---
title: "Appending Gene Symbols and Protein Descriptions with blastx"
output: html_document
date: "2025-03-26"
---

```{r, engine='bash'}
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_r2025_03.fasta.gz
gunzip -k uniprot_sprot_r2025_03.fasta.gz
ls ../data
```

```{r, engine='bash'}
/home/shared/ncbi-blast-2.11.0+/bin/makeblastdb \
-in /home/shared/8TB_HDD_02/cvaldi/Botryllus-Nickel-Tox/data/uniprot_sprot_r2025_03.fasta \
-dbtype prot \
-out /home/shared/8TB_HDD_02/cvaldi/Botryllus-Nickel-Tox/output/blastdb/uniprot_sprot_r2025_03

```

```{r, engine='bash'}
head -n 20 ../data/noname.fasta  # View the first 20 lines of the file to ensure it's correct
echo "How many sequences are there?"
grep -c ">" ../data/noname.fasta  # Count the number of sequences in the FASTA file
```
```{r, engine='bash'}
/home/shared/ncbi-blast-2.11.0+/bin/blastx \
-query ../data/noname.fasta \
-db ../output/blastdb/uniprot_sprot_r2025_03 \
-out ../output/Bsc-uniprot_blastx.tab \
-evalue 1E-20 \
-num_threads 20 \
-max_target_seqs 1 \
-outfmt 6

```


```{r, engine='bash'}
head -2 ../output/Bsc-uniprot_blastx.tab  # View the first two lines of the BLAST output
wc -l ../output/Bsc-uniprot_blastx.tab   # Count the number of results

```

```{r, engine='bash'}
tr '|' '\t' < ../output/Bsc-uniprot_blastx.tab | head -2

# replace the "|" with "\t" in the file "Ab_4-uniprot_blastx.tab"
# and save the output to the file "Ab_4-uniprot_blastx_sep.tab"

tr '|' '\t' < ../output/Bsc-uniprot_blastx.tab \
> ../output/Bsc-uniprot_blastx_sep.tab
```

```{r}
bltabl <- read.csv("../output/Bsc-uniprot_blastx_sep.tab", sep = '\t', header = FALSE)
```

```{r}
# Reading the Uniprot table
spgo <- read.csv("../data/uniprot_sprot_r2025_03_cleaned.tab", sep = "\t", header = TRUE)

# Merge the BLAST results with the Uniprot annotations
annotated_blast <- left_join(bltabl, spgo, by = c("V3" = "Entry")) %>%
   select(V1, V3, V4, V13, Protein.names, Organism) %>%
   write_delim("../output/blast_annot_go.tab", delim = '\t')

```