macmanes

################################################File locations

REF_FILE_NAME Mus.gtf
GEN_DIR genomes/mus/

###################################################Expression

NB_MOLECULES 5000000
TSS_MEAN 50
POLYA_SCALE 100

macmanes

#!/bin/bash

cat test.fastq | awk 'BEGIN{OFS="\n"} { 
a[NR % 4] = $0; 
if(NR % 4 == 0 && length(a[2]) == length(a[0])){
print a[1],a[2],a[3],a[0] 
}
}' > sim.fastq

macmanes

#!/bin/bash

~/ErrorCorrectReads.pl \
MAX_MEMORY_GB= 30 THREADS= 8 PHRED_ENCODING= 33 PAIRED_READS_A_IN= \
PAIRED_READS_B_IN=  UNPAIRED_READS_IN= sim.fastq \
FE_MAX_KMER_FREQ_TO_MARK= 0 EC_K= 24 HAPLOIDIFY= True FILL_FRAGMENTS= \
False FF_K=28 FE_USE_KMER_SPECTRUM=TRUE READS_OUT=corr

macmanes

InFaFile          data/both.fa
IQFile            data/both.q
OErrFile          data/both.reptile.err
QFlag             1
IFlag             1


BatchSize           5000000
KmerLen             13
hd_max              1

macmanes

#!/bin/bash

~/trinityrnaseq_r2013-02-25/Trinity.pl --seqType fq --JM 30G \
--left left.fastq -right right.fastq --full_cleanup --CPU 8

macmanes

#!/bin/bash

#Commands for producing error corrected reads

#Trimmomatic available at: http://www.usadellab.org/cms/index.php?page=trimmomatic
#Reptile available at: http://aluru-sun.ece.iastate.edu/doku.php?id=reptile
#Trinity available at: http://trinityrnaseq.sourceforge.net/

######Trim reads with Trimmomatic
java -jar -Xmx10g trimmomatic-0.30.jar PE -phred33 -threads 32 \

macmanes

10M.2.Trinity.fasta 10M.5.Trinity.fasta 10M.10.Trinity.fasta 10M.20.Trinity.fasta raw.10M.Trinity.fasta \
10M.2.Trinity.fasta.pslx 10M.5.Trinity.fasta.pslx 10M.10.Trinity.fasta.pslx 10M.20.Trinity.fasta.pslx raw.10M.Trinity.fasta.pslx \
10M.2.Trinity.fasta.pep 10M.5.Trinity.fasta.pep 10M.10.Trinity.fasta.pep 10M.20.Trinity.fasta.pep raw.10M.Trinity.fasta.pep \
10M.2.xprs 10M.5.xprs 10M.10.xprs 10M.20.xprs raw.10M.xprs: 10M.left.2.fq 10M.left.5.fq 10M.left.10.fq 10M.left.20.fq 10M.right.2.fq 10M.right.5.fq 10M.right.10.fq 10M.right.20.fq
  for TRIM in 20 2 5 10 0; do \
		$(TRINITY)/Trinity.pl --full_cleanup --min_kmer_cov 1 --seqType fq --JM $(MEM)G --bflyHeapSpaceMax $(MEM)G \
		--left 10M.left.$$TRIM.fq --right 10M.right.$$TRIM.fq --group_pairs_distance 999 --CPU $(CPU) --output 10M.$$TRIM; \
##FL Reconstruction
		$(TRINITY)/Analysis/FL_reconstruction_analysis/FL_trans_analysis_pipeline.pl --target $(MUS) --query 10M.$$TRIM.Trinity.fasta; rm *maps *selected *summary; \
##ORF ID

macmanes

##Input
##n	n:500	n:N50	min	N80	N50	N20	E-size	max	sum	name
##34	34	9	18562	111345	159114	321119	198500	406529	4313902	test.fa
##
##gm_es.pl test.fa --BP OFF > GenemarkES.log 2>&1


running hmm2nt.a2
74 files IN
Clusters were defined as:

macmanes

#Using Fastool downloaded with the most recent version of Trinity.

  fastool --rev  --illumina-trinity --to-fasta pero_left.2.fastq >> left.fa
  Sequences parsed: 164311463

#I have a number of reads that are not appended with the /1 that is supposed to happen with --illumina-trinity

  grep HSQ-7001360:67:H88RHADXX:1:1101:10000:20192 left.fa
  >HSQ-7001360:67:H88RHADXX:1:1101:10000:20192
  

macmanes

wget http://downloads.sourceforge.net/project/trinityrnaseq/trinityrnaseq_r20140413p1.tar.gz?r=http%3A%2F%2Fsourceforge.net%2Fprojects%2Ftrinityrnaseq%2Ffiles%2F&ts=1400703099&use_mirror=superb-dca2
tar -zxf trinityrnaseq_r20140413p1.tar.gz
cd trinityrnaseq_r20140413p1
make