Mercurial > repos > dnbenso > masurca
comparison default-masurca-config @ 0:3f13e9565679 draft
Uploaded
author | dnbenso |
---|---|
date | Mon, 24 Jan 2022 00:00:38 +0000 |
parents | |
children | 1808eaa9d699 |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:3f13e9565679 |
---|---|
1 DATA | |
2 #Illumina paired end reads supplied as <two-character prefix> <fragment mean> <fragment stdev> <forward_reads> <reverse_reads> | |
3 #if single-end, do not specify <reverse_reads> | |
4 #MUST HAVE Illumina paired end reads to use MaSuRCA | |
5 #PE= pe 500 50 /FULL_PATH/frag_1.fastq /FULL_PATH/frag_2.fastq | |
6 PE= pe MEAN STDDEV INPUTREAD1 INPUTREAD2 | |
7 #Illumina mate pair reads supplied as <two-character prefix> <fragment mean> <fragment stdev> <forward_reads> <reverse_reads> | |
8 #JUMP= sh 3600 200 /FULL_PATH/short_1.fastq /FULL_PATH/short_2.fastq | |
9 #pacbio OR nanopore reads must be in a single fasta or fastq file with absolute path, can be gzipped | |
10 #if you have both types of reads supply them both as NANOPORE type | |
11 #PACBIO=/FULL_PATH/pacbio.fa | |
12 #PACBIO=INPUTREADLONG | |
13 #NANOPORE=/FULL_PATH/nanopore.fa | |
14 #NANOPORE=INPUTREADLONG | |
15 #Other reads (Sanger, 454, etc) one frg file, concatenate your frg files into one if you have many | |
16 #OTHER=/FULL_PATH/file.frg | |
17 #synteny-assisted assembly, concatenate all reference genomes into one reference.fa; works for Illumina-only data | |
18 #REFERENCE=REF | |
19 END | |
20 | |
21 PARAMETERS | |
22 #PLEASE READ all comments to essential parameters below, and set the parameters according to your project | |
23 #set this to 1 if your Illumina jumping library reads are shorter than 100bp | |
24 EXTEND_JUMP_READS=0 | |
25 #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 | |
26 GRAPH_KMER_SIZE = auto | |
27 #set this to 1 for all Illumina-only assemblies | |
28 #set this to 0 if you have more than 15x coverage by long reads (Pacbio or Nanopore) or any other long reads/mate pairs (Illumina MP, Sanger, 454, etc) | |
29 USE_LINKING_MATES = 0 | |
30 #specifies whether to run the assembly on the grid | |
31 USE_GRID=0 | |
32 #specifies grid engine to use SGE or SLURM | |
33 GRID_ENGINE=SLURM | |
34 #specifies queue (for SGE) or partition (for SLURM) to use when running on the grid MANDATORY | |
35 GRID_QUEUE=defq | |
36 #batch size in the amount of long read sequence for each batch on the grid | |
37 GRID_BATCH_SIZE=500000000 | |
38 #use at most this much coverage by the longest Pacbio or Nanopore reads, discard the rest of the reads | |
39 #can increase this to 30 or 35 if your reads are short (N50<7000bp) | |
40 LHE_COVERAGE=25 | |
41 #set to 0 (default) to do two passes of mega-reads for slower, but higher quality assembly, otherwise set to 1 | |
42 MEGA_READS_ONE_PASS=0 | |
43 #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 | |
44 LIMIT_JUMP_COVERAGE = 300 | |
45 #these are the additional parameters to Celera Assembler. do not worry about performance, number or processors or batch sizes -- these are computed automatically. | |
46 #CABOG ASSEMBLY ONLY: set cgwErrorRate=0.25 for bacteria and 0.1<=cgwErrorRate<=0.15 for other organisms. | |
47 CA_PARAMETERS = cgwErrorRate=0.15 | |
48 #CABOG ASSEMBLY ONLY: whether to attempt to close gaps in scaffolds with Illumina or long read data | |
49 CLOSE_GAPS=1 | |
50 #number of cpus to use, set this to the number of CPUs/threads per node you will be using | |
51 NUM_THREADS = GALAXY_SLOTS | |
52 #this is mandatory jellyfish hash size -- a safe value is estimated_genome_size*20 | |
53 JF_SIZE = JELLYFISHSIZE | |
54 #ILLUMINA ONLY. Set this to 1 to use SOAPdenovo contigging/scaffolding module. | |
55 #Assembly will be worse but will run faster. Useful for very large (>=8Gbp) genomes from Illumina-only data | |
56 SOAP_ASSEMBLY=0 | |
57 #If you are doing Hybrid Illumina paired end + Nanopore/PacBio assembly ONLY (no Illumina mate pairs or OTHER frg files). | |
58 #Set this to 1 to use Flye assembler for final assembly of corrected mega-reads. | |
59 #A lot faster than CABOG, AND QUALITY IS THE SAME OR BETTER. | |
60 #Works well even when MEGA_READS_ONE_PASS is set to 1. | |
61 #DO NOT use if you have less than 15x coverage by long reads. | |
62 FLYE_ASSEMBLY=0 | |
63 END |