Laurel's Lab Notebook

Wednesday, September 24, 2014

perl ~/Scripts/blast_parser.pl <DR_004_Arjam_MOE_assembled_v_OR_VR_indices.tblastx >DR_004_Arjam_MOE_assembled_v_OR_VR_indices.tblastx.parsed2

OK, processed 8019 queries, 23298 hits

perl ~/Scripts/blast_parser.pl <DR_011_Arjam_VNO_assembled_v_OR_VR_indices.tblastx  >DR_011_Arjam_VNO_assembled_v_OR_VR_indices.tblastx.parsed2

OK, processed 8019 queries, 77307 hits

perl ~/Scripts/blast_parser.pl <DR_013_Mored_MOE_assembled_v_OR_VR_indices.tblastx  >DR_013_Arjam_MOE_assembled_v_OR_VR_indices.tblastx.parsed2

OK, processed 8019 queries, 251312 hits

perl ~/Scripts/blast_parser.pl <DR_013_Mored_VNO_assembled_v_OR_VR_indices.tblast  >DR_013_Arjam_VNO_assembled_v_OR_VR_indices.tblastx.parsed2

OK, processed 8019 queries, 232694 hits

perl ~/Scripts/blast_parser.pl <DR_091_Mobl_MOE_assembled_v_OR_VR_indices.tblastx  >DR_091_Mobl_MOE_assembled_v_OR_VR_indices.tblastx.parsed2

OK, processed 8019 queries, 96314 hits

Tuesday, September 16, 2014

#remove newlines
awk '{if (substr($0,1,1)==">"){print "\n"$0} else printf("%s",$0);p++;}END{print "\n"}' DR_091_Mobl_MOE_assembled.fasta > joined.fasta

If I try running BLASTALL with my transcriptome data as the database, I get this error:

[blastall 2.2.22] ERROR: SeqPortNew: lcl

All the names of the sequences are too similar so I have to rename them--I am just going to rename them by number.
awk '/^>/{print ">" ++i; next}{print}' < DR_091_Mobl_MOE_assembled.fasta > renamed_DR_091_Mobl_MOE_assembled.fasta

#export the path the blast
export PATH=$PATH:/Users/laurelyohe/blast-2.2.22/bin/

#format the database

#because the transcriptome is bigger than the indices, it will serve as the database

formatdb -i renamed_DR_091_Mobl_MOE_assembled.fasta -o T -p F

#run blast

blastall -p tblastx -d renamed_DR_013_Mored_MOE_assembled.fasta -i OR_VR_indices.fasta -e 1e-06 -v 5 -b 5 -a 2 -o ./DR_013_Mored_MOE_assembled_v_OR_VR_indices.tblastx

#now we need to parse the BLAST script

perl ~/Scripts/parse_bls.pl --i DR_091_Mobl_MOE_assembled_v_OR_VR_indices.tblastx > DR_091_Mobl_MOE_assembled_v_OR_VR_indices.tblastx.parsed

#next combine the parsed file with the sequences

~/Scripts/extract_hsps_new.pl -i renamed_DR_091_Mobl_MOE_assembled.fasta -t DR_091_Mobl_MOE_assembled_v_OR_VR_indices.tblastx.parsed -s DR_091_Mormoops_blainvelli

Okay, I have finally accepted that my data is not fitting an Ornstein-Uhlenbeck model of evolution and it makes zero sense to be running the tests that I have been running. My alpha value is way too small for all of my traits compared to the height of my tree.

I have run the fitContinuous() function in the "geiger" package on the geometric mean.

Thursday, September 4, 2014

export TRINITY_HOME=/usr/local/Cellar/trinity/r20131110

Thursday, August 21, 2014

#prior lambda = 6
#for the geometric mean (body size)
x<-data$GM
names(x)<-rownames(data)
prior <- make.prior(tree, model = "OU", param=list("dalpha"=list(),"dsig2"=list(),"dtheta"=list(),
"dk"=list(lambda=6,kmax=length(tree$tip.label)*2-2),

"dloc"=list(min=0,max=1),
"dsb"=list(bmax=Inf,prob=tree$edge.length)))

> effectiveSize(combine$lnL)
var1
47696.89
> effectiveSize(combine$alpha)
var1
17668.65
> effectiveSize(combine$k)
var1
200.3831

http://andrewgelman.com/2010/10/29/could_someone_p/

#GM
#lambda=15
prior <- make.prior(tree, dists=list(dalpha="dlnorm", dsig2="dlnorm",dsb="dsb", dk="cdpois",
dtheta="dnorm"), param=list(dalpha=list(meanlog=-5, sdlog=2),
dsig2=list(meanlog=-1, sdlog=5), dk=list(lambda=15, kmax=200),
dsb=list(bmax=Inf,prob=tree$edge.length),
dtheta=list(mean=mean(x), sd=2)))

fit.1<-bayou.mcmc(tree, x, model = "OU",prior= prior, ngen = 500000)
fit.2<-bayou.mcmc(tree, x,model = "OU", prior= prior, ngen = 500000)
chain.1 <- load.bayou(fit.1, save.Rdata=FALSE, cleanup=TRUE)
chain.2 <- load.bayou(fit.2, save.Rdata=FALSE, cleanup=TRUE)

combine<-combine.chains(chain.1, chain.2, burnin.prop = 0.2)

> effectiveSize(combine$lnL)
var1
54733.55
> effectiveSize(combine$alpha)
var1
21377.18
> effectiveSize(combine$k)
var1
460.0945
> median(combine$alpha)
[1] 0.005785393
> median(combine$k)
[1] 1
> median(combine$lnL)
[1] -226.6656
> median(combine$sig2)
[1] 0.1995975
> median(combine$ntheta)
[1] 2
> median(combine$theta)

plotSimmap.mcmc(tree,combine, burnin = 0, fsize = 0.5,circle.lwd = 0.5 )

#pPC1, lambda = 6
x<-data$PC1
names(x)<-rownames(data)
prior <- make.prior(tree, model = "OU", param=list("dalpha"=list(),"dsig2"=list(),"dtheta"=list(),
"dk"=list(lambda=6,kmax=length(tree$tip.label)*2-2),
"dloc"=list(min=0,max=1),
"dsb"=list(bmax=Inf,prob=tree$edge.length)))
> effectiveSize(combine$lnL)
var1
77556.68
> effectiveSize(combine$alpha)
var1
750.1128
> effectiveSize(combine$k)
var1
1098.867

> median(combine$alpha)

[1] 0.01054099

> median(combine$k)

[1] 5

> median(combine$lnL)

[1] -232.5772

> median(combine$sig2)

[1] 0.2309304

> median(combine$ntheta)

[1] 6

#pPC1

#lambda=15
prior <- make.prior(tree, dists=list(dalpha="dlnorm", dsig2="dlnorm",dsb="dsb", dk="cdpois",
dtheta="dnorm"), param=list(dalpha=list(meanlog=-5, sdlog=2),
dsig2=list(meanlog=-1, sdlog=5), dk=list(lambda=15, kmax=200),
dsb=list(bmax=Inf,prob=tree$edge.length),
dtheta=list(mean=mean(x), sd=2)))

fit.1<-bayou.mcmc(tree, x, model = "OU",prior= prior, ngen = 500000, plot.freq = NULL)
fit.2<-bayou.mcmc(tree, x,model = "OU", prior= prior, ngen = 500000, plot.freq = NULL)
chain.1 <- load.bayou(fit.1, save.Rdata=FALSE, cleanup=TRUE)
chain.2 <- load.bayou(fit.2, save.Rdata=FALSE, cleanup=TRUE)

combine<-combine.chains(chain.1, chain.2, burnin.prop = 0.2)

> effectiveSize(combine$lnL)
var1
46687.59
> effectiveSize(combine$alpha)
var1
1882.031
> effectiveSize(combine$k)
var1
1916.088
> median(combine$alpha)
[1] 0.01097906
> median(combine$k)
[1] 6
> median(combine$lnL)
[1] -682.1394
> median(combine$sig2)
[1] 187.9879
> median(combine$ntheta)
[1] 7

Tuesday, August 19, 2014

#installing Fasta_reader (needed to run script for stats on Trinity assembly)
#first need to install npm
brew install node
vi server.js
#paste the following
var http = require('http'); http.createServer(function (req, res) { res.writeHead(200, {'Content-Type': 'text/plain'}); res.end('Hello World\n'); }).listen(8124, "127.0.0.1"); console.log('Server running at http://127.0.0.1:8124/');
#ESC wq!

#to check if it works
node server.js

npm install fastareader

WOOPS! nevermind! All of this stuff is already installed with Trinity. To run TrinityStats.pl, it cannot be run alone. You must navigate to the directory in which it is found.

###################

#   Ar_jam MOE    #

###################

#combine data from Lanes 1 & 2

cat Arjam_MOE* >> DR_004_Arjam_MOE_assembled.fasta

sudo perl /Volumes/Spare/transcriptomes/Trinity/util/TrinityStats.pl /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/DR_004_Arjam_MOE_assembled.fasta

################################

## Counts of transcripts, etc.

################################

Total trinity transcripts: 140189

Total trinity components: 63956

Percent GC: 55.16

########################################

Stats based on ALL transcript contigs:

########################################

 Contig N10: 4088

 Contig N20: 3085

 Contig N30: 2434

 Contig N40: 1927

 Contig N50: 1502

 Median contig length: 426

 Average contig: 826.50

 Total assembled bases: 115865619

#####################################################

## Stats based on ONLY LONGEST ISOFORM per COMPONENT:

#####################################################

 Contig N10: 3860

 Contig N20: 2862

 Contig N30: 2212

 Contig N40: 1726

 Contig N50: 1310

 Median contig length: 440

 Average contig: 793.55

 Total assembled bases: 50752060 

###################

#   Ar_jam VNO    #

###################

#combine data from Lanes 1 & 2

cat Arjam_VNO* >> DR_011_Arjam_VNO_assembled.fasta

sudo perl /Volumes/Spare/transcriptomes/Trinity/util/TrinityStats.pl /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/DR_011_Arjam_VNO_assembled.fasta
################################
## Counts of transcripts, etc.
################################
Total trinity transcripts: 138142
Total trinity components: 61477
Percent GC: 55.51


########################################
Stats based on ALL transcript contigs:
########################################


 Contig N10: 4735
 Contig N20: 3550
 Contig N30: 2822
 Contig N40: 2240
 Contig N50: 1741


 Median contig length: 455
 Average contig: 920.11
 Total assembled bases: 127106357




#####################################################
## Stats based on ONLY LONGEST ISOFORM per COMPONENT:
#####################################################


 Contig N10: 3855
 Contig N20: 2871
 Contig N30: 2270
 Contig N40: 1814
 Contig N50: 1436


 Median contig length: 467
 Average contig: 848.36

 Total assembled bases: 52154403

###################

#   Mo_red MOE    #

###################

#combine data from Lanes 1 & 2

cat Mored_MOE* >> DR_013_Mored_MOE_assembled.fasta
sudo perl /Volumes/Spare/transcriptomes/Trinity/util/TrinityStats.pl /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/DR_013_Mored_MOE_assembled.fasta
################################
## Counts of transcripts, etc.
################################
Total trinity transcripts: 245573
Total trinity components: 100799
Percent GC: 56.14


########################################
Stats based on ALL transcript contigs:
########################################


 Contig N10: 5311
 Contig N20: 4036
 Contig N30: 3304
 Contig N40: 2703
 Contig N50: 2118


 Median contig length: 406
 Average contig: 960.45
 Total assembled bases: 235861464




#####################################################
## Stats based on ONLY LONGEST ISOFORM per COMPONENT:
#####################################################


 Contig N10: 4140
 Contig N20: 2880
 Contig N30: 2105
 Contig N40: 1512
 Contig N50: 1053


 Median contig length: 377
 Average contig: 685.78

 Total assembled bases: 69126334


###################

#   Mo_red VNO    #

###################

#combine data from Lanes 1 & 2

cat Mored_VNO* >> DR_013_Mored_VNO_assembled.fasta
sudo perl $TRINITY_HOME/util/TrinityStats.pl DR_013_Mored_VNO_assembled.fasta
################################
## Counts of transcripts, etc.
################################
Total trinity transcripts: 163233
Total trinity components: 70319
Percent GC: 55.74


########################################
Stats based on ALL transcript contigs:
########################################


 Contig N10: 4648
 Contig N20: 3450
 Contig N30: 2778
 Contig N40: 2186
 Contig N50: 1709


 Median contig length: 430
 Average contig: 883.37
 Total assembled bases: 144195048




#####################################################
## Stats based on ONLY LONGEST ISOFORM per COMPONENT:
#####################################################


 Contig N10: 3865
 Contig N20: 2811
 Contig N30: 2110
 Contig N40: 1605
 Contig N50: 1187


 Median contig length: 427
 Average contig: 754.88

 Total assembled bases: 53082440



###################

#   Mo_bla MOE    #

###################

cat Mobl_MOE* >> DR_091_Mobl_MOE_assembled.fasta
sudo perl $TRINITY_HOME/util/TrinityStats.pl DR_091_Mobl_MOE_assembled.fasta
################################
## Counts of transcripts, etc.
################################
Total trinity transcripts: 249551
Total trinity components: 115871
Percent GC: 54.01


########################################
Stats based on ALL transcript contigs:
########################################


 Contig N10: 4786
 Contig N20: 3549
 Contig N30: 2741
 Contig N40: 2123
 Contig N50: 1598


 Median contig length: 335
 Average contig: 763.67
 Total assembled bases: 190573978




#####################################################
## Stats based on ONLY LONGEST ISOFORM per COMPONENT:
#####################################################


 Contig N10: 3761
 Contig N20: 2670
 Contig N30: 1971
 Contig N40: 1426
 Contig N50: 989


 Median contig length: 344
 Average contig: 636.73

 Total assembled bases: 73778325

Monday, August 18, 2014

###################

#Lane 2 Ar_jam MOE#

###################

gunzip pair*

cat pair.DR004_Artibeus_Jamaicensis_MOE_ACAGTG_L002_R1* >> Arjam_MOE_L2_R1.fq

cat pair.DR004_Artibeus_Jamaicensis_MOE_ACAGTG_L002_R2* >> Arjam_MOE_L2_R2.fq

fastq_quality_filter -i Arjam_MOE_L2_R1.fq -o Arjam_MOE_R1_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 15317036 reads.

Output: 14847480 reads.

discarded 469556 (3%) low-quality reads.

fastq_quality_filter -i Arjam_MOE_L2_R2.fq -o Arjam_MOE_R2_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 15317036 reads.

Output: 14608448 reads.

discarded 708588 (4%) low-quality reads.

~/Scripts/both.py Arjam_MOE_R1_L2_fastxtrimmed.fastq Arjam_MOE_R2_L2_fastxtrimmed.fastq

#run trinity

Trinity.pl --seqType fq --left Arjam_MOE_R1_L2_fastxtrimmed.fastq.both --right Arjam_MOE_R2_L2_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane2

###################

#Lane 1 Ar_jam VNO#

###################

gunzip pair*

cat pair.DR011_Artibeus_Jamaicensis_VNO_TGACCA_L001_R1* >> Arjam_VNO_L1_R1.fq

cat pair.DR011_Artibeus_Jamaicensis_VNO_TGACCA_L001_R2* >> Arjam_VNO_L1_R2.fq

mv Arjam_VNO_L1_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_011_Arjam_VNO/

fastq_quality_filter -i Arjam_VNO_L1_R1.fq -o Arjam_VNO_R1_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 13582991 reads.

Output: 13087556 reads.

discarded 495435 (3%) low-quality reads.

fastq_quality_filter -i Arjam_VNO_L1_R2.fq -o Arjam_VNO_R2_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 13582991 reads.

Output: 12665813 reads.

discarded 917178 (6%) low-quality reads.

~/Scripts/both.py Arjam_VNO_R1_L1_fastxtrimmed.fastq Arjam_VNO_R2_L1_fastxtrimmed.fastq

Trinity.pl --seqType fq --left Arjam_VNO_R1_L1_fastxtrimmed.fastq.both --right Arjam_VNO_R2_L1_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane1

###################

#Lane 2 Ar_jam VNO#

###################

gunzip pair*

cat pair.DR011_Artibeus_Jamaicensis_VNO_TGACCA_L002_R1* >> Arjam_VNO_L2_R1.fq

cat pair.DR011_Artibeus_Jamaicensis_VNO_TGACCA_L002_R2* >> Arjam_VNO_L2_R2.fq

mv Arjam_VNO_L2_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_011_Arjam_VNO/

fastq_quality_filter -i Arjam_VNO_L2_R1.fq -o Arjam_VNO_R1_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 13746292 reads.

Output: 13242643 reads.

discarded 503649 (3%) low-quality reads.

fastq_quality_filter -i Arjam_VNO_L2_R2.fq -o Arjam_VNO_R2_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 13746292 reads.

Output: 12800383 reads.

discarded 945909 (6%) low-quality reads.

~/Scripts/both.py Arjam_VNO_R1_L2_fastxtrimmed.fastq Arjam_VNO_R2_L2_fastxtrimmed.fastq

Trinity.pl --seqType fq --left Arjam_VNO_R1_L2_fastxtrimmed.fastq.both --right Arjam_VNO_R2_L2_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane2

###################

#Lane 1 Mo_red MOE#

###################

gunzip pair*

cat pair.DR013_Monophyllus_Redmani_MOE_CAGATC_L001_R1* >> Mored_MOE_L1_R1.fq

cat pair.DR013_Monophyllus_Redmani_MOE_CAGATC_L001_R2* >> Mored_MOE_L1_R2.fq

mv Mored_MOE_L1_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_013_Mored_MOE/

fastq_quality_filter -i Mored_MOE_L1_R1.fq -o Mored_MOE_R1_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 14546140 reads.

Output: 14205942 reads.


discarded 340198 (2%) low-quality reads.

fastq_quality_filter -i Mored_MOE_L1_R2.fq -o Mored_MOE_R2_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 14546140 reads.

Output: 13998979 reads.

discarded 547161 (3%) low-quality reads.

~/Scripts/both.py Mored_MOE_R1_L1_fastxtrimmed.fastq Mored_MOE_R2_L1_fastxtrimmed.fastq


Trinity.pl --seqType fq --left Mored_MOE_R1_L1_fastxtrimmed.fastq.both --right Mored_MOE_R2_L1_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane1

###################

#Lane 2 Mo_red MOE#

###################

gunzip pair*

cat pair.DR013_Monophyllus_Redmani_MOE_CAGATC_L002_R1* >> Mored_MOE_L2_R1.fq

cat pair.DR013_Monophyllus_Redmani_MOE_CAGATC_L002_R2* >> Mored_MOE_L2_R2.fq
mv Mored_MOE_L2_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_013_Mored_MOE/

fastq_quality_filter -i Mored_MOE_L2_R1.fq -o Mored_MOE_R1_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v



Quality cut-off: 20

Minimum percentage: 80

Input: 14719223 reads.

Output: 14370971 reads.


discarded 348252 (2%) low-quality reads.


fastq_quality_filter -i Mored_MOE_L2_R2.fq -o Mored_MOE_R2_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v

Quality cut-off: 20

Minimum percentage: 80

Input: 14719223 reads.

Output: 14152391 reads.

discarded 566832 (3%) low-quality reads.

~/Scripts/both.py Mored_MOE_R1_L2_fastxtrimmed.fastq Mored_MOE_R2_L2_fastxtrimmed.fastq

Trinity.pl --seqType fq --left Mored_MOE_R1_L2_fastxtrimmed.fastq.both --right Mored_MOE_R2_L2_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane2



###################

#Lane 1 Mo_red VNO#

###################

gunzip pair*

cat pair.DR013_Monophyllus_Redmani_VNO_AGTCAA_L001_R1* >> Mored_VNO_L1_R1.fq

cat pair.DR013_Monophyllus_Redmani_VNO_AGTCAA_L001_R2* >> Mored_VNO_L1_R2.fq
mv Mored_VNO_L1_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_013_Mored_VNO/

fastq_quality_filter -i Mored_VNO_L1_R1.fq -o Mored_VNO_R1_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v
Quality cut-off: 20
Minimum percentage: 80
Input: 14001874 reads.
Output: 13728472 reads.
discarded 273402 (1%) low-quality reads
fastq_quality_filter -i Mored_VNO_L1_R2.fq -o Mored_VNO_R2_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v
Quality cut-off: 20
Minimum percentage: 80
Input: 14001874 reads.
Output: 13444029 reads.
discarded 557845 (3%) low-quality reads.

~/Scripts/both.py Mored_VNO_R1_L1_fastxtrimmed.fastq Mored_VNO_R2_L1_fastxtrimmed.fastq

Trinity.pl --seqType fq --left Mored_VNO_R1_L1_fastxtrimmed.fastq.both --right Mored_VNO_R2_L1_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane1

###################

#Lane 2 Mo_red VNO#

###################

gunzip pair*

cat pair.DR013_Monophyllus_Redmani_VNO_AGTCAA_L002_R1* >> Mored_VNO_L2_R1.fq

cat pair.DR013_Monophyllus_Redmani_VNO_AGTCAA_L002_R2* >> Mored_VNO_L2_R2.fq
mv Mored_VNO_L2_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_013_Mored_VNO/

fastq_quality_filter -i Mored_VNO_L2_R1.fq -o Mored_VNO_R1_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v
Quality cut-off: 20
Minimum percentage: 80
Input: 14176309 reads.
Output: 13892340 reads.
discarded 283969 (2%) low-quality reads.
fastq_quality_filter -i Mored_VNO_L2_R2.fq -o Mored_VNO_R2_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 
-v
Quality cut-off: 20
Minimum percentage: 80
Input: 14176309 reads.
Output: 13594457 reads.
discarded 581852 (4%) low-quality reads.


~/Scripts/both.py Mored_VNO_R1_L2_fastxtrimmed.fastq Mored_VNO_R2_L2_fastxtrimmed.fastq

Trinity.pl --seqType fq --left Mored_VNO_R1_L2_fastxtrimmed.fastq.both --right Mored_VNO_R2_L2_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane2

###################

#Lane 1 Mo_bla MOE#

###################

gunzip pair*

cat pair.DR091_Mormoops_Blainvelli_MOE_CGATGT_L001_R1* >> Mobla_MOE_L1_R1.fq

cat pair.DR091_Mormoops_Blainvelli_MOE_CGATGT_L001_R2* >> Mobla_MOE_L1_R2.fq
mv Mobla_MOE_L1_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_091_Mobl_MOE/

fastq_quality_filter -i Mobla_MOE_L1_R1.fq -o Mobl_MOE_R1_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v
Quality cut-off: 20
Minimum percentage: 80
Input: 16080335 reads.
Output: 15736163 reads.

discarded 344172 (2%) low-quality reads.
fastq_quality_filter -i Mobla_MOE_L1_R2.fq -o Mobl_MOE_R2_L1_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v
Quality cut-off: 20
Minimum percentage: 80
Input: 16080335 reads.
Output: 15462533 reads.

discarded 617802 (3%) low-quality reads.
~/Scripts/both.py Mobl_MOE_R1_L1_fastxtrimmed.fastq Mobl_MOE_R2_L1_fastxtrimmed.fastq

Trinity.pl --seqType fq --left Mobl_MOE_R1_L1_fastxtrimmed.fastq.both --right Mobl_MOE_R2_L1_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane1

###################

#Lane 2 Mo_bla MOE#

###################

gunzip pair*

cat pair.DR091_Mormoops_Blainvelli_MOE_CGATGT_L002_R1* >> Mobla_MOE_L2_R1.fq

cat pair.DR091_Mormoops_Blainvelli_MOE_CGATGT_L002_R2* >> Mobla_MOE_L2_R2.fq
mv Mobla_MOE_L2_R* /Volumes/Spare/transcriptomes/MOE_VNO_transcriptomes/Trinity_assembly/to_assemble/DR_091_Mobl_MOE/

fastq_quality_filter -i Mobla_MOE_L2_R1.fq -o Mobl_MOE_R1_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v
Quality cut-off: 20
Minimum percentage: 80
Input: 16263150 reads.
Output: 15909002 reads.

discarded 354148 (2%) low-quality reads.
fastq_quality_filter -i Mobla_MOE_L2_R2.fq -o Mobl_MOE_R2_L2_fastxtrimmed.fastq -q 20 -p 80 -Q 33 -v
Quality cut-off: 20
Minimum percentage: 80
Input: 16263150 reads.
Output: 15621798 reads.

discarded 641352 (3%) low-quality reads.

~/Scripts/both.py Mobl_MOE_R1_L2_fastxtrimmed.fastq Mobl_MOE_R2_L2_fastxtrimmed.fastq



Trinity.pl --seqType fq --left Mobl_MOE_R1_L2_fastxtrimmed.fastq.both --right Mobl_MOE_R2_L2_fastxtrimmed.fastq.both --CPU 4 --JM 20G --output output_Lane2