_fat.AAGTTCGAGGCAGGTT-1	donor1_fat	-1.0539844	-0.7540492	ENSG00000117707.PROX1	0.8052045
10	donor1_fat.AATCGACCAATTGCAC-1	donor1_fat	-1.3530891	-1.1469282	ENSG00000117707.PROX1	2.2499633
11	donor1_fat.ACAAAGACAATGACCT-1	donor1_fat	1.8577221	0.7200912	ENSG00000117707.PROX1	0.7807234
12	donor1_fat.ACAAAGACACTAACGT-1	donor1_fat	1.6504609	-0.9285525	ENSG00000117707.PROX1	0.0000000
13	donor1_fat.ACAACCAAGGGCTTCC-1	donor1_fat	-0.6354316	1.3237580	ENSG00000117707.PROX1	1.6079082
14	donor1_fat.ACAGGGATCTCATAGG-1	donor1_fat	-0.1048098	0.9759096	ENSG00000117707.PROX1	2.5479505
15	donor1_fat.ACATTTCCACTCCACT-1	donor1_fat	2.0356176	-0.3929195	ENSG00000117707.PROX1	0.0000000
16	donor1_fat.ACATTTCTCGATGGAG-1	donor1_fat	0.4631455	1.2451497	ENSG00000117707.PROX1	0.0000000
17	donor1_fat.ACCCTTGTCACCATAG-1	donor1_fat	0.8288960	-0.8372497	ENSG00000117707.PROX1	0.9320313
18	donor1_fat.ACCTACCAGACCTCCG-1	donor1_fat	2.0905075	0.3380302	ENSG00000117707.PROX1	0.0000000
19	donor1_fat.ACGGAAGCACACCTAA-1	donor1_fat	-3.9451654	0.2357324	ENSG00000117707.PROX1	2.1732948
20	donor1_fat.ACGTAGTTCCCGAAAT-1	donor1_fat	2.7871909	0.2391406	ENSG00000117707.PROX1	0.0000000
21	donor1_fat.ACGTTCCAGATGAATC-1	donor1_fat	-3.5143168	0.4605635	ENSG00000117707.PROX1	0.0000000
22	donor1_fat.ACTCTCGAGCCGTTGC-1	donor1_fat	-0.4711578	-0.9177226	ENSG00000117707.PROX1	0.0000000
23	donor1_fat.ACTTCCGTCAGGAACG-1	donor1_fat	-4.0332029	0.4111551	ENSG00000117707.PROX1	2.6920234
24	donor1_fat.AGACACTCAGGCGATA-1	donor1_fat	2.8228720	-1.0549392	ENSG00000117707.PROX1	0.0000000
25	donor1_fat.AGACCATTCAAAGGTA-1	donor1_fat	-0.2053631	0.8217293	ENSG00000117707.PROX1	1.4683445
26	donor1_fat.AGAGAGCCAAGCCCAC-1	donor1_fat	2.1387318	-0.4795322	ENSG00000117707.PROX1	0.0000000
27	donor1_fat.AGAGCCCAGTCTAGCT-1	donor1_fat	-0.9772060	-1.4272784	ENSG00000117707.PROX1	0.9130940
28	donor1_fat.AGATCCAGTGCAGTGA-1	donor1_fat	-1.1057518	-1.5379166	ENSG00000117707.PROX1	2.6862529
29	donor1_fat.AGATCGTGTTGCGTAT-1	donor1_fat	0.3803560	0.7960730	ENSG00000117707.PROX1	1.5156637
30	donor1_fat.AGGAGGTCAATACGAA-1	donor1_fat	-0.5325592	-1.5191154	ENSG00000117707.PROX1	0.0000000
⋮	⋮	⋮	⋮	⋮	⋮	⋮
512273	donor7_skin.TTTATGCTCGTGTCAA-1	donor7_skin	0.44066022	-2.3981223	ENSG00000154864.PIEZO2	0.0000000
512274	donor7_skin.TTTCACAAGCGATGGT-1	donor7_skin	-2.32789935	0.5459931	ENSG00000154864.PIEZO2	0.0000000
512275	donor7_skin.TTTCACAGTTGTAGCT-1	donor7_skin	-0.63556482	-1.3933723	ENSG00000154864.PIEZO2	0.0000000
512276	donor7_skin.TTTCAGTTCAATCGGT-1	donor7_skin	-0.62373890	-1.2646084	ENSG00000154864.PIEZO2	0.7371799
512277	donor7_skin.TTTCATGGTACAGTCT-1	donor7_skin	1.56131671	2.2107785	ENSG00000154864.PIEZO2	1.0879936
512278	donor7_skin.TTTCATGGTGGCTGCT-1	donor7_skin	1.27958320	1.3705374	ENSG00000154864.PIEZO2	0.0000000
512279	donor7_skin.TTTCATGTCCTTATGT-1	donor7_skin	1.51498244	-2.0856054	ENSG00000154864.PIEZO2	0.0000000
512280	donor7_skin.TTTCCTCAGCGGACAT-1	donor7_skin	-1.95951611	0.0865000	ENSG00000154864.PIEZO2	0.0000000
512281	donor7_skin.TTTCCTCCACTCTAGA-1	donor7_skin	3.84445618	0.9458799	ENSG00000154864.PIEZO2	1.4716415
512282	donor7_skin.TTTCCTCGTACAAAGT-1	donor7_skin	-1.86466755	0.1249833	ENSG00000154864.PIEZO2	0.0000000
512283	donor7_skin.TTTCCTCGTAGCGCTC-1	donor7_skin	0.96789597	-1.2941531	ENSG00000154864.PIEZO2	1.0866399
512284	donor7_skin.TTTCCTCGTGGCCCAT-1	donor7_skin	-1.77742146	1.0157657	ENSG00000154864.PIEZO2	0.0000000
512285	donor7_skin.TTTCGATAGTGTCATC-1	donor7_skin	1.08103965	-0.5591272	ENSG00000154864.PIEZO2	0.0000000
512286	donor7_skin.TTTCGATCAAGAAATC-1	donor7_skin	-2.02880452	-4.1955617	ENSG00000154864.PIEZO2	0.0000000
512287	donor7_skin.TTTCGATTCTGCCCTA-1	donor7_skin	-2.95822276	-1.6004554	ENSG00000154864.PIEZO2	0.0000000
512288	donor7_skin.TTTGACTCACCCTTAC-1	donor7_skin	-1.19297369	0.3856518	ENSG00000154864.PIEZO2	0.0000000
512289	donor7_skin.TTTGACTCAGTAACGG-1	donor7_skin	-2.75150790	-0.7835479	ENSG00000154864.PIEZO2	0.0000000
512290	donor7_skin.TTTGACTGTTCTGACA-1	donor7_skin	-1.31828757	-0.2367129	ENSG00000154864.PIEZO2	0.0000000
512291	donor7_skin.TTTGATCCACATATGC-1	donor7_skin	0.71390794	2.2297013	ENSG00000154864.PIEZO2	0.0000000
512292	donor7_skin.TTTGATCCACTAGAGG-1	donor7_skin	-1.83226659	0.5647108	ENSG00000154864.PIEZO2	0.0000000
512293	donor7_skin.TTTGATCGTCCCAAAT-1	donor7_skin	0.01913915	2.3483524	ENSG00000154864.PIEZO2	2.3022276
512294	donor7_skin.TTTGATCGTTCTCCAC-1	donor7_skin	0.83273528	2.6859512	ENSG00000154864.PIEZO2	0.0000000
512295	donor7_skin.TTTGATCTCTGTCTCG-1	donor7_skin	-1.36970748	-0.4502688	ENSG00000154864.PIEZO2	0.0000000
512296	donor7_skin.TTTGGAGAGCAAACAT-1	donor7_skin	2.42198656	0.8811707	ENSG00000154864.PIEZO2	1.7446003
512297	donor7_skin.TTTGGAGAGTACTCGT-1	donor7_skin	-0.99745222	2.7946794	ENSG00000154864.PIEZO2	0.0000000
512298	donor7_skin.TTTGGAGGTACGTGTT-1	donor7_skin	-0.40469517	3.2030871	ENSG00000154864.PIEZO2	0.0000000
512299	donor7_skin.TTTGGAGTCCATTTGT-1	donor7_skin	-2.61639698	-1.3488972	ENSG00000154864.PIEZO2	0.0000000
512300	donor7_skin.TTTGGAGTCTTACCGC-1	donor7_skin	0.74898480	2.0100686	ENSG00000154864.PIEZO2	1.3394578
512301	donor7_skin.TTTGGTTGTTGTAGCT-1	donor7_skin	0.60430000	2.4989591	ENSG00000154864.PIEZO2	0.0000000
512302	donor7_skin.TTTGTTGCAACTGTGT-1	donor7_skin	-0.57576229	-1.1000320	ENSG00000154864.PIEZO2	2.3025932

pdf("figures/umaps-all-markers-each-sample.pdf", width=10, height=8)
for(i in seq_len(length(ms))) {

    print(
        ggplot(ms[[i]], aes(x=UMAP.1, y=UMAP.2, colour = value)) +
        geom_point() +
        scale_colour_gradient(low = "grey80", high = "blue") +
        facet_wrap(~variable) +
        theme(legend.position="top") +
        ggtitle(names(ms)[i])
        )

}
dev.off()

pdf: 2

d <- bind_rows(per_block_umaps)
d_rnormd <- d[,-c(1:4)] + rnorm(prod(dim(d)), mean = 0, sd = .001)
ds <- split(d_rnormd, d$Sample)

pdf("figures/heatmaps-all-markers-each-sample.pdf", width=10, height=5)
for(i in seq_len(length(ds))) {
    pheatmap(t(ds[[i]]), show_colnames = FALSE,
    clustering_distance_cols = "correlation",
    clustering_distance_rows = "correlation",
    main = names(ds)[i]
    )

}
dev.off()

pdf: 3

ds_norm <- ds
pdf("figures/heatmaps-all-markers-each-sample-normalized.pdf", width=10, height=5)
for(i in seq_len(length(ds))) {
  
  qs <- apply(ds[[i]], 2, quantile, p=.90)
  qs[qs < 1] <- 1
  
  for(j in 1:ncol(ds[[i]]))
    ds_norm[[i]][,j] <- ds_norm[[i]][,j]/qs[j]

  ds_norm[[i]][ds_norm[[i]]>1] <- 1

  
  pheatmap(t(ds_norm[[i]]), show_colnames = FALSE,
           clustering_distance_cols = "correlation",
           clustering_distance_rows = "correlation",
           main = names(ds)[i]
           )

}
dev.off()

pdf: 3

# contaminants

options(repr.plot.width=20, repr.plot.height=20)

ggplot(d, aes(
    x = ENSG00000137077.CCL21,
    y = ENSG00000108821.COL1A1)
) + 
geom_jitter(width=.1, height = .5) +
facet_wrap(~Sample)

options(repr.plot.width=12, repr.plot.height=6)
boxplot(as.data.frame(d[,-(1:4)]), las=2)

exp <- d[,-(1:4)] %>% as.matrix
p90 <- exp %>% apply(2, quantile, probs=.9)
p90

ENSG00000117707.PROX1: 2.7040474964207
ENSG00000162493.PDPN: 1.69283581132588
ENSG00000133800.LYVE1: 3.26185058645611
ENSG00000137077.CCL21: 7.22691459652125
ENSG00000189056.RELN: 2.24996327230414
ENSG00000129048.ACKR4: 0
ENSG00000108691.CCL2: 3.71939503454669
ENSG00000081041.CXCL2: 2.89062607918324
ENSG00000013297.CLDN11: 0
ENSG00000272398.CD24: 0
ENSG00000149564.ESAM: 0.355130098838991
ENSG00000170017.ALCAM: 0
ENSG00000108821.COL1A1: 0
ENSG00000113721.PDGFRB: 0
ENSG00000107796.ACTA2: 0
ENSG00000186081.KRT5: 0
ENSG00000186847.KRT14: 0
ENSG00000081237.PTPRC: 0
ENSG00000102755.FLT1: 0
ENSG00000154721.JAM2: 0
ENSG00000090339.ICAM1: 1.88047655359566
ENSG00000103335.PIEZO1: 1.28664026201016
ENSG00000154864.PIEZO2: 1.73042322902796

col1a1 <- exp[,"ENSG00000108821.COL1A1"] / 2
col1a1[col1a1 > 1] <- 1

jam2 <- exp[,"ENSG00000154721.JAM2"] / 2
jam2[jam2 > 1] <- 1

prgfrb <- exp[,"ENSG00000113721.PDGFRB"] / 2
prgfrb[prgfrb > 1] <- 1

      
pdpn <- exp[,"ENSG00000162493.PDPN"] / p90["ENSG00000162493.PDPN"]
pdpn[pdpn > 1] <- 1

cxcl2 <- exp[,"ENSG00000081041.CXCL2"] / p90["ENSG00000081041.CXCL2"]
cxcl2[cxcl2 > 1] <- 1
             
ccl2 <- exp[,"ENSG00000108691.CCL2"] / p90["ENSG00000108691.CCL2"]
ccl2[ccl2 > 1] <- 1

ccl21 <- exp[,"ENSG00000137077.CCL21"] / p90["ENSG00000137077.CCL21"]
ccl21[ccl21 > 1] <- 1

lyve1 <- exp[,"ENSG00000133800.LYVE1"] / p90["ENSG00000133800.LYVE1"]
lyve1[lyve1 > 1] <- 1

prox1 <- exp[,"ENSG00000117707.PROX1"] / p90["ENSG00000117707.PROX1"]
prox1[prox1 > 1] <- 1

df <- data.frame(
    Sample=d$Sample, 
    col1a1, jam2, prgfrb, ccl21, lyve1,
    prox1, pdpn, ccl2, cxcl2
)

# noise? before filtering?
df[,-1] <- df[,-1] + rnorm(
    nrow(df)*(ncol(df)-1),
    mean=0, sd=.02
)

df

A data.frame: 22274 × 10
	Sample	col1a1	jam2	prgfrb	ccl21	lyve1	prox1	pdpn	ccl2	cxcl2
	<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
donor1_fat.AAAGAACCACATACGT-1	donor1_fat	-6.177371e-03	-0.0031744491	0.025607984	0.8637877	0.506185147	0.399910959	-2.141122e-02	-0.0147191045	-0.0092179474
donor1_fat.AAAGGTAGTCCGGTCA-1	donor1_fat	-2.562640e-02	0.0135274094	0.016411063	0.6995753	-0.030954370	-0.020318782	1.272878e-02	0.0321146768	-0.0155214929
donor1_fat.AAAGGTATCTCTCTTC-1	donor1_fat	3.954838e-03	-0.0047302147	-0.058921807	1.0064774	0.009121395	0.403507005	9.707439e-01	0.0009019757	-0.0097793427
donor1_fat.AACCACACAGTGGCTC-1	donor1_fat	-8.390417e-04	-0.0049775072	0.004997854	0.9798234	0.630962393	-0.022863151	3.719339e-01	0.6664521861	0.0467031244
donor1_fat.AACGGGATCTGCTGAA-1	donor1_fat	-3.294729e-02	0.0172184506	0.025801842	1.0099529	0.952636547	0.016039127	3.159890e-02	-0.0161948350	0.0093164554
donor1_fat.AAGAACATCTGTGCAA-1	donor1_fat	-9.278279e-03	-0.0432904238	-0.004928558	0.6361269	0.021998822	0.764609556	7.688593e-03	0.4987814014	0.2286961444
donor1_fat.AAGCATCTCGATCCCT-1	donor1_fat	8.961247e-03	0.0257253419	-0.007706475	0.5688781	0.011359943	0.668748819	-9.337751e-04	-0.0031576763	-0.0033508996
donor1_fat.AAGCGAGAGTATCCTG-1	donor1_fat	-2.025285e-02	-0.0427843370	0.043382435	0.7318062	0.612130896	0.729646983	4.289729e-03	1.0105701492	0.5701520444
donor1_fat.AAGTTCGAGGCAGGTT-1	donor1_fat	-1.957310e-02	-0.0155224185	-0.014063269	0.7817754	0.948710864	0.299500667	7.823209e-01	-0.0224818197	-0.0198374980
donor1_fat.AATCGACCAATTGCAC-1	donor1_fat	5.040912e-03	-0.0047053116	-0.001473258	0.6704721	0.547458265	0.829585304	-8.579479e-05	-0.0042205833	-0.0122900824
donor1_fat.ACAAAGACAATGACCT-1	donor1_fat	-2.382496e-02	0.0412669633	-0.004748681	0.7122134	-0.008654046	0.306771378	4.814842e-01	0.3609760289	0.5507497536
donor1_fat.ACAAAGACACTAACGT-1	donor1_fat	-2.887057e-02	-0.0007119733	-0.011167208	0.2209485	-0.004722751	-0.006377754	1.007664e-02	-0.0018593270	0.9934970903
donor1_fat.ACAACCAAGGGCTTCC-1	donor1_fat	7.492564e-03	0.0063471223	0.009616054	0.7539768	0.873148301	0.580555478	5.203047e-01	0.3668938136	-0.0005466140
donor1_fat.ACAGGGATCTCATAGG-1	donor1_fat	2.690249e-02	-0.0020851500	0.010444795	0.7800630	0.400894972	0.965109975	-1.875359e-02	0.6930383825	-0.0011001914
donor1_fat.ACATTTCCACTCCACT-1	donor1_fat	-2.288523e-02	0.0277930016	-0.001592410	1.0105555	0.331541713	-0.017978599	2.130233e-02	0.9701081869	0.6099380962
donor1_fat.ACATTTCTCGATGGAG-1	donor1_fat	1.469623e-02	0.0315918627	-0.030168437	0.7318597	0.807769612	0.013928482	2.950614e-02	0.8370519554	0.0040403227
donor1_fat.ACCCTTGTCACCATAG-1	donor1_fat	-2.389362e-02	-0.0308304543	0.003702698	0.9223370	0.451392924	0.348397754	1.515303e-02	1.0203946074	0.6950916051
donor1_fat.ACCTACCAGACCTCCG-1	donor1_fat	-5.153461e-05	-0.0112837207	-0.016008569	1.0031394	-0.006312337	-0.006464281	3.518851e-03	1.0086026451	-0.0328234172
donor1_fat.ACGGAAGCACACCTAA-1	donor1_fat	-4.068141e-02	-0.0195332344	-0.013722141	0.7616221	0.903429875	0.811012906	-2.210629e-02	0.0126439890	-0.0003801494
donor1_fat.ACGTAGTTCCCGAAAT-1	donor1_fat	1.864060e-02	0.0445714489	0.006365741	0.8880584	0.704812734	-0.033339004	1.545340e-03	0.5677575058	-0.0066729671
donor1_fat.ACGTTCCAGATGAATC-1	donor1_fat	-2.603773e-02	0.0030491045	0.006140261	0.9205795	0.967926311	0.041954248	1.651663e-02	-0.0126926382	0.0182637707
donor1_fat.ACTCTCGAGCCGTTGC-1	donor1_fat	-1.347052e-02	-0.0266749866	-0.005039600	0.8886155	-0.016309032	0.003981775	4.496706e-02	0.0007821924	-0.0156276358
donor1_fat.ACTTCCGTCAGGAACG-1	donor1_fat	3.204020e-02	-0.0264540226	0.001974596	0.5470836	-0.025112726	1.016290121	8.666760e-01	0.0273618310	-0.0189019862
donor1_fat.AGACACTCAGGCGATA-1	donor1_fat	-1.730093e-02	0.0059739468	0.015334581	0.5701491	0.476474856	-0.016580222	9.025668e-01	-0.0097566128	0.0045944003
donor1_fat.AGACCATTCAAAGGTA-1	donor1_fat	-1.537451e-02	-0.0036618865	0.010825460	0.8017194	0.346596916	0.572483367	4.284791e-01	0.5251782663	0.6016392301
donor1_fat.AGAGAGCCAAGCCCAC-1	donor1_fat	-2.320340e-02	-0.0068700812	-0.003882135	0.9658855	0.574961429	-0.007573551	-2.751537e-02	1.0131715862	-0.0037450447
donor1_fat.AGAGCCCAGTCTAGCT-1	donor1_fat	9.452643e-03	0.0290292370	-0.018340308	0.8366796	0.782972925	0.312903236	7.415997e-03	-0.0047334983	-0.0152212498
donor1_fat.AGATCCAGTGCAGTGA-1	donor1_fat	-1.201114e-02	0.0098563370	0.007610442	0.6463695	0.845765201	0.988111397	-1.628989e-02	-0.0451875636	0.4230879417
donor1_fat.AGATCGTGTTGCGTAT-1	donor1_fat	8.615362e-03	0.0034245307	0.003521553	0.9543483	0.258806687	0.545596044	8.743513e-01	0.8007611046	0.0106937511
donor1_fat.AGGAGGTCAATACGAA-1	donor1_fat	1.324703e-02	-0.0081669716	-0.002687446	1.0038940	0.705750068	0.024315192	2.940806e-03	0.0233627376	0.0038278500
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
donor7_skin.TTTATGCTCGTGTCAA-1	donor7_skin	-0.0003990615	0.0296742640	0.0024537346	-0.0022613577	0.005936938	-0.0152438542	0.011365044	0.0266668524	0.993266362
donor7_skin.TTTCACAAGCGATGGT-1	donor7_skin	0.0724061217	0.0163329879	-0.0121939738	0.8780212054	0.915039457	-0.0022887873	-0.003619139	0.6576163700	-0.022271624
donor7_skin.TTTCACAGTTGTAGCT-1	donor7_skin	-0.0193141786	0.0291989017	0.0173694292	0.6724375849	-0.014048362	0.8438412083	-0.014767578	0.3371750161	1.012992834
donor7_skin.TTTCAGTTCAATCGGT-1	donor7_skin	-0.0089066053	0.0535302078	0.0057074223	0.9399958719	0.837298673	0.7853596621	0.001170393	0.5677482638	-0.015832060
donor7_skin.TTTCATGGTACAGTCT-1	donor7_skin	0.0168256604	-0.0141936968	0.0342388298	0.8215068327	0.956895869	0.9802217122	-0.014461001	-0.0221556456	0.024801192
donor7_skin.TTTCATGGTGGCTGCT-1	donor7_skin	-0.0070698679	0.0068699903	-0.0091017995	0.2931002673	0.810785461	1.0026773554	0.492932180	0.0548301164	-0.010028765
donor7_skin.TTTCATGTCCTTATGT-1	donor7_skin	-0.0244871095	0.0021237005	0.0569417374	0.2855903543	0.008329916	0.7890122466	0.667711838	0.8982960297	0.859786864
donor7_skin.TTTCCTCAGCGGACAT-1	donor7_skin	0.0101579819	-0.0072413576	-0.0085471731	0.9655089864	0.537852124	-0.0006230239	0.019402825	0.9072832572	0.883812935
donor7_skin.TTTCCTCCACTCTAGA-1	donor7_skin	0.0078304239	-0.0350495412	-0.0009815983	0.4845271662	0.990405026	0.8220684204	0.019326832	0.0022491603	-0.011941081
donor7_skin.TTTCCTCGTACAAAGT-1	donor7_skin	-0.0362198769	-0.0103053609	0.0227414740	0.8186186769	0.576536763	0.9798925477	0.006112943	0.0073708300	-0.020194533
donor7_skin.TTTCCTCGTAGCGCTC-1	donor7_skin	-0.0272635933	-0.0507201323	0.0359429627	0.3640793752	0.693701713	0.2074575138	0.383341644	0.5185157652	0.002529597
donor7_skin.TTTCCTCGTGGCCCAT-1	donor7_skin	-0.0141176115	0.0140864067	0.0219909984	0.5788112613	0.027949546	0.0088000969	-0.032908415	0.6754636217	1.001629578
donor7_skin.TTTCGATAGTGTCATC-1	donor7_skin	0.0094453692	-0.0021904036	0.0250803613	0.7851348844	0.960259296	0.3687019867	-0.026586277	0.0046595506	0.021779652
donor7_skin.TTTCGATCAAGAAATC-1	donor7_skin	-0.0242377823	-0.0403578822	-0.0062238060	-0.0191509953	-0.003257678	0.9991128536	-0.008962441	0.0064038129	-0.021909010
donor7_skin.TTTCGATTCTGCCCTA-1	donor7_skin	-0.0032107839	0.0155023708	0.0389190531	-0.0136244979	0.020727457	0.7525883420	0.782999736	0.0112400347	0.463305575
donor7_skin.TTTGACTCACCCTTAC-1	donor7_skin	-0.0001306085	-0.0178902702	0.0078969840	0.9241689730	0.547651788	-0.0120514165	1.009696181	0.0331389587	-0.046051959
donor7_skin.TTTGACTCAGTAACGG-1	donor7_skin	0.0050997361	-0.0118696652	0.0130506358	0.5997844688	0.544050749	-0.0387092503	-0.021861516	1.0054835865	0.617677334
donor7_skin.TTTGACTGTTCTGACA-1	donor7_skin	-0.0033006433	-0.0167376666	-0.0095107318	0.7667512684	0.013864044	0.5748190268	0.007200415	0.8863525341	-0.012955067
donor7_skin.TTTGATCCACATATGC-1	donor7_skin	0.0086986293	0.0001716679	-0.0063615097	0.7438463843	-0.017501750	0.0030111330	0.043734232	0.4958974983	0.012600984
donor7_skin.TTTGATCCACTAGAGG-1	donor7_skin	-0.0032251796	-0.0021914976	0.0128733049	1.0157908962	-0.001787367	-0.0052518524	-0.008076685	-0.0090272773	0.973062128
donor7_skin.TTTGATCGTCCCAAAT-1	donor7_skin	-0.0195745681	0.0250537166	-0.0088243499	-0.0039134482	-0.022815206	-0.0144200855	0.005719765	0.0196336264	0.735776560
donor7_skin.TTTGATCGTTCTCCAC-1	donor7_skin	-0.0434723500	-0.0252945210	0.0179085736	0.6929848846	0.962433259	0.7529268707	0.020575347	0.0015099153	0.024224592
donor7_skin.TTTGATCTCTGTCTCG-1	donor7_skin	0.0070041822	-0.0115678572	0.0243900636	0.5309536652	0.608532916	-0.0109624939	0.828145276	0.3868799389	0.945091813
donor7_skin.TTTGGAGAGCAAACAT-1	donor7_skin	0.0041887005	0.0139418241	-0.0088589254	0.6603070090	0.998915741	0.8172057627	-0.022135229	-0.0187547122	0.979596396
donor7_skin.TTTGGAGAGTACTCGT-1	donor7_skin	0.0054559858	0.0175492243	0.0156962339	0.7827001774	0.987185754	0.6964182957	0.036893497	-0.0010041689	-0.004765871
donor7_skin.TTTGGAGGTACGTGTT-1	donor7_skin	0.0190830933	0.0145798248	-0.0356252672	1.0102405349	0.542353546	0.0361041893	-0.022489221	-0.0096067625	0.018684895
donor7_skin.TTTGGAGTCCATTTGT-1	donor7_skin	-0.0027773493	-0.0189338551	0.0359169146	0.0009260175	-0.000390323	0.4425000838	-0.012844999	0.5196031753	0.438295525
donor7_skin.TTTGGAGTCTTACCGC-1	donor7_skin	0.0331070097	-0.0074154506	0.0028981773	0.4783320616	0.747969470	0.4664506242	0.001862201	-0.0004225433	0.007729157
donor7_skin.TTTGGTTGTTGTAGCT-1	donor7_skin	-0.0246628673	-0.0032276620	-0.0063759478	0.8240156451	1.017997709	0.0117801748	0.006195800	0.0052499922	0.016706311
donor7_skin.TTTGTTGCAACTGTGT-1	donor7_skin	0.0128099107	0.0109123962	-0.0250518974	0.8200733693	0.914873636	0.6920174360	-0.027329639	0.3451530485	0.010775754

df$keep <- df %>% with((col1a1+jam2+prgfrb) < .1)
mean(!df$keep)
sum(!df$keep)
with(df, table(Sample, keep))

0.0311574032504265

694

                 keep
Sample            FALSE TRUE
  donor1_fat          2  156
  donor1_skin        19 3784
  donor2_fat         24 2794
  donor3_fat        297  724
  donor3_skin        29  540
  donor4_fat         38   50
  donor4_skin        47  582
  donor5_recovery   122 4757
  donor6_fat         25 1969
  donor6_skin        14 1696
  donor7_fat         26 1681
  donor7_skin        51 2847

options(repr.plot.width=20, repr.plot.height=20)

ggplot(df, aes(x=col1a1+jam2+prgfrb, y=ccl21+lyve1+prox1+pdpn+cxcl2+ccl2, shape=keep)) +
    geom_jitter(width=.01, height = .1) +
    geom_vline(xintercept = .05) +
    facet_wrap(~Sample) + geom_density_2d()

Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”
Warning message:
“`stat_contour()`: Zero contours were generated”
Warning message in min(x):
“nessun argomento non-mancante al minimo; si restituisce Inf”
Warning message in max(x):
“nessun argomento non-mancante al massimo; si restituisce -Inf”

match(rownames(colData(sce)), rownames(df))

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
⋯
13766
13767
13768
13769
13770
13771
13772
13773
13774
13775
13776
13777
13778
13779
13780
13781
13782
13783
13784
13785
13786
13787
13788
13789
13790
13791
13792
13793
13794
13795
13796
13797
13798
13799
13800
13801
13802
13803
13804
13805
13806
13807
13808
13809
13810
13811
13812
13813
13814
13815
13816
13817
13818
13819
13820
13821
13822
13823
13824
13825
13826
13827
13828
13829
13830
13831
13832
13833
13834
13835
13836
13837
13838
13839
13840
13841
13842
13843
13844
13845
13846
13847
13848
13849
13850
13851
13852
13853
13854
13855
13856
13857
13858
13859
13860
13861
13862
13863
13864
13865
13866
13867
13868
13869
13870
13871
13872
13873
13874
13875
13876
13877
13878
13879
13880
13881
13882
13883
13884
13885
13886
13887
13888
13889
13890
13891
13892
13893
13894
13895
13896
13897
13898
13899
13900
13901
13902
13903
13904
13905
13906
13907
13908
13909
13910
13911
13912
13913
13914
13915
13916
13917
13918
13919
13920
13921
13922
13923
13924
13925
13926
13927
13928
13929
13930
13931
13932
13933
13934
13935
13936
13937
13938
13939
13940
13941
13942
13943
13944
13945
13946
13947
13948
13949
13950
13951
13952
13953
13954
13955
13956
13957
13958
13959
13960
13961
13962
13963
13964
13965

df <- df[match(rownames(colData(sce)), rownames(df)),]
all(rownames(df) == rownames(colData(sce)))

TRUE

sce$outlier_contamination <- !df$keep
sce %>% colData %>% as.data.frame

A data.frame: 22274 × 21
	Sample	Barcode	donor	tissue	tissue_origin	sequencing_run	sex	sum	detected	percent.top_50	⋯	percent.top_200	percent.top_500	subsets_Mito_sum	subsets_Mito_detected	subsets_Mito_percent	total	outlier_sum	outlier_detected	sizeFactor	outlier_contamination
	<chr>	<chr>	<dbl>	<chr>	<chr>	<dbl>	<chr>	<dbl>	<int>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<int>	<dbl>	<dbl>	<otlr.flt>	<otlr.flt>	<dbl>	<lgl>
donor1_fat.AAAGAACCACATACGT-1	donor1_fat	AAAGAACCACATACGT-1	1	fat	abdomen	1	F	4276	1721	33.88681	⋯	52.99345	69.31712	752	16	17.5865295	4276	FALSE	FALSE	0.8543311	FALSE
donor1_fat.AAAGGTAGTCCGGTCA-1	donor1_fat	AAAGGTAGTCCGGTCA-1	1	fat	abdomen	1	F	3023	1084	39.66259	⋯	65.00165	80.68144	52	12	1.7201456	3023	FALSE	FALSE	0.7202661	FALSE
donor1_fat.AAAGGTATCTCTCTTC-1	donor1_fat	AAAGGTATCTCTCTTC-1	1	fat	abdomen	1	F	3892	1422	34.12127	⋯	58.35046	75.92497	48	12	1.2332991	3892	FALSE	FALSE	0.9319094	FALSE
donor1_fat.AACCACACAGTGGCTC-1	donor1_fat	AACCACACAGTGGCTC-1	1	fat	abdomen	1	F	7722	2633	26.89718	⋯	48.67910	64.12846	103	13	1.3338513	7722	FALSE	FALSE	1.8470909	FALSE
donor1_fat.AACGGGATCTGCTGAA-1	donor1_fat	AACGGGATCTGCTGAA-1	1	fat	abdomen	1	F	3256	1284	34.33661	⋯	59.06020	75.92138	123	11	3.7776413	3256	FALSE	FALSE	0.7595401	FALSE
donor1_fat.AAGAACATCTGTGCAA-1	donor1_fat	AAGAACATCTGTGCAA-1	1	fat	abdomen	1	F	6777	1989	32.86115	⋯	60.01180	74.07407	224	14	3.3052973	6777	FALSE	FALSE	1.5886582	FALSE
donor1_fat.AAGCATCTCGATCCCT-1	donor1_fat	AAGCATCTCGATCCCT-1	1	fat	abdomen	1	F	1746	839	34.07789	⋯	61.45475	80.58419	63	11	3.6082474	1746	FALSE	FALSE	0.4080134	FALSE
donor1_fat.AAGCGAGAGTATCCTG-1	donor1_fat	AAGCGAGAGTATCCTG-1	1	fat	abdomen	1	F	6750	2393	24.08889	⋯	46.69630	63.71852	277	18	4.1037037	6750	FALSE	FALSE	1.5692636	FALSE
donor1_fat.AAGTTCGAGGCAGGTT-1	donor1_fat	AAGTTCGAGGCAGGTT-1	1	fat	abdomen	1	F	5707	2041	31.20729	⋯	54.17908	68.91537	188	12	3.2942001	5707	FALSE	FALSE	1.3379833	FALSE
donor1_fat.AATCGACCAATTGCAC-1	donor1_fat	AATCGACCAATTGCAC-1	1	fat	abdomen	1	F	3401	1534	26.60982	⋯	49.51485	68.92091	107	15	3.1461335	3401	FALSE	FALSE	0.7985717	FALSE
donor1_fat.ACAAAGACAATGACCT-1	donor1_fat	ACAAAGACAATGACCT-1	1	fat	abdomen	1	F	5851	1802	32.49017	⋯	58.43446	74.67100	106	16	1.8116561	5851	FALSE	FALSE	1.3927730	FALSE
donor1_fat.ACAAAGACACTAACGT-1	donor1_fat	ACAAAGACACTAACGT-1	1	fat	abdomen	1	F	3602	1004	43.80900	⋯	72.01555	86.00777	60	11	1.6657413	3602	FALSE	FALSE	0.8586948	FALSE
donor1_fat.ACAACCAAGGGCTTCC-1	donor1_fat	ACAACCAAGGGCTTCC-1	1	fat	abdomen	1	F	10238	3273	22.24067	⋯	44.50088	59.89451	168	12	1.6409455	10238	FALSE	FALSE	2.4412922	FALSE
donor1_fat.ACAGGGATCTCATAGG-1	donor1_fat	ACAGGGATCTCATAGG-1	1	fat	abdomen	1	F	5210	1884	27.96545	⋯	53.03263	69.17466	105	13	2.0153551	5210	FALSE	FALSE	1.2376164	FALSE
donor1_fat.ACATTTCCACTCCACT-1	donor1_fat	ACATTTCCACTCCACT-1	1	fat	abdomen	1	F	3606	1305	36.30061	⋯	61.53633	77.67610	33	11	0.9151414	3606	FALSE	FALSE	0.8662102	FALSE
donor1_fat.ACATTTCTCGATGGAG-1	donor1_fat	ACATTTCTCGATGGAG-1	1	fat	abdomen	1	F	3853	1491	34.07734	⋯	58.44796	74.27978	68	13	1.7648586	3853	FALSE	FALSE	0.9176059	FALSE
donor1_fat.ACCCTTGTCACCATAG-1	donor1_fat	ACCCTTGTCACCATAG-1	1	fat	abdomen	1	F	4627	1604	34.92544	⋯	59.39053	74.82170	84	12	1.8154312	4627	FALSE	FALSE	1.1013695	FALSE
donor1_fat.ACCTACCAGACCTCCG-1	donor1_fat	ACCTACCAGACCTCCG-1	1	fat	abdomen	1	F	1732	651	46.76674	⋯	73.78753	91.28176	41	12	2.3672055	1732	FALSE	FALSE	0.4099528	FALSE
donor1_fat.ACGGAAGCACACCTAA-1	donor1_fat	ACGGAAGCACACCTAA-1	1	fat	abdomen	1	F	5069	2279	17.65634	⋯	36.41744	56.77648	369	14	7.2795423	5069	FALSE	FALSE	1.1394313	FALSE
donor1_fat.ACGTAGTTCCCGAAAT-1	donor1_fat	ACGTAGTTCCCGAAAT-1	1	fat	abdomen	1	F	3897	1246	36.23300	⋯	62.63793	80.70310	39	11	1.0007698	3897	FALSE	FALSE	0.9353034	FALSE
donor1_fat.ACGTTCCAGATGAATC-1	donor1_fat	ACGTTCCAGATGAATC-1	1	fat	abdomen	1	F	1884	1136	28.60934	⋯	47.29299	66.24204	280	13	14.8619958	1884	FALSE	FALSE	0.3888612	FALSE
donor1_fat.ACTCTCGAGCCGTTGC-1	donor1_fat	ACTCTCGAGCCGTTGC-1	1	fat	abdomen	1	F	1220	611	41.96721	⋯	66.31148	90.90164	154	15	12.6229508	1220	FALSE	FALSE	0.2584327	FALSE
donor1_fat.ACTTCCGTCAGGAACG-1	donor1_fat	ACTTCCGTCAGGAACG-1	1	fat	abdomen	1	F	4898	2364	17.29277	⋯	34.29971	53.14414	367	16	7.4928542	4898	FALSE	FALSE	1.0984603	FALSE
donor1_fat.AGACACTCAGGCGATA-1	donor1_fat	AGACACTCAGGCGATA-1	1	fat	abdomen	1	F	4601	1518	33.51445	⋯	59.70441	76.26603	171	12	3.7165834	4601	FALSE	FALSE	1.0739746	FALSE
donor1_fat.AGACCATTCAAAGGTA-1	donor1_fat	AGACCATTCAAAGGTA-1	1	fat	abdomen	1	F	7030	2375	27.28307	⋯	50.54054	66.28734	27	10	0.3840683	7030	FALSE	FALSE	1.6977527	FALSE
donor1_fat.AGAGAGCCAAGCCCAC-1	donor1_fat	AGAGAGCCAAGCCCAC-1	1	fat	abdomen	1	F	3437	1047	43.26447	⋯	69.53739	84.08496	85	12	2.4730870	3437	FALSE	FALSE	0.8126327	FALSE
donor1_fat.AGAGCCCAGTCTAGCT-1	donor1_fat	AGAGCCCAGTCTAGCT-1	1	fat	abdomen	1	F	4781	1680	33.44489	⋯	58.12592	73.41560	110	14	2.3007739	4781	FALSE	FALSE	1.1324008	FALSE
donor1_fat.AGATCCAGTGCAGTGA-1	donor1_fat	AGATCCAGTGCAGTGA-1	1	fat	abdomen	1	F	3119	1398	30.49054	⋯	53.83136	71.20872	84	12	2.6931709	3119	FALSE	FALSE	0.7357817	FALSE
donor1_fat.AGATCGTGTTGCGTAT-1	donor1_fat	AGATCGTGTTGCGTAT-1	1	fat	abdomen	1	F	4444	1616	32.06571	⋯	56.79568	73.33483	7	5	0.1575158	4444	FALSE	FALSE	1.0756716	FALSE
donor1_fat.AGGAGGTCAATACGAA-1	donor1_fat	AGGAGGTCAATACGAA-1	1	fat	abdomen	1	F	3179	1211	36.83548	⋯	61.81189	77.63448	108	12	3.3972947	3179	FALSE	FALSE	0.7445093	FALSE
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋱	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
donor5_recovery.TTTCGATAGTGGAATT-1	donor5_recovery	TTTCGATAGTGGAATT-1	5	mixed	abdomen	4	?	3048	1575	21.42388	⋯	42.84777	64.20604	139	16	4.5603675	3048	FALSE	FALSE	0.7052353	FALSE
donor5_recovery.TTTCGATGTGCTGATT-1	donor5_recovery	TTTCGATGTGCTGATT-1	5	mixed	abdomen	4	?	2238	1400	17.20286	⋯	36.90795	59.78552	57	15	2.5469169	2238	FALSE	FALSE	0.5287446	FALSE
donor5_recovery.TTTGACTAGATGGGCT-1	donor5_recovery	TTTGACTAGATGGGCT-1	5	mixed	abdomen	4	?	2448	1208	27.69608	⋯	53.10458	71.07843	95	16	3.8807190	2448	FALSE	FALSE	0.5704430	TRUE
donor5_recovery.TTTGACTAGTGTTCAC-1	donor5_recovery	TTTGACTAGTGTTCAC-1	5	mixed	abdomen	4	?	6499	2564	24.23450	⋯	44.72996	60.70165	78	13	1.2001846	6499	FALSE	FALSE	1.5566571	FALSE
donor5_recovery.TTTGACTGTCCAAATC-1	donor5_recovery	TTTGACTGTCCAAATC-1	5	mixed	abdomen	4	?	958	673	24.32150	⋯	50.62630	81.94154	8	4	0.8350731	958	FALSE	FALSE	0.2303106	FALSE
donor5_recovery.TTTGACTGTGATTCTG-1	donor5_recovery	TTTGACTGTGATTCTG-1	5	mixed	abdomen	4	?	1568	955	26.97704	⋯	50.70153	70.98214	71	14	4.5280612	1568	FALSE	FALSE	0.3629210	FALSE
donor5_recovery.TTTGACTGTTGTCTAG-1	donor5_recovery	TTTGACTGTTGTCTAG-1	5	mixed	abdomen	4	?	936	593	29.70085	⋯	58.01282	90.06410	38	11	4.0598291	936	FALSE	FALSE	0.2177041	FALSE
donor5_recovery.TTTGATCAGATGACCG-1	donor5_recovery	TTTGATCAGATGACCG-1	5	mixed	abdomen	4	?	956	596	30.75314	⋯	58.57741	89.95816	25	8	2.6150628	956	FALSE	FALSE	0.2257044	FALSE
donor5_recovery.TTTGATCAGCAATAAC-1	donor5_recovery	TTTGATCAGCAATAAC-1	5	mixed	abdomen	4	?	2148	939	34.35754	⋯	61.17318	79.56238	71	14	3.3054004	2148	FALSE	FALSE	0.5035317	FALSE
donor5_recovery.TTTGATCAGTTACTCG-1	donor5_recovery	TTTGATCAGTTACTCG-1	5	mixed	abdomen	4	?	3145	1486	21.90779	⋯	46.45469	67.59936	66	15	2.0985692	3145	FALSE	FALSE	0.7464487	FALSE
donor5_recovery.TTTGATCGTTGGGCCT-1	donor5_recovery	TTTGATCGTTGGGCCT-1	5	mixed	abdomen	4	?	2897	1316	30.54884	⋯	54.57370	71.83293	182	17	6.2823611	2897	FALSE	FALSE	0.6582034	FALSE
donor5_recovery.TTTGATCTCAAAGGTA-1	donor5_recovery	TTTGATCTCAAAGGTA-1	5	mixed	abdomen	4	?	2155	1136	26.07889	⋯	50.06961	70.48724	98	14	4.5475638	2155	FALSE	FALSE	0.4986830	FALSE
donor5_recovery.TTTGGAGAGTGCAAAT-1	donor5_recovery	TTTGGAGAGTGCAAAT-1	5	mixed	abdomen	4	?	1054	601	34.91461	⋯	61.95446	90.41746	43	14	4.0796964	1054	FALSE	FALSE	0.2450989	FALSE
donor5_recovery.TTTGGAGCATAGGTAA-1	donor5_recovery	TTTGGAGCATAGGTAA-1	5	mixed	abdomen	4	?	1846	1050	23.34778	⋯	47.50813	70.20585	89	14	4.8212351	1846	FALSE	FALSE	0.4259534	FALSE
donor5_recovery.TTTGGAGGTCAGTTTG-1	donor5_recovery	TTTGGAGGTCAGTTTG-1	5	mixed	abdomen	4	?	1222	769	26.67758	⋯	53.43699	77.98691	51	13	4.1734861	1222	FALSE	FALSE	0.2838881	FALSE
donor5_recovery.TTTGGAGGTCCAAGAG-1	donor5_recovery	TTTGGAGGTCCAAGAG-1	5	mixed	abdomen	4	?	1829	1058	27.28267	⋯	49.64461	69.49153	28	12	1.5308912	1829	FALSE	FALSE	0.4366204	FALSE
donor5_recovery.TTTGGAGGTCGACTTA-1	donor5_recovery	TTTGGAGGTCGACTTA-1	5	mixed	abdomen	4	?	2389	1430	17.91545	⋯	38.21683	61.07158	154	21	6.4462118	2389	FALSE	FALSE	0.5418360	FALSE
donor5_recovery.TTTGGAGGTTGAGAGC-1	donor5_recovery	TTTGGAGGTTGAGAGC-1	5	mixed	abdomen	4	?	1618	993	21.69345	⋯	46.66255	69.53028	38	11	2.3485785	1618	FALSE	FALSE	0.3830429	FALSE
donor5_recovery.TTTGGAGTCCAAGAGG-1	donor5_recovery	TTTGGAGTCCAAGAGG-1	5	mixed	abdomen	4	?	1262	830	23.85103	⋯	50.07924	73.85103	69	14	5.4675119	1262	FALSE	FALSE	0.2892216	FALSE
donor5_recovery.TTTGGAGTCTCAACCC-1	donor5_recovery	TTTGGAGTCTCAACCC-1	5	mixed	abdomen	4	?	1135	717	29.51542	⋯	54.44934	80.88106	18	10	1.5859031	1135	FALSE	FALSE	0.2707968	FALSE
donor5_recovery.TTTGGTTAGCCTCTTC-1	donor5_recovery	TTTGGTTAGCCTCTTC-1	5	mixed	abdomen	4	?	763	584	24.90170	⋯	49.67235	88.99083	24	8	3.1454784	763	FALSE	FALSE	0.1791574	FALSE
donor5_recovery.TTTGGTTCACTCTAGA-1	donor5_recovery	TTTGGTTCACTCTAGA-1	5	mixed	abdomen	4	?	812	570	27.58621	⋯	54.43350	91.37931	24	8	2.9556650	812	FALSE	FALSE	0.1910366	FALSE
donor5_recovery.TTTGGTTGTACGTGAG-1	donor5_recovery	TTTGGTTGTACGTGAG-1	5	mixed	abdomen	4	?	755	494	30.99338	⋯	61.05960	100.00000	34	9	4.5033113	755	FALSE	FALSE	0.1747936	FALSE
donor5_recovery.TTTGGTTGTCCTACAA-1	donor5_recovery	TTTGGTTGTCCTACAA-1	5	mixed	abdomen	4	?	835	625	24.07186	⋯	49.10180	85.02994	27	6	3.2335329	835	FALSE	FALSE	0.1958852	FALSE
donor5_recovery.TTTGGTTGTGACTCTA-1	donor5_recovery	TTTGGTTGTGACTCTA-1	5	mixed	abdomen	4	?	938	572	29.63753	⋯	60.34115	92.32409	2	2	0.2132196	938	FALSE	FALSE	0.2269165	FALSE
donor5_recovery.TTTGGTTTCGACCAAT-1	donor5_recovery	TTTGGTTTCGACCAAT-1	5	mixed	abdomen	4	?	1328	670	34.33735	⋯	64.30723	87.19880	67	10	5.0451807	1328	FALSE	FALSE	0.3057070	FALSE
donor5_recovery.TTTGTTGGTCCTACGG-1	donor5_recovery	TTTGTTGGTCCTACGG-1	5	mixed	abdomen	4	?	795	552	28.30189	⋯	55.72327	93.45912	44	12	5.5345912	795	FALSE	FALSE	0.1820666	FALSE
donor5_recovery.TTTGTTGGTCGCAGTC-1	donor5_recovery	TTTGTTGGTCGCAGTC-1	5	mixed	abdomen	4	?	1872	1250	16.18590	⋯	37.01923	59.93590	66	14	3.5256410	1872	FALSE	FALSE	0.4378325	FALSE
donor5_recovery.TTTGTTGGTGGCGTAA-1	donor5_recovery	TTTGTTGGTGGCGTAA-1	5	mixed	abdomen	4	?	1928	931	33.14315	⋯	58.97303	77.64523	51	13	2.6452282	1928	FALSE	FALSE	0.4550452	FALSE
donor5_recovery.TTTGTTGTCGGCATTA-1	donor5_recovery	TTTGTTGTCGGCATTA-1	5	mixed	abdomen	4	?	2091	1206	21.95122	⋯	45.28934	66.23625	53	14	2.5346724	2091	FALSE	FALSE	0.4940768	FALSE

d <- d[match(rownames(colData(sce)), rownames(d)),]
d$keep <- df$keep
all(rownames(d) == rownames(df))

TRUE

df1 <- cbind(d, df[,-c(1,11)])
df1

A data.frame: 22274 × 37
	rowname	Sample	UMAP.1	UMAP.2	ENSG00000117707.PROX1	ENSG00000162493.PDPN	ENSG00000133800.LYVE1	ENSG00000137077.CCL21	ENSG00000189056.RELN	ENSG00000129048.ACKR4	⋯	keep	col1a1	jam2	prgfrb	ccl21	lyve1	prox1	pdpn	ccl2	cxcl2
	<chr>	<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<lgl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
donor1_fat.AAAGAACCACATACGT-1	donor1_fat.AAAGAACCACATACGT-1	donor1_fat	-2.0484646	-1.1637262	1.1180317	0.0000000	1.7402855	6.106210	0.0000000	0.000000	⋯	TRUE	-6.177371e-03	-0.0031744491	0.025607984	0.8637877	0.506185147	0.399910959	-2.141122e-02	-0.0147191045	-0.0092179474
donor1_fat.AAAGGTAGTCCGGTCA-1	donor1_fat.AAAGGTAGTCCGGTCA-1	donor1_fat	2.8242526	-1.0391492	0.0000000	0.0000000	0.0000000	5.158232	0.0000000	0.000000	⋯	TRUE	-2.562640e-02	0.0135274094	0.016411063	0.6995753	-0.030954370	-0.020318782	1.272878e-02	0.0321146768	-0.0155214929
donor1_fat.AAAGGTATCTCTCTTC-1	donor1_fat.AAAGGTATCTCTCTTC-1	donor1_fat	0.9381566	0.6268698	1.0517659	2.0769685	0.0000000	7.544117	0.0000000	0.000000	⋯	TRUE	3.954838e-03	-0.0047302147	-0.058921807	1.0064774	0.009121395	0.403507005	9.707439e-01	0.0009019757	-0.0097793427
donor1_fat.AACCACACAGTGGCTC-1	donor1_fat.AACCACACAGTGGCTC-1	donor1_fat	-0.6080225	-0.6364202	0.0000000	0.6242337	2.0869030	7.002557	0.6242337	0.000000	⋯	TRUE	-8.390417e-04	-0.0049775072	0.004997854	0.9798234	0.630962393	-0.022863151	3.719339e-01	0.6664521861	0.0467031244
donor1_fat.AACGGGATCTGCTGAA-1	donor1_fat.AACGGGATCTGCTGAA-1	donor1_fat	-1.0524757	-1.6120028	0.0000000	0.0000000	3.1537271	7.438566	1.2120004	0.000000	⋯	TRUE	-3.294729e-02	0.0172184506	0.025801842	1.0099529	0.952636547	0.016039127	3.159890e-02	-0.0161948350	0.0093164554
donor1_fat.AAGAACATCTGTGCAA-1	donor1_fat.AAGAACATCTGTGCAA-1	donor1_fat	1.5718066	0.7489513	2.0521759	0.0000000	0.0000000	4.639207	0.0000000	0.000000	⋯	TRUE	-9.278279e-03	-0.0432904238	-0.004928558	0.6361269	0.021998822	0.764609556	7.688593e-03	0.4987814014	0.2286961444
donor1_fat.AAGCATCTCGATCCCT-1	donor1_fat.AAGCATCTCGATCCCT-1	donor1_fat	1.7909548	0.8797356	1.7869727	0.0000000	0.0000000	4.182398	0.0000000	0.000000	⋯	TRUE	8.961247e-03	0.0257253419	-0.007706475	0.5688781	0.011359943	0.668748819	-9.337751e-04	-0.0031576763	-0.0033508996
donor1_fat.AAGCGAGAGTATCCTG-1	donor1_fat.AAGCGAGAGTATCCTG-1	donor1_fat	-1.0558064	1.0522912	2.0656439	0.0000000	2.0656439	5.340170	1.1855387	0.000000	⋯	TRUE	-2.025285e-02	-0.0427843370	0.043382435	0.7318062	0.612130896	0.729646983	4.289729e-03	1.0105701492	0.5701520444
donor1_fat.AAGTTCGAGGCAGGTT-1	donor1_fat.AAGTTCGAGGCAGGTT-1	donor1_fat	-1.0539844	-0.7540492	0.8052045	1.3189166	3.0830320	5.494934	0.0000000	0.000000	⋯	TRUE	-1.957310e-02	-0.0155224185	-0.014063269	0.7817754	0.948710864	0.299500667	7.823209e-01	-0.0224818197	-0.0198374980
donor1_fat.AATCGACCAATTGCAC-1	donor1_fat.AATCGACCAATTGCAC-1	donor1_fat	-1.3530891	-1.1469282	2.2499633	0.0000000	1.8091969	4.835378	0.0000000	0.000000	⋯	TRUE	5.040912e-03	-0.0047053116	-0.001473258	0.6704721	0.547458265	0.829585304	-8.579479e-05	-0.0042205833	-0.0122900824
donor1_fat.ACAAAGACAATGACCT-1	donor1_fat.ACAAAGACAATGACCT-1	donor1_fat	1.8577221	0.7200912	0.7807234	0.7807234	0.0000000	5.148268	0.0000000	0.000000	⋯	TRUE	-2.382496e-02	0.0412669633	-0.004748681	0.7122134	-0.008654046	0.306771378	4.814842e-01	0.3609760289	0.5507497536
donor1_fat.ACAAAGACACTAACGT-1	donor1_fat.ACAAAGACACTAACGT-1	donor1_fat	1.6504609	-0.9285525	0.0000000	0.0000000	0.0000000	1.735139	0.0000000	0.000000	⋯	TRUE	-2.887057e-02	-0.0007119733	-0.011167208	0.2209485	-0.004722751	-0.006377754	1.007664e-02	-0.0018593270	0.9934970903
donor1_fat.ACAACCAAGGGCTTCC-1	donor1_fat.ACAACCAAGGGCTTCC-1	donor1_fat	-0.6354316	1.3237580	1.6079082	0.8633345	2.7516068	5.683224	0.8633345	0.000000	⋯	TRUE	7.492564e-03	0.0063471223	0.009616054	0.7539768	0.873148301	0.580555478	5.203047e-01	0.3668938136	-0.0005466140
donor1_fat.ACAGGGATCTCATAGG-1	donor1_fat.ACAGGGATCTCATAGG-1	donor1_fat	-0.1048098	0.9759096	2.5479505	0.0000000	1.3873679	5.628782	0.0000000	0.000000	⋯	TRUE	2.690249e-02	-0.0020851500	0.010444795	0.7800630	0.400894972	0.965109975	-1.875359e-02	0.6930383825	-0.0011001914
donor1_fat.ACATTTCCACTCCACT-1	donor1_fat.ACATTTCCACTCCACT-1	donor1_fat	2.0356176	-0.3929195	0.0000000	0.0000000	1.1073224	7.776050	0.0000000	1.107322	⋯	TRUE	-2.288523e-02	0.0277930016	-0.001592410	1.0105555	0.331541713	-0.017978599	2.130233e-02	0.9701081869	0.6099380962
donor1_fat.ACATTTCTCGATGGAG-1	donor1_fat.ACATTTCTCGATGGAG-1	donor1_fat	0.4631455	1.2451497	0.0000000	0.0000000	2.6890671	5.406405	0.0000000	0.000000	⋯	TRUE	1.469623e-02	0.0315918627	-0.030168437	0.7318597	0.807769612	0.013928482	2.950614e-02	0.8370519554	0.0040403227
donor1_fat.ACCCTTGTCACCATAG-1	donor1_fat.ACCCTTGTCACCATAG-1	donor1_fat	0.8288960	-0.8372497	0.9320313	0.0000000	1.4936069	6.744583	1.4936069	0.000000	⋯	TRUE	-2.389362e-02	-0.0308304543	0.003702698	0.9223370	0.451392924	0.348397754	1.515303e-02	1.0203946074	0.6950916051
donor1_fat.ACCTACCAGACCTCCG-1	donor1_fat.ACCTACCAGACCTCCG-1	donor1_fat	2.0905075	0.3380302	0.0000000	0.0000000	0.0000000	8.245428	0.0000000	0.000000	⋯	TRUE	-5.153461e-05	-0.0112837207	-0.016008569	1.0031394	-0.006312337	-0.006464281	3.518851e-03	1.0086026451	-0.0328234172
donor1_fat.ACGGAAGCACACCTAA-1	donor1_fat.ACGGAAGCACACCTAA-1	donor1_fat	-3.9451654	0.2357324	2.1732948	0.0000000	3.0037904	5.174136	2.8366140	0.000000	⋯	TRUE	-4.068141e-02	-0.0195332344	-0.013722141	0.7616221	0.903429875	0.811012906	-2.210629e-02	0.0126439890	-0.0003801494
donor1_fat.ACGTAGTTCCCGAAAT-1	donor1_fat.ACGTAGTTCCCGAAAT-1	donor1_fat	2.7871909	0.2391406	0.0000000	0.0000000	2.3996324	6.304685	0.0000000	0.000000	⋯	TRUE	1.864060e-02	0.0445714489	0.006365741	0.8880584	0.704812734	-0.033339004	1.545340e-03	0.5677575058	-0.0066729671
donor1_fat.ACGTTCCAGATGAATC-1	donor1_fat.ACGTTCCAGATGAATC-1	donor1_fat	-3.5143168	0.4605635	0.0000000	0.0000000	4.2480247	6.801925	1.8365751	0.000000	⋯	TRUE	-2.603773e-02	0.0030491045	0.006140261	0.9205795	0.967926311	0.041954248	1.651663e-02	-0.0126926382	0.0182637707
donor1_fat.ACTCTCGAGCCGTTGC-1	donor1_fat.ACTCTCGAGCCGTTGC-1	donor1_fat	-0.4711578	-0.9177226	0.0000000	0.0000000	0.0000000	6.292590	0.0000000	0.000000	⋯	TRUE	-1.347052e-02	-0.0266749866	-0.005039600	0.8886155	-0.016309032	0.003981775	4.496706e-02	0.0007821924	-0.0156276358
donor1_fat.ACTTCCGTCAGGAACG-1	donor1_fat.ACTTCCGTCAGGAACG-1	donor1_fat	-4.0332029	0.4111551	2.6920234	1.4960688	0.0000000	3.681983	0.9338485	0.000000	⋯	TRUE	3.204020e-02	-0.0264540226	0.001974596	0.5470836	-0.025112726	1.016290121	8.666760e-01	0.0273618310	-0.0189019862
donor1_fat.AGACACTCAGGCGATA-1	donor1_fat.AGACACTCAGGCGATA-1	donor1_fat	2.8228720	-1.0549392	0.0000000	1.5171453	1.5171453	4.150574	0.0000000	0.000000	⋯	TRUE	-1.730093e-02	0.0059739468	0.015334581	0.5701491	0.476474856	-0.016580222	9.025668e-01	-0.0097566128	0.0045944003
donor1_fat.AGACCATTCAAAGGTA-1	donor1_fat.AGACCATTCAAAGGTA-1	donor1_fat	-0.2053631	0.8217293	1.4683445	0.6681318	1.1230224	5.770836	0.0000000	0.000000	⋯	TRUE	-1.537451e-02	-0.0036618865	0.010825460	0.8017194	0.346596916	0.572483367	4.284791e-01	0.5251782663	0.6016392301
donor1_fat.AGAGAGCCAAGCCCAC-1	donor1_fat.AGAGAGCCAAGCCCAC-1	donor1_fat	2.1387318	-0.4795322	0.0000000	0.0000000	1.7912458	7.487297	0.0000000	0.000000	⋯	TRUE	-2.320340e-02	-0.0068700812	-0.003882135	0.9658855	0.574961429	-0.007573551	-2.751537e-02	1.0131715862	-0.0037450447
donor1_fat.AGAGCCCAGTCTAGCT-1	donor1_fat.AGAGCCCAGTCTAGCT-1	donor1_fat	-0.9772060	-1.4272784	0.9130940	0.0000000	2.6550031	5.973050	0.0000000	0.000000	⋯	TRUE	9.452643e-03	0.0290292370	-0.018340308	0.8366796	0.782972925	0.312903236	7.415997e-03	-0.0047334983	-0.0152212498
donor1_fat.AGATCCAGTGCAGTGA-1	donor1_fat.AGATCCAGTGCAGTGA-1	donor1_fat	-1.1057518	-1.5379166	2.6862529	0.0000000	2.6862529	4.745392	1.2382358	0.000000	⋯	TRUE	-1.201114e-02	0.0098563370	0.007610442	0.6463695	0.845765201	0.988111397	-1.628989e-02	-0.0451875636	0.4230879417
donor1_fat.AGATCGTGTTGCGTAT-1	donor1_fat.AGATCGTGTTGCGTAT-1	donor1_fat	0.3803560	0.7960730	1.5156637	1.5156637	0.9483405	6.802562	0.0000000	0.000000	⋯	TRUE	8.615362e-03	0.0034245307	0.003521553	0.9543483	0.258806687	0.545596044	8.743513e-01	0.8007611046	0.0106937511
donor1_fat.AGGAGGTCAATACGAA-1	donor1_fat.AGGAGGTCAATACGAA-1	donor1_fat	-0.5325592	-1.5191154	0.0000000	0.0000000	2.3304149	7.858134	0.0000000	0.000000	⋯	TRUE	1.324703e-02	-0.0081669716	-0.002687446	1.0038940	0.705750068	0.024315192	2.940806e-03	0.0233627376	0.0038278500
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋱	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
donor5_recovery.TTTCGATAGTGGAATT-1	donor5_recovery.TTTCGATAGTGGAATT-1	donor5_recovery	0.931899659	0.9874523770	1.273794	1.939578	2.738090	5.295910	1.273794	0	⋯	TRUE	0.0078565286	-0.057756457	-0.014375509	0.72361653	8.451639e-01	0.465701289	1.0021322779	0.024510657	0.001530271
donor5_recovery.TTTCGATGTGCTGATT-1	donor5_recovery.TTTCGATGTGCTGATT-1	donor5_recovery	3.102502457	0.6960900914	3.386309	0.000000	2.257778	4.780195	1.531704	0	⋯	TRUE	-0.0088987663	0.005490213	-0.043369000	0.67533106	7.024431e-01	1.043129369	-0.0101730319	-0.014094991	0.018495620
donor5_recovery.TTTGACTAGATGGGCT-1	donor5_recovery.TTTGACTAGATGGGCT-1	donor5_recovery	-2.869293698	-1.1133072484	0.000000	0.000000	0.000000	5.878965	1.461017	0	⋯	FALSE	-0.0080437276	0.746968267	-0.018369823	0.79137227	2.986268e-02	0.017854879	0.0294468781	1.002458934	0.955267980
donor5_recovery.TTTGACTAGTGTTCAC-1	donor5_recovery.TTTGACTAGTGTTCAC-1	donor5_recovery	1.664190642	-1.3018784631	2.074509	0.000000	2.618055	5.711280	1.192071	0	⋯	TRUE	-0.0035028445	-0.009318380	0.003125337	0.79445088	8.138261e-01	0.765391191	0.0433107484	0.004387637	0.021394056
donor5_recovery.TTTGACTGTCCAAATC-1	donor5_recovery.TTTGACTGTCCAAATC-1	donor5_recovery	-0.966822632	-0.6384149898	3.275592	0.000000	0.000000	5.730737	3.275592	0	⋯	TRUE	0.0354439677	0.023959903	-0.042248876	0.79037410	1.087581e-03	0.993731390	0.0034982672	0.665586256	0.829429226
donor5_recovery.TTTGACTGTGATTCTG-1	donor5_recovery.TTTGACTGTGATTCTG-1	donor5_recovery	-0.445122727	-0.0006952394	1.908975	1.908975	2.702844	5.090220	0.000000	0	⋯	TRUE	-0.0157393377	-0.008596564	-0.018597758	0.71798386	7.873196e-01	0.712328288	1.0224097005	0.530886129	0.635044719
donor5_recovery.TTTGACTGTTGTCTAG-1	donor5_recovery.TTTGACTGTTGTCTAG-1	donor5_recovery	1.368694297	-0.5846982110	0.000000	2.483723	0.000000	4.835941	2.483723	0	⋯	TRUE	-0.0048798873	0.041886363	0.010982527	0.69210490	3.078261e-02	-0.003647282	1.0260963791	0.663098789	1.006265200
donor5_recovery.TTTGATCAGATGACCG-1	donor5_recovery.TTTGATCAGATGACCG-1	donor5_recovery	-2.969551571	-1.9333430637	0.000000	0.000000	0.000000	4.785731	0.000000	0	⋯	TRUE	0.0049796262	-0.017490582	-0.028089584	0.71132958	-8.360597e-05	-0.011483696	-0.0162825909	0.980354720	0.991351882
donor5_recovery.TTTGATCAGCAATAAC-1	donor5_recovery.TTTGATCAGCAATAAC-1	donor5_recovery	-1.709560879	0.5504284989	0.000000	0.000000	2.313810	3.897415	2.313810	0	⋯	TRUE	0.0020095366	-0.016285486	-0.040712249	0.53686022	7.452480e-01	0.025949401	0.0056907374	0.406526968	0.555830859
donor5_recovery.TTTGATCAGTTACTCG-1	donor5_recovery.TTTGATCAGTTACTCG-1	donor5_recovery	0.267802707	1.6214266907	1.226309	1.226309	1.879452	4.202872	0.000000	0	⋯	TRUE	-0.0258017198	-0.029121559	-0.003151891	0.57797358	6.069127e-01	0.433515779	0.7166358416	0.035210088	0.996010501
donor5_recovery.TTTGATCGTTGGGCCT-1	donor5_recovery.TTTGATCGTTGGGCCT-1	donor5_recovery	-2.176621445	0.4464715611	2.474530	1.333016	2.013846	5.040236	0.000000	0	⋯	TRUE	0.0134119960	-0.010139829	-0.005379385	0.68251086	6.489346e-01	0.928533940	0.8013680439	0.004283741	-0.002875205
donor5_recovery.TTTGATCTCAAAGGTA-1	donor5_recovery.TTTGATCTCAAAGGTA-1	donor5_recovery	-0.603514918	1.1894396435	2.324973	0.000000	1.587500	5.618437	1.587500	0	⋯	TRUE	0.0316904299	0.031706872	-0.005089500	0.76535833	4.907608e-01	0.835413458	0.0452100049	0.458816864	0.529348538
donor5_recovery.TTTGGAGAGTGCAAAT-1	donor5_recovery.TTTGGAGAGTGCAAAT-1	donor5_recovery	1.878585807	-1.7861404825	0.000000	0.000000	0.000000	4.885569	0.000000	0	⋯	TRUE	-0.0619833289	-0.013402551	-0.008624484	0.66754052	-1.080015e-02	-0.016247571	0.0161020449	0.022663335	0.004043271
donor5_recovery.TTTGGAGCATAGGTAA-1	donor5_recovery.TTTGGAGCATAGGTAA-1	donor5_recovery	1.836256198	2.0150197636	0.000000	2.509784	1.743159	5.899463	0.000000	0	⋯	TRUE	-0.0301521554	-0.031969654	-0.044194671	0.85170500	5.239608e-01	0.001799755	1.0241798955	0.463552702	0.614902318
donor5_recovery.TTTGGAGGTCAGTTTG-1	donor5_recovery.TTTGGAGGTCAGTTTG-1	donor5_recovery	-1.074542531	-0.6555272449	0.000000	2.177125	0.000000	5.750545	2.177125	0	⋯	TRUE	0.0012958515	-0.005301574	0.006366746	0.76019623	-1.548313e-02	-0.005096393	0.9813391205	0.598935412	0.031390193
donor5_recovery.TTTGGAGGTCCAAGAG-1	donor5_recovery.TTTGGAGGTCCAAGAG-1	donor5_recovery	-0.190672883	0.7834137570	2.480430	0.000000	0.000000	5.617554	0.000000	0	⋯	TRUE	0.0246976849	0.006555066	0.022130622	0.75928545	-4.184287e-02	0.927049462	0.0060278824	0.871505983	0.000916595
donor5_recovery.TTTGGAGGTCGACTTA-1	donor5_recovery.TTTGGAGGTCGACTTA-1	donor5_recovery	3.671599380	1.8101390492	1.508721	0.000000	0.000000	5.441227	1.508721	0	⋯	TRUE	0.0332257688	-0.004227929	0.034628239	0.74670302	-1.086385e-02	0.603558678	0.0226744277	0.011588924	0.025319511
donor5_recovery.TTTGGAGGTTGAGAGC-1	donor5_recovery.TTTGGAGGTTGAGAGC-1	donor5_recovery	0.003620616	2.9168378007	1.852268	1.852268	0.000000	3.142744	1.852268	0	⋯	TRUE	-0.0006157999	-0.035827474	0.000994279	0.43876522	-2.388770e-02	0.682955565	0.9690956326	0.008550913	0.005462183
donor5_recovery.TTTGGAGTCCAAGAGG-1	donor5_recovery.TTTGGAGTCCAAGAGG-1	donor5_recovery	2.601738057	-0.4427393783	2.156253	0.000000	0.000000	3.890469	2.984610	0	⋯	TRUE	0.0081313922	-0.006917426	-0.004137815	0.53481200	-1.358548e-02	0.793416894	0.0234968804	-0.026179733	-0.006334056
donor5_recovery.TTTGGAGTCTCAACCC-1	donor5_recovery.TTTGGAGTCTCAACCC-1	donor5_recovery	-3.085723408	-1.6553999815	0.000000	0.000000	0.000000	5.379235	0.000000	0	⋯	TRUE	0.0229661385	-0.002785685	0.014491942	0.69413300	-6.715803e-03	0.013639157	0.0319976176	0.775310750	0.996777514
donor5_recovery.TTTGGTTAGCCTCTTC-1	donor5_recovery.TTTGGTTAGCCTCTTC-1	donor5_recovery	0.379168502	-0.6033170331	0.000000	0.000000	2.718457	6.200887	0.000000	0	⋯	TRUE	0.0159770391	-0.030253281	0.018827326	0.85607541	8.387669e-01	0.012585263	0.0195137018	0.011391660	0.014805679
donor5_recovery.TTTGGTTCACTCTAGA-1	donor5_recovery.TTTGGTTCACTCTAGA-1	donor5_recovery	-1.271802434	-0.9042818058	0.000000	0.000000	0.000000	5.422125	0.000000	0	⋯	TRUE	0.0005551034	0.002609067	0.017852325	0.72905845	-8.366208e-03	-0.041417373	0.0252338117	-0.002223779	0.039848818
donor5_recovery.TTTGGTTGTACGTGAG-1	donor5_recovery.TTTGGTTGTACGTGAG-1	donor5_recovery	-1.942956456	-1.6052285690	0.000000	0.000000	2.748683	5.547458	0.000000	0	⋯	TRUE	-0.0045435839	0.010477268	0.026323274	0.76677997	8.295560e-01	-0.003306779	-0.0108690302	0.029159402	0.003339426
donor5_recovery.TTTGGTTGTCCTACAA-1	donor5_recovery.TTTGGTTGTCCTACAA-1	donor5_recovery	0.055927030	0.0280046355	3.486722	0.000000	0.000000	4.729289	0.000000	0	⋯	TRUE	-0.0055102803	-0.029907189	0.002991879	0.66621842	2.914754e-02	0.991302344	0.0001031865	0.014177467	-0.012870370
donor5_recovery.TTTGGTTGTGACTCTA-1	donor5_recovery.TTTGGTTGTGACTCTA-1	donor5_recovery	-2.104454049	-0.7065999616	0.000000	0.000000	2.434803	5.628656	2.434803	0	⋯	TRUE	0.0053178274	-0.006904177	-0.021327896	0.76737950	7.614108e-01	0.010816247	-0.0349556397	-0.013907964	0.992275798
donor5_recovery.TTTGGTTTCGACCAAT-1	donor5_recovery.TTTGGTTTCGACCAAT-1	donor5_recovery	-3.072308549	-1.2226327170	0.000000	0.000000	0.000000	6.810155	0.000000	0	⋯	TRUE	-0.0196506085	-0.020662980	0.020700614	0.96829368	5.692978e-02	0.011930542	-0.0282590883	-0.011952372	0.023237628
donor5_recovery.TTTGTTGGTCCTACGG-1	donor5_recovery.TTTGTTGGTCCTACGG-1	donor5_recovery	-0.856789836	-1.2551037479	0.000000	0.000000	0.000000	5.301861	0.000000	0	⋯	TRUE	-0.0168946830	-0.002951992	-0.006812661	0.76314051	7.248523e-03	0.017844289	-0.0012970226	0.710317045	0.022999301
donor5_recovery.TTTGTTGGTCGCAGTC-1	donor5_recovery.TTTGTTGGTCGCAGTC-1	donor5_recovery	3.593091539	1.3092576157	3.634581	1.715445	1.715445	5.230497	1.715445	0	⋯	TRUE	-0.0171547874	0.004613047	-0.002779767	0.77820613	5.612141e-01	1.015181387	1.0078475380	-0.011442070	-0.029356296
donor5_recovery.TTTGTTGGTGGCGTAA-1	donor5_recovery.TTTGTTGGTGGCGTAA-1	donor5_recovery	1.460117213	-2.1077972461	2.431668	0.000000	0.000000	0.000000	0.000000	0	⋯	TRUE	0.0033150125	-0.018099916	-0.002460468	-0.00730366	5.005984e-03	0.865443464	-0.0463183614	-0.008029120	0.001738280
donor5_recovery.TTTGTTGTCGGCATTA-1	donor5_recovery.TTTGTTGTCGGCATTA-1	donor5_recovery	-0.309542426	2.9477435242	1.596447	0.000000	0.000000	1.596447	0.000000	0	⋯	TRUE	-0.0403284420	-0.019161737	0.005990958	0.20457458	7.002154e-03	0.603981121	0.0025060108	-0.019188513	0.012098517

pdf("figures/contam-removal-spotcheck.pdf", width=10, height=5)

ggplot(df1, aes(x=UMAP.1, y=UMAP.2, colour=ccl21+lyve1+prox1+pdpn+cxcl2+ccl2)) +
    geom_point() +
    scale_colour_gradient(low = "grey80", high = "blue") +
    facet_wrap(~Sample, scales = "free") +
    theme(legend.position="bottom")

ggplot(df1, aes(x=UMAP.1, y=UMAP.2, colour=col1a1+jam2+prgfrb)) +
    geom_point() +
    scale_colour_gradient(low = "grey80", high = "red") +
    facet_wrap(~Sample, scales = "free") +
    theme(legend.position="bottom")

ggplot(df1, aes(x=UMAP.1, y=UMAP.2)) +
    geom_point(colour="grey") +
    geom_point(data = df1 %>% dplyr::filter(!keep), colour="black") +
    facet_wrap(~Sample, scales = "free") +
    theme(legend.position="bottom")

dev.off()

pdf: 2

table(sce$Sample, sce$outlier_contamination)

                 
                  FALSE TRUE
  donor1_fat        156    2
  donor1_skin      3784   19
  donor2_fat       2794   24
  donor3_fat        724  297
  donor3_skin       540   29
  donor4_fat         50   38
  donor4_skin       582   47
  donor5_recovery  4757  122
  donor6_fat       1969   25
  donor6_skin      1696   14
  donor7_fat       1681   26
  donor7_skin      2847   51

sce <- sce[,!sce$outlier_contamination]
sce

class: SingleCellExperiment 
dim: 18627 21580 
metadata(0):
assays(2): counts logcounts
rownames(18627): ENSG00000187634.SAMD11 ENSG00000188976.NOC2L ...
  ENSG00000278817.ENSG00000278817 ENSG00000277196.ENSG00000277196
rowData names(3): ID Symbol Type
colnames(21580): donor1_fat.AAAGAACCACATACGT-1
  donor1_fat.AAAGGTAGTCCGGTCA-1 ... donor5_recovery.TTTGTTGGTGGCGTAA-1
  donor5_recovery.TTTGTTGTCGGCATTA-1
colData names(21): Sample Barcode ... sizeFactor outlier_contamination
reducedDimNames(0):
mainExpName: NULL
altExpNames(0):

table(sce$Sample)


     donor1_fat     donor1_skin      donor2_fat      donor3_fat     donor3_skin 
            156            3784            2794             724             540 
     donor4_fat     donor4_skin donor5_recovery      donor6_fat     donor6_skin 
             50             582            4757            1969            1696 
     donor7_fat     donor7_skin 
           1681            2847

saveRDS(sce, file="../output/0.2-sce-after-contamination-removal.rds")