/scripts/01.2_commands-CDHIT-2D.txt
Version 1

_p_stRT/_I_STRT/_S_04_stPanTr/_A_02_cdhit_3cvs-GFFmerged

SEEK ID: https://fairdomhub.org/data_files/3460?version=1

Filename: scripts/01.2_commands-CDHIT-2D.txt  Download

Format: Plain text document

Size: 1.27 KB

# zagor
# set of commands B)

###########################
### post R script chunk ###

# if not: cd ../intermediate
dos2unix singletons.tetra.seqID.txt
dos2unix singletons.DM.seqID.txt

xargs faidx -d ' ' ../input/5cv.aa.fasta < singletons.tetra.seqID.txt > stPanTr_aa_singletons.tetraploid.fasta 2> stPanTr_aa_singletons.tetraploid.error;
xargs faidx -d ' ' ../input/5cv.aa.fasta < singletons.DM.seqID.txt > stPanTr_aa_singletons.DM.fasta 2> stPanTr_aa_singletons.DM.error;

# replace * in polypeptide Sotub sequences with X
sed 's/[*]/X/g' stPanTr_aa_singletons.DM.fasta | sponge stPanTr_aa_singletons.DM.fasta

##################
### cdhit-2d   ###
##################

cdhit-2d -i stPanTr_aa_singletons.DM.fasta \
-i2 stPanTr_aa_singletons.tetraploid.fasta \
-o stPanTr_aa_singletons_tetra_on_DM_aS.45_c.90 \
-G 0 -n 5 -g 1 -c 0.90 -aS 0.45 -p 1 -bak 1 -d 200 -b 45 -uS 0.55 \
-M 0 -T 28;
# 43005 compared  429 clustered


cdhit-2d -i stPanTr_aa_singletons.tetraploid.fasta \
-i2 stPanTr_aa_singletons.DM.fasta \
-o stPanTr_aa_singletons_DM_on_tetra_aS.45_c.90 \
-G 0 -n 5 -g 1 -c 0.90 -aS 0.45 -p 1 -bak 1 -d 200 -b 45 -uS 0.55 \
-M 0 -T 28;
# 17439 compared  262 clustered

# now run 
## chunks: cdhit-2d 1 - cdhit-2d 8 and , merge 1 - , merge 5



rm ../input/5cv.aa.fasta
rm ../input/5cv.cds.fasta
help Creators and Submitter
Creator
Submitter
Activity

Views: 2460   Downloads: 70

Created: 19th Mar 2020 at 10:54

Last updated: 19th Mar 2020 at 10:54

help Tags
help Attributions

None

Version History

Version 1 (earliest) Created 19th Mar 2020 at 10:54 by Andrej Blejec

No revision comments

Powered by
(v.1.18.0)