xyz1396 / siprostoolkits-sipros4 Goto Github PK

conda create -n py2 scikit-learn python=2.7
conda create -n mono -c conda-forge mono
conda create -n r -c conda-forge -c bioconda r-base r-stringr r-tidyr bioconductor-biostrings

conda activate mono
# -j is the threads that you want to limit
mono bin/Raxport.exe -i raw -o ft -j 8

# OMP_NUM_THREADS is the threads that you want to limit
export OMP_NUM_THREADS=10
# search the scans against the fasta databse, this command will take a long time
bin/SiprosEnsembleOMP -f demo.FT2 -c configTemplates/SiprosEnsembleConfig.cfg -o sip

conda activate py2
# convert .Spe2Pep.txt file to .tab file
EnsembleScripts/sipros_psm_tabulating.py -i sip -c configTemplates/SiprosEnsembleConfig.cfg -o sip
# filter PSMs, output qualified PSMs to .psm.txt file
EnsembleScripts/sipros_ensemble_filtering.py -i demo.tab configTemplates/SiprosEnsembleConfig.cfg -o sip
# assembly protein groups from peptide, output proteins to .pro.txt
EnsembleScripts/sipros_peptides_assembling.py -c configTemplates/SiprosEnsembleConfig.cfg -w sip

conda activate r
# control FDR, output qualified protein groups to .proRefineFDR.txt
Rscript V4Scripts/refineProteinFDR.R -pro demo.pro.txt -psm demo.psm.txt -fdr 0.005 -o demo
# get spectra count of each protein groups, output spectra count to .SPcount.txt
Rscript V4Scripts/getSpectraCountInEachFT.R -pro dmo.proRefineFDR.txt -psm demo.psm.txt -o demo

# generate configs
mkdir configs raw ft sip fasta
configGenerator -i SiprosV4Config.cfg -o configs -e C

conda activate r

# make db of identified proteins by SiprosEnsemble
Rscript V4Scripts/makeDBforLabelSearch.R \
    -pro YOUR_PATH/*.pro.txt \
    -faa YOUR_PATH/db.fasta \
    -o fasta/db.faa

# search the scans against the fasta database, this command will take a long time
SiprosV4OMP -f demo.FT2 -c C13_10000Pct.cfg -o sip

conda activate py2

# filter PSMs
python V4Scripts/sipros_peptides_filtering.py \
    -c SiprosV4Config.cfg \
    -w sip

# filter proteins
python V4Scripts/sipros_peptides_assembling.py \
    -c SiprosV4Config.cfg \
    -w sip

# cluster SIP abundance of protein
python V4Scripts/ClusterSip.py \
    -c SiprosV4Config.cfg \
    -w sip

conda activate r

# refine protein FDR
Rscript ${binPath}/refineProteinFDR.R \
    -pro sip/*.pro.txt \
    -psm sip/*.psm.txt \
    -fdr 0.01 \
    -o sip/YOUR_FILE_NAME

# get SIP abundance of each protein in each FT2 file
Rscript ${binPath}/getLabelPCTinEachFT.R \
    -pro sip/YOUR_FILE_NAME.proRefineFDR.txt \
    -psm sip/*.psm.txt \
    -thr 5 \
    -o sip/YOUR_FILE_NAME