Skip to content

GitLab

S
stat_methods_bioinf
Commit af74e54f authored by Bernd Klaus's avatar Bernd Klaus
Browse files
Options

extended the introduction of the data handling lab, added a section on joins and a basic R intro

parent 8da24947
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 1361 additions and 216 deletions
data_handling_bioinf.R
View file @ af74e54f
......@@ -36,21 +36,155 @@ library("limma")
library("Single.mTEC.Transcriptomes")
theme_set(theme_gray(base_size = 18))
library(BiocParallel)
multicoreParam <- MulticoreParam(workers = round(parallel::detectCores() * 0.5))
register(multicoreParam)
data_dir <- file.path("data/")
## ----save_qc_data, eval=FALSE, echo=FALSE--------------------------------
## data("percentsGG")
##
## sc_qc_stats <- as_tibble(percentsGG)
## save(sc_qc_stats, file = file.path(data_dir, "sc_qc_stats.RData"),
## compress = "xz")
## ----simple_ex, echo = TRUE----------------------------------------------
4 + 6
## ----simple_ex_2, echo = TRUE--------------------------------------------
x <- 6
y <- 4
z <- x + y
z
## ----simple_ex_3, echo = TRUE--------------------------------------------
ls()
## ----simple_ex_4, echo = TRUE--------------------------------------------
sqrt(16)
## ----simple_ex_5, echo = TRUE--------------------------------------------
z <- c(5, 9, 1, 0)
## ----simple_ex_5b, echo = TRUE-------------------------------------------
x <- c(5, 9)
y <- c(1, 0)
z <- c(x, y)
## ----simple_ex_6, echo = TRUE--------------------------------------------
seq(1, 9, by = 2)
seq(8, 20, length = 6)
## ----simple_ex_7, echo = TRUE--------------------------------------------
x <- seq(1, 10)
## ----simple_ex_8, echo = TRUE--------------------------------------------
rep(1:3, 6)
rep(1:3, times = c(6, 6, 6))
## ----vec-----------------------------------------------------------------
x <- 1:5
y <- 5:1
x + y
x^2
x * y
## ----vec-2---------------------------------------------------------------
x <- c(6, 8 , 9 )
x + 2
## ----summary_1, echo = TRUE--------------------------------------------
x <- c(7.5, 8.2, 3.1, 5.6, 8.2, 9.3, 6.5, 7.0, 9.3, 1.2, 14.5, 6.2)
mean(x)
var(x)
summary(x)
## ----subscr, echo = TRUE-----------------------------------------------
x[1:6]
x[7:12]
summary(x[1:6])
summary(x[7:12])
## ----subscr_2, echo = TRUE---------------------------------------------
x[c(2, 4, 9)]
x[-(1:6)]
head(x)
## ----sort-rank, echo = TRUE--------------------------------------------
x <- c(1.3, 3.5, 2.7, 6.3, 6.3)
sort(x)
order(x)
x[order(x)]
rank(x)
## ----cbind-ex, echo = TRUE---------------------------------------------
x <- c(5, 7 , 9)
y <- c(6, 3 , 4)
z <- cbind(x, y)
z
dim(z)
## ----matrix_direct, echo = TRUE----------------------------------------
z <- matrix(c(5, 7, 9, 6, 3, 4), nrow = 3)
## ----Matrix-ex, echo = TRUE--------------------------------------------
z <- matrix(c(5, 7 , 9 , 6 , 3 , 4), nrow = 3, byrow = TRUE)
z
## ----Matrix-op, echo = TRUE--------------------------------------------
y <- matrix(c(1, 3, 0, 9, 5, -1), nrow = 3, byrow = TRUE)
y
y + z
y * z
## ----Matrix-op-4, echo = TRUE------------------------------------------
z[1, 1]
z[, 2]
z[1:2, ]
z[-1, ]
z[-c(1, 2), ]
## ----load-Patients, echo = TRUE----------------------------------------
pat <- read_csv("http://www-huber.embl.de/users/klaus/BasicR/Patients.csv")
pat
glimpse(pat)
## ----subset_data---------------------------------------------------------
pat_tiny <- filter(pat, Height < 1.7)
select(pat_tiny, PatientId, Height, Gender)
## ----light_and_small_patients, echo = TRUE-----------------------------
filter(pat, Height < 1.5, Gender == "f")
## ----light_or_small_patients, echo = TRUE------------------------------
filter(pat, (Height < 1.5) | (Gender == "f"))
## ----list_example, echo = TRUE-----------------------------------------
L <- list(one = 1, two = c(1, 2), five = seq(1, 4, length = 5),
list(string = "Hello World"))
L
## ----list_access, echo = TRUE------------------------------------------
names(L)
L$five + 10
L[[3]] + 10
## ------------------------------------------------------------------------
L[[4]]$string
L[2]
## ----list-example_df, echo = TRUE--------------------------------------
pat$Height
pat[[2]]
pat[["Gender"]]
## ----acces_recap---------------------------------------------------------
sample_vector <- c("Alice" = 5.4, "Bob" = 3.7, "Claire" = 8.8)
sample_vector
## ----access_index, dependson="accesRecap"--------------------------------
sample_vector[1:2]
sample_vector[-(1:2)]
## ----access_boolean, dependson="acces_recap"-----------------------------
sample_vector[c(TRUE, FALSE, TRUE)]
## ----access_boolean2, dependson="acces_recap"----------------------------
sample_vector[sample_vector < 6]
## ----access_name---------------------------------------------------------
sample_vector[c("Alice", "Claire")]
## ----load_inspect_qc_data------------------------------------------------
load(file.path(data_dir, "sc_qc_stats.RData"))
......@@ -133,7 +267,33 @@ worst_cells <- group_by(sc_qc_stats, batch, type ) %>%
worst_cells
## ----ex_high_qual--------------------------------------------------------
## ----data_q_pcr----------------------------------------------------------
q_pcr <- read_csv("qPCR.csv")
sample_n(q_pcr, 5)
## ----add_rep_info--------------------------------------------------------
q_pcr <- q_pcr %>%
group_by(sample_name) %>%
{.$replicate = c("r_1", "r_2")
.} %>% ungroup
head(q_pcr)
## ----sum_across_reps, dependson="add_rep_info"---------------------------
summary_across_reps <- group_by(q_pcr,
sample_name,
target_Name) %>%
dplyr::summarize(mean = mean(C_T, na.rm = TRUE),
spread = abs(diff(C_T))) %>%
ungroup()
sample_n(summary_across_reps, 5)
## ----left_join_summ, dependson="sum_across_reps"-------------------------
augmented_table <- left_join(q_pcr, summary_across_reps )
sample_n(augmented_table, 5)
## ----ex_high_qual, echo=FALSE, results="hide"----------------------------
hq_cells <- group_by(sc_qc_stats, type, percent) %>%
mutate(high_qual = percent > 60) %>%
......@@ -147,7 +307,7 @@ prop_hgh_qual <- group_by(hq_cells, type, percent, high_qual) %>%
mutate(perc_qual = n / sum(n))
## ----ex_high_qual_batch--------------------------------------------------
## ----ex_high_qual_batch, echo=FALSE, results="hide"----------------------
group_by(hq_cells, batch) %>%
filter(type == "concordantUniq") %>%
......
data_handling_bioinf.Rmd
View file @ af74e54f
This diff is collapsed.
data_handling_bioinf.html
View file @ af74e54f
This diff is collapsed.
qPCR.csv 0 → 100644
View file @ af74e54f
sample_name,target_Name,C_T
WT,gene_a,24.8207817077637
WT,gene_a,25.9677886962891
b8,gene_a,24.4559593200684
b8,gene_a,24.4405784606934
F3,gene_a,23.6839485168457
F3,gene_a,24.2055950164795
F36,gene_a,33.1261901855469
F36,gene_a,28.3654613494873
F39,gene_a,24.1689414978027
F39,gene_a,23.9666805267334
E44,gene_a,27.2618999481201
E44,gene_a,23.2965393066406
WT,Nestin,26.8165702819824
WT,Nestin,26.2029857635498
b8,Nestin,NA
b8,Nestin,25.3436145782471
F3,Nestin,22.0685329437256
F3,Nestin,22.4327087402344
F36,Nestin,33.9980049133301
F36,Nestin,31.8512554168701
F39,Nestin,24.5574321746826
F39,Nestin,24.6024322509766
E44,Nestin,24.9621963500977
E44,Nestin,28.8070507049561
WT,Olig1,27.3039169311523
WT,Olig1,26.9210567474365
b8,Olig1,25.7709541320801
b8,Olig1,25.7648391723633
F3,Olig1,27.6712665557861
F3,Olig1,25.313907623291
F36,Olig1,30.9405784606934
F36,Olig1,33.7159881591797
F39,Olig1,26.0550689697266
F39,Olig1,25.9595985412598
E44,Olig1,30.9561042785645
E44,Olig1,29.1239891052246
WT,Fgf5,31.9329700469971
WT,Fgf5,31.6467914581299
b8,Fgf5,30.1550693511963
b8,Fgf5,30.3175163269043
F3,Fgf5,25.8816261291504
F3,Fgf5,25.7737941741943
F36,Fgf5,30.9831104278564
F36,Fgf5,30.5151252746582
F39,Fgf5,27.9479236602783
F39,Fgf5,27.9073581695557
E44,Fgf5,26.9267253875732
E44,Fgf5,28.9032249450684
WT,Gapdh,18.772008895874
WT,Gapdh,18.4264850616455
b8,Gapdh,18.0875434875488
b8,Gapdh,18.0503425598145
F3,Gapdh,17.0720252990723
F3,Gapdh,17.0865039825439
F36,Gapdh,24.3258533477783
F36,Gapdh,22.45188331604
F39,Gapdh,17.8303165435791
F39,Gapdh,17.7388877868652
E44,Gapdh,18.8592185974121
E44,Gapdh,16.9910259246826
WT,gene_b,28.8529148101807
WT,gene_b,28.431526184082
b8,gene_b,28.1249256134033
b8,gene_b,28.0070934295654
F3,gene_b,29.1006412506104
F3,gene_b,27.0610027313232
F36,gene_b,35.911003112793
F36,gene_b,34.3274230957031
F39,gene_b,27.9753360748291
F39,gene_b,27.326587677002
E44,gene_b,29.3122825622559
E44,gene_b,26.9847259521484
WT,Nanog,21.4305057525635
WT,Nanog,21.3123302459717
b8,Nanog,21.8583736419678
b8,Nanog,21.9018230438232
F3,Nanog,20.1171798706055
F3,Nanog,20.1576995849609
F36,Nanog,26.0692310333252
F36,Nanog,28.4226493835449
F39,Nanog,20.6684265136719
F39,Nanog,20.0346660614014
E44,Nanog,19.6608333587646
E44,Nanog,19.5777854919434
WT,Oct4,20.9365711212158
WT,Oct4,20.7781562805176
b8,Oct4,20.8147048950195
b8,Oct4,20.7255210876465
F3,Oct4,18.9341983795166
F3,Oct4,20.9064426422119
F36,Oct4,26.3930683135986
F36,Oct4,25.6811389923096
F39,Oct4,20.4974098205566
F39,Oct4,20.3517150878906
E44,Oct4,19.7934150695801
E44,Oct4,19.4240188598633
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment