Cleaning and manipulating data with the tidyverse: dplyr, readr, and stringr in action (CC121)

Data cleaning is one of the more undervalued steps in a data anlaysis. In this episode we'll use a variety of functions from the tidyverse to get three data frames into the right format and then we'll join them all together. This will help us get ready for downstream analyses looking for microbiome-based biomarkers associated with colorectal cancer.

You can also find complete tutorials for learning R with the tidyverse using...

0:00 Introduction
2:29 Tidying a mothur shared file
6:21 Formatting a taxonomy file
15:14 Calculating genus relative abundances
17:39 Formatting metadata and joining to relative abundances
23:31 Committing changes
24:26 Recap

[Riffomonas]

What part of working with regular expressions do you find the most frustrating?

[getachewaga]

HI Pat, great presentation. I love your tutorials. Many thanks for your generous gift.

Great example of real use for manipulating data. Thanks!

[timmytesla]

I learnt about rename_all() for the first time. Thank you.

[m.shihamadam]

I am loving it - just found about the channel!

[marialeticiabonatelli]

So happy, it worked! And I had a completely different raw data - from dada2!

[mikodine]

Hi Pat, great tutorial! Thanks a lot for this :)

[EMlSHI]

Could you introduce how to clean up and manipulate taxnomy data output from qiime2?

[shrez]

Will machine learning methods such as performing random forest on compositional data (as we have relative abundances for the genera) require any type of data transformation?

[ahmedJaber]

Hi Pat, thank you for this. Is there a way to specify in the regular expression
if you don't find this regex, look for 2nd form, 3rd form etc???

[wapsyed]

You look and sound like a smart version of Seth Rogen haha

[richardbennett]

The presenter appears to know R; however he doesn't seem to know that parentheSIS is the singular for parentheSES. 😮