Tackled two primary tasks

Identified proteins involved in key energy utilization pathways and identified proteins corresponding to epigenetic machinery.

For the energy utilization pathways,

we focused on the following:

- 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

and ran something on order of.

Variables

# Global R options
knitr::opts_chunk$set(echo = TRUE)

# Define key paths and tool directories
 
OUT_DIR <- "../output/23-Apul-energy-GO/"
evalue <- "1E-20"
fasta <- "../data/Apulchra-genome.pep.faa"

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

Glycolysis GO:0006096

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

For Machinery…

more along the lines of

Apul

https://raw.githubusercontent.com/urol-e5/deep-dive-expression/main/D-Apul/data/Apulchra-genome.pep.faa

cd ../data
curl -o Apulchra-genome.pep.faa https://raw.githubusercontent.com/urol-e5/deep-dive-expression/main/D-Apul/data/Apulchra-genome.pep.faa

head ../data/Apulchra-genome.pep.faa


/home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \
-in ../data/Apulchra-genome.pep.faa \
-dbtype prot \
-out ../output/25-Apul-epimods-blast/Apul-proteins

head ../data/Machinery.fasta

fasta="../data/Machinery.fasta"

/home/shared/ncbi-blast-2.15.0+/bin/blastp \
-query $fasta \
-db ../output/25-Apul-epimods-blast/Apul-proteins \
-out ../output/25-Apul-epimods-blast/Mach-blastp-Apul_out.tab \
-evalue 1E-05 \
-num_threads 48 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt 6

wc -l ../output/25-Apul-epimods-blast/Mach-blastp-Apul_out.tab

head ../output/25-Apul-epimods-blast/Mach-blastp-Apul_out.tab

--- title: "Energy staging" description: "Can we predict where they are on the curve?" categories: [e5, methylation] #citation: date: 04-10-2025 image: http://gannet.fish.washington.edu/seashell/snaps/Monosnap_23_GO_Annoations_2025-04-10_12-36-18.png # finding a good image author: - name: Steven Roberts url: orcid: 0000-0001-8302-1138 affiliation: Professor, UW - School of Aquatic and Fishery Sciences affiliation-url: https://robertslab.info #url: # self-defined draft: false # setting this to `true` will prevent your post from appearing on your listing page until you're ready! format: html: code-fold: FALSE code-tools: true code-copy: true highlight-style: github code-overflow: wrap --- ```{r esetup, include=FALSE} knitr::opts_chunk$set( echo = TRUE, # Display code chunks eval = FALSE, # Avoid automatic execution warning = FALSE, # Hide warnings message = FALSE, # Hide messages fig.width = 6, # Set default plot width fig.height = 4, # Set default plot height fig.align = "center", # Center align plots comment = "" # Prevents '##' in output ) ``` Tackled two primary tasks Identified proteins involved in key energy utilization pathways and identified proteins corresponding to epigenetic machinery. # For the energy utilization pathways, we focused on the following: ``` - Glycolysis GO:0006096 - Gluconeogenesis GO:0006094 - Lipolysis/lipid catabolism GO:0016042 - Fatty acid beta oxidation GO:0006635 - Starvation GO:0042594 - Lipid biosynthesis GO:0008610 - Protein catabolic process GO:0030163 ``` and ran something on order of. # Variables ```{r} # Global R options knitr::opts_chunk$set(echo = TRUE) # Define key paths and tool directories OUT_DIR <- "../output/23-Apul-energy-GO/" evalue <- "1E-20" fasta <- "../data/Apulchra-genome.pep.faa" # 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 ``` # For Machinery... more along the lines of Apul https://raw.githubusercontent.com/urol-e5/deep-dive-expression/main/D-Apul/data/Apulchra-genome.pep.faa ```{bash} cd ../data curl -o Apulchra-genome.pep.faa https://raw.githubusercontent.com/urol-e5/deep-dive-expression/main/D-Apul/data/Apulchra-genome.pep.faa ``` ```{bash} head ../data/Apulchra-genome.pep.faa ``` ```{bash} /home/shared/ncbi-blast-2.15.0+/bin/makeblastdb \ -in ../data/Apulchra-genome.pep.faa \ -dbtype prot \ -out ../output/25-Apul-epimods-blast/Apul-proteins ``` ```{bash} head ../data/Machinery.fasta ``` ```{bash} fasta="../data/Machinery.fasta" /home/shared/ncbi-blast-2.15.0+/bin/blastp \ -query $fasta \ -db ../output/25-Apul-epimods-blast/Apul-proteins \ -out ../output/25-Apul-epimods-blast/Mach-blastp-Apul_out.tab \ -evalue 1E-05 \ -num_threads 48 \ -max_target_seqs 1 \ -max_hsps 1 \ -outfmt 6 ``` ```{r, engine='bash'} wc -l ../output/25-Apul-epimods-blast/Mach-blastp-Apul_out.tab ``` ```{r, engine='bash'} head ../output/25-Apul-epimods-blast/Mach-blastp-Apul_out.tab ```