In hirscheylab/tidybiology: Utility Functions and Data Sets for Tidy Biology

library(tidyverse)
library(tidybiology)
library(mitocarta)
library(viridis)

#clear environment
#rm(list=ls()) 

mitocarta_class5 <- mitocarta %>% 
  filter(mcarta2_list == 1) %>% 
  mutate(cerebrum = if_else(str_detect(tissues, "cerebrum|all"), TRUE, FALSE)) %>% 
  mutate(cerebellum = if_else(str_detect(tissues, "cerebellum|all"), TRUE, FALSE))  %>% 
  mutate(brainstem = if_else(str_detect(tissues, "brainstem|all"), TRUE, FALSE)) %>% 
  mutate(spinalcord = if_else(str_detect(tissues, "spinalcord|all"), TRUE, FALSE)) %>% 
  mutate(kidney = if_else(str_detect(tissues, "kidney|all"), TRUE, FALSE)) %>% 
  mutate(liver = if_else(str_detect(tissues, "liver|all"), TRUE, FALSE)) %>% 
  mutate(heart = if_else(str_detect(tissues, "heart|all"), TRUE, FALSE)) %>% 
  mutate(skeletalmuscle = if_else(str_detect(tissues, "skeletalmuscle|all"), TRUE, FALSE)) %>% 
  mutate(adipose = if_else(str_detect(tissues, "adipose|all"), TRUE, FALSE)) %>% 
  mutate(smallintestine = if_else(str_detect(tissues, "smallintestine|all"), TRUE, FALSE)) %>% 
  mutate(largeintestine = if_else(str_detect(tissues, "largeintestine|all"), TRUE, FALSE)) %>% 
  mutate(stomach = if_else(str_detect(tissues, "stomach|all"), TRUE, FALSE)) %>% 
  mutate(placenta = if_else(str_detect(tissues, "placenta|all"), TRUE, FALSE)) %>% 
  mutate(testis = if_else(str_detect(tissues, "testis|all"), TRUE, FALSE)) %>% 
  select(symbol, tissues, cerebrum:testis) 

mitocarta_class5 %>% summarize_if(is.logical, sum, na.rm = TRUE)

mitocarta_class5_long <- mitocarta_class5 %>% 
  pivot_longer(cerebrum:testis, names_to = "location", values_to = "true_false")

mitocarta_class5_long %>% group_by(location) %>% count(true_false, sort = TRUE)

mitocarta_class5_intensity <- mitocarta %>% 
  filter(mcarta2_list == 1) %>% 
  pivot_longer(cerebrum_total_peak_intensity_log10:testis_total_peak_intensity_log10, names_to = "location_intensity", values_to = "intensity") %>% 
  select(symbol, location_intensity, intensity, protein_length)

mitocarta_class5_intensity$location_intensity <- str_replace(mitocarta_class5_intensity$location_intensity, "_total_peak_intensity_log10", "")

mitocarta_class5 <- mitocarta_class5_long %>% 
  left_join(mitocarta_class5_intensity, by = c("symbol" = "symbol", "location" = "location_intensity")) %>% 
  select(-tissues)

rm(list = c("mitocarta_class5_intensity", "mitocarta_class5_long"))

#####STUDENTS START HERE#####

#Which tissue has the most unique mitochondrial proteins?
mitocarta_class5 %>% 
  group_by(location) %>% 
  count(true_false, sort = TRUE)

#Store an object to call below
top <- mitocarta_class5 %>% 
  group_by(location) %>% 
  count(true_false, sort = TRUE) %>% 
  ungroup() %>% 
  slice(1)

#calculate average lengths of all proteins
avg_length <- mitocarta_class5 %>% 
  filter(true_false == TRUE) %>% 
  group_by(location) %>% 
  summarize(mean_length = mean(protein_length, na.rm = TRUE)) %>% #need to remove NAs to make fun(mean) work
  arrange(desc(mean_length))

#Store favorite gene
fav <- mitocarta_class5 %>% 
  filter(symbol == params$gene) %>% 
  arrange(desc(intensity)) %>% 
  slice(1)

#store an object to call longer
longer <- if_else(
  fav$protein_length > avg_length %>% filter(location == fav$location) %>% pull(mean_length), "longer", "shorter"
)

My favorite gene is r fav$symbol, which encodes a mitochondrial protein that is most abundant in the r fav$location and is r fav$protein_length amino acids long. The average length of proteins in the r fav$location is r round(avg_length %>% filter(location == fav$location) %>% pull(mean_length),0) amino acids, which makes r fav$symbol r longer than average.

#Session information for provenance and reproducibility
session_provenance()

hirscheylab/tidybiology documentation built on May 20, 2022, 10:55 p.m.