22100 - R for Bio Data Science

Getting Started

First of all, make sure to read every line in these exercises carefully!

For these exercises, work 2-and-2 in your desk groups. If you get stuck, go visit the chapter on data visualisation you prepared for today or try to practise your google’ing skills. I will of course also be circulating and available for questions.

First, go to your RStudio Cloud session from last time and login and choose the project you created.

Recall the layout of the IDE (Integrated Development Environment)

Then, before we start, we need to install the packages we need, so without further ado, run each of the following lines separatly in your console:

install.packages("tidyverse")
install.packages("devtools")
library("devtools")
install_github("ramhiser/datamicroarray")

Once this has been installed after ~5 minutes, create a new rmarkdown document (File -> New File -> R Markdown…)

Recall the syntax for a new code chunk:

```{r}
# Here goes the code... Note how this part does not get executed
```

Short-cuts:

• Mac: CMD + OPTION + i
• Windows: CTRL + OPTION + i

Now, in your rmarkdown document, add a new code chunk with the command

library("tidyverse")
library("datamicroarray")

This will load out data science toolbox, including ggplot and a set of various bio-data. You can read more about the datamicroarray here

Create data

Before we can visualise the data, we need to wrangle it a bit. Nevermind the details here, we will get to that later. Just create a new chunk, copy/paste the below code and run it:

data('gravier', package = 'datamicroarray')
set.seed(676571)
cancer_data=mutate(as_tibble(pluck(gravier,"x")),y=pluck(gravier,"y"),pt_id=1:length(pluck(gravier, "y")),age=round(rnorm(length(pluck(gravier,"y")),mean=55,sd=10),1))
cancer_data=rename(cancer_data,event_label=y)
cancer_data$age_group=cut(cancer_data$age,breaks=seq(10,100,by=10))

Now we have the data set as an tibble, which is an augmented data frame (we will also get to that later):

select(slice(cancer_data,1:8),pt_id,age,age_group,event_label,1:5)

## # A tibble: 8 x 9
##   pt_id   age age_group event_label    g2E09    g7F07    g1A01   g3C09
##   <int> <dbl> <fct>     <fct>          <dbl>    <dbl>    <dbl>   <dbl>
## 1     1  34.2 (30,40]   good        -0.00144 -0.00144 -0.0831  -0.0475
## 2     2  47   (40,50]   good        -0.0604   0.0129  -0.00144  0.0104
## 3     3  60.3 (60,70]   good         0.0398   0.0524  -0.0786   0.0635
## 4     4  57.8 (50,60]   good         0.0101   0.0314  -0.0218   0.0215
## 5     5  54.9 (50,60]   good         0.0496   0.0201   0.0370   0.0311
## 6     6  58.8 (50,60]   good        -0.0664   0.0468   0.00720 -0.370 
## 7     7  52.9 (50,60]   good        -0.00289 -0.0816  -0.0291  -0.0249
## 8     8  74.5 (70,80]   good        -0.198   -0.0499  -0.0634  -0.0298
## # … with 1 more variable: g3H08 <dbl>

This is just the first 8 rows and the first 8 columns, so

• Q1: What is this data?

Hint: Where did the data come from?

• Q2: How many rows and columns are there in the data set in total?

Hint: Do you think you are the first person in the world to try to find out how many rows and columns are in a data set in R?

• Q3: Which are the variables and which are the observations in relation to rows and columns?

ggplot - The Very Basics

ggplot(data = my_data,
       mapping = aes(x = variable_1_name, y = variable_2_name)) +
  geom_something() +
  labs()

ggplot(data = tibble(x = rnorm(20), y = rnorm(20)),
       mapping = aes(x = x, y = y)) +
  geom_point()

Further ressources for data visualisation

• A very handy cheat-sheet can be found here
• So which plot to choose? Check this handy guide
• Explore ways of plotting here