---
title: "05-Peve energy GO"
author: "Steven Roberts"
date: "`r format(Sys.time(), '%d %B, %Y')`"  
format:
  html:
    toc: true
    toc-depth: 2
    html-math-method: katex
    css: styles.css
    theme: sandstone
editor: 
  markdown: 
    wrap: 72
---




```{r setup, include=FALSE}
knitr::opts_chunk$set(
  echo = TRUE,         # Display code chunks
  eval = FALSE,         # Evaluate code chunks
  warning = FALSE,     # Hide warnings
  message = FALSE,     # Hide messages
  fig.width = 6,       # Set plot width in inches
  fig.height = 4,      # Set plot height in inches
  fig.align = "center", # Align plots to the center
  comment = ""         # Prevents appending '##' to beginning of lines in code output
)
```


Grabbing GOs 

- Glycolysis GO:0006096
- Gluconeogenesis GO:0006094
- Lipolysis/lipid catabolism GO:0016042
- Fatty acid beta oxidation GO:0006635
- Starvation GO:0042594
- Lipid biosynthesis GO:0008610
- Protein catabolic process GO:0030163


#Variables

```{bash}
cd ../data
curl -O https://gannet.fish.washington.edu/seashell/snaps/Porites_evermanni_v1.annot.pep.fa
```


```{r}
# Global R options
knitr::opts_chunk$set(echo = TRUE)

# Define key paths and tool directories
 
OUT_DIR <- "../output/05-Peve-energy-GO/"
evalue <- "1E-20"
fasta <- "../data/Porites_evermanni_v1.annot.pep.fa"

# Export these as environment variables for bash chunks.
Sys.setenv(
  OUT_DIR = OUT_DIR,
  evalue = evalue,
  fasta =fasta
)
```


# Glycolysis GO:0006096

```{bash}
GO="0006096"

curl -H "Accept: text/plain" "https://rest.uniprot.org/uniprotkb/stream?format=fasta&query=%28%28go%3A"${GO}"%29%29+AND+%28reviewed%3Atrue%29" -o "${OUT_DIR}"SwissProt-GO:"${GO}".fa

head "${OUT_DIR}"SwissProt-GO:"${GO}".fa

echo "Number of Proteins"
grep -c ">" "${OUT_DIR}"SwissProt-GO:"${GO}".fa

/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in "${OUT_DIR}"SwissProt-GO:"${GO}".fa \
-dbtype prot \
-out "${OUT_DIR}"SwissProt-GO:"${GO}"


/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db "${OUT_DIR}"SwissProt-GO:"${GO}" \
-out "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab \
-evalue "${evalue}" \
-num_threads 42 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
2> "${OUT_DIR}"blast_warnings"${GO}".txt

head "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab

echo "Number of hits"

wc -l "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab
```


# Gluconeogenesis GO:0006094

```{bash}
GO="0006094"

curl -H "Accept: text/plain" "https://rest.uniprot.org/uniprotkb/stream?format=fasta&query=%28%28go%3A"${GO}"%29%29+AND+%28reviewed%3Atrue%29" -o "${OUT_DIR}"SwissProt-GO:"${GO}".fa

head "${OUT_DIR}"SwissProt-GO:"${GO}".fa

echo "Number of Proteins"
grep -c ">" "${OUT_DIR}"SwissProt-GO:"${GO}".fa

/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in "${OUT_DIR}"SwissProt-GO:"${GO}".fa \
-dbtype prot \
-out "${OUT_DIR}"SwissProt-GO:"${GO}"


/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db "${OUT_DIR}"SwissProt-GO:"${GO}" \
-out "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab \
-evalue "${evalue}" \
-num_threads 42 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
2> "${OUT_DIR}"blast_warnings"${GO}".txt

head "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab

echo "Number of hits"

wc -l "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab
```


# Lipolysis/lipid catabolism GO:0016042

```{bash}
GO="0016042"

curl -H "Accept: text/plain" "https://rest.uniprot.org/uniprotkb/stream?format=fasta&query=%28%28go%3A"${GO}"%29%29+AND+%28reviewed%3Atrue%29" -o "${OUT_DIR}"SwissProt-GO:"${GO}".fa

head "${OUT_DIR}"SwissProt-GO:"${GO}".fa

echo "Number of Proteins"
grep -c ">" "${OUT_DIR}"SwissProt-GO:"${GO}".fa

/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in "${OUT_DIR}"SwissProt-GO:"${GO}".fa \
-dbtype prot \
-out "${OUT_DIR}"SwissProt-GO:"${GO}"


/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db "${OUT_DIR}"SwissProt-GO:"${GO}" \
-out "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab \
-evalue "${evalue}" \
-num_threads 42 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
2> "${OUT_DIR}"blast_warnings"${GO}".txt

head "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab

echo "Number of hits"

wc -l "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab
```


# Fatty acid beta oxidation GO:0006635

```{bash}
GO="0006635"

curl -H "Accept: text/plain" "https://rest.uniprot.org/uniprotkb/stream?format=fasta&query=%28%28go%3A"${GO}"%29%29+AND+%28reviewed%3Atrue%29" -o "${OUT_DIR}"SwissProt-GO:"${GO}".fa

head "${OUT_DIR}"SwissProt-GO:"${GO}".fa

echo "Number of Proteins"
grep -c ">" "${OUT_DIR}"SwissProt-GO:"${GO}".fa

/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in "${OUT_DIR}"SwissProt-GO:"${GO}".fa \
-dbtype prot \
-out "${OUT_DIR}"SwissProt-GO:"${GO}"


/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db "${OUT_DIR}"SwissProt-GO:"${GO}" \
-out "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab \
-evalue "${evalue}" \
-num_threads 42 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
2> "${OUT_DIR}"blast_warnings"${GO}".txt

head "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab

echo "Number of hits"

wc -l "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab
```

# Starvation GO:0042594

```{bash}
GO="0042594"

curl -H "Accept: text/plain" "https://rest.uniprot.org/uniprotkb/stream?format=fasta&query=%28%28go%3A"${GO}"%29%29+AND+%28reviewed%3Atrue%29" -o "${OUT_DIR}"SwissProt-GO:"${GO}".fa

head "${OUT_DIR}"SwissProt-GO:"${GO}".fa

echo "Number of Proteins"
grep -c ">" "${OUT_DIR}"SwissProt-GO:"${GO}".fa

/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in "${OUT_DIR}"SwissProt-GO:"${GO}".fa \
-dbtype prot \
-out "${OUT_DIR}"SwissProt-GO:"${GO}"


/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db "${OUT_DIR}"SwissProt-GO:"${GO}" \
-out "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab \
-evalue "${evalue}" \
-num_threads 42 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
2> "${OUT_DIR}"blast_warnings"${GO}".txt

head "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab

echo "Number of hits"

wc -l "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab
```


# Lipid biosynthesis GO:0008610

```{bash}
GO="0008610"

curl -H "Accept: text/plain" "https://rest.uniprot.org/uniprotkb/stream?format=fasta&query=%28%28go%3A"${GO}"%29%29+AND+%28reviewed%3Atrue%29" -o "${OUT_DIR}"SwissProt-GO:"${GO}".fa

head "${OUT_DIR}"SwissProt-GO:"${GO}".fa

echo "Number of Proteins"
grep -c ">" "${OUT_DIR}"SwissProt-GO:"${GO}".fa

/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in "${OUT_DIR}"SwissProt-GO:"${GO}".fa \
-dbtype prot \
-out "${OUT_DIR}"SwissProt-GO:"${GO}"


/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db "${OUT_DIR}"SwissProt-GO:"${GO}" \
-out "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab \
-evalue "${evalue}" \
-num_threads 42 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
2> "${OUT_DIR}"blast_warnings"${GO}".txt

head "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab

echo "Number of hits"

wc -l "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab
```



# Protein catabolic process GO:0030163

```{bash}
GO="0030163"

curl -H "Accept: text/plain" "https://rest.uniprot.org/uniprotkb/stream?format=fasta&query=%28%28go%3A"${GO}"%29%29+AND+%28reviewed%3Atrue%29" -o "${OUT_DIR}"SwissProt-GO:"${GO}".fa

head "${OUT_DIR}"SwissProt-GO:"${GO}".fa

echo "Number of Proteins"
grep -c ">" "${OUT_DIR}"SwissProt-GO:"${GO}".fa

/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in "${OUT_DIR}"SwissProt-GO:"${GO}".fa \
-dbtype prot \
-out "${OUT_DIR}"SwissProt-GO:"${GO}"


/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db "${OUT_DIR}"SwissProt-GO:"${GO}" \
-out "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab \
-evalue "${evalue}" \
-num_threads 42 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6 \
2> "${OUT_DIR}"blast_warnings"${GO}".txt

head "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab

echo "Number of hits"

wc -l "${OUT_DIR}"Apul_blastp-GO:"${GO}"_out.tab
```

```{r, engine='bash', eval=TRUE}
wc -l "${OUT_DIR}"*tab
```