init

MaSuRCA/Bacteria/config

@@ -0,0 +1,55 @@
+# example configuration file 
+
+# DATA is specified as type {PE,JUMP,OTHER,PACBIO} and 5 fields:
+# 1)two_letter_prefix 2)mean 3)stdev 4)fastq(.gz)_fwd_reads
+# 5)fastq(.gz)_rev_reads. The PE reads are always assumed to be
+# innies, i.e. --->.<---, and JUMP are assumed to be outties
+# <---.--->. If there are any jump libraries that are innies, such as
+# longjump, specify them as JUMP and specify NEGATIVE mean. Reverse reads
+# are optional for PE libraries and mandatory for JUMP libraries. Any
+# OTHER sequence data (454, Sanger, Ion torrent, etc) must be first
+# converted into Celera Assembler compatible .frg files (see
+# http://wgs-assembler.sourceforge.com)
+DATA
+##PE= pe 525 60  avg_read_length std_dev /FULL_PATH/paired_read1.fastq /FULL_PATH/paired_read2.fastq 
+PE= pe 221 1952 /home/CAM/mxu/tutorial/Bacteria/Sample_1.fastq  /home/CAM/mxu/tutorial/Bacteria/Sample_2.fastq 
+PE= se 176 4194 /home/CAM/mxu/tutorial/Bacteria/Sample_s.fastq  
+#JUMP= sh 3600 200  /FULL_PATH/short_1.fastq  /FULL_PATH/short_2.fastq
+#pacbio reads must be in a single fasta file! make sure you provide absolute path
+#PACBIO=/FULL_PATH/pacbio.fa
+#OTHER= /home/CAM/mxu/MaSuRCA/Sample_1.frg /home/CAM/mxu/MaSuRCA/Sample_2.frg
+END
+
+PARAMETERS
+#set this to 1 if your Illumina jumping library reads are shorter than 100bp
+EXTEND_JUMP_READS=0
+#this is k-mer size for deBruijn graph values between 25 and 127 are supported, auto will compute the optimal size based on the read data and GC content
+GRAPH_KMER_SIZE = auto
+#set this to 1 for all Illumina-only assemblies
+#set this to 1 if you have less than 20x long reads (454, Sanger, Pacbio) and less than 50x CLONE coverage by Illumina, Sanger or 454 mate pairs
+#otherwise keep at 0
+USE_LINKING_MATES = 0
+#specifies whether to run mega-reads correction on the grid
+USE_GRID=0
+#specifies queue to use when running on the grid MANDATORY
+GRID_QUEUE=all.q
+#batch size in the amount of long read sequence for each batch on the grid
+GRID_BATCH_SIZE=300000000
+#coverage by the longest Long reads to use
+LHE_COVERAGE=30
+#this parameter is useful if you have too many Illumina jumping library mates. Typically set it to 60 for bacteria and 300 for the other organisms 
+LIMIT_JUMP_COVERAGE = 300
+#these are the additional parameters to Celera Assembler.  do not worry about performance, number or processors or batch sizes -- these are computed automatically. 
+#set cgwErrorRate=0.25 for bacteria and 0.1<=cgwErrorRate<=0.15 for other organisms.
+CA_PARAMETERS =  cgwErrorRate=0.15
+#minimum count k-mers used in error correction 1 means all k-mers are used.  one can increase to 2 if Illumina coverage >100
+KMER_COUNT_THRESHOLD = 1
+#whether to attempt to close gaps in scaffolds with Illumina data
+CLOSE_GAPS=1
+#auto-detected number of cpus to use
+NUM_THREADS = 16
+#this is mandatory jellyfish hash size -- a safe value is estimated_genome_size*estimated_coverage
+JF_SIZE = 200000000
+#set this to 1 to use SOAPdenovo contigging/scaffolding module.  Assembly will be worse but will run faster. Useful for very large (>5Gbp) genomes from Illumina-only data
+SOAP_ASSEMBLY=0
+END

MaSuRCA/Bacteria/ma_assemble.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+#SBATCH --job-name=masurca
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 16 
+#SBATCH --partition=himem1
+#SBATCH --mail-type=END
+#SBATCH --mem=128G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o masurca_%j.out
+#SBATCH -e masurca_%j.err
+
+module load MaSuRCA/3.2.4
+
+masurca config
+bash assemble.sh

MaSuRCA/Bacteria/sample_seq_stats.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+#SBATCH --job-name=seqStats
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 4 
+#SBATCH --partition=general
+#SBATCH --mail-type=END
+#SBATCH --mem=8G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o stats_%j.out
+#SBATCH -e stats_%j.err
+
+
+awk 'BEGIN { t=0.0;sq=0.0; n=0;} ;NR%4==2 {n++;L=length($0);t+=L;sq+=L*L;}END{m=t/n;printf("total %d avg=%f stddev=%f\n",n,m,sq/n-m*m);}' ../../dataset/Bacteria/Sample_[12].fastq > Sample_stats.txt
+
+

MaSuRCA/Butterfly/config

@@ -0,0 +1,56 @@
+# example configuration file 
+
+# DATA is specified as type {PE,JUMP,OTHER,PACBIO} and 5 fields:
+# 1)two_letter_prefix 2)mean 3)stdev 4)fastq(.gz)_fwd_reads
+# 5)fastq(.gz)_rev_reads. The PE reads are always assumed to be
+# innies, i.e. --->.<---, and JUMP are assumed to be outties
+# <---.--->. If there are any jump libraries that are innies, such as
+# longjump, specify them as JUMP and specify NEGATIVE mean. Reverse reads
+# are optional for PE libraries and mandatory for JUMP libraries. Any
+# OTHER sequence data (454, Sanger, Ion torrent, etc) must be first
+# converted into Celera Assembler compatible .frg files (see
+# http://wgs-assembler.sourceforge.com)
+DATA
+##PE= pe 525 60  avg_read_length std_dev /FULL_PATH/paired_read1.fastq /FULL_PATH/paired_read2.fastq 
+PE= p1 147 160 /home/CAM/mxu/tutorial/p3/dataset/DRR021673_1.fastq  /home/CAM/mxu/tutorial/p3/dataset/DRR021673_2.fastq 
+PE= p2 145 251 /home/CAM/mxu/tutorial/p3/dataset/DRR021674_1.fastq  /home/CAM/mxu/tutorial/p3/dataset/DRR021674_2.fastq 
+JUMP= m1 124 1539 /home/CAM/mxu/tutorial/p3/dataset/DRR021675_1.fastq /home/CAM/mxu/tutorial/p3/dataset/DRR021675_2.fastq 
+JUMP= m2 125 1493 /home/CAM/mxu/tutorial/p3/dataset/DRR021677_1.fastq /home/CAM/mxu/tutorial/p3/dataset/DRR021677_2.fastq 
+#pacbio reads must be in a single fasta file! make sure you provide absolute path
+#PACBIO=/FULL_PATH/pacbio.fa
+#OTHER=/FULL_PATH/file.frg
+END
+
+PARAMETERS
+#set this to 1 if your Illumina jumping library reads are shorter than 100bp
+#EXTEND_JUMP_READS=0
+#this is k-mer size for deBruijn graph values between 25 and 127 are supported, auto will compute the optimal size based on the read data and GC content
+GRAPH_KMER_SIZE = auto
+#set this to 1 for all Illumina-only assemblies
+#set this to 1 if you have less than 20x long reads (454, Sanger, Pacbio) and less than 50x CLONE coverage by Illumina, Sanger or 454 mate pairs
+#otherwise keep at 0
+USE_LINKING_MATES = 0
+#specifies whether to run mega-reads correction on the grid
+USE_GRID=0
+#specifies queue to use when running on the grid MANDATORY
+GRID_QUEUE=all.q
+#batch size in the amount of long read sequence for each batch on the grid
+GRID_BATCH_SIZE=300000000
+#coverage by the longest Long reads to use
+##LHE_COVERAGE=30
+#this parameter is useful if you have too many Illumina jumping library mates. Typically set it to 60 for bacteria and 300 for the other organisms 
+LIMIT_JUMP_COVERAGE = 300 
+#these are the additional parameters to Celera Assembler.  do not worry about performance, number or processors or batch sizes -- these are computed automatically. 
+#set cgwErrorRate=0.25 for bacteria and 0.1<=cgwErrorRate<=0.15 for other organisms.
+CA_PARAMETERS = cgwErrorRate=0.15
+#minimum count k-mers used in error correction 1 means all k-mers are used.  one can increase to 2 if Illumina coverage >100
+KMER_COUNT_THRESHOLD = 1
+#whether to attempt to close gaps in scaffolds with Illumina data
+CLOSE_GAPS=1
+#auto-detected number of cpus to use
+NUM_THREADS = 16
+#this is mandatory jellyfish hash size -- a safe value is estimated_genome_size*estimated_coverage
+JF_SIZE = 200000000
+#set this to 1 to use SOAPdenovo contigging/scaffolding module.  Assembly will be worse but will run faster. Useful for very large (>5Gbp) genomes from Illumina-only data
+SOAP_ASSEMBLY=0
+END

MaSuRCA/Butterfly/ma_assemble.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+#SBATCH --job-name=masurca
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 16 
+#SBATCH --partition=himem1
+#SBATCH --mail-type=END
+#SBATCH --mem=128G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o masurca_%j.out
+#SBATCH -e masurca_%j.err
+
+module load MaSuRCA/3.2.4
+
+masurca config
+bash assemble.sh

MaSuRCA/Butterfly/xut_seq_stats.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+#SBATCH --job-name=seqStats
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 4 
+#SBATCH --partition=general
+#SBATCH --mail-type=END
+#SBATCH --mem=8G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o stats_%j.out
+#SBATCH -e stats_%j.err
+
+
+awk 'BEGIN { t=0.0;sq=0.0; n=0;} ;NR%4==2 {n++;L=length($0);t+=L;sq+=L*L;}END{m=t/n;printf("total %d avg=%f stddev=%f\n",n,m,sq/n-m*m);}' ../../dataset/butterfly/DRR021675*.fastq > DRR021675_stats.txt
+
+awk 'BEGIN { t=0.0;sq=0.0; n=0;} ;NR%4==2 {n++;L=length($0);t+=L;sq+=L*L;}END{m=t/n;printf("total %d avg=%f stddev=%f\n",n,m,sq/n-m*m);}' ../../dataset/butterfly/DRR021677*.fastq > DRR021677_stats.txt
+
+awk 'BEGIN { t=0.0;sq=0.0; n=0;} ;NR%4==2 {n++;L=length($0);t+=L;sq+=L*L;}END{m=t/n;printf("total %d avg=%f stddev=%f\n",n,m,sq/n-m*m);}' ../../dataset/butterfly/DRR021673*.fastq > DRR021673_stats.txt
+
+awk 'BEGIN { t=0.0;sq=0.0; n=0;} ;NR%4==2 {n++;L=length($0);t+=L;sq+=L*L;}END{m=t/n;printf("total %d avg=%f stddev=%f\n",n,m,sq/n-m*m);}' ../../dataset/butterfly/DRR021674*.fastq > DRR021674_stats.txt

Platanus/Bacteria/gap_close.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+#SBATCH --job-name=platnus_GapClose
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 16
+#SBATCH --partition=general
+#SBATCH --mail-type=END
+#SBATCH --mem=65G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o gap_%j.Pxut
+#SBATCH -e gap_%j.err
+
+module load platanus/1.2.4
+
+platanus gap_close -o Pxut -c /home/CAM/mxu/tutorial/p3/Pxut_scaffold.fa -IP1 /home/CAM/mxu/tutorial/p3/Sample_1.fastq  /home/CAM/mxu/tutorial/p3/Sample_2.fastq -t 16 2> gap_close.log

Platanus/Bacteria/platanus.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+#SBATCH --job-name=platnus_assemble
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 16
+#SBATCH --partition=general
+#SBATCH --mail-type=END
+#SBATCH --mem=130G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o assemble_%j.out
+#SBATCH -e assemble_%j.err
+
+module load platanus/1.2.4
+
+platanus assemble -o sample -f ../../dataset/Bacteria/Sample_[12s].fastq -t 16 -m 128
+
+platanus scaffold -o sample -c sample_contig.fa -b sample_contigBubble.fa -IP1 ../../dataset/Bacteria/Sample_1.fastq ../../dataset/Bacteria/Sample_2.fastq  -t 16
+
+platanus gap_close -o sample -c sample_scaffold.fa -IP1 ../../dataset/Bacteria/Sample_1.fastq  ../../dataset/Bacteria/Sample_2.fastq -t 16

Platanus/Bacteria/scaffold.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+#SBATCH --job-name=platnus_scaffold
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 16
+#SBATCH --partition=general
+#SBATCH --mail-type=END
+#SBATCH --mem=65G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o Scaffold_%j.Pxut
+#SBATCH -e Scaffold_%j.err
+
+module load platanus/1.2.4
+
+platanus scaffold -o Pxut -c Pxut_contig.fa -b Pxut_contigBubble.fa -IP1 ../../dataset/Bacteria/Sample_1.fastq ../../dataset/Bacteria/Sample_2.fastq  -t 16

Platanus/Bacteria/trim.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+#$ -N Platanus-trim 
+#$ -M muyang.xu@uconn.edu
+#$ -q highmem.q
+#$ -m ea
+#$ -S /bin/bash
+#$ -cwd
+#$ -pe smp 4
+#$ -o trim_$JOB_ID.out
+#$ -e trim_$JOB_ID.err
+
+module load Platanus/1.2.4
+
+Platanus_trim /home/CAM/mxu/tutorial/MaSuRCA_illumina/dataset/DRR021673_1.fastq.bz2 /home/CAM/mxu/tutorial/MaSuRCA_illumina/dataset/DRR021673_2.fastq.bz2 
+

Platanus/Butterfly/platanus.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+#SBATCH --job-name=platnus_assemble
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 16
+#SBATCH --partition=himem3
+#SBATCH --mail-type=END
+#SBATCH --mem=256G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o assemble_%j.out
+#SBATCH -e assemble_%j.err
+
+module load platanus/1.2.4
+
+platanus assemble -o Pxut -f /home/CAM/mxu/tutorial/p3/dataset/DRR02167[34]_[12].fastq -t 16 -m 128 
+
+platanus scaffold -o Pxut -c Pxut_contig.fa -b Pxut_contigBubble.fa -IP1 ../../dataset/Butterfly/DRR021673_1.fastq ../../dataset/Butterfly/DRR021673_2.fastq -IP2  ../../dataset/Butterfly/DRR021674_1.fastq  ../../dataset/Butterfly/DRR021674_2.fastq -t 16 
+
+
+

Quast/Bacteria/quast.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+#SBATCH --job-name=quast
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 8 
+#SBATCH --partition=general
+#SBATCH --mail-type=END
+#SBATCH --mem=64G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o quast_%j.out
+#SBATCH -e quast_%j.err
+
+module load quast/4.6
+
+quast.py -t 8 ../../SOAPdenovo/Bacteria/graph_Sample_31.scafSeq -o SOAP/
+
+quast.py -t 8 ../../SPAdes/Bacteria/scaffolds.fasta -o SPAdes/
+
+quast.py -t 8 ../../MaSuRCA/Bacteria/CA/scaffolds.ref.fa -o MaSuRCA/
+
+quast.py -t 8 ../../Platanus/Bacteria/Pxut_scaffold.fa -o Platanus/
+

Quast/Butterfly/quast.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+#SBATCH --job-name=quast
+#SBATCH -N 1
+#SBATCH -n 1
+#SBATCH -c 8 
+#SBATCH --partition=general
+#SBATCH --mail-type=END
+#SBATCH --mem=64G
+#SBATCH --mail-user=muyang.xu@uconn.edu
+#SBATCH -o quast_%j.out
+#SBATCH -e quast_%j.err
+
+module load quast/4.6
+
+
+quast.py -t 8 ../../SOAPdenovo/Butterfly/graph_xuthus_31.scafSeq -o SOAPdenovo/
+
+quast.py -t 8 ../../SPAdes/Butterfly/scaffolds.fasta -o SPAdes/
+
+quast.py -t 8 ../../MaSuRCA/Butterfly/CA/scaffolds.ref.fa -o MaSuRCA/
+
+quast.py -t 8 ../../Platanus/Butterfly/Pxut_scaffold.fa -o Platanus/
+