/scripts/commands-components_1_3cvs-gffmerged.txt
Version 2

_p_stRT/_I_STRT/_S_04_stPanTr/_A_03_components_3cvs-GFFmerged

SEEK ID: https://fairdomhub.org/data_files/3470?version=2

Filename: commands-components_1_3cvs-gffmerged.txt  Download

Format: Plain text document

Size: 4.99 KB

# zagor

## input
# ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-D_aa_representatives.fasta
# ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-D_cds_representatives.fasta
# ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-P_aa_representatives.fasta
# ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-P_cds_representatives.fasta
# ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-R_aa_representatives.fasta
# ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-R_cds_representatives.fasta
# ../../_A_01_GC_content-count/input/StPGSC4.04n_seq_3_PGSC-c-rep_ITAG-cds_gff-2019-04-23.fasta
# ../../_A_02_cdhit_3cvs-GFFmerged/input/StPGSC4.04n_seq_4_PGSC-p-rep_ITAG-pep_gff-2019-04-23.fasta
# ../../_A_02_cdhit_3cvs-GFFmerged/input/Solanum_tuberosum_PGSC_DM_v4.04_converterWithDescriptions.txt


# cd ../scripts

cat ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-*_aa_representatives.fasta ../../_A_02_cdhit_3cvs-GFFmerged/input/StPGSC4.04n_seq_4_PGSC-p-rep_ITAG-pep_gff-2019-04-23.fasta > ../output/stPanTr.aa.fasta
cat ../../../_S_03_stCuSTr/_A_03.2_components/output/fasta_1A_rep-per-cv/stCuSTr-*_cds_representatives.fasta ../../_A_01_GC_content-count/input/StPGSC4.04n_seq_3_PGSC-c-rep_ITAG-cds_gff-2019-04-23.fasta > ../output/stPanTr.cds.fasta
cut -f1 -d " " ../output/stPanTr.aa.fasta | sponge ../output/stPanTr.aa.fasta
cut -f1 -d " " ../output/stPanTr.cds.fasta | sponge ../output/stPanTr.cds.fasta

grep ">" ../output/stPanTr.aa.fasta | wc -l
grep ">" ../output/stPanTr.cds.fasta | wc -l
wc -l ../../_A_02_cdhit_3cvs-GFFmerged/output/5cv_weak-components.txt

cut -f4  ../../_A_02_cdhit_3cvs-GFFmerged/output/5cv_weak-components.txt | grep -w "representative" -n | wc -l
cut -f4  ../../_A_02_cdhit_3cvs-GFFmerged/output/5cv_weak-components.txt | grep -w "alternative" -n | wc -l

cut -f4  ../../_A_02_cdhit_3cvs-GFFmerged/output/5cv_weak-components.txt | grep -w "representative" -n | cut -d : -f 1 | wc -l
cut -f4  ../../_A_02_cdhit_3cvs-GFFmerged/output/5cv_weak-components.txt | grep -w "alternative" -n | cut -d : -f 1 | wc -l 

awk '$4 == "representative" {print $1}' ../../_A_02_cdhit_3cvs-GFFmerged/output/5cv_weak-components.txt > ../output/rep.cds.IDs
awk '$4 == "alternative" {print $1}' ../../_A_02_cdhit_3cvs-GFFmerged/output/5cv_weak-components.txt > ../output/alt.cds.IDs

wc -l ../output/rep.cds.IDs
wc -l ../output/alt.cds.IDs


xargs faidx -d ' ' ../output/stPanTr.cds.fasta < ../output/rep.cds.IDs > ../output/stPanTr_rep.cds.fasta 2> ../output/stPanTr_rep.cds.error;
xargs faidx -d ' ' ../output/stPanTr.cds.fasta < ../output/alt.cds.IDs > ../output/stPanTr_alt.cds.fasta 2> ../output/stPanTr_alt.cds.error;

sort ../output/rep.cds.IDs | sponge ../output/rep.cds.IDs
sort ../output/alt.cds.IDs | sponge ../output/alt.cds.IDs
cp ../../_A_02_cdhit_3cvs-GFFmerged/input/Solanum_tuberosum_PGSC_DM_v4.04_converterWithDescriptions.txt ../input/Solanum_tuberosum_PGSC_DM_v4.04_converterWithDescriptions.txt
sort -u -k 3 ../input/Solanum_tuberosum_PGSC_DM_v4.04_converterWithDescriptions.txt | sponge ../input/Solanum_tuberosum_PGSC_DM_v4.04_converterWithDescriptions.txt
cut -f3,4  ../input/Solanum_tuberosum_PGSC_DM_v4.04_converterWithDescriptions.txt > ../output/Solanum_tuberosum_PGSC_DM_v4.04_CDS-to-AA_converter.txt

join  ../output/rep.cds.IDs ../output/Solanum_tuberosum_PGSC_DM_v4.04_CDS-to-AA_converter.txt | cut -f2 -d " " > ../output/PGSC.rep.aa.IDs
grep -v "PGSC*" ../output/rep.cds.IDs > ../output/nonPGSC.rep.aa.IDs
join  ../output/alt.cds.IDs ../output/Solanum_tuberosum_PGSC_DM_v4.04_CDS-to-AA_converter.txt | cut -f2 -d " " > ../output/PGSC.alt.aa.IDs
grep -v "PGSC*" ../output/alt.cds.IDs > ../output/nonPGSC.alt.aa.IDs

cat ../output/PGSC.alt.aa.IDs ../output/nonPGSC.alt.aa.IDs > ../output/alt.aa.IDs
cat ../output/PGSC.rep.aa.IDs ../output/nonPGSC.rep.aa.IDs > ../output/rep.aa.IDs
wc -l ../output/alt.aa.IDs
wc -l ../output/rep.aa.IDs



xargs faidx -d ' ' ../output/stPanTr.aa.fasta < ../output/rep.aa.IDs > ../output/stPanTr_rep.aa.fasta 2> ../output/stPanTr_rep.aa.error;
xargs faidx -d ' ' ../output/stPanTr.aa.fasta < ../output/alt.aa.IDs > ../output/stPanTr_alt.aa.fasta 2> ../output/stPanTr_alt.aa.error;


grep ">" ../output/stPanTr_rep.aa.fasta | wc -l
grep ">" ../output/stPanTr_alt.aa.fasta | wc -l



if [ -s ../output/stPanTr_rep.aa.error ] ; then
echo "check ../output/stPanTr_rep.aa.error"
else
rm ../output/stPanTr_rep.aa.error
fi

if [ -s ../output/stPanTr_alt.aa.error ] ; then
echo "check ../output/stPanTr_alt.aa.error"
else
rm ../output/stPanTr_alt.aa.error
fi

if [ -s ../output/stPanTr_rep.cds.error ] ; then
echo "check ../output/stPanTr_rep.cds.error"
else
rm ../output/stPanTr_rep.cds.error
fi

if [ -s ../output/stPanTr_alt.cds.error ] ; then
echo "check ../output/stPanTr_alt.cds.error"
else
rm ../output/stPanTr_alt.cds.error
fi


rm ../output/*.fai
rm ../output/*PGSC*IDs*
rm ../output/*nonPGSC*
rm ../output/*PGSC.*
rm ../output/*.error





help Creators and Submitter
Creator
Submitter
Activity

Views: 2470   Downloads: 135

Created: 19th Mar 2020 at 10:56

Last updated: 12th Apr 2020 at 09:28

help Tags
help Attributions

None

Version History

Version 2 (latest) Created 12th Apr 2020 at 09:28 by Maja Zagorscak

No revision comments

Powered by
(v.1.18.0)