Updated from dicook/SISBID-2017

Author: bdwilliamson

0-preamble/index.Rmd

@@ -147,4 +147,4 @@ devtools::install_github("haleyjeppson/ggmosaic")
 
 Materials for this workshop build on slides provided by several people, but primarily Hadley Wickham and Carson Sievert. 
 
-This work is licensed under the Creative Commons Attribution-Noncommercial 3.0 United States License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc/ 3.0/us/ or send a letter to Creative Commons, 171 Second Street, Suite 300, San Francisco, California, 94105, USA.
+This work is licensed under the Creative Commons Attribution-Noncommercial 3.0 United States License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc/3.0/us/ or send a letter to Creative Commons, 171 Second Street, Suite 300, San Francisco, California, 94105, USA.

0-preamble/index.html

@@ -147,7 +147,7 @@
 "highlightLines": true,
 "countIncrementalSlides": false
 });
-if (window.HTMLWidgets) slideshow.on('afterShowSlide', function (slide) {window.dispatchEvent(new Event('resize'));});</script>
+if (window.HTMLWidgets) slideshow.on('showSlide', function (slide) {setTimeout(function() {window.dispatchEvent(new Event('resize'));}, 100)});</script>
 
 <script type="text/x-mathjax-config">
 MathJax.Hub.Config({
@@ -161,7 +161,7 @@
 (function () {
   var script = document.createElement('script');
   script.type = 'text/javascript';
-  script.src  = 'https://cdn.bootcss.com/mathjax/2.7.1/MathJax.js?config=TeX-MML-AM_CHTML';
+  script.src  = 'https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
   if (location.protocol !== 'file:' && /^https?:/.test(script.src))
     script.src  = script.src.replace(/^https?:/, '');
   document.getElementsByTagName('head')[0].appendChild(script);

1.1-ggplot/index.Rmd

@@ -1,6 +1,6 @@
 ---
 title: "Grammar of Graphics and ggplot2"
-subtitle: "SISBID 2017"
+subtitle: "SISBID 2017 <br> https://github.com/SISBID/Module2"
 author: "Di Cook ([email protected], @visnut) <br> Heike Hofmann ([email protected], @heike_hh)"
 date: "07/12-14/2017"
 output:
@@ -28,12 +28,7 @@ knitr::opts_chunk$set(
 ```
 
 ```{r echo=FALSE}
-library(ggplot2)
-library(tidyr)
-library(dplyr)
-library(lubridate)
-library(scales)
-library(readr)
+library(tidyverse)
 library(ggmap)
 library(HLMdiag)
 library(RColorBrewer)
@@ -141,7 +136,7 @@ autism, x and y position along a line, point, none
 
 ```{r}
 ggplot(autism, aes(x=age2, y=vsae)) + 
-  geom_jitter()
+  geom_jitter(width=0.3, height=0)
 ```
 
 ---
@@ -182,15 +177,17 @@ ggplot(autism, aes(x=age2, y=vsae, group=childid)) +
 
 ```{r}
 ggplot(autism, aes(x=age2, y=vsae, group=childid)) + 
-  geom_point() + geom_line(alpha=0.5)
+  geom_point() + geom_line(alpha=0.1)
 ```
 
 ---
 # Log scale y?
 
 ```{r}
 ggplot(autism, aes(x=age2, y=vsae, group=childid)) + 
-  geom_point() + geom_line(alpha=0.5) + scale_y_log10()
+  geom_point() + geom_line(alpha=0.2) + scale_y_log10()
+ggplot(autism, aes(x=age2, y=log(vsae), group=childid)) + 
+  geom_point() + geom_line(alpha=0.2) 
 ```
 
 ---
@@ -208,7 +205,7 @@ ggplot(autism, aes(x=age2, y=vsae, group=childid, colour=bestest2)) +
 ggplot(autism, aes(x=age2, y=vsae, colour=bestest2)) + 
   geom_point(alpha=0.1) + geom_line(aes(group=childid), alpha=0.1) + 
   geom_smooth(se=F) +
-  scale_y_log10()
+  scale_y_log10() 
 ```
 
 ---
@@ -308,6 +305,9 @@ fly$`How often do you travel by plane?` <-
     "Never","Once a year or less","Once a month or less",
     "A few times per month","A few times per week","Every day"))
 ggplot(fly, aes(x=`How often do you travel by plane?`)) + geom_bar() + coord_flip()
+ggplot(fly, aes(x=`How often do you travel by plane?`, 
+                fill=`How often do you travel by plane?`)) + geom_bar() + coord_flip() +
+  scale_fill_brewer(palette="Dark2")
 ```
 
 ---
@@ -412,6 +412,10 @@ ggplot(fly_sub, aes(x=`Do you ever recline your seat when you fly?`)) +
   geom_bar() + 
   facet_wrap(~`Is itrude to recline your seat on a plane?`, ncol=3) +
   coord_flip()
+ggplot(fly_sub, aes(x=`Do you ever recline your seat when you fly?`,
+    fill=`Is itrude to recline your seat on a plane?`)) +
+  geom_bar(position="fill") +
+  coord_flip()
 ```
 
 
@@ -486,12 +490,12 @@ p + scale_fill_manual("", values=clrs) + theme(legend.position = "none")
 ---
 # Hierarchy of mappings
 
-- 1. Position - common scale (BEST)
-- 2. Position - nonaligned scale
-- 3. Length, direction, angle
-- 4. Area
-- 5. Volume, curvature
-- 6. Shading, color (WORST)
+- 1.Position - common scale (BEST)
+- 2.Position - nonaligned scale
+- 3.Length, direction, angle
+- 4.Area
+- 5.Volume, curvature
+- 6.Shading, color (WORST)
 
 ---
 # Pre-attentive

1.1-ggplot/index.html

@@ -496,12 +496,12 @@
 ---
 # Hierarchy of mappings
 
-- 1. Position - common scale (BEST)
-- 2. Position - nonaligned scale
-- 3. Length, direction, angle
-- 4. Area
-- 5. Volume, curvature
-- 6. Shading, color (WORST)
+- 1.Position - common scale (BEST)
+- 2.Position - nonaligned scale
+- 3.Length, direction, angle
+- 4.Area
+- 5.Volume, curvature
+- 6.Shading, color (WORST)
 
 ---
 # Pre-attentive
@@ -627,7 +627,7 @@
 "highlightLines": true,
 "countIncrementalSlides": false
 });
-if (window.HTMLWidgets) slideshow.on('showSlide', function (slide) {setTimeout(function() {window.dispatchEvent(new Event('resize'));}, 100)});</script>
+if (window.HTMLWidgets) slideshow.on('afterShowSlide', function (slide) {window.dispatchEvent(new Event('resize'));});</script>
 
 <script type="text/x-mathjax-config">
 MathJax.Hub.Config({
@@ -641,7 +641,7 @@
 (function () {
   var script = document.createElement('script');
   script.type = 'text/javascript';
-  script.src  = 'https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
+  script.src  = 'https://cdn.bootcss.com/mathjax/2.7.1/MathJax.js?config=TeX-MML-AM_CHTML';
   if (location.protocol !== 'file:' && /^https?:/.test(script.src))
     script.src  = script.src.replace(/^https?:/, '');
   document.getElementsByTagName('head')[0].appendChild(script);

1.2-mvplot/index.Rmd

@@ -1,6 +1,6 @@
 ---
 title: "Multivariate data plots"
-subtitle: "SISBID 2017"
+subtitle: "SISBID 2017 <br> https://github.com/SISBID/Module2"
 author: "Di Cook ([email protected], @visnut) <br> Heike Hofmann ([email protected], @heike_hh)"
 date: "07/12-14/2017"
 output:
@@ -371,7 +371,7 @@ sig.tab <- sig.tab %>% filter(PValue < 0.01)
 ---
 
 
-```{r}
+```{r fig.height=6, fig.width=6}
 sig.tab <- merge(sig.tab, coty[,1:7], by.x="genes", by.y="ID")
 ggscatmat(sig.tab, columns=5:10, alpha=0.1)
 ```
@@ -417,13 +417,114 @@ ggplot(data=sig.tab) +
   geom_segment(aes(x=C_S1_R1, xend=C_S1_R2, y=C_S2_R1, yend=C_S2_R2))
 ```
 
+---
+# biobroom and limma
+
+```{r}
+bb <- data.frame(read_tsv("../data/biotin-rma2.txt"))
+head(data.frame(bb[,-2]))
+row.names(bb) <- bb$Gene
+```
+
+---
+# Looking at the gene expression data
+
+```{r fig.width=6, fig.height=6}
+ggpairs(bb, columns=c(3,7,4,8))
+```
+
+---
+# A porcupine plot again
+
+```{r fig.width=6, fig.height=6}
+sub <- bb %>% select(Gene, biotin.WT.01.1, biotin.WT.02.1, biotin.bio101.4, biotin.bio102.4)
+ggplot(sub, aes(x=biotin.WT.01.1, xend=biotin.WT.02.1, y=biotin.bio101.4, yend=biotin.bio102.4)) +
+  geom_segment() +
+  theme(aspect.ratio = 1) +
+  xlab("wildtype, control treatment") +
+  ylab("mutant, treated")
+```
+
+---
+# Fit a limma model
+
+```{r}
+design <- expand.grid(type=c("wild", "mutant"), trt=c("control", "treatment"), rep=1:2)
+
+fit <- lmFit(bb[,-(1:2)], model.matrix(~ type*trt, design))
+fit <- eBayes(fit)
+
+head(topTable(fit))
+```
+
+---
+class: inverse middle 
+# Your Turn
+
+![](lorikeets.png)
+
+- For the previous example, try out what output the different broom functions (`glance`, `tidy`, `augment`)  produce.
+- Create a Volcano plot for each of the model terms, i.e. plot estimates on x by log(p.values) on y. 
+- Are there differences visible between the terms?
+
+```{r, echo=FALSE, eval=FALSE}
+head(tidy(fit))
+ggplot(tidy(fit), aes(x=estimate, y=log(p.value), colour = p.value < 0.05)) +
+  facet_wrap(~term) +
+  geom_point() + ggtitle("Volcano Plots with limma") 
+```
+
+---
+
+```{r}
+bbfit <- tidy(fit)
+ggplot(data=bbfit, aes(x=term, y=estimate, group=gene)) +
+  geom_line(alpha=0.1) +
+  geom_point(aes(color=log(p.value)), size=2, alpha=0.6)
+```
+
+---
+
+Is type*treatment interaction necessary? Very strong negative correlation is suspicious.
+
+
+```{r fig.show='hide'}
+bbfit_m <- bbfit %>% select(gene, term, estimate, p.value) %>% 
+  gather(fit.stat, value, -gene, -term) %>%
+  unite(term_stat, term, fit.stat) %>%
+  spread(term_stat, value) %>% 
+  rename(trt=trttreatment_estimate, mut=typemutant_estimate,
+         int=`typemutant:trttreatment_estimate`, 
+         trtp=trttreatment_p.value, mutp=typemutant_p.value, 
+         intp=`typemutant:trttreatment_p.value`) 
+ggpairs(bbfit_m, columns=c(2,4,6), upper=list(continuous="points"),
+          ggplot2::aes(colour=intp)) + theme(aspect.ratio=1)
+```
+
+---
+
+```{r echo=FALSE, fig.width=8, fig.height=8}
+ggpairs(bbfit_m, columns=c(2,4,6), upper=list(continuous="points"),
+          ggplot2::aes(colour=intp)) + theme(aspect.ratio=1)
+```
+
+---
+
+```{r}
+fit2 <- lmFit(bb[,-(1:2)], model.matrix(~ type+trt, design))
+fit2 <- eBayes(fit2)
+bbfit2 <- tidy(fit2)
+ggplot(data=bbfit2, aes(x=term, y=estimate, group=gene)) +
+  geom_line(alpha=0.1) +
+  geom_point(aes(color=log(p.value)), size=2, alpha=0.6)
+```
+
 ---
 # Resources
 
 - [GGobi web site](http://www.ggobi.org), [ggobi book](http://www.ggobi.org/book)
 - Emerson et al (2013) The Generalized Pairs Plot, Journal of Computational and Graphical Statistics, 22:1, 79-91
 - Cook et al (2007) Exploring Gene Expression Data, Using Plots, Journal of Data Science, 5(2):151-182
-- [Antony Unwin, Graphical Data Analysis with R](https://www.crcpress.com/Graphical-Data-Analysis-with-R/Unwin/9781498715232)
 
 ---
 # Share and share alike

1.2-mvplot/index.html

@@ -12,7 +12,7 @@
 class: center, middle, inverse, title-slide
 
 # Multivariate data plots
-## SISBID 2017
+## SISBID 2017 <br> <a href="https://github.com/SISBID/Module2" class="uri">https://github.com/SISBID/Module2</a>
 ### Di Cook (<a href="mailto:[email protected]">[email protected]</a>, <span class="citation">@visnut</span>) <br> Heike Hofmann (<a href="mailto:[email protected]">[email protected]</a>, <span class="citation">@heike_hh</span>)
 ### 07/12-14/2017
 
@@ -347,7 +347,6 @@
 - [GGobi web site](http://www.ggobi.org), [ggobi book](http://www.ggobi.org/book)
 - Emerson et al (2013) The Generalized Pairs Plot, Journal of Computational and Graphical Statistics, 22:1, 79-91
 - Cook et al (2007) Exploring Gene Expression Data, Using Plots, Journal of Data Science, 5(2):151-182
-- [Antony Unwin, Graphical Data Analysis with R](https://www.crcpress.com/Graphical-Data-Analysis-with-R/Unwin/9781498715232)
 
 ---
 # Share and share alike
@@ -360,7 +359,7 @@
 "highlightLines": true,
 "countIncrementalSlides": false
 });
-if (window.HTMLWidgets) slideshow.on('showSlide', function (slide) {setTimeout(function() {window.dispatchEvent(new Event('resize'));}, 100)});</script>
+if (window.HTMLWidgets) slideshow.on('afterShowSlide', function (slide) {window.dispatchEvent(new Event('resize'));});</script>
 
 <script type="text/x-mathjax-config">
 MathJax.Hub.Config({
@@ -374,7 +373,7 @@
 (function () {
   var script = document.createElement('script');
   script.type = 'text/javascript';
-  script.src  = 'https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML';
+  script.src  = 'https://cdn.bootcss.com/mathjax/2.7.1/MathJax.js?config=TeX-MML-AM_CHTML';
   if (location.protocol !== 'file:' && /^https?:/.test(script.src))
     script.src  = script.src.replace(/^https?:/, '');
   document.getElementsByTagName('head')[0].appendChild(script);

2.1-tidyr/index.Rmd

@@ -63,6 +63,13 @@ student2012.sub <- readRDS("../data/student_sub.rds")
 student2012.sub %>% group_by(CNT) %>% tally()
 ```
 
+---
+# What is **tidy data**? 
+
+- Why do we want tidy data? 
+- Couple of exercises to look closer at what we find in practice 
+
+
 ---
 class: inverse middle 
 # Your turn 1
@@ -180,10 +187,10 @@ There are various features of messy data that one can observe in practice. Here
 ---
 # Tidy Verbs
 
-- **gather**: specify the **keys** (identifiers) and the **values** (measures) to make long form (used to be called melting)
-- **spread**: variables in columns (used to be called casting)
-- nest/unnest: working with lists
-- separate/unite: split and combine columns
+- `gather`: specify the **keys** (identifiers) and the **values** (measures) to make long form (used to be called melting)
+- `spread`: variables in columns (used to be called casting)
+- `nest`/`unnest`: working with list variables
+- `separate`/`unite`: split and combine columns
 
 ---
 # French Fries 
@@ -264,6 +271,7 @@ ff.m <- french_fries %>%
 head(ff.m)
 ```
 
+--
 
 ```{r, fig.height=2, fig.width=8}
 ggplot(data=ff.m, aes(x=rating)) + geom_histogram(binwidth=2) + 
@@ -291,6 +299,10 @@ We need to gather the data into long form, and then get the replicates spread in
 
 ```{r}
 head(ff.m)
+```
+
+
+```{r}
 ff.s <- ff.m %>% spread(rep, rating)
 head(ff.s)
 ```