ensembl_to_GO.Rmd

---
title: "ensembl_to_GO"
author: "EC Harding"
date: "2024-04-09"
output: html_document
version: "R version 4.4.2"
---

```{r setup, include=FALSE, warning=FALSE}
knitr::opts_chunk$set(echo = FALSE, warning=FALSE, message=FALSE) 
```

# Libraries

```{r echo=FALSE, message=FALSE, warning=TRUE}

library(BiocManager)
library(biomaRt)
library(ensembldb)
library(tidyverse)
library(janitor)

```

# Load Query Data and extract ID lis to vector

## e.g ensembl_example.csv

```{r, echo=FALSE, message=FALSE, warning=FALSE}

ensembl_df <- read.csv("ensembl_example.csv", header = TRUE) %>% janitor::clean_names()
ensembl_vector <- ensembl_df %>% pull(ensembl_gene_id)

```

# Choose species for Biomart data

```{r, echo=FALSE, message=FALSE, warning=FALSE}

mouse <- "mmusculus_gene_ensembl" # Comment out as needed
#human <- hsapiens_gene_ensembl # Comment out as needed



```

# Make BioMart object and query with vector

```{r, echo=FALSE, message=FALSE, warning=FALSE}

# make a Biomart object to query with vector list
Biomart_genome = useMart("ensembl", dataset = mouse)
#attributes(mouse_genome) # uncomment to see genome data only

#Query the BioMart object for the IDs
mus_gene_id <- getBM(filters = "ensembl_gene_id",
                     attributes = c("ensembl_gene_id", "external_gene_name", "transcript_biotype", "description",
                                    "go_id", "name_1006"
                     values = ensembl_vector,
                     mart = Biomart_genome,
                     uniqueRows = TRUE) 
head(mus_gene_id)

```

#Combine data for export

```{r, echo=FALSE, message=FALSE, warning=FALSE}

features_frequency_IDs <- merge(features_frequency, mus_gene_id, by = "feature", all.x = TRUE) %>% arrange(rank)
features_leave_one_out_IDs <- merge(features_leave_one_out, mus_gene_id, by = "feature", all.x = TRUE) %>% arrange(rank)

```