cysteine_posterFigures.Rmd

---
title: "cysteine_posterFigures"
output: html_document
---

# df = scoreFiltereByMaxScore

# number of strains with gene -- barplot
```{r}
# library(dplyr)
# library(ggplot2)
# library(reshape2)
# 
# df <- melt(scoreFilteredByMaxScore_cysteine_results_updatedStrains, id.vars = c("strain"), variable.name = "gene")

# group_by to reorder bars by count
subset(df, !is.na(df$value)) %>%
  group_by(gene) %>%
  summarise(perc = round((n() / 214)*100), digits = 3) %>%
  
  ggplot(aes(x = reorder(gene, -perc), y = perc)) +
    geom_bar(stat = "identity", fill = "darkorange", width = 0.5) +
    geom_text(stat='identity', aes(label=paste(perc, "%")), vjust = -0.5, size = 4) +
    ylab("Percentage of Strains") +
    xlab("Gene") +
    ggtitle("Percentage of Strains with Hits per Gene") +
    theme_bw() +
    theme(axis.text.x = element_text(face = "italic", size = 12), axis.text.y = element_text(size = 12), axis.title = element_text(size = 14)) +
    scale_y_continuous(expand = c(0, 0), limits = c(0,100))

```

# proportion of each taxon with hits? 
```{r}
# taxa_hits_df <- subset(subset(df, `Category by Percentage of E. coli Hit Score` == ">75%"))
# taxa_hits_df <- subset(df, select = -c(gene, hit_score, perc_of_ecoli_score, category, `Category by Percentage of E. coli Hit Score`)) %>% distinct(strain, .keep_all = TRUE)
 
ggplot(subset(df, `Category by Percentage of E. coli Hit Score` == ">75%"), aes(y = phylum)) +
  facet_wrap(vars(gene)) +
  geom_bar()

```

# heatmap (not rly bc it's binary) for strain vs. gene
```{r}
library(forcats)
# 
# df$phylum_colors <- ifelse(df$phylum == "Firmicutes", "orange",
#                         ifelse(df$phylum == "Actinobacteria", "blue", 
#                                ifelse(df$phylum == "Bacteroidetes", "purple",
#                                       ifelse(df$phylum == "Verrucomicrobia", "red",
                                             # ifelse(df$phylum == "Proteobacteria", "green", NA)))))

phylum_levels <- c("Firmicutes", "Bacteroidetes", "Actinobacteria", "Proteobacteria", "Verrumicrobia")

df %>%
  mutate(across(c("phylum", "strain"), factor, levels = phylum_levels))

ggplot(subset(df, `Category by Percentage of E. coli Hit Score` == ">75%"), aes(y = reorder(strain, phylum), x = gene, fill = hit_score)) +
  geom_tile() +
  theme_classic() +
  theme(axis.text.y = element_text(colour = phylum_colors, size = 3))

# ggplot(subset(df, `Category by Percentage of E. coli Hit Score` == ">75%" & phylum == "Firmicutes"), aes(y = strain, x = gene, fill = hit_score)) +
#   geom_tile() +
#   theme_classic() +
#   ggtitle("Firmicutes")
#   # theme(axis.text.y = element_text(colour = phylum_colors, size = 3))
# 
# ggplot(subset(df, `Category by Percentage of E. coli Hit Score` == ">75%" & phylum == "Bacteroidetes"), aes(y = strain, x = gene, fill = hit_score)) +
#   geom_tile() +
#   theme_classic() +
#   ggtitle("Bacteroidetes")
# 
# ggplot(subset(df, `Category by Percentage of E. coli Hit Score` == ">75%" & phylum == "Actinobacteria"), aes(y = strain, x = gene, fill = hit_score)) +
#   geom_tile() +
#   theme_classic() +
#   ggtitle("Actinobacteria")
# 
# ggplot(subset(df, `Category by Percentage of E. coli Hit Score` == ">75%" & phylum == "Proteobacteria"), aes(y = strain, x = gene, fill = hit_score)) +
#   geom_tile() +
#   theme_classic() +
#   ggtitle("Proteobacteria")

```