Comandas Shell para material y métodos
4.i Instalación BLAST
export PATH=$PATH:/disc8/bin/exonerate/bin
export PATH=$PATH:/disc8/bin
export WISECONFIGDIR=/disc8/soft/wise-2.2.0/wisecfg
Aplicacions_RepositoriUPF_BLAST i NETBLAST
4.ii Creación base de datos
formatdb -i B_bigemina.contigs.fa -p F
4.iii tBLASTn
blastall -p TBLASTN -d B_bigemina.contigs.fa -i selenopthsapiens.fa -e 10.0 -F F> alinsinx10.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i selenopthsapiens.fa -e 1.0 -F F> alinsinx1.txt
Para obtener los resultados en forma de tabla:
blastall -p TBLASTN -d B_bigemina.contigs.fa -i selenopthsapiens.fa -e 1.0 -F F -m 9 > alintaula1.txt
4.v Index selenoproteínas humanas y contigns de B.bigemina
fastaindex selenopthsapiens.fa selenopthsapiens.index
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000005_1.0> GPx2.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000002_1.0> DI2.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000032_1.0> SPS1.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000013_1.0> Sel15.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000015_1.0> SelI.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000021_1.0> SelR1.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000023_1.0> SelR3.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000024_1.0> SelS.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000028_1.0> SelU3.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000031_1.0> SelW2.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000038_1.0> eEFSec.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000029_1.0> SelV.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000034_1.0> TR1.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000035_1.0> TR2.fa
fastafetch selenopthsapiens.fa selenopthsapiens.index SPP00000036_1.0> TR3.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig2766 > contig2766.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig2984 > contig2984.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig3973 > contig3973.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4131.0 > contig4131.0.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4096 > contig4096.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4165 > contig4165.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig1507 > contig1507.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4088 > contig4088.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig1916 > contig1916.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4102 > contig4102.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig3160 > contig3160.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4158 > contig4158.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4075 > contig4075.fa
4.vi Extracción subsecuencias
fastasubseq -f contig2766.fa -s 4000 -l 3000> blast2766_4000-7000.fa
fastasubseq -f contig4096.fa -s 45000 -l 3000> blast4096_45000-48000.fa
fastasubseq -f contig4158.fa -s 21000 -l 3000> blast4158_21000-24000.fa
fastasubseq -f contig4075.fa -s 18500 -l 3000> blast4075_18500-21500.fa
fastasubseq -f contig2984.fa -s 0 -l 3000> blast2984_0-3000.fa
fastasubseq -f contig3973.fa -s 9000 -l 3000> blast3973_9000-12000.fa
fastasubseq -f contig4131.0.fa -s 37000 -l 3000> blast4131.0_37000-40000.fa
fastasubseq -f contig4165.fa -s 9500 -l 3000> blast4165_9500-12500.fa
fastasubseq -f contig1507.fa -s 0 -l 1000> blast1507_0-3000.fa
fastasubseq -f contig4088.fa -s 0 -l 3000> blast4088_0-3000.fa
fastasubseq -f contig1916.fa -s 1500 -l 3000> blast1916_1500-4500.fa
fastasubseq -f contig4102.fa -s 34000 -l 3000> blast4102_34000-37000.fa
fastasubseq -f contig3160.fa -s 13500 -l 3000> blast3160_13500-16500.fa
4.vii Paso de forma reversa a directa
fastarevcomp contig2984.fa> revc2984.fa
fastarevcomp contig3973.fa> revc3973.fa
fastarevcomp contig4131.0.fa> revc4131.0.fa
fastarevcomp contig4165.fa> revc4165.fa
fastarevcomp contig1507.fa> revc1507.fa
fastarevcomp contig4088.fa> revc4088.fa
fastarevcomp contig1916.fa> revc1916.fa
fastarevcomp contig4102.fa> revc4102.fa
fastarevcomp contig3160.fa> revc3160.fa
4.viii Repeteción de los pasos anteriore para las reversas
formatdb -i revc3973.fa -p F
formatdb -i revc4131.0.fa -p F
formatdb -i revc4165.fa -p F
formatdb -i revc1507.fa -p F
formatdb -i revc4088.fa -p F
formatdb -i revc1916.fa -p F
formatdb -i revc4102.fa -p F
formatdb -i revc3160.fa -p F
blastall -p TBLASTN -d revc3973.fa -i SPS1.fa -e 1.0 -F F -m 9 > r3973alintaula1.txt
blastall -p TBLASTN -d revc4131.0.fa -i Sel15.fa -e 1.0 -F F -m 9 > r4131.0alintaula1.txt
blastall -p TBLASTN -d revc4165.fa -i SelR1.fa -e 1.0 -F F -m 9 > r4165alintaula1.txt
blastall -p TBLASTN -d revc1507.fa -i SelR3.fa -e 1.0 -F F -m 9 > r1507alintaula1.txt
blastall -p TBLASTN -d revc4088.fa -i SelS.fa -e 1.0 -F F -m 9 > r4088alintaula1.txt
blastall -p TBLASTN -d revc1916.fa -i SelU3.fa -e 1.0 -F F -m 9 > r1916alintaula1.txt
blastall -p TBLASTN -d revc4102.fa -i SelW2.fa -e 1.0 -F F -m 9 > r4102alintaula1.txt
blastall -p TBLASTN -d revc3160.fa -i eEFSec.fa -e 1.0 -F F -m 9 > r3160alintaula1.txt
fastasubseq -f revc2984.fa -s 0 -l 3000> rblast2984_0-3000.fa
fastasubseq -f revc3973.fa -s 9000 -l 3000> rblast3973_9000-12000.fa
fastasubseq -f revc4131.0.fa -s 37000 -l 3000> rblast4131.0_37000-40000.fa
fastasubseq -f revc4165.fa -s 9500 -l 3000> rblast4165_9500-12500.fa
fastasubseq -f revc1507.fa -s 0 -l 1000> rblast1507_0-3000.fa
fastasubseq -f revc4088.fa -s 0 -l 3000> rblast4088_0-3000.fa
fastasubseq -f revc1916.fa -s 1500 -l 3000> rblast1916_1500-4500.fa
fastasubseq -f revc4102.fa -s 34000 -l 3000> rblast4102_34000-37000.fa
fastasubseq -f revc3160.fa -s 13500 -l 3000> rblast3160_13500-16500.fa
4.ix Genewise
genewise GPx2.fa blast2766_4000-7000.fa> GPx2genewise.fa
genewise SelI.fa blast4096_45000-48000.fa> SelIgenewise.fa
genewise TR1.fa blast4075_18500-21500.fa> TR1genewise.fa
genewise TR2.fa blast4075_18500-21500.fa> TR2genewise.fa
genewise TR3.fa blast4075_18500-21500.fa> TR3genewise.fa
genewise SelV.fa blast4158_21000-24000.fa> SelVgenewise.fa
genewise DI2.fa rblast2984_0-3000.fa> rDI2genewise.fa
genewise SPS1.fa rblast3973_9000-12000.fa> rSPS1genewise.fa
genewise Sel15.fa rblast4131.0_37000-40000.fa> rSel15genewise.fa
genewise SelR1.fa rblast4165_9500-12500.fa> rSelR1genewise.fa
genewise SelR3.fa rblast1507_0-3000.fa > rSelR3genewise.fa
genewise SelS.fa rblast4088_0-3000.fa> rSelSgenewise.fa
genewise SelU3.fa rblast1916_1500-4500.fa> rSelU3genewise.fa
genewise SelW2.fa rblast4102_34000-37000.fa> rSelW2genewise.fa
genewise eEFSec.fa rblast3160_13500-16500.fa> reEFSecgenewise.fa
4.x Exonerate
exonerate -m p2g -q GPx2.fa -t blast2766_4000-7000.fa> GPx2exonerate.fa
exonerate -m p2g -q SelI.fa -t blast4096_45000-48000.fa> SelIexonerate.fa
exonerate -m p2g -q TR1.fa -t blast4075_18500-21500.fa> TR1exonerate.fa
exonerate -m p2g -q TR2.fa -t blast4075_18500-21500.fa> TR2exonerate.fa
exonerate -m p2g -q TR3.fa -t blast4075_18500-21500.fa> TR3exonerate.fa
exonerate -m p2g -q SelV.fa -t blast4158_21000-24000.fa> SelVexonerate.fa
exonerate -m p2g -q DI2.fa -t rblast2984_0-3000.fa> rDI2exonerate.fa
exonerate -m p2g -q SPS1.fa -t rblast3973_9000-12000.fa> rSPS1exonerate.fa
exonerate -m p2g -q Sel15.fa -t rblast4131.0_37000-40000.fa> rSel15exonerate.fa
exonerate -m p2g -q SelR1.fa -t rblast4165_9500-12500.fa> rSelR1exonerate.fa
exonerate -m p2g -q SelR3.fa -t rblast1507_0-3000.fa > rSelR3exonerate.fa
exonerate -m p2g -q SelS.fa -t rblast4088_0-3000.fa> rSelSexonerate.fa
exonerate -m p2g -q SelU3.fa -t rblast1916_1500-4500.fa> rSelU3exonerate.fa
exonerate -m p2g -q SelW2.fa -t rblast4102_34000-37000.fa> rSelW2exonerate.fa
exonerate -m p2g -q eEFSec.fa -t rblast3160_13500-16500.fa> reEFSecexonerate.fa
4.xi Genewise y exonerate para las proteínas compuestas
genewise SelIcompuesta.fa contig4096.fa> SelIcompgenewise.fa
genewise compTR1.fa contig4075.fa > compTR1genewise.fa
genewise compTR2.fa contig4075.fa > compTR2genewise.fa
genewise compTR3.fa contig4075.fa > compTR3genewise.fa
exonerate -m p2g -q SelIcompuesta.fa -t contig4096.fa> SelIcompexonerate.fa
exonerate -m p2g -q compTR1.fa -t contig4075.fa > compTR1exonerate.fa
exonerate -m p2g -q compTR2.fa -t contig4075.fa > compTR2exonerate.fa
exonerate -m p2g -q compTR3.fa -t contig4075.fa > compTR3exonerate.fa
5.i Instalación BLAST
export PATH=$PATH:/disc8/bin/exonerate/bin
Aplicacions_RepositoriUPF_BLAST i NETBLAST
5.ii Archivos secuencias
falciparum1.fa
falciparum2.fa
falciparum3.fa
alciparum4.fa
huxleii.fa
SelJ.fa
SelP.fa
5.iii tBLASTn
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum1.fa -e 1.0 -F F -m 9 > fal1alintaula1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum1.fa -e 1.0 -F F > fal1alinsinx1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum2.fa -e 1.0 -F F -m 9 > fal2alintaula1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum2.fa -e 1.0 -F F > fal2alinsinx1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum3.fa -e 1.0 -F F -m 9 > fal3alintaula1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum3.fa -e 1.0 -F F > fal3alinsinx1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum4.fa -e 1.0 -F F -m 9 > fal4alintaula1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i falciparum4.fa -e 1.0 -F F > fal4alinsinx1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i huxleii.fa -e 1.0 -F F -m 9 > huxalintaula1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i huxleii.fa -e 1.0 -F F > huxalinsinx1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i selJ.fa -e 1.0 -F F -m 9 > seljalintaula1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i selJ.fa -e 1.0 -F F > seljalinsinx1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i selP.fa -e 1.0 -F F -m 9 > selpalintaula1.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i selP.fa -e 1.0 -F F > selpalinsinx1.txt
5.vExtracción subsecuencias
fastafetch B_bigemina.contigs.fa bigemina.index Contig3965 > contig3965.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4175.0 > contig4175.0.fa
fastasubseq -f contig3965.fa -s 3000 -l 3000 > blast3965_3000-6000.fa
fastasubseq -f contig4175.0.fa -s 58500 -l 3000 > blast4175.0_58500-61500.fa
5.vi genewise y exonerate
genewise falciparum4.fa blast3965_3000-6000.fa > fal4genewise.fa
genewise huxleii.fa blast4175.0_58500-61500.fa > huxgenewise.fa
exonerate -m p2g -q falciparum4.fa -t blast3965_3000-6000.fa > fal4exonerate.fa
exonerate -m p2g -q huxleii.fa -t blast4175.0_58500-61500.fa > huxexonerate.fa
5.vii Proteínas compuestas
fastafetch B_bigemina.contigs.fa bigemina.index Contig3965 > contig3965.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4058 > contig4058.fa
genewise fal4_3965compuesta.fa contig3965.fa > fal4_3965compgenewise.fa
genewise fal4_4058compuesta.fa contig4058.fa > fal4_4058compgenewise.fa
exonerate -m p2g -q fal4_3965compuesta.fa -t contig3965.fa > fal4_3965compexonerate.fa
exonerate -m p2g -q fal4_4058compuesta.fa -t contig4058.fa > fal4_4058compexonerate.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4169.0 > contig4169.0.fa
genewise huxcompuesta.fa contig4169.0.fa > huxcompgenewise.fa
exonerate -m p2g -q huxcompuesta.fa -t contig4169.0.fa > huxcompexonerate.fa
7.iii tBLASTn
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SPS1drosophila.fa -e 1.0 -F F > SPS1droalinsinx.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SPS2drosophila.fa -e 1.0 -F F > SPS2droalinsinx.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SBP2.fa -e 1.0 -F F > alinSBP2.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i Secp43.fa -e 1.0 -F F > alinSecp43.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i Secp43.fa -e 1.0 -F F -m 9 > alintaulaSecp43.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SelK.fa -e 1.0 -F F > alinSelK.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SelK.fa -e 1.0 -F F -m 9 > alintaulaSelK.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SLA_LP.fa -e 1.0 -F F > alinSLA_LP.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SLA_LP.fa -e 1.0 -F F -m 9 > alintaulaSLA_LP.txt
blastall -p BLASTN -d B_bigemina.contigs.fa -i tRNASec.fa -e 1.0 -F F > alintRNASec.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SelH.fa -e 1.0 -F F -m 9 > alintaulaSelH.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i SelH.fa -e 1.0 -F F > alinsinxSelH.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i PSTK.fa -e 1.0 -F F -m 9 > alintaulaPSTK.txt
blastall -p TBLASTN -d B_bigemina.contigs.fa -i PSTK.fa -e 1.0 -F F > alinsinxPSTK.txt
7.iv Extracción subsecuencias
fastafetch B_bigemina.contigs.fa bigemina.index Contig4184.3 > contig4184.3.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4132 > contig4132.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig3744 > contig3744.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig3887 > contig3887.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4120 > contig4120.fa
fastasubseq -f contig4184.3.fa -s 29000 -l 3000 > blast4184.3_29000-32000.fa
fastasubseq -f contig4132.fa -s 12000 -l 3000 > blast4132_12000-15000.fa
fastasubseq -f contig3744.fa -s 500 -l 3000 > blast3744_500-3500.fa
fastasubseq -f contig3887.fa -s 13500 -l 3000 > blast3887_13500-16500.fa
fastasubseq -f contig4120.fa -s 30000 -l 3000 > blast4120_30000-33000.fa
7.v Repeteción de los pasos anteriore para las secuencias reversas
fastarevcomp contig4184.3.fa > rcontig4184.3.fa
formatdb -i rcontig4184.3.fa -p F
blastall -p TBLASTN -d rcontig4184.3.fa -i Secp43.fa -e 1.0 -F F -m 9 > alintaula1Secp43.txt
blastall -p TBLASTN -d rcontig4184.3.fa -i Secp43.fa -e 1.0 -F F > alinsinx1Secp43.txt
7.vi Genewise y exonerate
genewise Secp43.fa blast4184.3_29000-32000.fa > Secp43genewise.fa
genewise SelK.fa blast4132_12000-15000.fa > SelKgenewise.fa
genewise SLA_LP.fa blast3744_500-3500.fa > SLA_LPgenewise.fa
genewise SelH.fa blast3887_13500-16500.fa > SelHgenewise.fa
genewise PSTK.fa blast4120_30000-33000.fa > PSTKgenewise.fa
exonerate -m p2g -q Secp43.fa -t blast4184.3_29000-32000.fa > Secp43exonerate.fa
exonerate -m p2g -q SelK.fa -t blast4132_12000-15000.fa > SelKexonerate.fa
exonerate -m p2g -q SLA_LP.fa -t blast3744_500-3500.fa > SLA_LPexonerate.fa
exonerate -m p2g -q SelH.fa -t blast3887_13500-16500.fa > SelHexonerate.fa
exonerate -m p2g -q PSTK.fa -t blast4120_30000-33000.fa > PSTKexonerate.fa
7.vii Proteínas compuestas
blastall -p TBLASTN -d rcontig4184.3.fa -i secp43comp.fa -e 1.0 -F F -m 9 > alintaula1Secp43comp.txt
blastall -p TBLASTN -d rcontig4184.3.fa -i secp43comp.fa -e 1.0 -F F > alinsinx1Secp43comp.txt
fastasubseq -f rcontig4184.3.fa -s 106000 -l 3000 > blast4184.3_106000-109000.fa
genewise secp43comp.fa blast4184.3_106000-109000.fa > secp43compgenewise.fa
exonerate -m p2g -q secp43comp.fa -t blast4184.3_106000-109000.fa > sep43compexonerate.fa
8.iii Extracción subsecuencias
fastafetch B_bigemina.contigs.fa bigemina.index Contig2633.0 > contig2633.0.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig3144 > contig3144.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig3170 > contig3170.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4073 > contig4073.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4102 > contig4102.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4170 > contig4170.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4171 > contig4171.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig4173.0 > contig4173.0.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig1846 > contig1846.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig2517 > contig2517.fa
fastafetch B_bigemina.contigs.fa bigemina.index Contig2953 > contig2953.fa
fastasubseq -f contig2633.0.fa -s 1650 -l 3000 > blast2633.0_1650-4650.fa
fastasubseq -f contig3144.fa -s 0 -l 3300 > blast3144_0-3300.fa
fastasubseq -f contig3170.fa -s 0 -l 2200 > blast3170_0-2200.fa
fastasubseq -f contig4073.fa -s 8685 -l 3000 > blast4073_8685-11685.fa
fastasubseq -f contig4102.fa -s 1307 -l 3000 > blast4102_1307-4307.fa
astasubseq -f contig4170.fa -s 67896 -l 3000 > blast4170_67896-70896.fa
fastasubseq -f contig4171.fa -s 11522 -l 3000 > blast4171_11522-14522.fa
fastasubseq -f contig4171.fa -s 11702 -l 3000 > blast4171_11702-14702.fa
fastasubseq -f contig4173.0.fa -s 45520 -l 3000 > blast4173.0_45520-48520.fa
fastasubseq -f contig2953.fa -s 0 -l 1500 > blast2953_0-1500.fa
8.v Archivos con los alineamientos y programa en perl
emacs blast2633.0.fa
emacs blast3144.fa
emacs blast3170.fa
emacs blast4073.fa
emacs blast4102.fa
emacs blast4170.fa
emacs blast4171_a.fa
emacs blast4171_b.fa
emacs blast4173.0.fa
emacs blast2953.fa
perl ast-c.pl < blast2633.0.fa
perl ast-c.pl < blast3144.fa
perl ast-c.pl < blast3170.fa
perl ast-c.pl < blast4073.fa
perl ast-c.pl < blast4102.fa
perl ast-c.pl < blast4170.fa
perl ast-c.pl < blast4171_a.fa
perl ast-c.pl < blast4171_b.fa
perl ast-c.pl < blast4173.0.fa
perl ast-c.pl < blast2953.fa