bioconnector/bims8382

Introduction to Biomedical Data Science

bims8382's Issues

spell check all the .Rmd files

add text about creating projects for dplyr and ggplot2 lesson

ggplot2 homework exercises on yeast data

The ggplot2 lesson uses the gapminder data. Add some homework questions using the yeast data. as in http://varianceexplained.org/r/tidy-genomics/

RNA-seq: take mean, not sum of counts

In the poor man's DGE section, you're summing the control and treated samples, not getting the mean. Fix with something like:

meancounts <- rawcounts %>%
  mutate(controlmean=(SRR1039508+SRR1039512+SRR1039516+SRR1039520)/4) %>%
  select(ensgene, controlmean)

Questions about problem3 in exercise set 4 in Power & sample size in Essential Statistics with R

Dear Sir,

Thanks for your tutorial, and it helps me a lot.

I am curious about the difference between pwr.2p.test and power.prop.test. There is a difference between the results. Which one is better?

Question:
You’re doing a population genome-wide association study (GWAS) looking at the effect of a SNP on disease X. Disease X has a baseline prevalence of 5% in the population, but you suspect the SNP might increase the risk of disease X by 10% (this is typical for SNP effects on common, complex diseases). Calculate the number of samples do you need to have 80% power to detect this effect, given that you want a genome-wide statistical significance of p<5×10−8
to account for multiple testing. (Hint, you can expressed 5×10−8 in R using 5e-8 instead of .00000005).

power.prop.test(power = 0.8, p1 = 0.05, p2 = 0.055, sig.level = 5e-8)

The result is 157589.5.

pwr.2p.test(h = ES.h(p1 = 0.05, p2 = 0.055), sig.level = 5e-8, power = 0.8)

The result is 157505.8.

add homework for dplyr lesson using gapminder data

The dplyr lesson uses the Brauer yeast data, but the ggplot2 lesson uses the gapminder data. Write a few homework questions as a follow up to the dplyr lesson so students are familiar with the gapminder data prior to the ggplot2 lesson.

• discuss the variables in the data
• load the data with readr::read_csv
• review dplyr verbs

Use the existing dplyr lesson (http://bioconnector.org/workshops/lessons/r/r-manipulation/) as a guide.

landing page link to bioconnector/workshops for 2017- course

See bioconnector/workshops#28

If we move BIMS8382 2017's course material to bioconnector/workshops and update as described in bioconnector/workshops#28, need to update the landing page here to note in bold that this is for the 2016 course, and see (link) for 2017 material.