zr.Rmd

---
title: "L'ORA - zoonoses report"
author: "Alfredo Acosta SVA" 
date: "`r Sys.Date()`" 
output: 
  html_document:
    toc: yes
    toc_float: true
    theme: cosmo
    fig_caption: yes
    number_sections: yes
    code_folding: show
  html_notebook: 
    toc: yes
---
# Working example zoonoses

# Libraries
```{r}
# Spill over analysis
# Update: 17/01/2024
library(tidyverse)
library(lubridate)
library(stringr)
library(readr)
library(data.table)
library(plotly)
library(DT)
library(arsenal)
```
# Working directory
## Loading zoonoses report from zenodo locally adquired cases
```{r}
setwd("C:/Users/alfredo.acosta/SVA/LiRA_consortium - Documents/WG1 Disease occurrence/datasources/Second-disease-group/Zoonoses_report/")

zr <- read.csv2("PREVALENCE_2022.csv")
```

# Checking Colnames
```{r}
colnames(zr)

unique_count_values <- zr %>%
  select(REPYEAR, REPCOUNTRY, ZOONOSIS, SPECIESTYPE, MATRIX) %>%
  summarise(across(everything(), ~ list(unique(.)))) # Extract unique values for each column

#Number of unique values
# unique_count_values

# To print it as a more human-readable form:
unique_values <- unique_count_values %>%
  mutate(across(everything(), ~ paste(unlist(.), collapse = ", ")))

# unique_values

# unique_values$REPYEAR
# unique(unique_values$REPCOUNTRY)
# unique(unique_values$ZOONOSIS)
# unique(unique_values$SPECIESTYPE)
# unique(unique_values$MATRIX)


```

# Filtering zoonoses name
```{r}
library(dplyr)
library(stringr)

zr2 <- zr %>%
  filter(SPECIESTYPE == "animal") %>% 
  filter(str_detect(ZOONOSIS, "Coxiella") | 
         str_detect(ZOONOSIS, "Echinococcus") | 
         str_detect(ZOONOSIS, "Leishmania") | 
        str_detect(ZOONOSIS, "Echinococcus spp.")) %>%
  filter(!str_detect(ZOONOSIS, "multiloc")) %>% 
  mutate(DISEASE = case_when(
    str_detect(ZOONOSIS, "granulosus") ~ "Echinococcosis",
    str_detect(ZOONOSIS, "Echinococcus") ~ "Echinococcosis",
    str_detect(ZOONOSIS, "Coxiella|Q fever") ~ "Q fever",
    TRUE ~ ZOONOSIS # Keeps the original ZOONOSIS value if no match is found
  )) %>% 
  select(REPYEAR, ZOONOSIS, ZOONOSIS_C, REPCOUNTRY, MATRIX, MATRIX_C, DISEASE, TOTUNITSPOSITIVE, TOTUNITSTESTED, SAMPUNIT)

# unique(zr2$REPYEAR)
# unique(zr2$REPCOUNTRY)
# unique(zr2$ZOONOSIS_C)
# unique(zr2$MATRIX)
# unique(zr2$DISEASE)

```

# Diseases codes (diseases-zoonoses_C)
```{r}
table(zr2$ZOONOSIS_C, zr2$DISEASE)
```

# Number of reports availables
```{r}
datatable(zr2 %>% 
  group_by(REPYEAR, DISEASE, REPCOUNTRY) %>% 
  summarize(number_reports=(sum(TOTUNITSPOSITIVE, na.rm = TRUE))) %>% 
  arrange(DISEASE, desc(number_reports)))
```

# Number of reports by type of study
```{r}
datatable(zr2 %>% 
  group_by(REPYEAR, DISEASE, REPCOUNTRY, SAMPUNIT) %>% 
  summarize(number_reports=(sum(TOTUNITSPOSITIVE, na.rm = TRUE))) %>% 
  spread(key = SAMPUNIT , value = number_reports))
        
```

# Species
## from 78 species we reorganize them to 13
```{r}
zr2 %>% group_by(MATRIX) %>%
  summarise(reports=n())

  zr2 <- mutate(zr2, species_fg =  case_when(
    str_detect(MATRIX, "Solipeds") ~ "Domesticated Equids",
    str_detect(MATRIX, "Pigs") ~ "Pigs",
    str_detect(MATRIX, "Goat") ~"Goats",
    str_detect(MATRIX, "Sheep") ~ "Sheep", 
    str_detect(MATRIX, "Cattle") ~ "Cattle", 
    str_detect(MATRIX, "Deer") ~ "Wildlife",
    str_detect(MATRIX, "Dogs") ~"Dogs",
    str_detect(MATRIX, "Reindeer") ~"Reindeer", 
    str_detect(MATRIX, "Cats") ~ "Cats",
    str_detect(MATRIX, regex("wild", ignore_case = TRUE)) ~ "Wildlife", 
    str_detect(MATRIX, "Wild boar") ~ "Wild boars",
    str_detect(MATRIX, regex("Fox", ignore_case = TRUE)) ~ "Foxes",
    MATRIX == "Badgers"| MATRIX == "Deer" | MATRIX == "Coypu"|MATRIX == "Hares" |
      MATRIX == "Mouflons" | MATRIX =="Raccoons" | MATRIX == "Squirrels" ~ "Wildlife",
    str_detect(MATRIX, regex("Zoo", ignore_case = TRUE)) ~ "Zoo_animal",
    TRUE ~ MATRIX))

#13 species found
zr2 %>% group_by(species_fg) %>%
  summarise(reports=n())

# species and disease
  zr2 %>% group_by(DISEASE, species_fg) %>%
  summarise(reports=n())

  zr2 %>% group_by(species_fg, DISEASE) %>%
  summarise(reports=n())

```
# Assigning functional groups 
## Acording how it appears in the last code chunk and comparison witn WG3 list 
```{r}
zr2$fg <- "0"
zr2$fg[zr2$species_fg == "Alpacas - farmed" & zr2$DISEASE == "Q fever"] <- "Domestic amplification"
zr2$fg[zr2$species_fg == "Cats" & zr2$DISEASE == "Echinococcosis"] <- "Domestic amplification"
zr2$fg[zr2$species_fg == "Cattle" & zr2$DISEASE == "Echinococcosis"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Cattle" & zr2$DISEASE == "Q fever"] <- "Domestic amplification"
zr2$fg[zr2$species_fg == "Dogs" & zr2$DISEASE == "Echinococcosis"] <- "Domestic amplification"
zr2$fg[zr2$species_fg == "Dogs" & zr2$DISEASE == "Leishmania"] <- "Domestic amplification"
zr2$fg[zr2$species_fg == "Dogs" & zr2$DISEASE == "Q fever"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Domesticated Equids" & zr2$DISEASE == "Q fever"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Domesticated Equids" & zr2$DISEASE == "Echinococcosis"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Foxes" & zr2$DISEASE == "Echinococcosis"] <- "Wildlife amplification"
zr2$fg[zr2$species_fg == "Goats" & zr2$DISEASE == "Echinococcosis"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Goats" & zr2$DISEASE == "Q fever"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Goats" & zr2$DISEASE == "Q fever"] <- "Domestic amplification"
zr2$fg[zr2$species_fg == "Pigs" & zr2$DISEASE == "Q fever"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Pigs" & zr2$DISEASE == "Echinococcosis"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Reindeer" & zr2$DISEASE == "Echinococcosis"] <- "Wildlife amplification"  # not sure
zr2$fg[zr2$species_fg == "Sheep" & zr2$DISEASE == "Echinococcosis"] <- "Domestic amplification"  
zr2$fg[zr2$species_fg == "Sheep" & zr2$DISEASE == "Q fever"] <- "Domestic amplification"  
zr2$fg[zr2$species_fg == "Water buffalos" & zr2$DISEASE == "Echinococcosis"] <- "Domestic spillover"  
zr2$fg[zr2$species_fg == "Water buffalos" & zr2$DISEASE == "Q fever"] <- "Domestic spillover"
zr2$fg[zr2$species_fg == "Wildlife" & zr2$DISEASE == "Q fever"] <- "Wildlife spillover"  #only because is the most common
zr2$fg[zr2$species_fg == "Wildlife" & zr2$DISEASE == "Echinococcosis"] <- "Wildlife amplification" #only because is the most common
zr2$fg[zr2$species_fg == "Zoo_animal" & zr2$DISEASE == "Echinococcosis"] <- "Domestic spillover" #Because they are confined could be a dead end "spillover" also those animals receive veterinary attention, diagnosis, these reported cases would have had a desition and reduced their possibility to transmit "amplification"  
zr2$fg[zr2$species_fg == "Zoo_animal" & zr2$DISEASE == "Q fever"] <- "Domestic spillover" #Same consideration

  zr2 %>% group_by(species_fg, DISEASE, fg) %>%
  summarise(reports=n())


```

```{r}
species_fg <- zr2 %>% 
  group_by(MATRIX_C, MATRIX, DISEASE, fg) %>% 
  summarise(number=n()) %>% 
  arrange(desc(number))

# write.csv(species_fg, file = "species_fg_zoonoses.csv")
```


# Credits Acosta, A.; Ernholm, L. <sup>1</sup>.
**SVA<sup>1</sup>**: SVA <http://www.sva.se/>.