课程总览

Data Analysis and Visualisation in R for Ecologists

species_id,genus,species,taxa
AB,Amphispiza,bilineata,Bird
AH,Ammospermophilus,harrisi,Rodent, not censused
AS,Ammodramus,savannarum,Bird
BA,Baiomys,taylori,Rodent
species_id,genus,species,taxa
"AB","Amphispiza","bilineata","Bird"
"AH","Ammospermophilus","harrisi","Rodent, not censused"
"AS","Ammodramus","savannarum","Bird"
"BA","Baiomys","taylori","Rodent"
bioc-intro/data/
          /fig_output/fig1.pdf
          /fig_output/fig2.png
?barplot
args(lm)
??kruskal
## iris is an example data frame that comes with R and head() is a
## function that returns the first part of the data frame
dput(head(iris))
structure(list(Sepal.Length = c(5.1, 4.9, 4.7, 4.6, 5, 5.4),
    Sepal.Width = c(3.5, 3, 3.2, 3.1, 3.6, 3.9), Petal.Length = c(1.4,
    1.4, 1.3, 1.5, 1.4, 1.7), Petal.Width = c(0.2, 0.2, 0.2,
    0.2, 0.2, 0.4), Species = structure(c(1L, 1L, 1L, 1L, 1L,
    1L), levels = c("setosa", "versicolor", "virginica"), class = "factor")), row.names = c(NA,
6L), class = "data.frame")
saveRDS(iris, file="/tmp/iris.rds")
some_data <- readRDS(file="~/Downloads/iris.rds")
sessionInfo()
R version 4.6.2 (2026-10-29)
Platform: aarch64-apple-darwin23
Running under: macOS Golden Gate 27.2

Matrix products: default
BLAS:   /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.1

locale:
[1] C.UTF-8/C.UTF-8/C.UTF-8/C/C.UTF-8/C.UTF-8

time zone: Asia/Tokyo
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base

loaded via a namespace (and not attached):
[1] compiler_4.6.2 cli_3.6.6      tools_4.6.2    otel_0.2.0     knitr_1.52
[6] xfun_0.62      rlang_1.3.0    png_0.1-9      evaluate_1.0.5
library("ggplot2")
install.packages("dplyr")
install.packages("BiocManager")
BiocManager::install("SummarizedExperiment")
BiocManager::install("DESeq2")
3 + 5
[1] 8
12 / 7
[1] 1.714286
weight_kg <- 55
weight_kg <- 55    # doesn't print anything
(weight_kg <- 55)  # but putting parenthesis around the call prints the value of `weight_kg`
[1] 55
weight_kg          # and so does typing the name of the object
[1] 55
2.2 * weight_kg
[1] 121
weight_kg <- 57.5
2.2 * weight_kg
[1] 126.5
weight_lb <- 2.2 * weight_kg
weight_kg <- 100
mass <- 47.5            # mass?
age  <- 122             # age?
mass <- mass * 2.0      # mass?
age  <- age - 20        # age?
mass_index <- mass/age  # mass_index?
b <- sqrt(a)
round(3.14159)
[1] 3
args(round)
function (x, digits = 0, ...)
NULL
?round
round(3.14159, digits = 2)
[1] 3.14
round(3.14159, 2)
[1] 3.14
round(digits = 2, x = 3.14159)
[1] 3.14
weight_g <- c(50, 60, 65, 82)
weight_g
[1] 50 60 65 82
molecules <- c("dna", "rna", "protein")
molecules
[1] "dna"     "rna"     "protein"
length(weight_g)
[1] 4
length(molecules)
[1] 3
class(weight_g)
[1] "numeric"
class(molecules)
[1] "character"
str(weight_g)
 num [1:4] 50 60 65 82
str(molecules)
 chr [1:3] "dna" "rna" "protein"
weight_g <- c(weight_g, 90) # add to the end of the vector
weight_g <- c(30, weight_g) # add to the beginning of the vector
weight_g
[1] 30 50 60 65 82 90
num_char <- c(1, 2, 3, "a")
num_logical <- c(1, 2, 3, TRUE, FALSE)
char_logical <- c("a", "b", "c", TRUE)
tricky <- c(1, 2, 3, "4")
class(num_char)
[1] "character"
num_char
[1] "1" "2" "3" "a"
class(num_logical)
[1] "numeric"
num_logical
[1] 1 2 3 1 0
class(char_logical)
[1] "character"
char_logical
[1] "a"    "b"    "c"    "TRUE"
class(tricky)
[1] "character"
tricky
[1] "1" "2" "3" "4"
num_logical <- c(1, 2, 3, TRUE)
char_logical <- c("a", "b", "c", TRUE)
combined_logical <- c(num_logical, char_logical)
combined_logical
[1] "1"    "2"    "3"    "1"    "a"    "b"    "c"    "TRUE"
molecules <- c("dna", "rna", "peptide", "protein")
molecules[2]
[1] "rna"
molecules[c(3, 2)]
[1] "peptide" "rna"    
more_molecules <- molecules[c(1, 2, 3, 2, 1, 4)]
more_molecules
[1] "dna"     "rna"     "peptide" "rna"     "dna"     "protein"
molecules ## all molecules
[1] "dna"     "rna"     "peptide" "protein"
molecules[-1] ## all but the first one
[1] "rna"     "peptide" "protein"
molecules[-c(1, 3)] ## all but 1st/3rd ones
[1] "rna"     "protein"
molecules[c(-1, -3)] ## all but 1st/3rd ones
[1] "rna"     "protein"
weight_g <- c(21, 34, 39, 54, 55)
weight_g[c(TRUE, FALSE, TRUE, TRUE, FALSE)]
[1] 21 39 54
## will return logicals with TRUE for the indices that meet
## the condition
weight_g > 50
[1] FALSE FALSE FALSE  TRUE  TRUE
## so we can use this to select only the values above 50
weight_g[weight_g > 50]
[1] 54 55
weight_g[weight_g < 30 | weight_g > 50]
[1] 21 54 55
weight_g[weight_g >= 30 & weight_g == 21]
numeric(0)
molecules <- c("dna", "rna", "protein", "peptide")
molecules[molecules == "rna" | molecules == "dna"] # returns both rna and dna
[1] "dna" "rna"
molecules %in% c("rna", "dna", "metabolite", "peptide", "glycerol")
[1]  TRUE  TRUE FALSE  TRUE
molecules[molecules %in% c("rna", "dna", "metabolite", "peptide", "glycerol")]
[1] "dna"     "rna"     "peptide"
"four" > "five"
[1] TRUE
x <- c(1, 5, 3, 5, 10)
names(x) ## no names
NULL
names(x) <- c("A", "B", "C", "D", "E")
names(x) ## now we have names
[1] "A" "B" "C" "D" "E"
x[c(1, 3)]
A C
1 3 
x[c("A", "C")]
A C
1 3 
heights <- c(2, 4, 4, NA, 6)
mean(heights)
[1] NA
max(heights)
[1] NA
mean(heights, na.rm = TRUE)
[1] 4
max(heights, na.rm = TRUE)
[1] 6
## Extract those elements which are not missing values.
heights[!is.na(heights)]
[1] 2 4 4 6
## Returns the object with incomplete cases removed.
## The returned object is an atomic vector of type `"numeric"`
## (or `"double"`).
na.omit(heights)
[1] 2 4 4 6
attr(,"na.action")
[1] 4
attr(,"class")
[1] "omit"
## Extract those elements which are complete cases.
## The returned object is an atomic vector of type `"numeric"`
## (or `"double"`).
heights[complete.cases(heights)]
[1] 2 4 4 6
heights <- c(63, 69, 60, 65, NA, 68, 61, 70, 61, 59, 64, 69, 63, 63, NA, 72, 65, 64, 70, 63, 65)
heights_no_na <- heights[!is.na(heights)]
## or
heights_no_na <- na.omit(heights)
median(heights, na.rm = TRUE)
[1] 64
heights_above_67 <- heights_no_na[heights_no_na > 67]
length(heights_above_67)
[1] 6
numeric(3)
[1] 0 0 0
numeric(10)
 [1] 0 0 0 0 0 0 0 0 0 0
numeric(0)
numeric(0)
character(2) ## the empty character
[1] "" ""
logical(2)   ## FALSE
[1] FALSE FALSE
rep(-1, 5)
[1] -1 -1 -1 -1 -1
rep(NA, 5)
[1] NA NA NA NA NA
rep(c(1, 2, 3), 5)
 [1] 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3
rep(c(1, 2, 3), each = 5)
 [1] 1 1 1 1 1 2 2 2 2 2 3 3 3 3 3
sort(rep(c(1, 2, 3), 5))
 [1] 1 1 1 1 1 2 2 2 2 2 3 3 3 3 3
seq(from = 1, to = 20, by = 2)
 [1]  1  3  5  7  9 11 13 15 17 19
seq(1, 5, 1)
[1] 1 2 3 4 5
seq(1, 5) ## default by
[1] 1 2 3 4 5
1:5
[1] 1 2 3 4 5
seq(from = 1, to = 20, length.out = 3)
[1]  1.0 10.5 20.0
sample(1:10)
 [1]  9  4  7  1  2  5  3 10  6  8
sample(letters, 5)
[1] "s" "a" "u" "x" "j"
sample(1:5, 10, replace = TRUE)
 [1] 2 1 5 5 1 1 5 5 2 2
sample(1:10)
 [1]  9  1  4  3  6  2  5  8 10  7
sample(1:10)
 [1]  4  9  7  6  1 10  8  3  2  5
set.seed(123)
sample(1:10)
 [1]  3 10  2  8  6  9  1  7  5  4
set.seed(123)
sample(1:10)
 [1]  3 10  2  8  6  9  1  7  5  4
set.seed(1)
sample(1:10)
 [1]  9  4  7  1  2  5  3 10  6  8
set.seed(1)
sample(1:10)
 [1]  9  4  7  1  2  5  3 10  6  8
rnorm(5)
[1]  0.69641761  0.05351568 -1.31028350 -2.12306606 -0.20807859
rnorm(5, 2, 2)
[1]  1.3744268 -0.1164714  2.8344472  1.3690969  3.6510983
rnorm(5, 100, 5)
[1] 106.45636  96.87448  95.62427 100.71678 107.12595
download.file(url = "https://github.com/carpentries-incubator/bioc-intro/raw/main/episodes/data/rnaseq.csv",
              destfile = "data/rnaseq.csv")
rna <- read.csv("data/rnaseq.csv")
rna
head(rna)
     gene     sample expression     organism age    sex  infection  strain time
1     Asl GSM2545336       1170 Mus musculus   8 Female InfluenzaA C57BL/6    8
2    Apod GSM2545336      36194 Mus musculus   8 Female InfluenzaA C57BL/6    8
3 Cyp2d22 GSM2545336       4060 Mus musculus   8 Female InfluenzaA C57BL/6    8
4    Klk6 GSM2545336        287 Mus musculus   8 Female InfluenzaA C57BL/6    8
5   Fcrls GSM2545336         85 Mus musculus   8 Female InfluenzaA C57BL/6    8
6  Slc2a4 GSM2545336        782 Mus musculus   8 Female InfluenzaA C57BL/6    8
      tissue mouse ENTREZID
1 Cerebellum    14   109900
2 Cerebellum    14    11815
3 Cerebellum    14    56448
4 Cerebellum    14    19144
5 Cerebellum    14    80891
6 Cerebellum    14    20528
                                                                       product
1                               argininosuccinate lyase, transcript variant X1
2                                       apolipoprotein D, transcript variant 3
3 cytochrome P450, family 2, subfamily d, polypeptide 22, transcript variant 2
4                         kallikrein related-peptidase 6, transcript variant 2
5                Fc receptor-like S, scavenger receptor, transcript variant X1
6          solute carrier family 2 (facilitated glucose transporter), member 4
     ensembl_gene_id external_synonym chromosome_name   gene_biotype
1 ENSMUSG00000025533    2510006M18Rik               5 protein_coding
2 ENSMUSG00000022548             <NA>              16 protein_coding
3 ENSMUSG00000061740             2D22              15 protein_coding
4 ENSMUSG00000050063             Bssp               7 protein_coding
5 ENSMUSG00000015852    2810439C17Rik               3 protein_coding
6 ENSMUSG00000018566           Glut-4              11 protein_coding
                            phenotype_description
1           abnormal circulating amino acid level
2                      abnormal lipid homeostasis
3                        abnormal skin morphology
4                         abnormal cytokine level
5 decreased CD8-positive alpha-beta T cell number
6              abnormal circulating glucose level
  hsapiens_homolog_associated_gene_name
1                                   ASL
2                                  APOD
3                                CYP2D6
4                                  KLK6
5                                 FCRL2
6                                SLC2A4
## Try also
## View(rna)
rna <- read.table(file = "data/rnaseq.csv",
                  sep = ",",
                  header = TRUE)
str(rna)
'data.frame':	32428 obs. of  19 variables:
 $ gene                                 : chr  "Asl" "Apod" "Cyp2d22" "Klk6" ...
 $ sample                               : chr  "GSM2545336" "GSM2545336" "GSM2545336" "GSM2545336" ...
 $ expression                           : int  1170 36194 4060 287 85 782 1619 288 43217 1071 ...
 $ organism                             : chr  "Mus musculus" "Mus musculus" "Mus musculus" "Mus musculus" ...
 $ age                                  : int  8 8 8 8 8 8 8 8 8 8 ...
 $ sex                                  : chr  "Female" "Female" "Female" "Female" ...
 $ infection                            : chr  "InfluenzaA" "InfluenzaA" "InfluenzaA" "InfluenzaA" ...
 $ strain                               : chr  "C57BL/6" "C57BL/6" "C57BL/6" "C57BL/6" ...
 $ time                                 : int  8 8 8 8 8 8 8 8 8 8 ...
 $ tissue                               : chr  "Cerebellum" "Cerebellum" "Cerebellum" "Cerebellum" ...
 $ mouse                                : int  14 14 14 14 14 14 14 14 14 14 ...
 $ ENTREZID                             : int  109900 11815 56448 19144 80891 20528 97827 118454 18823 14696 ...
 $ product                              : chr  "argininosuccinate lyase, transcript variant X1" "apolipoprotein D, transcript variant 3" "cytochrome P450, family 2, subfamily d, polypeptide 22, transcript variant 2" "kallikrein related-peptidase 6, transcript variant 2" ...
 $ ensembl_gene_id                      : chr  "ENSMUSG00000025533" "ENSMUSG00000022548" "ENSMUSG00000061740" "ENSMUSG00000050063" ...
 $ external_synonym                     : chr  "2510006M18Rik" NA "2D22" "Bssp" ...
 $ chromosome_name                      : chr  "5" "16" "15" "7" ...
 $ gene_biotype                         : chr  "protein_coding" "protein_coding" "protein_coding" "protein_coding" ...
 $ phenotype_description                : chr  "abnormal circulating amino acid level" "abnormal lipid homeostasis" "abnormal skin morphology" "abnormal cytokine level" ...
 $ hsapiens_homolog_associated_gene_name: chr  "ASL" "APOD" "CYP2D6" "KLK6" ...
# first element in the first column of the data frame (as a vector)
rna[1, 1]
# first element in the 6th column (as a vector)
rna[1, 6]
# first column of the data frame (as a vector)
rna[, 1]
# first column of the data frame (as a data.frame)
rna[1]
# first three elements in the 7th column (as a vector)
rna[1:3, 7]
# the 3rd row of the data frame (as a data.frame)
rna[3, ]
# equivalent to head_rna <- head(rna)
head_rna <- rna[1:6, ]
head_rna
rna[, -1]          ## The whole data frame, except the first column
rna[-c(7:66465), ] ## Equivalent to head(rna)
rna["gene"]       # Result is a data.frame
rna[, "gene"]     # Result is a vector
rna[["gene"]]     # Result is a vector
rna$gene          # Result is a vector
## 1.
rna_200 <- rna[200, ]
## 2.
## Saving `n_rows` to improve readability and reduce duplication
n_rows <- nrow(rna)
rna_last <- rna[n_rows, ]
## 3.
rna_middle <- rna[n_rows / 2, ]
## 4.
rna_head <- rna[-(7:n_rows), ]
sex <- factor(c("male", "female", "female", "male", "female"))
levels(sex)
[1] "female" "male"  
nlevels(sex)
[1] 2
sex ## current order
[1] male   female female male   female
Levels: female male
sex <- factor(sex, levels = c("male", "female"))
sex ## after re-ordering
[1] male   female female male   female
Levels: male female
plot(sex)
as.character(sex)
[1] "male"   "female" "female" "male"   "female"
levels(sex)
[1] "male"   "female"
levels(sex) <- c("M", "F")
sex
[1] M F F M F
Levels: M F
plot(sex)
levels(sex)
[1] "M" "F"
levels(sex) <- c("Male", "Female")
animal_data <- data.frame(
       animal = c(dog, cat, sea cucumber, sea urchin),
       feel = c("furry", "squishy", "spiny"),
       weight = c(45, 8 1.1, 0.8))
country_climate <- data.frame(
       country = c("Canada", "Panama", "South Africa", "Australia"),
       climate = c("cold", "hot", "temperate", "hot/temperate"),
       temperature = c(10, 30, 18, "15"),
       northern_hemisphere = c(TRUE, TRUE, FALSE, "FALSE"),
       has_kangaroo = c(FALSE, FALSE, FALSE, 1)
       )
country_climate <- data.frame(
       country = c("Canada", "Panama", "South Africa", "Australia"),
       climate = c("cold", "hot", "temperate", "hot/temperate"),
       temperature = c(10, 30, 18, "15"),
       northern_hemisphere = c(TRUE, TRUE, FALSE, "FALSE"),
       has_kangaroo = c(FALSE, FALSE, FALSE, 1)
       )
str(country_climate)
'data.frame':	4 obs. of  5 variables:
 $ country            : chr  "Canada" "Panama" "South Africa" "Australia"
 $ climate            : chr  "cold" "hot" "temperate" "hot/temperate"
 $ temperature        : chr  "10" "30" "18" "15"
 $ northern_hemisphere: chr  "TRUE" "TRUE" "FALSE" "FALSE"
 $ has_kangaroo       : num  0 0 0 1
m <- matrix(1:9, ncol = 3, nrow = 3)
m
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9
## create the matrix
ip <- installed.packages()
head(ip)
## try also View(ip)
## number of package
nrow(ip)
## names of all installed packages
rownames(ip)
## type of information we have about each package
colnames(ip)
set.seed(123)
m <- matrix(rnorm(3000), ncol = 3)
dim(m)
[1] 1000    3
head(m)
            [,1]        [,2]       [,3]
[1,] -0.56047565 -0.99579872 -0.5116037
[2,] -0.23017749 -1.03995504  0.2369379
[3,]  1.55870831 -0.01798024 -0.5415892
[4,]  0.07050839 -0.13217513  1.2192276
[5,]  0.12928774 -2.54934277  0.1741359
[6,]  1.71506499  1.04057346 -0.6152683
library("lubridate")
my_date <- ymd("2015-01-01")
str(my_date)
 Date[1:1], format: "2015-01-01"
# sep indicates the character to use to separate each component
my_date <- ymd(paste("2015", "1", "1", sep = "-"))
str(my_date)
 Date[1:1], format: "2015-01-01"
x <- data.frame(year = c(1996, 1992, 1987, 1986, 2000, 1990, 2002, 1994, 1997, 1985),
                month = c(2,  3,  3, 10,  1,  8,  3,  4,  5,  5),
                day = c(24,  8,  1,  5,  8, 17, 13, 10, 11, 24),
                value = c(4,  5,  1,  9,  3,  8, 10,  2,  6,  7))
x
   year month day value
1  1996     2  24     4
2  1992     3   8     5
3  1987     3   1     1
4  1986    10   5     9
5  2000     1   8     3
6  1990     8  17     8
7  2002     3  13    10
8  1994     4  10     2
9  1997     5  11     6
10 1985     5  24     7
paste(x$year, x$month, x$day, sep = "-")
 [1] "1996-2-24" "1992-3-8"  "1987-3-1"  "1986-10-5" "2000-1-8"  "1990-8-17"
 [7] "2002-3-13" "1994-4-10" "1997-5-11" "1985-5-24"
ymd(paste(x$year, x$month, x$day, sep = "-"))
 [1] "1996-02-24" "1992-03-08" "1987-03-01" "1986-10-05" "2000-01-08"
 [6] "1990-08-17" "2002-03-13" "1994-04-10" "1997-05-11" "1985-05-24"
x$date <- ymd(paste(x$year, x$month, x$day, sep = "-"))
str(x) # notice the new column, with 'date' as the class
'data.frame':	10 obs. of  5 variables:
 $ year : num  1996 1992 1987 1986 2000 ...
 $ month: num  2 3 3 10 1 8 3 4 5 5
 $ day  : num  24 8 1 5 8 17 13 10 11 24
 $ value: num  4 5 1 9 3 8 10 2 6 7
 $ date : Date, format: "1996-02-24" "1992-03-08" ...
summary(x$date)
        Min.      1st Qu.       Median         Mean      3rd Qu.         Max.
"1985-05-24" "1988-01-11" "1993-03-24" "1993-03-18" "1997-01-20" "2002-03-13" 
dmy(paste(x$day, x$month, x$year, sep = "-"))
 [1] "1996-02-24" "1992-03-08" "1987-03-01" "1986-10-05" "2000-01-08"
 [6] "1990-08-17" "2002-03-13" "1994-04-10" "1997-05-11" "1985-05-24"
l <- list(1:10, ## numeric
          letters, ## character
          installed.packages(), ## a matrix
          cars, ## a data.frame
          list(1, 2, 3)) ## a list
length(l)
[1] 5
str(l)
List of 5
 $ : int [1:10] 1 2 3 4 5 6 7 8 9 10
 $ : chr [1:26] "a" "b" "c" "d" ...
 $ : chr [1:261, 1:17] "litedown" "metabolomicsWorkbenchR" "mgcv" "MultiAssayExperiment" ...
  ..- attr(*, "dimnames")=List of 2
  .. ..$ : chr [1:261] "litedown" "metabolomicsWorkbenchR" "mgcv" "MultiAssayExperiment" ...
  .. ..$ : chr [1:17] "Package" "LibPath" "Version" "Priority" ...
 $ :'data.frame':	50 obs. of  2 variables:
  ..$ speed: num [1:50] 4 4 7 7 8 9 10 10 10 11 ...
  ..$ dist : num [1:50] 2 10 4 22 16 10 18 26 34 17 ...
 $ :List of 3
  ..$ : num 1
  ..$ : num 2
  ..$ : num 3
l[[1]] ## first element
 [1]  1  2  3  4  5  6  7  8  9 10
l[1:2] ## a list of length 2
[[1]]
 [1]  1  2  3  4  5  6  7  8  9 10

[[2]]
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s"
[20] "t" "u" "v" "w" "x" "y" "z"
l[1]   ## a list of length 1
[[1]]
 [1]  1  2  3  4  5  6  7  8  9 10
write.csv(rna, file = "data_output/my_rna.csv")
## load the tidyverse packages, incl. dplyr
library("tidyverse")
BiocManager::install("tidyverse")
rna <- read_csv("data/rnaseq.csv")

## view the data
rna
# A tibble: 32,428 × 19
   gene    sample  expression organism   age sex   infection strain  time tissue
   <chr>   <chr>        <dbl> <chr>    <dbl> <chr> <chr>     <chr>  <dbl> <chr>
 1 Asl     GSM254…       1170 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 2 Apod    GSM254…      36194 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 3 Cyp2d22 GSM254…       4060 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 4 Klk6    GSM254…        287 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 5 Fcrls   GSM254…         85 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 6 Slc2a4  GSM254…        782 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 7 Exd2    GSM254…       1619 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 8 Gjc2    GSM254…        288 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 9 Plp1    GSM254…      43217 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
10 Gnb4    GSM254…       1071 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
# ℹ 32,418 more rows
# ℹ 9 more variables: mouse <dbl>, ENTREZID <dbl>, product <chr>,
#   ensembl_gene_id <chr>, external_synonym <chr>, chromosome_name <chr>,
#   gene_biotype <chr>, phenotype_description <chr>,
#   hsapiens_homolog_associated_gene_name <chr>
select(rna, gene, sample, tissue, expression)
# A tibble: 32,428 × 4
   gene    sample     tissue     expression
   <chr>   <chr>      <chr>           <dbl>
 1 Asl     GSM2545336 Cerebellum       1170
 2 Apod    GSM2545336 Cerebellum      36194
 3 Cyp2d22 GSM2545336 Cerebellum       4060
 4 Klk6    GSM2545336 Cerebellum        287
 5 Fcrls   GSM2545336 Cerebellum         85
 6 Slc2a4  GSM2545336 Cerebellum        782
 7 Exd2    GSM2545336 Cerebellum       1619
 8 Gjc2    GSM2545336 Cerebellum        288
 9 Plp1    GSM2545336 Cerebellum      43217
10 Gnb4    GSM2545336 Cerebellum       1071
# ℹ 32,418 more rows
select(rna, -tissue, -organism)
# A tibble: 32,428 × 17
   gene    sample   expression   age sex   infection strain  time mouse ENTREZID
   <chr>   <chr>         <dbl> <dbl> <chr> <chr>     <chr>  <dbl> <dbl>    <dbl>
 1 Asl     GSM2545…       1170     8 Fema… Influenz… C57BL…     8    14   109900
 2 Apod    GSM2545…      36194     8 Fema… Influenz… C57BL…     8    14    11815
 3 Cyp2d22 GSM2545…       4060     8 Fema… Influenz… C57BL…     8    14    56448
 4 Klk6    GSM2545…        287     8 Fema… Influenz… C57BL…     8    14    19144
 5 Fcrls   GSM2545…         85     8 Fema… Influenz… C57BL…     8    14    80891
 6 Slc2a4  GSM2545…        782     8 Fema… Influenz… C57BL…     8    14    20528
 7 Exd2    GSM2545…       1619     8 Fema… Influenz… C57BL…     8    14    97827
 8 Gjc2    GSM2545…        288     8 Fema… Influenz… C57BL…     8    14   118454
 9 Plp1    GSM2545…      43217     8 Fema… Influenz… C57BL…     8    14    18823
10 Gnb4    GSM2545…       1071     8 Fema… Influenz… C57BL…     8    14    14696
# ℹ 32,418 more rows
# ℹ 7 more variables: product <chr>, ensembl_gene_id <chr>,
#   external_synonym <chr>, chromosome_name <chr>, gene_biotype <chr>,
#   phenotype_description <chr>, hsapiens_homolog_associated_gene_name <chr>
filter(rna, sex == "Male")
# A tibble: 14,740 × 19
   gene    sample  expression organism   age sex   infection strain  time tissue
   <chr>   <chr>        <dbl> <chr>    <dbl> <chr> <chr>     <chr>  <dbl> <chr>
 1 Asl     GSM254…        626 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 2 Apod    GSM254…      13021 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 3 Cyp2d22 GSM254…       2171 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 4 Klk6    GSM254…        448 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 5 Fcrls   GSM254…        180 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 6 Slc2a4  GSM254…        313 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 7 Exd2    GSM254…       2366 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 8 Gjc2    GSM254…        310 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 9 Plp1    GSM254…      53126 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
10 Gnb4    GSM254…       1355 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
# ℹ 14,730 more rows
# ℹ 9 more variables: mouse <dbl>, ENTREZID <dbl>, product <chr>,
#   ensembl_gene_id <chr>, external_synonym <chr>, chromosome_name <chr>,
#   gene_biotype <chr>, phenotype_description <chr>,
#   hsapiens_homolog_associated_gene_name <chr>
filter(rna, sex == "Male" & infection == "NonInfected")
# A tibble: 4,422 × 19
   gene    sample  expression organism   age sex   infection strain  time tissue
   <chr>   <chr>        <dbl> <chr>    <dbl> <chr> <chr>     <chr>  <dbl> <chr>
 1 Asl     GSM254…        535 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 2 Apod    GSM254…      13668 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 3 Cyp2d22 GSM254…       2008 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 4 Klk6    GSM254…       1101 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 5 Fcrls   GSM254…        375 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 6 Slc2a4  GSM254…        249 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 7 Exd2    GSM254…       3126 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 8 Gjc2    GSM254…        791 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 9 Plp1    GSM254…      98658 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
10 Gnb4    GSM254…       2437 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
# ℹ 4,412 more rows
# ℹ 9 more variables: mouse <dbl>, ENTREZID <dbl>, product <chr>,
#   ensembl_gene_id <chr>, external_synonym <chr>, chromosome_name <chr>,
#   gene_biotype <chr>, phenotype_description <chr>,
#   hsapiens_homolog_associated_gene_name <chr>
genes <- select(rna, gene, hsapiens_homolog_associated_gene_name)
genes
# A tibble: 32,428 × 2
   gene    hsapiens_homolog_associated_gene_name
   <chr>   <chr>
 1 Asl     ASL
 2 Apod    APOD
 3 Cyp2d22 CYP2D6
 4 Klk6    KLK6
 5 Fcrls   FCRL2
 6 Slc2a4  SLC2A4
 7 Exd2    EXD2
 8 Gjc2    GJC2
 9 Plp1    PLP1
10 Gnb4    GNB4
# ℹ 32,418 more rows
filter(genes, is.na(hsapiens_homolog_associated_gene_name))
# A tibble: 4,290 × 2
   gene     hsapiens_homolog_associated_gene_name
   <chr>    <chr>
 1 Prodh    <NA>
 2 Tssk5    <NA>
 3 Vmn2r1   <NA>
 4 Gm10654  <NA>
 5 Hexa     <NA>
 6 Sult1a1  <NA>
 7 Gm6277   <NA>
 8 Tmem198b <NA>
 9 Adam1a   <NA>
10 Ebp      <NA>
# ℹ 4,280 more rows
filter(genes, !is.na(hsapiens_homolog_associated_gene_name))
# A tibble: 28,138 × 2
   gene    hsapiens_homolog_associated_gene_name
   <chr>   <chr>
 1 Asl     ASL
 2 Apod    APOD
 3 Cyp2d22 CYP2D6
 4 Klk6    KLK6
 5 Fcrls   FCRL2
 6 Slc2a4  SLC2A4
 7 Exd2    EXD2
 8 Gjc2    GJC2
 9 Plp1    PLP1
10 Gnb4    GNB4
# ℹ 28,128 more rows
rna2 <- filter(rna, sex == "Male")
rna3 <- select(rna2, gene, sample, tissue, expression)
rna3
# A tibble: 14,740 × 4
   gene    sample     tissue     expression
   <chr>   <chr>      <chr>           <dbl>
 1 Asl     GSM2545340 Cerebellum        626
 2 Apod    GSM2545340 Cerebellum      13021
 3 Cyp2d22 GSM2545340 Cerebellum       2171
 4 Klk6    GSM2545340 Cerebellum        448
 5 Fcrls   GSM2545340 Cerebellum        180
 6 Slc2a4  GSM2545340 Cerebellum        313
 7 Exd2    GSM2545340 Cerebellum       2366
 8 Gjc2    GSM2545340 Cerebellum        310
 9 Plp1    GSM2545340 Cerebellum      53126
10 Gnb4    GSM2545340 Cerebellum       1355
# ℹ 14,730 more rows
rna3 <- select(filter(rna, sex == "Male"), gene, sample, tissue, expression)
rna3
# A tibble: 14,740 × 4
   gene    sample     tissue     expression
   <chr>   <chr>      <chr>           <dbl>
 1 Asl     GSM2545340 Cerebellum        626
 2 Apod    GSM2545340 Cerebellum      13021
 3 Cyp2d22 GSM2545340 Cerebellum       2171
 4 Klk6    GSM2545340 Cerebellum        448
 5 Fcrls   GSM2545340 Cerebellum        180
 6 Slc2a4  GSM2545340 Cerebellum        313
 7 Exd2    GSM2545340 Cerebellum       2366
 8 Gjc2    GSM2545340 Cerebellum        310
 9 Plp1    GSM2545340 Cerebellum      53126
10 Gnb4    GSM2545340 Cerebellum       1355
# ℹ 14,730 more rows
rna |>
  filter(sex == "Male") |>
  select(gene, sample, tissue, expression)
# A tibble: 14,740 × 4
   gene    sample     tissue     expression
   <chr>   <chr>      <chr>           <dbl>
 1 Asl     GSM2545340 Cerebellum        626
 2 Apod    GSM2545340 Cerebellum      13021
 3 Cyp2d22 GSM2545340 Cerebellum       2171
 4 Klk6    GSM2545340 Cerebellum        448
 5 Fcrls   GSM2545340 Cerebellum        180
 6 Slc2a4  GSM2545340 Cerebellum        313
 7 Exd2    GSM2545340 Cerebellum       2366
 8 Gjc2    GSM2545340 Cerebellum        310
 9 Plp1    GSM2545340 Cerebellum      53126
10 Gnb4    GSM2545340 Cerebellum       1355
# ℹ 14,730 more rows
rna3 <- rna |>
  filter(sex == "Male") |>
  select(gene, sample, tissue, expression)

rna3
# A tibble: 14,740 × 4
   gene    sample     tissue     expression
   <chr>   <chr>      <chr>           <dbl>
 1 Asl     GSM2545340 Cerebellum        626
 2 Apod    GSM2545340 Cerebellum      13021
 3 Cyp2d22 GSM2545340 Cerebellum       2171
 4 Klk6    GSM2545340 Cerebellum        448
 5 Fcrls   GSM2545340 Cerebellum        180
 6 Slc2a4  GSM2545340 Cerebellum        313
 7 Exd2    GSM2545340 Cerebellum       2366
 8 Gjc2    GSM2545340 Cerebellum        310
 9 Plp1    GSM2545340 Cerebellum      53126
10 Gnb4    GSM2545340 Cerebellum       1355
# ℹ 14,730 more rows
rna |>
  filter(expression > 50000,
         sex == "Female",
         time == 0 ) |>
  select(gene, sample, time, expression, age)
# A tibble: 9 × 5
  gene   sample      time expression   age
  <chr>  <chr>      <dbl>      <dbl> <dbl>
1 Plp1   GSM2545337     0     101241     8
2 Atp1b1 GSM2545337     0      53260     8
3 Plp1   GSM2545338     0      96534     8
4 Atp1b1 GSM2545338     0      50614     8
5 Plp1   GSM2545348     0     102790     8
6 Atp1b1 GSM2545348     0      59544     8
7 Plp1   GSM2545353     0      71237     8
8 Glul   GSM2545353     0      52451     8
9 Atp1b1 GSM2545353     0      61451     8
rna |>
  mutate(time_hours = time * 24) |>
  select(time, time_hours)
# A tibble: 32,428 × 2
    time time_hours
   <dbl>      <dbl>
 1     8        192
 2     8        192
 3     8        192
 4     8        192
 5     8        192
 6     8        192
 7     8        192
 8     8        192
 9     8        192
10     8        192
# ℹ 32,418 more rows
rna |>
  mutate(time_hours = time * 24,
         time_mn = time_hours * 60) |>
  select(time, time_hours, time_mn)
# A tibble: 32,428 × 3
    time time_hours time_mn
   <dbl>      <dbl>   <dbl>
 1     8        192   11520
 2     8        192   11520
 3     8        192   11520
 4     8        192   11520
 5     8        192   11520
 6     8        192   11520
 7     8        192   11520
 8     8        192   11520
 9     8        192   11520
10     8        192   11520
# ℹ 32,418 more rows
rna |>
  mutate(expression = log(expression)) |>
  select(gene, chromosome_name, phenotype_description, sample, expression) |>
  filter(chromosome_name == "X" | chromosome_name == "Y") |>
  filter(!is.na(phenotype_description)) |>
  filter(expression > 5)
# A tibble: 649 × 5
   gene   chromosome_name phenotype_description                sample expression
   <chr>  <chr>           <chr>                                <chr>       <dbl>
 1 Plp1   X               abnormal CNS glial cell morphology   GSM25…      10.7
 2 Slc7a3 X               decreased body length                GSM25…       5.46
 3 Plxnb3 X               abnormal coat appearance             GSM25…       6.58
 4 Rbm3   X               abnormal liver morphology            GSM25…       9.32
 5 Cfp    X               abnormal cardiovascular system phys… GSM25…       6.18
 6 Ebp    X               abnormal embryonic erythrocyte morp… GSM25…       6.68
 7 Cd99l2 X               abnormal cellular extravasation      GSM25…       8.04
 8 Piga   X               abnormal brain development           GSM25…       6.06
 9 Pim2   X               decreased T cell proliferation       GSM25…       7.11
10 Itm2a  X               no abnormal phenotype detected       GSM25…       7.48
# ℹ 639 more rows
rna |>
  group_by(gene)
# A tibble: 32,428 × 19
# Groups:   gene [1,474]
   gene    sample  expression organism   age sex   infection strain  time tissue
   <chr>   <chr>        <dbl> <chr>    <dbl> <chr> <chr>     <chr>  <dbl> <chr>
 1 Asl     GSM254…       1170 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 2 Apod    GSM254…      36194 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 3 Cyp2d22 GSM254…       4060 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 4 Klk6    GSM254…        287 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 5 Fcrls   GSM254…         85 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 6 Slc2a4  GSM254…        782 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 7 Exd2    GSM254…       1619 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 8 Gjc2    GSM254…        288 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 9 Plp1    GSM254…      43217 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
10 Gnb4    GSM254…       1071 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
# ℹ 32,418 more rows
# ℹ 9 more variables: mouse <dbl>, ENTREZID <dbl>, product <chr>,
#   ensembl_gene_id <chr>, external_synonym <chr>, chromosome_name <chr>,
#   gene_biotype <chr>, phenotype_description <chr>,
#   hsapiens_homolog_associated_gene_name <chr>
rna |>
  group_by(sample)
# A tibble: 32,428 × 19
# Groups:   sample [22]
   gene    sample  expression organism   age sex   infection strain  time tissue
   <chr>   <chr>        <dbl> <chr>    <dbl> <chr> <chr>     <chr>  <dbl> <chr>
 1 Asl     GSM254…       1170 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 2 Apod    GSM254…      36194 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 3 Cyp2d22 GSM254…       4060 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 4 Klk6    GSM254…        287 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 5 Fcrls   GSM254…         85 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 6 Slc2a4  GSM254…        782 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 7 Exd2    GSM254…       1619 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 8 Gjc2    GSM254…        288 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 9 Plp1    GSM254…      43217 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
10 Gnb4    GSM254…       1071 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
# ℹ 32,418 more rows
# ℹ 9 more variables: mouse <dbl>, ENTREZID <dbl>, product <chr>,
#   ensembl_gene_id <chr>, external_synonym <chr>, chromosome_name <chr>,
#   gene_biotype <chr>, phenotype_description <chr>,
#   hsapiens_homolog_associated_gene_name <chr>
rna |>
  group_by(gene) |>
  summarise(mean_expression = mean(expression))
# A tibble: 1,474 × 2
   gene     mean_expression
   <chr>              <dbl>
 1 AI504432         1053.
 2 AW046200          131.
 3 AW551984          295.
 4 Aamp             4751.
 5 Abca12              4.55
 6 Abcc8            2498.
 7 Abhd14a           525.
 8 Abi2             4909.
 9 Abi3bp           1002.
10 Abl2             2124.
# ℹ 1,464 more rows
rna |>
  group_by(sample) |>
  summarise(mean_expression = mean(expression))
# A tibble: 22 × 2
   sample     mean_expression
   <chr>                <dbl>
 1 GSM2545336           2062.
 2 GSM2545337           1766.
 3 GSM2545338           1668.
 4 GSM2545339           1696.
 5 GSM2545340           1682.
 6 GSM2545341           1638.
 7 GSM2545342           1594.
 8 GSM2545343           2107.
 9 GSM2545344           1712.
10 GSM2545345           1700.
# ℹ 12 more rows
rna |>
  group_by(gene, infection, time) |>
  summarise(mean_expression = mean(expression))
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene, infection, and time.
ℹ Output is grouped by gene and infection.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, infection, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 4,422 × 4
# Groups:   gene, infection [2,948]
   gene     infection    time mean_expression
   <chr>    <chr>       <dbl>           <dbl>
 1 AI504432 InfluenzaA      4           1104.
 2 AI504432 InfluenzaA      8           1014
 3 AI504432 NonInfected     0           1034.
 4 AW046200 InfluenzaA      4            152.
 5 AW046200 InfluenzaA      8             81
 6 AW046200 NonInfected     0            155.
 7 AW551984 InfluenzaA      4            302.
 8 AW551984 InfluenzaA      8            342.
 9 AW551984 NonInfected     0            238
10 Aamp     InfluenzaA      4           4870
# ℹ 4,412 more rows
rna |>
  group_by(gene, infection, time) |>
  summarise(mean_expression = mean(expression),
            median_expression = median(expression))
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene, infection, and time.
ℹ Output is grouped by gene and infection.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, infection, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 4,422 × 5
# Groups:   gene, infection [2,948]
   gene     infection    time mean_expression median_expression
   <chr>    <chr>       <dbl>           <dbl>             <dbl>
 1 AI504432 InfluenzaA      4           1104.             1094.
 2 AI504432 InfluenzaA      8           1014               985
 3 AI504432 NonInfected     0           1034.             1016
 4 AW046200 InfluenzaA      4            152.              144.
 5 AW046200 InfluenzaA      8             81                82
 6 AW046200 NonInfected     0            155.              163
 7 AW551984 InfluenzaA      4            302.              245
 8 AW551984 InfluenzaA      8            342.              287
 9 AW551984 NonInfected     0            238               265
10 Aamp     InfluenzaA      4           4870              4708
# ℹ 4,412 more rows
rna |>
  filter(gene == "Dok3") |>
  group_by(time) |>
  summarise(mean = mean(expression))
# A tibble: 3 × 2
   time  mean
  <dbl> <dbl>
1     0  169
2     4  156.
3     8   61 
rna |>
    count(infection)
# A tibble: 2 × 2
  infection       n
  <chr>       <int>
1 InfluenzaA  22110
2 NonInfected 10318
rna |>
    group_by(infection) |>
    summarise(n = n())
# A tibble: 2 × 2
  infection       n
  <chr>       <int>
1 InfluenzaA  22110
2 NonInfected 10318
rna |>
    count(infection, time)
# A tibble: 3 × 3
  infection    time     n
  <chr>       <dbl> <int>
1 InfluenzaA      4 11792
2 InfluenzaA      8 10318
3 NonInfected     0 10318
rna |>
  group_by(infection, time) |>
  summarise(n = n())
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by infection and time.
ℹ Output is grouped by infection.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(infection, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 3 × 3
# Groups:   infection [2]
  infection    time     n
  <chr>       <dbl> <int>
1 InfluenzaA      4 11792
2 InfluenzaA      8 10318
3 NonInfected     0 10318
rna |>
  count(infection, time) |>
  arrange(time)
# A tibble: 3 × 3
  infection    time     n
  <chr>       <dbl> <int>
1 NonInfected     0 10318
2 InfluenzaA      4 11792
3 InfluenzaA      8 10318
rna |>
  count(infection, time) |>
  arrange(n)
# A tibble: 3 × 3
  infection    time     n
  <chr>       <dbl> <int>
1 InfluenzaA      8 10318
2 NonInfected     0 10318
3 InfluenzaA      4 11792
rna |>
  count(infection, time) |>
  arrange(desc(n))
# A tibble: 3 × 3
  infection    time     n
  <chr>       <dbl> <int>
1 InfluenzaA      4 11792
2 InfluenzaA      8 10318
3 NonInfected     0 10318
## 1.
rna |>
  count(sample)
# A tibble: 22 × 2
   sample         n
   <chr>      <int>
 1 GSM2545336  1474
 2 GSM2545337  1474
 3 GSM2545338  1474
 4 GSM2545339  1474
 5 GSM2545340  1474
 6 GSM2545341  1474
 7 GSM2545342  1474
 8 GSM2545343  1474
 9 GSM2545344  1474
10 GSM2545345  1474
# ℹ 12 more rows
## 2.
rna |>
  group_by(sample) |>
  summarise(seq_depth = sum(expression)) |>
  arrange(desc(seq_depth))
# A tibble: 22 × 2
   sample     seq_depth
   <chr>          <dbl>
 1 GSM2545350   3255566
 2 GSM2545352   3216163
 3 GSM2545343   3105652
 4 GSM2545336   3039671
 5 GSM2545380   3036098
 6 GSM2545353   2953249
 7 GSM2545348   2913678
 8 GSM2545362   2913517
 9 GSM2545351   2782464
10 GSM2545349   2758006
# ℹ 12 more rows
## 3.
rna |>
  filter(sample == "GSM2545336") |>
  count(gene_biotype) |>
  arrange(desc(n))
# A tibble: 13 × 2
   gene_biotype                           n
   <chr>                              <int>
 1 protein_coding                      1321
 2 lncRNA                                69
 3 processed_pseudogene                  59
 4 miRNA                                  7
 5 snoRNA                                 5
 6 TEC                                    4
 7 polymorphic_pseudogene                 2
 8 unprocessed_pseudogene                 2
 9 IG_C_gene                              1
10 scaRNA                                 1
11 transcribed_processed_pseudogene       1
12 transcribed_unitary_pseudogene         1
13 transcribed_unprocessed_pseudogene     1
## 4.
rna |>
  filter(phenotype_description == "abnormal DNA methylation") |>
  group_by(gene, time) |>
  summarise(mean_expression = mean(log(expression))) |>
  arrange()
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene and time.
ℹ Output is grouped by gene.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 6 × 3
# Groups:   gene [2]
  gene   time mean_expression
  <chr> <dbl>           <dbl>
1 Xist      0            6.95
2 Xist      4            6.34
3 Xist      8            7.13
4 Zdbf2     0            6.27
5 Zdbf2     4            6.27
6 Zdbf2     8            6.19
rna |>
  arrange(gene)
# A tibble: 32,428 × 19
   gene     sample expression organism   age sex   infection strain  time tissue
   <chr>    <chr>       <dbl> <chr>    <dbl> <chr> <chr>     <chr>  <dbl> <chr>
 1 AI504432 GSM25…       1230 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 2 AI504432 GSM25…       1085 Mus mus…     8 Fema… NonInfec… C57BL…     0 Cereb…
 3 AI504432 GSM25…        969 Mus mus…     8 Fema… NonInfec… C57BL…     0 Cereb…
 4 AI504432 GSM25…       1284 Mus mus…     8 Fema… Influenz… C57BL…     4 Cereb…
 5 AI504432 GSM25…        966 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
 6 AI504432 GSM25…        918 Mus mus…     8 Male  Influenz… C57BL…     8 Cereb…
 7 AI504432 GSM25…        985 Mus mus…     8 Fema… Influenz… C57BL…     8 Cereb…
 8 AI504432 GSM25…        972 Mus mus…     8 Male  NonInfec… C57BL…     0 Cereb…
 9 AI504432 GSM25…       1000 Mus mus…     8 Fema… Influenz… C57BL…     4 Cereb…
10 AI504432 GSM25…        816 Mus mus…     8 Male  Influenz… C57BL…     4 Cereb…
# ℹ 32,418 more rows
# ℹ 9 more variables: mouse <dbl>, ENTREZID <dbl>, product <chr>,
#   ensembl_gene_id <chr>, external_synonym <chr>, chromosome_name <chr>,
#   gene_biotype <chr>, phenotype_description <chr>,
#   hsapiens_homolog_associated_gene_name <chr>
# A tibble: 1,474 × 23
   gene    GSM2545336 GSM2545337 GSM2545338 GSM2545339 GSM2545340 GSM2545341
   <chr>        <dbl>      <dbl>      <dbl>      <dbl>      <dbl>      <dbl>
 1 Asl           1170        361        400        586        626        988
 2 Apod         36194      10347       9173      10620      13021      29594
 3 Cyp2d22       4060       1616       1603       1901       2171       3349
 4 Klk6           287        629        641        578        448        195
 5 Fcrls           85        233        244        237        180         38
 6 Slc2a4         782        231        248        265        313        786
 7 Exd2          1619       2288       2235       2513       2366       1359
 8 Gjc2           288        595        568        551        310        146
 9 Plp1         43217     101241      96534      58354      53126      27173
10 Gnb4          1071       1791       1867       1430       1355        798
# ℹ 1,464 more rows
# ℹ 16 more variables: GSM2545342 <dbl>, GSM2545343 <dbl>, GSM2545344 <dbl>,
#   GSM2545345 <dbl>, GSM2545346 <dbl>, GSM2545347 <dbl>, GSM2545348 <dbl>,
#   GSM2545349 <dbl>, GSM2545350 <dbl>, GSM2545351 <dbl>, GSM2545352 <dbl>,
#   GSM2545353 <dbl>, GSM2545354 <dbl>, GSM2545362 <dbl>, GSM2545363 <dbl>,
#   GSM2545380 <dbl>
rna_exp <- rna |>
  select(gene, sample, expression)
rna_exp
# A tibble: 32,428 × 3
   gene    sample     expression
   <chr>   <chr>           <dbl>
 1 Asl     GSM2545336       1170
 2 Apod    GSM2545336      36194
 3 Cyp2d22 GSM2545336       4060
 4 Klk6    GSM2545336        287
 5 Fcrls   GSM2545336         85
 6 Slc2a4  GSM2545336        782
 7 Exd2    GSM2545336       1619
 8 Gjc2    GSM2545336        288
 9 Plp1    GSM2545336      43217
10 Gnb4    GSM2545336       1071
# ℹ 32,418 more rows
rna_wide <- rna_exp |>
  pivot_wider(names_from = sample,
              values_from = expression)
rna_wide
# A tibble: 1,474 × 23
   gene    GSM2545336 GSM2545337 GSM2545338 GSM2545339 GSM2545340 GSM2545341
   <chr>        <dbl>      <dbl>      <dbl>      <dbl>      <dbl>      <dbl>
 1 Asl           1170        361        400        586        626        988
 2 Apod         36194      10347       9173      10620      13021      29594
 3 Cyp2d22       4060       1616       1603       1901       2171       3349
 4 Klk6           287        629        641        578        448        195
 5 Fcrls           85        233        244        237        180         38
 6 Slc2a4         782        231        248        265        313        786
 7 Exd2          1619       2288       2235       2513       2366       1359
 8 Gjc2           288        595        568        551        310        146
 9 Plp1         43217     101241      96534      58354      53126      27173
10 Gnb4          1071       1791       1867       1430       1355        798
# ℹ 1,464 more rows
# ℹ 16 more variables: GSM2545342 <dbl>, GSM2545343 <dbl>, GSM2545344 <dbl>,
#   GSM2545345 <dbl>, GSM2545346 <dbl>, GSM2545347 <dbl>, GSM2545348 <dbl>,
#   GSM2545349 <dbl>, GSM2545350 <dbl>, GSM2545351 <dbl>, GSM2545352 <dbl>,
#   GSM2545353 <dbl>, GSM2545354 <dbl>, GSM2545362 <dbl>, GSM2545363 <dbl>,
#   GSM2545380 <dbl>
rna_with_missing_values <- rna |>
  select(gene, sample, expression) |>
  filter(gene %in% c("Asl", "Apod", "Cyp2d22")) |>
  filter(sample %in% c("GSM2545336", "GSM2545337", "GSM2545338")) |>
  arrange(sample) |>
  filter(!(gene == "Cyp2d22" & sample != "GSM2545338"))
rna_with_missing_values
# A tibble: 7 × 3
  gene    sample     expression
  <chr>   <chr>           <dbl>
1 Asl     GSM2545336       1170
2 Apod    GSM2545336      36194
3 Asl     GSM2545337        361
4 Apod    GSM2545337      10347
5 Asl     GSM2545338        400
6 Apod    GSM2545338       9173
7 Cyp2d22 GSM2545338       1603
rna_with_missing_values |>
  pivot_wider(names_from = sample,
              values_from = expression)
# A tibble: 3 × 4
  gene    GSM2545336 GSM2545337 GSM2545338
  <chr>        <dbl>      <dbl>      <dbl>
1 Asl           1170        361        400
2 Apod         36194      10347       9173
3 Cyp2d22         NA         NA       1603
rna_with_missing_values |>
  pivot_wider(names_from = sample,
              values_from = expression,
              values_fill = 0)
# A tibble: 3 × 4
  gene    GSM2545336 GSM2545337 GSM2545338
  <chr>        <dbl>      <dbl>      <dbl>
1 Asl           1170        361        400
2 Apod         36194      10347       9173
3 Cyp2d22          0          0       1603
rna_long <- rna_wide |>
    pivot_longer(names_to = "sample",
                 values_to = "expression",
                 -gene)
rna_long
# A tibble: 32,428 × 3
   gene  sample     expression
   <chr> <chr>           <dbl>
 1 Asl   GSM2545336       1170
 2 Asl   GSM2545337        361
 3 Asl   GSM2545338        400
 4 Asl   GSM2545339        586
 5 Asl   GSM2545340        626
 6 Asl   GSM2545341        988
 7 Asl   GSM2545342        836
 8 Asl   GSM2545343        535
 9 Asl   GSM2545344        586
10 Asl   GSM2545345        597
# ℹ 32,418 more rows
rna_wide |>
    pivot_longer(names_to = "sample",
                 values_to = "expression",
                 cols = starts_with("GSM"))
# A tibble: 32,428 × 3
   gene  sample     expression
   <chr> <chr>           <dbl>
 1 Asl   GSM2545336       1170
 2 Asl   GSM2545337        361
 3 Asl   GSM2545338        400
 4 Asl   GSM2545339        586
 5 Asl   GSM2545340        626
 6 Asl   GSM2545341        988
 7 Asl   GSM2545342        836
 8 Asl   GSM2545343        535
 9 Asl   GSM2545344        586
10 Asl   GSM2545345        597
# ℹ 32,418 more rows
rna_wide |>
    pivot_longer(names_to = "sample",
                 values_to = "expression",
                 GSM2545336:GSM2545380)
# A tibble: 32,428 × 3
   gene  sample     expression
   <chr> <chr>           <dbl>
 1 Asl   GSM2545336       1170
 2 Asl   GSM2545337        361
 3 Asl   GSM2545338        400
 4 Asl   GSM2545339        586
 5 Asl   GSM2545340        626
 6 Asl   GSM2545341        988
 7 Asl   GSM2545342        836
 8 Asl   GSM2545343        535
 9 Asl   GSM2545344        586
10 Asl   GSM2545345        597
# ℹ 32,418 more rows
rna_with_missing_values
# A tibble: 7 × 3
  gene    sample     expression
  <chr>   <chr>           <dbl>
1 Asl     GSM2545336       1170
2 Apod    GSM2545336      36194
3 Asl     GSM2545337        361
4 Apod    GSM2545337      10347
5 Asl     GSM2545338        400
6 Apod    GSM2545338       9173
7 Cyp2d22 GSM2545338       1603
wide_with_NA <- rna_with_missing_values |>
  pivot_wider(names_from = sample,
              values_from = expression)
wide_with_NA
# A tibble: 3 × 4
  gene    GSM2545336 GSM2545337 GSM2545338
  <chr>        <dbl>      <dbl>      <dbl>
1 Asl           1170        361        400
2 Apod         36194      10347       9173
3 Cyp2d22         NA         NA       1603
wide_with_NA |>
    pivot_longer(names_to = "sample",
                 values_to = "expression",
                 -gene)
# A tibble: 9 × 3
  gene    sample     expression
  <chr>   <chr>           <dbl>
1 Asl     GSM2545336       1170
2 Asl     GSM2545337        361
3 Asl     GSM2545338        400
4 Apod    GSM2545336      36194
5 Apod    GSM2545337      10347
6 Apod    GSM2545338       9173
7 Cyp2d22 GSM2545336         NA
8 Cyp2d22 GSM2545337         NA
9 Cyp2d22 GSM2545338       1603
rna1 <- rna |>
select(gene, mouse, expression) |>
pivot_wider(names_from = mouse, values_from = expression)
rna1
# A tibble: 1,474 × 23
   gene     `14`    `9`  `10`  `15`  `18`   `6`   `5`  `11`  `22`  `13`  `23`
   <chr>   <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1 Asl      1170    361   400   586   626   988   836   535   586   597   938
 2 Apod    36194  10347  9173 10620 13021 29594 24959 13668 13230 15868 27769
 3 Cyp2d22  4060   1616  1603  1901  2171  3349  3122  2008  2254  2277  2985
 4 Klk6      287    629   641   578   448   195   186  1101   537   567   327
 5 Fcrls      85    233   244   237   180    38    68   375   199   177    89
 6 Slc2a4    782    231   248   265   313   786   528   249   266   357   654
 7 Exd2     1619   2288  2235  2513  2366  1359  1474  3126  2379  2173  1531
 8 Gjc2      288    595   568   551   310   146   186   791   454   370   240
 9 Plp1    43217 101241 96534 58354 53126 27173 28728 98658 61356 61647 38019
10 Gnb4     1071   1791  1867  1430  1355   798   806  2437  1394  1554   960
# ℹ 1,464 more rows
# ℹ 11 more variables: `24` <dbl>, `8` <dbl>, `7` <dbl>, `1` <dbl>, `16` <dbl>,
#   `21` <dbl>, `4` <dbl>, `2` <dbl>, `20` <dbl>, `12` <dbl>, `19` <dbl>
rna1 |>
pivot_longer(names_to = "mouse_id", values_to = "counts", -gene)
# A tibble: 32,428 × 3
   gene  mouse_id counts
   <chr> <chr>     <dbl>
 1 Asl   14         1170
 2 Asl   9           361
 3 Asl   10          400
 4 Asl   15          586
 5 Asl   18          626
 6 Asl   6           988
 7 Asl   5           836
 8 Asl   11          535
 9 Asl   22          586
10 Asl   13          597
# ℹ 32,418 more rows
 rna |>
  filter(chromosome_name == "Y" | chromosome_name == "X") |>
  group_by(sex, chromosome_name) |>
  summarise(mean = mean(expression))
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by sex and chromosome_name.
ℹ Output is grouped by sex.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(sex, chromosome_name))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 4 × 3
# Groups:   sex [2]
  sex    chromosome_name  mean
  <chr>  <chr>           <dbl>
1 Female X               3504.
2 Female Y                  3
3 Male   X               2497.
4 Male   Y               2117.
rna_1 <- rna |>
  filter(chromosome_name == "Y" | chromosome_name == "X") |>
  group_by(sex, chromosome_name) |>
  summarise(mean = mean(expression)) |>
  pivot_wider(names_from = sex,
              values_from = mean)
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by sex and chromosome_name.
ℹ Output is grouped by sex.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(sex, chromosome_name))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
rna_1
# A tibble: 2 × 3
  chromosome_name Female  Male
  <chr>            <dbl> <dbl>
1 X                3504. 2497.
2 Y                   3  2117.
rna_1 |>
  pivot_longer(names_to = "gender",
               values_to = "mean",
               -chromosome_name)
# A tibble: 4 × 3
  chromosome_name gender  mean
  <chr>           <chr>  <dbl>
1 X               Female 3504.
2 X               Male   2497.
3 Y               Female    3
4 Y               Male   2117.
rna |>
  group_by(gene, time) |>
  summarise(mean_exp = mean(expression))
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene and time.
ℹ Output is grouped by gene.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 4,422 × 3
# Groups:   gene [1,474]
   gene      time mean_exp
   <chr>    <dbl>    <dbl>
 1 AI504432     0    1034.
 2 AI504432     4    1104.
 3 AI504432     8    1014
 4 AW046200     0     155.
 5 AW046200     4     152.
 6 AW046200     8      81
 7 AW551984     0     238
 8 AW551984     4     302.
 9 AW551984     8     342.
10 Aamp         0    4603.
# ℹ 4,412 more rows
rna_time <- rna |>
  group_by(gene, time) |>
  summarise(mean_exp = mean(expression)) |>
  pivot_wider(names_from = time,
              values_from = mean_exp)
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene and time.
ℹ Output is grouped by gene.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
rna_time
# A tibble: 1,474 × 4
# Groups:   gene [1,474]
   gene         `0`     `4`     `8`
   <chr>      <dbl>   <dbl>   <dbl>
 1 AI504432 1034.   1104.   1014
 2 AW046200  155.    152.     81
 3 AW551984  238     302.    342.
 4 Aamp     4603.   4870    4763.
 5 Abca12      5.29    4.25    4.14
 6 Abcc8    2576.   2609.   2292.
 7 Abhd14a   591.    547.    432.
 8 Abi2     4881.   4903.   4945.
 9 Abi3bp   1175.   1061.    762.
10 Abl2     2170.   2078.   2131.
# ℹ 1,464 more rows
rna |>
  group_by(gene, time) |>
  summarise(mean_exp = mean(expression)) |>
  pivot_wider(names_from = time,
              values_from = mean_exp) |>
  select(gene, 4)
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene and time.
ℹ Output is grouped by gene.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 1,474 × 2
# Groups:   gene [1,474]
   gene         `8`
   <chr>      <dbl>
 1 AI504432 1014
 2 AW046200   81
 3 AW551984  342.
 4 Aamp     4763.
 5 Abca12      4.14
 6 Abcc8    2292.
 7 Abhd14a   432.
 8 Abi2     4945.
 9 Abi3bp    762.
10 Abl2     2131.
# ℹ 1,464 more rows
rna |>
  group_by(gene, time) |>
  summarise(mean_exp = mean(expression)) |>
  pivot_wider(names_from = time,
              values_from = mean_exp) |>
  select(gene, `4`)
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene and time.
ℹ Output is grouped by gene.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 1,474 × 2
# Groups:   gene [1,474]
   gene         `4`
   <chr>      <dbl>
 1 AI504432 1104.
 2 AW046200  152.
 3 AW551984  302.
 4 Aamp     4870
 5 Abca12      4.25
 6 Abcc8    2609.
 7 Abhd14a   547.
 8 Abi2     4903.
 9 Abi3bp   1061.
10 Abl2     2078.
# ℹ 1,464 more rows
rna |>
  group_by(gene, time) |>
  summarise(mean_exp = mean(expression)) |>
  pivot_wider(names_from = time,
              values_from = mean_exp) |>
  rename("time0" = `0`, "time4" = `4`, "time8" = `8`) |>
  select(gene, time4)
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene and time.
ℹ Output is grouped by gene.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
# A tibble: 1,474 × 2
# Groups:   gene [1,474]
   gene       time4
   <chr>      <dbl>
 1 AI504432 1104.
 2 AW046200  152.
 3 AW551984  302.
 4 Aamp     4870
 5 Abca12      4.25
 6 Abcc8    2609.
 7 Abhd14a   547.
 8 Abi2     4903.
 9 Abi3bp   1061.
10 Abl2     2078.
# ℹ 1,464 more rows
rna_time
# A tibble: 1,474 × 4
# Groups:   gene [1,474]
   gene         `0`     `4`     `8`
   <chr>      <dbl>   <dbl>   <dbl>
 1 AI504432 1034.   1104.   1014
 2 AW046200  155.    152.     81
 3 AW551984  238     302.    342.
 4 Aamp     4603.   4870    4763.
 5 Abca12      5.29    4.25    4.14
 6 Abcc8    2576.   2609.   2292.
 7 Abhd14a   591.    547.    432.
 8 Abi2     4881.   4903.   4945.
 9 Abi3bp   1175.   1061.    762.
10 Abl2     2170.   2078.   2131.
# ℹ 1,464 more rows
rna_time |>
  mutate(time_8_vs_0 = `8` / `0`, time_8_vs_4 = `8` / `4`)
# A tibble: 1,474 × 6
# Groups:   gene [1,474]
   gene         `0`     `4`     `8` time_8_vs_0 time_8_vs_4
   <chr>      <dbl>   <dbl>   <dbl>       <dbl>       <dbl>
 1 AI504432 1034.   1104.   1014          0.981       0.918
 2 AW046200  155.    152.     81          0.522       0.532
 3 AW551984  238     302.    342.         1.44        1.13
 4 Aamp     4603.   4870    4763.         1.03        0.978
 5 Abca12      5.29    4.25    4.14       0.784       0.975
 6 Abcc8    2576.   2609.   2292.         0.889       0.878
 7 Abhd14a   591.    547.    432.         0.731       0.791
 8 Abi2     4881.   4903.   4945.         1.01        1.01
 9 Abi3bp   1175.   1061.    762.         0.649       0.719
10 Abl2     2170.   2078.   2131.         0.982       1.03
# ℹ 1,464 more rows
rna_time |>
  mutate(time_8_vs_0 = `8` / `0`, time_8_vs_4 = `8` / `4`) |>
  pivot_longer(names_to = "comparisons",
               values_to = "Fold_changes",
               time_8_vs_0:time_8_vs_4)
# A tibble: 2,948 × 6
# Groups:   gene [1,474]
   gene         `0`     `4`     `8` comparisons Fold_changes
   <chr>      <dbl>   <dbl>   <dbl> <chr>              <dbl>
 1 AI504432 1034.   1104.   1014    time_8_vs_0        0.981
 2 AI504432 1034.   1104.   1014    time_8_vs_4        0.918
 3 AW046200  155.    152.     81    time_8_vs_0        0.522
 4 AW046200  155.    152.     81    time_8_vs_4        0.532
 5 AW551984  238     302.    342.   time_8_vs_0        1.44
 6 AW551984  238     302.    342.   time_8_vs_4        1.13
 7 Aamp     4603.   4870    4763.   time_8_vs_0        1.03
 8 Aamp     4603.   4870    4763.   time_8_vs_4        0.978
 9 Abca12      5.29    4.25    4.14 time_8_vs_0        0.784
10 Abca12      5.29    4.25    4.14 time_8_vs_4        0.975
# ℹ 2,938 more rows
rna_mini <- rna |>
   select(gene, sample, expression) |>
   head(10)
rna_mini
# A tibble: 10 × 3
   gene    sample     expression
   <chr>   <chr>           <dbl>
 1 Asl     GSM2545336       1170
 2 Apod    GSM2545336      36194
 3 Cyp2d22 GSM2545336       4060
 4 Klk6    GSM2545336        287
 5 Fcrls   GSM2545336         85
 6 Slc2a4  GSM2545336        782
 7 Exd2    GSM2545336       1619
 8 Gjc2    GSM2545336        288
 9 Plp1    GSM2545336      43217
10 Gnb4    GSM2545336       1071
download.file(url = "https://carpentries-incubator.github.io/bioc-intro/data/annot1.csv",
              destfile = "data/annot1.csv")
annot1 <- read_csv(file = "data/annot1.csv")
annot1
# A tibble: 10 × 2
   gene    gene_description
   <chr>   <chr>
 1 Cyp2d22 cytochrome P450, family 2, subfamily d, polypeptide 22 [Source:MGI S…
 2 Klk6    kallikrein related-peptidase 6 [Source:MGI Symbol;Acc:MGI:1343166]
 3 Fcrls   Fc receptor-like S, scavenger receptor [Source:MGI Symbol;Acc:MGI:19…
 4 Plp1    proteolipid protein (myelin) 1 [Source:MGI Symbol;Acc:MGI:97623]
 5 Exd2    exonuclease 3'-5' domain containing 2 [Source:MGI Symbol;Acc:MGI:192…
 6 Apod    apolipoprotein D [Source:MGI Symbol;Acc:MGI:88056]
 7 Gnb4    guanine nucleotide binding protein (G protein), beta 4 [Source:MGI S…
 8 Slc2a4  solute carrier family 2 (facilitated glucose transporter), member 4 …
 9 Asl     argininosuccinate lyase [Source:MGI Symbol;Acc:MGI:88084]
10 Gjc2    gap junction protein, gamma 2 [Source:MGI Symbol;Acc:MGI:2153060]    
full_join(rna_mini, annot1)
Joining with `by = join_by(gene)`
# A tibble: 10 × 4
   gene    sample     expression gene_description
   <chr>   <chr>           <dbl> <chr>
 1 Asl     GSM2545336       1170 argininosuccinate lyase [Source:MGI Symbol;Acc…
 2 Apod    GSM2545336      36194 apolipoprotein D [Source:MGI Symbol;Acc:MGI:88…
 3 Cyp2d22 GSM2545336       4060 cytochrome P450, family 2, subfamily d, polype…
 4 Klk6    GSM2545336        287 kallikrein related-peptidase 6 [Source:MGI Sym…
 5 Fcrls   GSM2545336         85 Fc receptor-like S, scavenger receptor [Source…
 6 Slc2a4  GSM2545336        782 solute carrier family 2 (facilitated glucose t…
 7 Exd2    GSM2545336       1619 exonuclease 3'-5' domain containing 2 [Source:…
 8 Gjc2    GSM2545336        288 gap junction protein, gamma 2 [Source:MGI Symb…
 9 Plp1    GSM2545336      43217 proteolipid protein (myelin) 1 [Source:MGI Sym…
10 Gnb4    GSM2545336       1071 guanine nucleotide binding protein (G protein)…
download.file(url = "https://carpentries-incubator.github.io/bioc-intro/data/annot2.csv",
              destfile = "data/annot2.csv")
annot2 <- read_csv(file = "data/annot2.csv")
annot2
# A tibble: 10 × 2
   external_gene_name description
   <chr>              <chr>
 1 Cyp2d22            cytochrome P450, family 2, subfamily d, polypeptide 22 [S…
 2 Klk6               kallikrein related-peptidase 6 [Source:MGI Symbol;Acc:MGI…
 3 Fcrls              Fc receptor-like S, scavenger receptor [Source:MGI Symbol…
 4 Plp1               proteolipid protein (myelin) 1 [Source:MGI Symbol;Acc:MGI…
 5 Exd2               exonuclease 3'-5' domain containing 2 [Source:MGI Symbol;…
 6 Apod               apolipoprotein D [Source:MGI Symbol;Acc:MGI:88056]
 7 Gnb4               guanine nucleotide binding protein (G protein), beta 4 [S…
 8 Slc2a4             solute carrier family 2 (facilitated glucose transporter)…
 9 Asl                argininosuccinate lyase [Source:MGI Symbol;Acc:MGI:88084]
10 Gjc2               gap junction protein, gamma 2 [Source:MGI Symbol;Acc:MGI:…
full_join(rna_mini, annot2, by = c("gene" = "external_gene_name"))
# A tibble: 10 × 4
   gene    sample     expression description
   <chr>   <chr>           <dbl> <chr>
 1 Asl     GSM2545336       1170 argininosuccinate lyase [Source:MGI Symbol;Acc…
 2 Apod    GSM2545336      36194 apolipoprotein D [Source:MGI Symbol;Acc:MGI:88…
 3 Cyp2d22 GSM2545336       4060 cytochrome P450, family 2, subfamily d, polype…
 4 Klk6    GSM2545336        287 kallikrein related-peptidase 6 [Source:MGI Sym…
 5 Fcrls   GSM2545336         85 Fc receptor-like S, scavenger receptor [Source…
 6 Slc2a4  GSM2545336        782 solute carrier family 2 (facilitated glucose t…
 7 Exd2    GSM2545336       1619 exonuclease 3'-5' domain containing 2 [Source:…
 8 Gjc2    GSM2545336        288 gap junction protein, gamma 2 [Source:MGI Symb…
 9 Plp1    GSM2545336      43217 proteolipid protein (myelin) 1 [Source:MGI Sym…
10 Gnb4    GSM2545336       1071 guanine nucleotide binding protein (G protein)…
annot3 <- read_csv("data/annot3.csv")
full_join(rna_mini, annot3)
# A tibble: 15 × 4
   gene    sample     expression gene_description
   <chr>   <chr>           <dbl> <chr>
 1 Asl     GSM2545336       1170 argininosuccinate lyase [Source:MGI Symbol;Acc…
 2 Apod    GSM2545336      36194 apolipoprotein D [Source:MGI Symbol;Acc:MGI:88…
 3 Cyp2d22 GSM2545336       4060 cytochrome P450, family 2, subfamily d, polype…
 4 Klk6    GSM2545336        287 <NA>
 5 Fcrls   GSM2545336         85 Fc receptor-like S, scavenger receptor [Source…
 6 Slc2a4  GSM2545336        782 solute carrier family 2 (facilitated glucose t…
 7 Exd2    GSM2545336       1619 exonuclease 3'-5' domain containing 2 [Source:…
 8 Gjc2    GSM2545336        288 gap junction protein, gamma 2 [Source:MGI Symb…
 9 Plp1    GSM2545336      43217 proteolipid protein (myelin) 1 [Source:MGI Sym…
10 Gnb4    GSM2545336       1071 guanine nucleotide binding protein (G protein)…
11 mt-Tf   <NA>               NA mitochondrially encoded tRNA phenylalanine [So…
12 mt-Rnr1 <NA>               NA mitochondrially encoded 12S rRNA [Source:MGI S…
13 mt-Tv   <NA>               NA mitochondrially encoded tRNA valine [Source:MG…
14 mt-Rnr2 <NA>               NA mitochondrially encoded 16S rRNA [Source:MGI S…
15 mt-Tl1  <NA>               NA mitochondrially encoded tRNA leucine 1 [Source…
write_csv(rna_wide, file = "data_output/rna_wide.csv")
library("tidyverse")
rna <- read.csv("data/rnaseq.csv")
ggplot(data = <DATA>, mapping = aes(<MAPPINGS>)) +  <GEOM_FUNCTION>()
ggplot(data = rna)
ggplot(data = rna, mapping = aes(x = expression))
* `geom_point()` for scatter plots, dot plots, etc.
* `geom_histogram()` for histograms
* `geom_boxplot()` for, well, boxplots!
* `geom_line()` for trend lines, time series, etc.
ggplot(data = rna, mapping = aes(x = expression)) +
  geom_histogram()
`stat_bin()` using `bins = 30`. Pick better value `binwidth`.
# Assign plot to a variable
rna_plot <- ggplot(data = rna,
                   mapping = aes(x = expression))

# Draw the plot
rna_plot + geom_histogram()
`stat_bin()` using `bins = 30`. Pick better value `binwidth`.
# change bins
ggplot(rna, aes(x = expression)) +
    geom_histogram(bins = 15)
# change binwidth
ggplot(rna, aes(x = expression)) +
    geom_histogram(binwidth = 2000)
rna <- rna |>
  mutate(expression_log = log2(expression + 1))
ggplot(rna, aes(x = expression_log)) + geom_histogram()
`stat_bin()` using `bins = 30`. Pick better value `binwidth`.
ggplot(data = rna,mapping = aes(x = expression))+
  geom_histogram() +
  scale_x_log10()
Warning in scale_x_log10(): log-10 transformation introduced infinite values.
`stat_bin()` using `bins = 30`. Pick better value `binwidth`.
Warning: Removed 507 rows containing non-finite outside the scale range
(`stat_bin()`).
# This is the correct syntax for adding layers
rna_plot +
  geom_histogram()

# This will not add the new layer and will return an error message
rna_plot
  + geom_histogram()
rna_fc <- rna |> select(gene, time,
                         gene_biotype, expression_log) |>
  group_by(gene, time, gene_biotype) |>
  summarize(mean_exp = mean(expression_log)) |>
  pivot_wider(names_from = time,
              values_from = mean_exp) |>
  mutate(time_8_vs_0 = `8` - `0`, time_4_vs_0 = `4` - `0`)
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene, time, and gene_biotype.
ℹ Output is grouped by gene and time.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time, gene_biotype))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0)) +
  geom_point()
ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0)) +
  geom_point(alpha = 0.3)
ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0)) +
  geom_point(alpha = 0.3, color = "blue")
ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0)) +
  geom_point(alpha = 0.3, aes(color = gene_biotype))
ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0,
                                color = gene_biotype)) +
  geom_point(alpha = 0.3)
ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0,
                                color = gene_biotype)) +
  geom_point(alpha = 0.3) +
  geom_abline(intercept = 0)
ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0,
                                color = gene_biotype)) +
  geom_jitter(alpha = 0.3) +
  geom_abline(intercept = 0)
install.packages("hexbin")
library("hexbin")

ggplot(data = rna_fc, mapping = aes(x = time_4_vs_0, y = time_8_vs_0)) +
  geom_hex() +
  geom_abline(intercept = 0)
ggplot(data = rna, mapping = aes(y = expression_log, x = sample)) +
    geom_point(aes(color = time))
ggplot(data = rna,
         mapping = aes(y = expression_log, x = sample)) +
  geom_boxplot()
ggplot(data = rna,
         mapping = aes(y = expression_log, x = sample)) +
  geom_jitter(alpha = 0.2, color = "tomato") +
  geom_boxplot(alpha = 0)
ggplot(data = rna,
         mapping = aes(y = expression_log, x = sample)) +
  geom_boxplot(alpha = 0) +
  geom_jitter(alpha = 0.2, color = "tomato")
ggplot(data = rna,
         mapping = aes(y = expression_log, x = sample)) +
  geom_jitter(alpha = 0.2, color = "tomato") +
  geom_boxplot(alpha = 0) +
  theme(axis.text.x = element_text(angle = 90,  hjust = 0.5, vjust = 0.5))
# time as integer
ggplot(data = rna,
         mapping = aes(y = expression_log,
                       x = sample)) +
  geom_jitter(alpha = 0.2, aes(color = time)) +
  geom_boxplot(alpha = 0) +
  theme(axis.text.x = element_text(angle = 90,  hjust = 0.5, vjust = 0.5))
# time as factor
ggplot(data = rna,
         mapping = aes(y = expression_log,
                       x = sample)) +
  geom_jitter(alpha = 0.2, aes(color = as.factor(time))) +
  geom_boxplot(alpha = 0) +
  theme(axis.text.x = element_text(angle = 90,  hjust = 0.5, vjust = 0.5))
ggplot(data = rna,
         mapping = aes(y = expression_log, x = sample)) +
  geom_violin(aes(fill = as.factor(time))) +
  theme(axis.text.x = element_text(angle = 90,  hjust = 0.5, vjust = 0.5))
ggplot(data = rna,
         mapping = aes(y = expression_log, x = sample)) +
  geom_violin(aes(fill = sex)) +
  theme(axis.text.x = element_text(angle = 90,  hjust = 0.5, vjust = 0.5))
rna_fc <- rna_fc |> arrange(desc(time_8_vs_0))

genes_selected <- rna_fc$gene[1:10]

sub_rna <- rna |>
    filter(gene %in% genes_selected)

mean_exp_by_time <- sub_rna |>
  group_by(gene,time) |>
    summarize(mean_exp = mean(expression_log))
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene and time.
ℹ Output is grouped by gene.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
mean_exp_by_time
# A tibble: 30 × 3
# Groups:   gene [10]
   gene   time mean_exp
   <chr> <int>    <dbl>
 1 Acr       0     5.07
 2 Acr       4     5.54
 3 Acr       8     7.31
 4 Aipl1     0     3.70
 5 Aipl1     4     3.89
 6 Aipl1     8     6.56
 7 Bst1      0     3.20
 8 Bst1      4     3.77
 9 Bst1      8     5.22
10 Chil3     0     4.00
# ℹ 20 more rows
ggplot(data = mean_exp_by_time, mapping = aes(x = time, y = mean_exp)) +
  geom_line()
ggplot(data = mean_exp_by_time,
       mapping = aes(x = time, y = mean_exp, group = gene)) +
  geom_line()
ggplot(data = mean_exp_by_time,
       mapping = aes(x = time, y = mean_exp, color = gene)) +
  geom_line()
ggplot(data = mean_exp_by_time,
       mapping = aes(x = time, y = mean_exp)) + geom_line() +
  facet_wrap(~ gene)
ggplot(data = mean_exp_by_time,
       mapping = aes(x = time, y = mean_exp)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y")
mean_exp_by_time_sex <- sub_rna |>
  group_by(gene, time, sex) |>
    summarize(mean_exp = mean(expression_log))
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by gene, time, and sex.
ℹ Output is grouped by gene and time.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(gene, time, sex))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
mean_exp_by_time_sex
# A tibble: 60 × 4
# Groups:   gene, time [30]
   gene   time sex    mean_exp
   <chr> <int> <chr>     <dbl>
 1 Acr       0 Female     5.13
 2 Acr       0 Male       5.00
 3 Acr       4 Female     5.93
 4 Acr       4 Male       5.15
 5 Acr       8 Female     7.27
 6 Acr       8 Male       7.36
 7 Aipl1     0 Female     3.67
 8 Aipl1     0 Male       3.73
 9 Aipl1     4 Female     4.07
10 Aipl1     4 Male       3.72
# ℹ 50 more rows
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y")
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank())
mean_exp_by_chromosome <- rna |>
  group_by(chromosome_name, time) |>
  summarize(mean_exp = mean(expression_log))
`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by chromosome_name and time.
ℹ Output is grouped by chromosome_name.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(chromosome_name, time))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.
ggplot(data = mean_exp_by_chromosome, mapping = aes(x = time,
                                y = mean_exp)) +
  geom_line() +
  facet_wrap(~ chromosome_name, scales = "free_y")
# One column, facet by rows
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = gene)) +
  geom_line() +
  facet_grid(sex ~ .)
# One row, facet by column
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = gene)) +
  geom_line() +
  facet_grid(. ~ sex)
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank()) +
  labs(title = "Mean gene expression by duration of the infection",
       x = "Duration of the infection (in days)",
       y = "Mean gene expression")
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank()) +
  labs(title = "Mean gene expression by duration of the infection",
       x = "Duration of the infection (in days)",
       y = "Mean gene expression")  +
  theme(text = element_text(size = 16))
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank()) +
  labs(title = "Mean gene expression by duration of the infection",
       x = "Duration of the infection (in days)",
       y = "Mean gene expression")  +
  theme(text = element_text(size = 16),
        axis.text.x = element_text(colour = "royalblue4", size = 12),
        axis.text.y = element_text(colour = "royalblue4", size = 12),
        panel.grid = element_line(colour="lightsteelblue1"),
        legend.position = "top")
blue_theme <- theme(axis.text.x = element_text(colour = "royalblue4",
                                               size = 12),
                    axis.text.y = element_text(colour = "royalblue4",
                                               size = 12),
                    text = element_text(size = 16),
                    panel.grid = element_line(colour="lightsteelblue1"))

ggplot(rna, aes(x = expression_log)) +
  geom_histogram(bins = 20) +
    blue_theme
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank())
# change the thickness of the lines
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line(size=1.5) +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank())
Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.
This warning is displayed once per session.
Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
generated.
# change the name of the legend and the labels
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank()) +
  scale_color_discrete(name = "Gender", labels = c("F", "M"))
# using a different color palette
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank()) +
  scale_color_brewer(name = "Gender", labels = c("F", "M"), palette = "Dark2")
# manually specifying the colors
ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  theme_bw() +
  theme(panel.grid = element_blank()) +
  scale_color_manual(name = "Gender",  labels = c("F", "M"),
                     values = c("royalblue", "deeppink"))
rna$chromosome_name <- factor(rna$chromosome_name,
                               levels = c(1:19,"X","Y"))

count_gene_chromosome <- rna |>
  select(chromosome_name, gene) |>
  distinct() |> ggplot() +
  geom_bar(aes(x = chromosome_name), fill = "seagreen",
           position = "dodge", stat = "count") +
  labs(y = "log10(n genes)", x = "chromosome") +
  scale_y_log10()

count_gene_chromosome
exp_boxplot_sex <- ggplot(rna, aes(y=expression_log, x = as.factor(time),
                 color=sex)) +
   geom_boxplot(alpha = 0) +
  labs(y = "Mean gene exp",
       x = "time") + theme(legend.position = "none")

exp_boxplot_sex
install.packages("patchwork")
library("patchwork")
count_gene_chromosome + exp_boxplot_sex
## or count_gene_chromosome | exp_boxplot_sex
count_gene_chromosome / exp_boxplot_sex
count_gene_chromosome + exp_boxplot_sex + plot_layout(ncol = 1)
count_gene_chromosome +
 (count_gene_chromosome + exp_boxplot_sex) +
 exp_boxplot_sex +
 plot_layout(ncol = 1)
count_gene_chromosome /
 (count_gene_chromosome | exp_boxplot_sex) /
 exp_boxplot_sex
install.packages("gridExtra")
library("gridExtra")
grid.arrange(count_gene_chromosome, exp_boxplot_sex, ncol = 2)
my_plot <- ggplot(data = mean_exp_by_time_sex,
       mapping = aes(x = time, y = mean_exp, color = sex)) +
  geom_line() +
  facet_wrap(~ gene, scales = "free_y") +
  labs(title = "Mean gene expression by duration of the infection",
         x = "Duration of the infection (in days)",
         y = "Mean gene expression") +
  guides(color=guide_legend(title="Gender")) +
  theme_bw() +
  theme(axis.text.x = element_text(colour = "royalblue4", size = 12),
        axis.text.y = element_text(colour = "royalblue4", size = 12),
        text = element_text(size = 16),
        panel.grid = element_line(colour="lightsteelblue1"),
        legend.position = "top")
ggsave("fig_output/mean_exp_by_time_sex.png", my_plot, width = 15,
       height = 10)

# This also works for grid.arrange() plots
combo_plot <- grid.arrange(count_gene_chromosome, exp_boxplot_sex,
                           ncol = 2, widths = c(4, 6))
ggsave("fig_output/combo_plot_chromosome_sex.png", combo_plot,
       width = 10, dpi = 300)
par(mfrow = c(1, 3))
plot(1:20, main = "First layer, produced with plot(1:20)")

plot(1:20, main = "A horizontal red line, added with abline(h = 10)")
abline(h = 10, col = "red")

plot(1:20, main = "A rectangle, added with rect(5, 5, 15, 15)")
abline(h = 10, col = "red")
rect(5, 5, 15, 15, lwd = 3)
par(mfrow = c(2, 2))
boxplot(rnorm(100),
        main = "Boxplot of rnorm(100)")
boxplot(matrix(rnorm(100), ncol = 10),
        main = "Boxplot of matrix(rnorm(100), ncol = 10)")
hist(rnorm(100))
hist(matrix(rnorm(100), ncol = 10))
count_matrix <- read.csv("data/count_matrix.csv",
                         row.names = 1) |>
    as.matrix()

count_matrix[1:5, ]
        GSM2545336 GSM2545337 GSM2545338 GSM2545339 GSM2545340 GSM2545341
Asl           1170        361        400        586        626        988
Apod         36194      10347       9173      10620      13021      29594
Cyp2d22       4060       1616       1603       1901       2171       3349
Klk6           287        629        641        578        448        195
Fcrls           85        233        244        237        180         38
        GSM2545342 GSM2545343 GSM2545344 GSM2545345 GSM2545346 GSM2545347
Asl            836        535        586        597        938       1035
Apod         24959      13668      13230      15868      27769      34301
Cyp2d22       3122       2008       2254       2277       2985       3452
Klk6           186       1101        537        567        327        233
Fcrls           68        375        199        177         89         67
        GSM2545348 GSM2545349 GSM2545350 GSM2545351 GSM2545352 GSM2545353
Asl            494        481        666        937        803        541
Apod         11258      11812      15816      29242      20415      13682
Cyp2d22       1883       2014       2417       3678       2920       2216
Klk6           742        881        828        250        798        710
Fcrls          300        233        231         81        303        285
        GSM2545354 GSM2545362 GSM2545363 GSM2545380
Asl            473        748        576       1192
Apod         11088      15916      11166      38148
Cyp2d22       1821       2842       2011       4019
Klk6           894        501        598        259
Fcrls          248        179        184         68
dim(count_matrix)
[1] 1474   22
sample_metadata <- read.csv("data/sample_metadata.csv")
sample_metadata
       sample     organism age    sex   infection  strain time     tissue mouse
1  GSM2545336 Mus musculus   8 Female  InfluenzaA C57BL/6    8 Cerebellum    14
2  GSM2545337 Mus musculus   8 Female NonInfected C57BL/6    0 Cerebellum     9
3  GSM2545338 Mus musculus   8 Female NonInfected C57BL/6    0 Cerebellum    10
4  GSM2545339 Mus musculus   8 Female  InfluenzaA C57BL/6    4 Cerebellum    15
5  GSM2545340 Mus musculus   8   Male  InfluenzaA C57BL/6    4 Cerebellum    18
6  GSM2545341 Mus musculus   8   Male  InfluenzaA C57BL/6    8 Cerebellum     6
7  GSM2545342 Mus musculus   8 Female  InfluenzaA C57BL/6    8 Cerebellum     5
8  GSM2545343 Mus musculus   8   Male NonInfected C57BL/6    0 Cerebellum    11
9  GSM2545344 Mus musculus   8 Female  InfluenzaA C57BL/6    4 Cerebellum    22
10 GSM2545345 Mus musculus   8   Male  InfluenzaA C57BL/6    4 Cerebellum    13
11 GSM2545346 Mus musculus   8   Male  InfluenzaA C57BL/6    8 Cerebellum    23
12 GSM2545347 Mus musculus   8   Male  InfluenzaA C57BL/6    8 Cerebellum    24
13 GSM2545348 Mus musculus   8 Female NonInfected C57BL/6    0 Cerebellum     8
14 GSM2545349 Mus musculus   8   Male NonInfected C57BL/6    0 Cerebellum     7
15 GSM2545350 Mus musculus   8   Male  InfluenzaA C57BL/6    4 Cerebellum     1
16 GSM2545351 Mus musculus   8 Female  InfluenzaA C57BL/6    8 Cerebellum    16
17 GSM2545352 Mus musculus   8 Female  InfluenzaA C57BL/6    4 Cerebellum    21
18 GSM2545353 Mus musculus   8 Female NonInfected C57BL/6    0 Cerebellum     4
19 GSM2545354 Mus musculus   8   Male NonInfected C57BL/6    0 Cerebellum     2
20 GSM2545362 Mus musculus   8 Female  InfluenzaA C57BL/6    4 Cerebellum    20
21 GSM2545363 Mus musculus   8   Male  InfluenzaA C57BL/6    4 Cerebellum    12
22 GSM2545380 Mus musculus   8 Female  InfluenzaA C57BL/6    8 Cerebellum    19
dim(sample_metadata)
[1] 22  9
gene_metadata <- read.csv("data/gene_metadata.csv")
gene_metadata[1:10, 1:4]
      gene ENTREZID
1      Asl   109900
2     Apod    11815
3  Cyp2d22    56448
4     Klk6    19144
5    Fcrls    80891
6   Slc2a4    20528
7     Exd2    97827
8     Gjc2   118454
9     Plp1    18823
10    Gnb4    14696
                                                                         product
1                                 argininosuccinate lyase, transcript variant X1
2                                         apolipoprotein D, transcript variant 3
3   cytochrome P450, family 2, subfamily d, polypeptide 22, transcript variant 2
4                           kallikrein related-peptidase 6, transcript variant 2
5                  Fc receptor-like S, scavenger receptor, transcript variant X1
6            solute carrier family 2 (facilitated glucose transporter), member 4
7                                          exonuclease 3'-5' domain containing 2
8                            gap junction protein, gamma 2, transcript variant 1
9                           proteolipid protein (myelin) 1, transcript variant 1
10 guanine nucleotide binding protein (G protein), beta 4, transcript variant X2
      ensembl_gene_id
1  ENSMUSG00000025533
2  ENSMUSG00000022548
3  ENSMUSG00000061740
4  ENSMUSG00000050063
5  ENSMUSG00000015852
6  ENSMUSG00000018566
7  ENSMUSG00000032705
8  ENSMUSG00000043448
9  ENSMUSG00000031425
10 ENSMUSG00000027669
dim(gene_metadata)
[1] 1474    9
## BiocManager::install("SummarizedExperiment")
library("SummarizedExperiment")
stopifnot(rownames(count_matrix) == gene_metadata$gene)
stopifnot(colnames(count_matrix) == sample_metadata$sample)
se <- SummarizedExperiment(assays = list(counts = count_matrix),
                           colData = sample_metadata,
                           rowData = gene_metadata)
se
class: SummarizedExperiment
dim: 1474 22
metadata(0):
assays(1): counts
rownames(1474): Asl Apod ... Lmx1a Pbx1
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(22): GSM2545336 GSM2545337 ... GSM2545363 GSM2545380
colData names(9): sample organism ... tissue mouse
saveRDS(se, file = "data_output/se.rds")
rm(se)
se <- readRDS("data_output/se.rds")
head(se)
head(assay(se))
        GSM2545336 GSM2545337 GSM2545338 GSM2545339 GSM2545340 GSM2545341
Asl           1170        361        400        586        626        988
Apod         36194      10347       9173      10620      13021      29594
Cyp2d22       4060       1616       1603       1901       2171       3349
Klk6           287        629        641        578        448        195
Fcrls           85        233        244        237        180         38
Slc2a4         782        231        248        265        313        786
        GSM2545342 GSM2545343 GSM2545344 GSM2545345 GSM2545346 GSM2545347
Asl            836        535        586        597        938       1035
Apod         24959      13668      13230      15868      27769      34301
Cyp2d22       3122       2008       2254       2277       2985       3452
Klk6           186       1101        537        567        327        233
Fcrls           68        375        199        177         89         67
Slc2a4         528        249        266        357        654        693
        GSM2545348 GSM2545349 GSM2545350 GSM2545351 GSM2545352 GSM2545353
Asl            494        481        666        937        803        541
Apod         11258      11812      15816      29242      20415      13682
Cyp2d22       1883       2014       2417       3678       2920       2216
Klk6           742        881        828        250        798        710
Fcrls          300        233        231         81        303        285
Slc2a4         271        304        349        715        513        320
        GSM2545354 GSM2545362 GSM2545363 GSM2545380
Asl            473        748        576       1192
Apod         11088      15916      11166      38148
Cyp2d22       1821       2842       2011       4019
Klk6           894        501        598        259
Fcrls          248        179        184         68
Slc2a4         248        350        317        796
dim(assay(se))
[1] 1474   22
colData(se)
DataFrame with 22 rows and 9 columns
                sample     organism       age         sex   infection
           <character>  <character> <integer> <character> <character>
GSM2545336  GSM2545336 Mus musculus         8      Female  InfluenzaA
GSM2545337  GSM2545337 Mus musculus         8      Female NonInfected
GSM2545338  GSM2545338 Mus musculus         8      Female NonInfected
GSM2545339  GSM2545339 Mus musculus         8      Female  InfluenzaA
GSM2545340  GSM2545340 Mus musculus         8        Male  InfluenzaA
...                ...          ...       ...         ...         ...
GSM2545353  GSM2545353 Mus musculus         8      Female NonInfected
GSM2545354  GSM2545354 Mus musculus         8        Male NonInfected
GSM2545362  GSM2545362 Mus musculus         8      Female  InfluenzaA
GSM2545363  GSM2545363 Mus musculus         8        Male  InfluenzaA
GSM2545380  GSM2545380 Mus musculus         8      Female  InfluenzaA
                strain      time      tissue     mouse
           <character> <integer> <character> <integer>
GSM2545336     C57BL/6         8  Cerebellum        14
GSM2545337     C57BL/6         0  Cerebellum         9
GSM2545338     C57BL/6         0  Cerebellum        10
GSM2545339     C57BL/6         4  Cerebellum        15
GSM2545340     C57BL/6         4  Cerebellum        18
...                ...       ...         ...       ...
GSM2545353     C57BL/6         0  Cerebellum         4
GSM2545354     C57BL/6         0  Cerebellum         2
GSM2545362     C57BL/6         4  Cerebellum        20
GSM2545363     C57BL/6         4  Cerebellum        12
GSM2545380     C57BL/6         8  Cerebellum        19
dim(colData(se))
[1] 22  9
head(rowData(se))
DataFrame with 6 rows and 9 columns
               gene  ENTREZID                product    ensembl_gene_id
        <character> <integer>            <character>        <character>
Asl             Asl    109900 argininosuccinate ly.. ENSMUSG00000025533
Apod           Apod     11815 apolipoprotein D, tr.. ENSMUSG00000022548
Cyp2d22     Cyp2d22     56448 cytochrome P450, fam.. ENSMUSG00000061740
Klk6           Klk6     19144 kallikrein related-p.. ENSMUSG00000050063
Fcrls         Fcrls     80891 Fc receptor-like S, .. ENSMUSG00000015852
Slc2a4       Slc2a4     20528 solute carrier famil.. ENSMUSG00000018566
        external_synonym chromosome_name   gene_biotype  phenotype_description
             <character>     <character>    <character>            <character>
Asl        2510006M18Rik               5 protein_coding abnormal circulating..
Apod                  NA              16 protein_coding abnormal lipid homeo..
Cyp2d22             2D22              15 protein_coding abnormal skin morpho..
Klk6                Bssp               7 protein_coding abnormal cytokine le..
Fcrls      2810439C17Rik               3 protein_coding decreased CD8-positi..
Slc2a4            Glut-4              11 protein_coding abnormal circulating..
        hsapiens_homolog_associated_gene_name
                                  <character>
Asl                                       ASL
Apod                                     APOD
Cyp2d22                                CYP2D6
Klk6                                     KLK6
Fcrls                                   FCRL2
Slc2a4                                 SLC2A4
dim(rowData(se))
[1] 1474    9
se1 <- se[1:5, 1:3]
se1
class: SummarizedExperiment
dim: 5 3
metadata(0):
assays(1): counts
rownames(5): Asl Apod Cyp2d22 Klk6 Fcrls
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(3): GSM2545336 GSM2545337 GSM2545338
colData names(9): sample organism ... tissue mouse
colData(se1)
DataFrame with 3 rows and 9 columns
                sample     organism       age         sex   infection
           <character>  <character> <integer> <character> <character>
GSM2545336  GSM2545336 Mus musculus         8      Female  InfluenzaA
GSM2545337  GSM2545337 Mus musculus         8      Female NonInfected
GSM2545338  GSM2545338 Mus musculus         8      Female NonInfected
                strain      time      tissue     mouse
           <character> <integer> <character> <integer>
GSM2545336     C57BL/6         8  Cerebellum        14
GSM2545337     C57BL/6         0  Cerebellum         9
GSM2545338     C57BL/6         0  Cerebellum        10
rowData(se1)
DataFrame with 5 rows and 9 columns
               gene  ENTREZID                product    ensembl_gene_id
        <character> <integer>            <character>        <character>
Asl             Asl    109900 argininosuccinate ly.. ENSMUSG00000025533
Apod           Apod     11815 apolipoprotein D, tr.. ENSMUSG00000022548
Cyp2d22     Cyp2d22     56448 cytochrome P450, fam.. ENSMUSG00000061740
Klk6           Klk6     19144 kallikrein related-p.. ENSMUSG00000050063
Fcrls         Fcrls     80891 Fc receptor-like S, .. ENSMUSG00000015852
        external_synonym chromosome_name   gene_biotype  phenotype_description
             <character>     <character>    <character>            <character>
Asl        2510006M18Rik               5 protein_coding abnormal circulating..
Apod                  NA              16 protein_coding abnormal lipid homeo..
Cyp2d22             2D22              15 protein_coding abnormal skin morpho..
Klk6                Bssp               7 protein_coding abnormal cytokine le..
Fcrls      2810439C17Rik               3 protein_coding decreased CD8-positi..
        hsapiens_homolog_associated_gene_name
                                  <character>
Asl                                       ASL
Apod                                     APOD
Cyp2d22                                CYP2D6
Klk6                                     KLK6
Fcrls                                   FCRL2
se1 <- se[rowData(se)$gene_biotype == "miRNA",
          colData(se)$infection == "NonInfected"]
se1
class: SummarizedExperiment
dim: 7 7
metadata(0):
assays(1): counts
rownames(7): Mir1901 Mir378a ... Mir128-1 Mir7682
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(7): GSM2545337 GSM2545338 ... GSM2545353 GSM2545354
colData names(9): sample organism ... tissue mouse
assay(se1)
         GSM2545337 GSM2545338 GSM2545343 GSM2545348 GSM2545349 GSM2545353
Mir1901          45         44         74         55         68         33
Mir378a          11          7          9          4         12          4
Mir133b           4          6          5          4          6          7
Mir30c-2         10          6         16         12          8         17
Mir149            1          2          0          0          0          0
Mir128-1          4          1          2          2          1          2
Mir7682           2          0          4          1          3          5
         GSM2545354
Mir1901          60
Mir378a           8
Mir133b           3
Mir30c-2         15
Mir149            2
Mir128-1          1
Mir7682           5
colData(se1)
DataFrame with 7 rows and 9 columns
                sample     organism       age         sex   infection
           <character>  <character> <integer> <character> <character>
GSM2545337  GSM2545337 Mus musculus         8      Female NonInfected
GSM2545338  GSM2545338 Mus musculus         8      Female NonInfected
GSM2545343  GSM2545343 Mus musculus         8        Male NonInfected
GSM2545348  GSM2545348 Mus musculus         8      Female NonInfected
GSM2545349  GSM2545349 Mus musculus         8        Male NonInfected
GSM2545353  GSM2545353 Mus musculus         8      Female NonInfected
GSM2545354  GSM2545354 Mus musculus         8        Male NonInfected
                strain      time      tissue     mouse
           <character> <integer> <character> <integer>
GSM2545337     C57BL/6         0  Cerebellum         9
GSM2545338     C57BL/6         0  Cerebellum        10
GSM2545343     C57BL/6         0  Cerebellum        11
GSM2545348     C57BL/6         0  Cerebellum         8
GSM2545349     C57BL/6         0  Cerebellum         7
GSM2545353     C57BL/6         0  Cerebellum         4
GSM2545354     C57BL/6         0  Cerebellum         2
rowData(se1)
DataFrame with 7 rows and 9 columns
                gene  ENTREZID        product    ensembl_gene_id
         <character> <integer>    <character>        <character>
Mir1901      Mir1901 100316686  microRNA 1901 ENSMUSG00000084565
Mir378a      Mir378a    723889  microRNA 378a ENSMUSG00000105200
Mir133b      Mir133b    723817  microRNA 133b ENSMUSG00000065480
Mir30c-2    Mir30c-2    723964 microRNA 30c-2 ENSMUSG00000065567
Mir149        Mir149    387167   microRNA 149 ENSMUSG00000065470
Mir128-1    Mir128-1    387147 microRNA 128-1 ENSMUSG00000065520
Mir7682      Mir7682 102466847  microRNA 7682 ENSMUSG00000106406
         external_synonym chromosome_name gene_biotype  phenotype_description
              <character>     <character>  <character>            <character>
Mir1901          Mirn1901              18        miRNA                     NA
Mir378a           Mirn378              18        miRNA abnormal mitochondri..
Mir133b          mir 133b               1        miRNA no abnormal phenotyp..
Mir30c-2        mir 30c-2               1        miRNA                     NA
Mir149            Mirn149               1        miRNA increased circulatin..
Mir128-1          Mirn128               1        miRNA no abnormal phenotyp..
Mir7682      mmu-mir-7682               1        miRNA                     NA
         hsapiens_homolog_associated_gene_name
                                   <character>
Mir1901                                     NA
Mir378a                                MIR378A
Mir133b                                MIR133B
Mir30c-2                               MIR30C2
Mir149                                      NA
Mir128-1                              MIR128-1
Mir7682                                     NA
assay(se)[1:3, colData(se)$time != 4]
        GSM2545336 GSM2545337 GSM2545338 GSM2545341 GSM2545342 GSM2545343
Asl           1170        361        400        988        836        535
Apod         36194      10347       9173      29594      24959      13668
Cyp2d22       4060       1616       1603       3349       3122       2008
        GSM2545346 GSM2545347 GSM2545348 GSM2545349 GSM2545351 GSM2545353
Asl            938       1035        494        481        937        541
Apod         27769      34301      11258      11812      29242      13682
Cyp2d22       2985       3452       1883       2014       3678       2216
        GSM2545354 GSM2545380
Asl            473       1192
Apod         11088      38148
Cyp2d22       1821       4019
# Equivalent to
assay(se)[1:3, colData(se)$time == 0 | colData(se)$time == 8]
        GSM2545336 GSM2545337 GSM2545338 GSM2545341 GSM2545342 GSM2545343
Asl           1170        361        400        988        836        535
Apod         36194      10347       9173      29594      24959      13668
Cyp2d22       4060       1616       1603       3349       3122       2008
        GSM2545346 GSM2545347 GSM2545348 GSM2545349 GSM2545351 GSM2545353
Asl            938       1035        494        481        937        541
Apod         27769      34301      11258      11812      29242      13682
Cyp2d22       2985       3452       1883       2014       3678       2216
        GSM2545354 GSM2545380
Asl            473       1192
Apod         11088      38148
Cyp2d22       1821       4019
rna |>
    filter(gene %in% c("Asl", "Apod", "Cyd2d22")) |>
    filter(time != 4) |>
    select(expression)
# A tibble: 28 × 1
   expression
        <dbl>
 1       1170
 2      36194
 3        361
 4      10347
 5        400
 6       9173
 7        988
 8      29594
 9        836
10      24959
# ℹ 18 more rows
colData(se)$center <- rep("University of Illinois", nrow(colData(se)))
colData(se)
DataFrame with 22 rows and 10 columns
                sample     organism       age         sex   infection
           <character>  <character> <integer> <character> <character>
GSM2545336  GSM2545336 Mus musculus         8      Female  InfluenzaA
GSM2545337  GSM2545337 Mus musculus         8      Female NonInfected
GSM2545338  GSM2545338 Mus musculus         8      Female NonInfected
GSM2545339  GSM2545339 Mus musculus         8      Female  InfluenzaA
GSM2545340  GSM2545340 Mus musculus         8        Male  InfluenzaA
...                ...          ...       ...         ...         ...
GSM2545353  GSM2545353 Mus musculus         8      Female NonInfected
GSM2545354  GSM2545354 Mus musculus         8        Male NonInfected
GSM2545362  GSM2545362 Mus musculus         8      Female  InfluenzaA
GSM2545363  GSM2545363 Mus musculus         8        Male  InfluenzaA
GSM2545380  GSM2545380 Mus musculus         8      Female  InfluenzaA
                strain      time      tissue     mouse                 center
           <character> <integer> <character> <integer>            <character>
GSM2545336     C57BL/6         8  Cerebellum        14 University of Illinois
GSM2545337     C57BL/6         0  Cerebellum         9 University of Illinois
GSM2545338     C57BL/6         0  Cerebellum        10 University of Illinois
GSM2545339     C57BL/6         4  Cerebellum        15 University of Illinois
GSM2545340     C57BL/6         4  Cerebellum        18 University of Illinois
...                ...       ...         ...       ...                    ...
GSM2545353     C57BL/6         0  Cerebellum         4 University of Illinois
GSM2545354     C57BL/6         0  Cerebellum         2 University of Illinois
GSM2545362     C57BL/6         4  Cerebellum        20 University of Illinois
GSM2545363     C57BL/6         4  Cerebellum        12 University of Illinois
GSM2545380     C57BL/6         8  Cerebellum        19 University of Illinois
se
class: SummarizedExperiment
dim: 1474 22
metadata(0):
assays(1): counts
rownames(1474): Asl Apod ... Lmx1a Pbx1
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(22): GSM2545336 GSM2545337 ... GSM2545363 GSM2545380
colData names(10): sample organism ... mouse center
## BiocManager::install("tidySummarizedExperiment")
library("tidySummarizedExperiment")

se
class: SummarizedExperiment
dim: 1474 22
metadata(0):
assays(1): counts
rownames(1474): Asl Apod ... Lmx1a Pbx1
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(22): GSM2545336 GSM2545337 ... GSM2545363 GSM2545380
colData names(10): sample organism ... mouse center
se |> filter(sample == "GSM2545336")
class: SummarizedExperiment
dim: 1474 1
metadata(1): latest_filter_scope_report
assays(1): counts
rownames(1474): Asl Apod ... Lmx1a Pbx1
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(1): GSM2545336
colData names(10): sample organism ... mouse center
se |> filter(sex == "Female")
class: SummarizedExperiment
dim: 1474 12
metadata(1): latest_filter_scope_report
assays(1): counts
rownames(1474): Asl Apod ... Lmx1a Pbx1
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(12): GSM2545336 GSM2545337 ... GSM2545362 GSM2545380
colData names(10): sample organism ... mouse center
se |> select(sample, sex)
Warning: `when()` was deprecated in purrr 1.0.0.
ℹ Please use `if` instead.
ℹ The deprecated feature was likely used in the tidySummarizedExperiment
  package.
  Please report the issue at
  <https://github.com/stemangiola/tidySummarizedExperiment/issues>.
This warning is displayed once per session.
Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
generated.
tidySummarizedExperiment says: Key columns are missing. A data frame is returned for independent data analysis.
# A tibble: 32,428 × 2
   sample     sex
   <chr>      <chr>
 1 GSM2545336 Female
 2 GSM2545336 Female
 3 GSM2545336 Female
 4 GSM2545336 Female
 5 GSM2545336 Female
 6 GSM2545336 Female
 7 GSM2545336 Female
 8 GSM2545336 Female
 9 GSM2545336 Female
10 GSM2545336 Female
# ℹ 32,418 more rows
se |> mutate(center = "Heidelberg University")
class: SummarizedExperiment
dim: 1474 22
metadata(1): latest_mutate_scope_report
assays(1): counts
rownames(1474): Asl Apod ... Lmx1a Pbx1
rowData names(9): gene ENTREZID ... phenotype_description
  hsapiens_homolog_associated_gene_name
colnames(22): GSM2545336 GSM2545337 ... GSM2545363 GSM2545380
colData names(10): sample organism ... mouse center
se |>
    group_by(.sample) |>
    summarise(total_counts=sum(counts))
tidySummarizedExperiment says: A data frame is returned for independent data analysis.
# A tibble: 22 × 2
   .sample    total_counts
   <chr>             <int>
 1 GSM2545336      3039671
 2 GSM2545337      2602360
 3 GSM2545338      2458618
 4 GSM2545339      2500082
 5 GSM2545340      2479024
 6 GSM2545341      2413723
 7 GSM2545342      2349728
 8 GSM2545343      3105652
 9 GSM2545344      2524137
10 GSM2545345      2506038
# ℹ 12 more rows
se |>
    ggplot(aes(counts + 1, group=.sample, color=infection)) +
    geom_density() +
    scale_x_log10() +
    theme_bw()

良好的名称	良好的替代方案	避免
Max_temp_C	MaxTemp	Maximum Temp (°C)
Precipitation_mm	Precipitation	precmm
Mean_year_growth	MeanYearGrowth	Mean growth/year
sex	sex	M/F
weight	weight	w.
cell_type	CellType	Cell Type
Observation_01	first_observation	1st Obs

列	描述
gene	所测量的基因名称
sample	测量基因表达的样本名称
expression	基因表达的值
organism	生物体/物种 —— 此处所有数据均来自小鼠
age	小鼠的年龄（此处所有小鼠均为 8 周龄）
sex	小鼠的性别
infection	小鼠的感染状态，即是否感染甲型流感。
strain	甲型流感毒株。
time	感染持续时间（以天为单位）。
tissue	用于基因表达实验的组织，即小脑或脊髓。
mouse	小鼠唯一标识符。

课程总览

概述

问题

学习目标

电子表格软件

电子表格大纲

本课程不会教你的内容

为什么我们不教使用电子表格进行数据分析？

挑战：与邻座讨论以下要点

电子表格的问题

使用电子表格进行数据录入与清洗

在电子表格中格式化数据表

记录您的分析过程

电子表格中的数据结构

挑战：我们将处理一个杂乱的数据集，并描述如何对其进行清洗。

挑战：在清理好数据后，请回答以下问题：

常见的电子表格错误

使用多个表格

使用多个选项卡

未填写零

使用有问题的空值

使用格式传递信息

使用格式化使数据表看起来美观

在单元格中放置注释或单位

在单元格中输入多项信息

使用有问题的字段名

在数据中使用特殊字符

在数据表中包含元数据

导出数据

关于逗号的注意事项

总结

概述

问题

学习目标

什么是 R？什么是 RStudio？

为什么要学习 R？

R 不需要频繁地点击操作，而这正是其优势所在。

R 代码有助于实现可复现性

R 具有跨学科性和可扩展性

R 适用于各种形状和规模的数据

R 能生成高质量的图表

R 拥有一个规模庞大且热情友好的社区

R 不仅免费，而且还是开源且跨平台的

熟悉 RStudio 的用法

设置指南

整理工作目录

挑战：创建项目目录结构

工作目录

与 R 交互

如何在课程期间及课程结束后进一步学习？

寻求帮助

使用 RStudio 内置的帮助界面搜索更多关于 R 函数的信息

我知道想要使用的函数名称，但不确定如何使用它

R

R

我想使用一个能实现 X 功能的函数，肯定有相应的函数，但我不知道是哪一个……

R

我卡住了……收到了一条我不理解的错误消息

寻求帮助

R

输出

R

R

R

输出

在哪里寻求帮助？

更多资源

R 包

加载包

R

安装包

R

R

R

概述

问题

学习目标

在 R 中创建对象

R

输出