13-ortho-select

head ../output/11-orthology-analysis/ortholog_groups.csv

wc -l ../output/11-orthology-analysis/ortholog_groups.csv

Annotated

head ../output/12-ortho-annot/ortholog_groups_annotated.csv

wc -l ../output/12-ortho-annot/ortholog_groups_annotated.csv

Physiology based selection

Filter for specific GO terms

# Filter orthologs for metabolic and stress-related processes
echo "Filtering for:"
echo "- Glycolysis (GO:0006096)"
echo "- Gluconeogenesis (GO:0006094)"
echo "- Lipolysis/lipid catabolism (GO:0016042)"
echo "- Fatty acid beta oxidation (GO:0006635)"
echo "- Starvation (GO:0042594)"
echo "- Lipid biosynthesis (GO:0008610)"
echo "- Protein catabolic process (GO:0030163)"
echo "- Reproductive Process (GO:0022414)"
echo ""

# Create output directory if it doesn't exist
mkdir -p ../output/13-ortho-select

# Extract header
head -1 ../output/12-ortho-annot/ortholog_groups_annotated.csv > ../output/13-ortho-select/selected_orthologs.csv

# Filter for the specified GO terms and reproduction-related processes
grep -E 'GO:0006096|GO:0006094|GO:0016042|GO:0006635|GO:0042594|GO:0008610|GO:0030163|GO:0022414' \
  ../output/12-ortho-annot/ortholog_groups_annotated.csv \
  >> ../output/13-ortho-select/selected_orthologs.csv

echo "Total orthologs selected:"
wc -l ../output/13-ortho-select/selected_orthologs.csv

# Show first few selected orthologs
head ../output/13-ortho-select/selected_orthologs.csv

# Count orthologs by each GO category
echo "=== Glycolysis (GO:0006096) ==="
grep -c 'GO:0006096' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

echo "=== Gluconeogenesis (GO:0006094) ==="
grep -c 'GO:0006094' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

echo "=== Lipolysis/lipid catabolism (GO:0016042) ==="
grep -c 'GO:0016042' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

echo "=== Fatty acid beta oxidation (GO:0006635) ==="
grep -c 'GO:0006635' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

echo "=== Starvation (GO:0042594) ==="
grep -c 'GO:0042594' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

echo "=== Lipid biosynthesis (GO:0008610) ==="
grep -c 'GO:0008610' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

echo "=== Protein catabolic process (GO:0030163) ==="
grep -c 'GO:0030163' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

echo "=== Reproductive Process (GO:0022414) ==="
grep -c 'GO:0022414' ../output/13-ortho-select/selected_orthologs.csv || echo "0"

Other Formats

Annotated

Physiology based selection

Filter for specific GO terms