---
tags: prions-fo-life
title: Annotating plaac-positive proteins with InterProScan and KOs
---

# Annotating plaac-positive proteins with InterProScan and KOs

Working with data from 1-Jun-2021, UniProt "Standard" proteomes only. The files used below are from [this drive](https://drive.google.com/drive/u/0/folders/1AO0Q_nHx4iNA1loP8LO8CGmSUloJ9lVH).

---
> **NOTE**
> The code below works based on the directory structure in [the google drive](https://drive.google.com/drive/u/0/folders/1AO0Q_nHx4iNA1loP8LO8CGmSUloJ9lVH), with commands being run from within the sub-directory "[further-annotating-plaac-positive-proteins](https://drive.google.com/drive/u/0/folders/1unPlMfWbnvGCV5fD59qXVGwOepE7-R18)". If not working in that structure, the code below would need to be modified to point to the correct file paths.
---

[toc]

# Environment setup

conda install -c conda-forge mamba

## bit

mamba create -n bit -c conda-forge -c bioconda -c defaults -c astrobiomike bit=1.8.42

## Interproscan

mamba create -n interproscan5 -c conda-forge -c bioconda -c defaults interproscan=5.54_87.0

5.54_87.0

conda activate interproscan

# setting up reference db
wget http://ftp.ebi.ac.uk/pub/software/unix/iprscan/5/5.54_87.0/interproscan-5.54_87.0-64-bit.tar.gz

tar -pxvzf interproscan-5.54_87.0-64-bit.tar.gz

rm -rf ${CONDA_PREFIX}/share/InterProScan/data/

mv interproscan-5.54_87.0/data/ ${CONDA_PREFIX}/share/InterProScan

rm -rf interproscan-5.54_87.0/ interproscan-5.54_87.0-64-bit.tar.gz

# test
interproscan.sh -i ${CONDA_PREFIX}/share/InterProScan/test_all_appl.fasta -f tsv

interproscan.sh -i ${CONDA_PREFIX}/share/InterProScan/test_all_appl.fasta -f tsv -dp

Setting to automatically delete working directory after finishing (though it only deletes the files, not the temp dir it makes):

# doing in a way that works on typical darwin sed also
sed 's/delete.temporary.directory.on.completion=false/delete.temporary.directory.on.completion=true/' ${CONDA_PREFIX}/share/InterProScan/interproscan.properties > t && mv t ${CONDA_PREFIX}/share/InterProScan/interproscan.properties

## KOFamScan

mamba create -y -n kofamscan -c conda-forge -c bioconda -c defaults kofamscan=1.3.0 hmmer=3.3.0

# getting ref db, need to point to these when running
curl -L -O ftp://ftp.genome.jp/pub/db/kofam/ko_list.gz
gunzip ko_list.gz

curl -L -O ftp://ftp.genome.jp/pub/db/kofam/profiles.tar.gz
tar -xzvf profiles.tar.gz && rm profiles.tar.gz

# Getting fasta files of plaac-positive proteins

mkdir archaea bacteria eukarya

conda activate bit

bit-parse-fasta-by-headers -i ../archaea/reference-genome-info/archaea-proteomes.faa.gz -w ../archaea/plaac-core-score-0/archaea-plaac-core-score-0-positive-protein-accs.txt -o archaea/archaea-plaac-positive-seqs.faa --gz

bit-parse-fasta-by-headers -i ../bacteria/reference-genome-info/bacteria-proteomes.faa.gz -w ../bacteria/plaac-core-score-0/bacteria-plaac-core-score-0-positive-protein-accs.txt -o bacteria/bacteria-plaac-positive-seqs.faa --gz

bit-parse-fasta-by-headers -i ../eukarya/reference-genome-info/eukarya-proteomes.faa.gz -w ../eukarya/plaac-core-score-0/eukarya-plaac-core-score-0-positive-protein-accs.txt -o eukarya/eukarya-plaac-positive-seqs.faa --gz

# Running annotations
Scripts are below and in the [google drive](https://drive.google.com/drive/u/0/folders/1unPlMfWbnvGCV5fD59qXVGwOepE7-R18) in the "helper-scripts" subdirectory.

bash helper-scripts/run-kofamscan.sh

bash helper-scripts/run-interproscan.sh

# Scripts

## run-kofamscan.sh

#!/usr/env/bin bash
set -e

eval "$(conda shell.bash hook)"

for domain in archaea bacteria eukarya
do

    printf "\n\n\tDoing ${domain}\n\n"

    mkdir -p ${domain}/${domain}-ko-annotations

    conda activate kofamscan
    exec_annotation -p profiles/ -k ko_list --cpu 50 -f detail-tsv -o ${domain}/${domain}-ko-annotations/${domain}-ko-annots.tmp ${domain}/${domain}-plaac-positive-seqs.faa
    rm -rf tmp

    conda deactivate
    conda activate bit

    bit-filter-KOFamScan-results -i ${domain}/${domain}-ko-annotations/${domain}-ko-annots.tmp -o ${domain}/${domain}-ko-annotations/${domain}-plaac-positive-KO-annots.tsv
    rm ${domain}/${domain}-ko-annotations/${domain}-ko-annots.tmp

done

## run-interproscan.sh

#!/usr/env/bin bash
set -e

eval "$(conda shell.bash hook)"

conda activate interproscan5

for domain in archaea bacteria
do

    printf "\n\n\tDoing ${domain}\n\n"

    mkdir -p ${domain}/${domain}-interproscan-out

    interproscan.sh --cpu 20 --goterms --disable-residue-annot -f tsv -i ${domain}/${domain}-plaac-positive-seqs.faa -o ${domain}/${domain}-interproscan-out/${domain}-interpro-out.tsv 2> ${domain}/${domain}-interproscan-out/${domain}-interpro-stderr.log

    rm -rf temp/

done

# splitting euks because it's a lot of seqs
head -n 110000 eukarya/eukarya-plaac-positive-seqs.faa > eukarya/eukarya-plaac-positive-seqs-p1.faa
sed -n '110001,210000p' eukarya/eukarya-plaac-positive-seqs.faa > eukarya/eukarya-plaac-positive-seqs-p2.faa
sed -n '210001,310000p' eukarya/eukarya-plaac-positive-seqs.faa > eukarya/eukarya-plaac-positive-seqs-p3.faa
sed -n '310001,421018p' eukarya/eukarya-plaac-positive-seqs.faa > eukarya/eukarya-plaac-positive-seqs-p4.faa

for set in p1 p2 p3 p4
do
    printf "\n\n\tDoing eukarya ${set}\n\n"
    interproscan.sh --cpu 20 --goterms --disable-residue-annot -f tsv -i eukarya/eukarya-plaac-positive-seqs-${set}.faa -o eukarya/eukarya-interproscan-out/eukarya-interpro-out-${set}.tsv 2> eukarya/eukarya-interproscan-out/eukarya-interpro-${set}-stderr.log
    
    rm -rf temp

done