---
title: "01-blast"
output: html_document
date: "2023-03-30"
---

#Download Software

#change directory
```{bash}
cd /home/jovyan/applications
```

#download software from NCBI
```{bash}
curl -O https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/LATEST/ncbi-blast-2.13.0+-x64-linux.tar.gz
```

#unzip
```{bash}
cd /home/jovyan/applications
tar -xf ncbi-blast-2.13.0+-x64-linux.tar.gz
```

#check if it's working
```{bash}
~/applications/ncbi-blast-2.13.0+/bin/blastx -h
```

#make blast database
#mv renames the file into something I want
#cd../data is relative file path
```{bash}
#download from url
cd ../data
curl -O https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz
mv uniprot_sprot.fasta.gz uniprot_sprot_r2023_01.fasta.gz
gunzip -k uniprot_sprot_r2023_01.fasta.gz
ls ../data
```
```{bash}
#back slash makes it possible for you to separate codes on different lines
#make the blast database
~/applications/ncbi-blast-2.13.0+/bin/makeblastdb \
-in ../data/uniprot_sprot_r2023_01.fasta \
-dbtype prot \
-out ../blastdb/uniprot_sprot_r2023_01
```
```{bash}
curl https://eagle.fish.washington.edu/cnidarian/Ab_4denovo_CLC6_a.fa \
-k \
> ../data/Ab_4denovo_CLC6_a.fa
```
```{bash}
head ../data/Ab_4denovo_CLC6_a.fa
echo "How many sequences are there?"
grep -c ">" ../data/Ab_4denovo_CLC6_a.fa
```
####Run Blast####
#~/ is home directory
#evalue is the percent match
```{bash}
~/applications/ncbi-blast-2.13.0+/bin/blastx \
-query ../data/Ab_4denovo_CLC6_a.fa \
-db ../blastdb/uniprot_sprot_r2023_01 \
-out ../output/Ab_4-uniprot_blastx.tab \
-evalue 1E-20 \
-num_threads 8 \
-max_target_seqs 1 \
-outfmt 6
```
```{bash}
head -2 ../output/Ab_4-uniprot_blastx.tab
wc -l ../output/Ab_4-uniprot_blastx.tab
```

#####join blast table with annotation table#####
```{bash}
head -2 ../output/Ab_4-uniprot_blastx.tab
wc -l ../output/Ab_4-uniprot_blastx.tab
```
#change format of blast output
```{bash}
tr '|' '\t' < ../output/Ab_4-uniprot_blastx.tab \
> ../output/Ab_4-uniprot_blastx_sep.tab
```

#load package in R
```{r}
library(tidyverse)
```

#read in annotation table
```{r}
spgo <- read.csv("https://gannet.fish.washington.edu/seashell/snaps/uniprot_table_r2023_01.tab", sep = '\t', header = TRUE)
```
#read in data table
```{r}
bltabl <- read.csv("../output/Ab_4-uniprot_blastx_sep.tab", sep = '\t', header = FALSE)
```
#join tables
```{r}
left_join(bltabl, spgo,  by = c("V3" = "Entry")) %>%
  select(V1, V3, V13, Protein.names, Organism, Gene.Ontology..biological.process., Gene.Ontology.IDs) %>% mutate(V1 = str_replace_all(V1, 
            pattern = "solid0078_20110412_FRAG_BC_WHITE_WHITE_F3_QV_SE_trimmed", replacement = "Ab")) %>%
  write_delim("../output/blast_annot_go.tab", delim = '\t')
```

#read in combined table
```{r}
annot_tab <- read.csv("../output/blast_annot_go.tab", sep = '\t', header = TRUE)
```