2020\u5e74\u5ea6\u306e\u751f\u7269\u79d1\u5b66\u57fa\u790e\u5b9f\u9a13I\u304c\u30b3\u30ed\u30ca\u5bfe\u7b56\u3068\u3057\u3066\u30ea\u30e2\u30fc\u30c8\u6388\u696d\u3068\u306a\u3063\u305f\u969b\u306b\u3001\u6b21\u4e16\u4ee3\u30b7\u30fc\u30af\u30a8\u30f3\u30b9\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u305f\u30a2\u30bb\u30f3\u30d6\u30eb\u306e\u539f\u7406\u3068\u3001\u30c7\u30e2\u30f3\u30b9\u30c8\u30ec\u30fc\u30b7\u30e7\u30f3\u3068\u3057\u3066\u30c7\u30fc\u30bf\u306e\u53d6\u5f97\u304b\u3089\u30a2\u30bb\u30f3\u30d6\u30eb\u307e\u3067\u306e\u4e00\u9023\u306e\u6d41\u308c\u3092\u8b1b\u7fa9\u3057\u305f\u3002<\/p>\n\n\n\n
\u4ee5\u4e0b\u306e\u4e00\u9023\u306e\u30b3\u30de\u30f3\u30c9\u3092\u5fd8\u5099\u9332\u3068\u3057\u3066\u6b8b\u3057\u3066\u304a\u304f\u3002\u30c7\u30fc\u30bf\u306b\u306f\u6e05\u9152\u9175\u6bcd\u306e\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u305f\u9175\u6bcd\u306e\u30b2\u30ce\u30e0\u30b5\u30a4\u30ba\u306f\u5c0f\u3055\u3044\u306e\u3067\u300190\u5206\u306e\u6388\u696d\u6642\u9593\u306e\u4e2d\u3067\u30c7\u30e2\u3059\u308b\u306e\u306b\u306f\u3061\u3087\u3046\u3069\u3088\u3044\u3068\u601d\u308f\u308c\u308b\u3002<\/p>\n\n\n\n
#fastq-dump\u3067fastq\u30d5\u30a1\u30a4\u30eb\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\uff08\u30b5\u30b1\u9175\u6bcd\u306e\u30c7\u30fc\u30bf\uff09\nfastq-dump --split-files DRR093946\n\n#seqkit stats\u3067fastq\u30d5\u30a1\u30a4\u30eb\u3092\u30c1\u30a7\u30c3\u30af\nseqkit stats *.fastq\n\n#trimmomatic\u3067\u30c8\u30ea\u30df\u30f3\u30b0\u3092\u884c\u3046\ntrimmomatic PE \\\n-threads 8 \\\n-phred33 \\\n-trimlog log.txt \\\nDRR093946_1.fastq \\\nDRR093946_2.fastq \\\npaired_output_1.fq \\\nunpaired_output_1.fq \\\npaired_output_2.fq \\\nunpaired_output_2.fq \\\nILLUMINACLIP:TruSeq3-PE-2.fa:2:30:10 \\\nLEADING:20 \\\nTRAILING:20 \\\nSLIDINGWINDOW:4:15 \\\nMINLEN:36\n\n#masurca\u3067\u30a2\u30bb\u30f3\u30d6\u30eb\u3092\u884c\u3046\nconda activate py27\nmkdir masurca_assembly\nmasurca -g config\nmasurca config -o assemble.sh\n.\/assemble.sh<\/pre>\n\n\n\nmasurca\u306e\u8a2d\u5b9a\u30d5\u30a1\u30a4\u30eb<\/p>\n\n\n\n
# DATA is specified as type {PE,JUMP,OTHER,PACBIO} and 5 fields:\n # 1)two_letter_prefix 2)mean 3)stdev 4)fastq(.gz)_fwd_reads\n # 5)fastq(.gz)_rev_reads. The PE reads are always assumed to be\n # innies, i.e. --->.<---, and JUMP are assumed to be outties\n # <---.--->. If there are any jump libraries that are innies, such as\n # longjump, specify them as JUMP and specify NEGATIVE mean. Reverse reads\n # are optional for PE libraries and mandatory for JUMP libraries. Any\n # OTHER sequence data (454, Sanger, Ion torrent, etc) must be first\n # converted into Celera Assembler compatible .frg files (see\n # http:\/\/wgs-assembler.sourceforge.com)\n DATA\n #Illumina paired end reads supplied as <two-character prefix> <fragment mean> <fragment stdev> <forward_reads> <reverse_reads>\n #if single-end, do not specify <reverse_reads>\n #MUST HAVE Illumina paired end reads to use MaSuRCA\n PE= pe 400 50\u00a0 \/mnt\/4TB_HDD\/koubogenome2\/paired_output_1.fq \/mnt\/4TB_HDD\/koubogenome2\/paired_output_2.fq\n #Illumina mate pair reads supplied as <two-character prefix> <fragment mean> <fragment stdev> <forward_reads> <reverse_reads>\n #JUMP= sh 3600 200\u00a0 \/FULL_PATH\/short_1.fastq\u00a0 \/FULL_PATH\/short_2.fastq\n #pacbio OR nanopore reads must be in a single fasta or fastq file with absolute path, can be gzipped\n #if you have both types of reads supply them both as NANOPORE type\n #PACBIO=\/FULL_PATH\/pacbio.fa\n #NANOPORE=\/FULL_PATH\/nanopore.fa\n #Other reads (Sanger, 454, etc) one frg file, concatenate your frg files into one if you have many\n #OTHER=\/FULL_PATH\/file.frg\n END\n \u00a0\n PARAMETERS\n #set this to 1 if your Illumina jumping library reads are shorter than 100bp\n EXTEND_JUMP_READS=0\n #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\n GRAPH_KMER_SIZE = auto\n #set this to 1 for all Illumina-only assemblies\n #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)\n USE_LINKING_MATES = 0\n #specifies whether to run mega-reads correction on the grid\n USE_GRID=0\n #specifies grid engine to use SGE or SLURM\n GRID_ENGINE=SGE\n #specifies queue (for SGE) or partition (for SLURM) to use when running on the grid MANDATORY\n GRID_QUEUE=all.q\n #batch size in the amount of long read sequence for each batch on the grid\n GRID_BATCH_SIZE=300000000\n #use at most this much coverage by the longest Pacbio or Nanopore reads, discard the rest of the reads\n LHE_COVERAGE=25\n #set to 1 to only do one pass of mega-reads, for faster but worse quality assembly\n MEGA_READS_ONE_PASS=0\n #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 \n LIMIT_JUMP_COVERAGE = 300\n #these are the additional parameters to Celera Assembler.\u00a0 do not worry about performance, number or processors or batch sizes -- these are computed automatically. \n #set cgwErrorRate=0.25 for bacteria and 0.1<=cgwErrorRate<=0.15 for other organisms.\n CA_PARAMETERS =\u00a0 cgwErrorRate=0.15\n #minimum count k-mers used in error correction 1 means all k-mers are used.\u00a0 one can increase to 2 if Illumina coverage >100\n KMER_COUNT_THRESHOLD = 1\n #whether to attempt to close gaps in scaffolds with Illumina data\n CLOSE_GAPS=1\n #auto-detected number of cpus to use\n NUM_THREADS = 16\n #this is mandatory jellyfish hash size -- a safe value is estimated_genome_size*estimated_coverage\n JF_SIZE = 200000000\n #set this to 1 to use SOAPdenovo contigging\/scaffolding module.\u00a0 Assembly will be worse but will run faster. Useful for very large (>5Gbp) genomes from Illumina-only data\n SOAP_ASSEMBLY=0\n END <\/pre>\n","protected":false},"excerpt":{"rendered":"2020\u5e74\u5ea6\u306e\u751f\u7269\u79d1\u5b66\u57fa\u790e\u5b9f\u9a13I\u304c\u30b3\u30ed\u30ca<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"colormag_page_container_layout":"default_layout","colormag_page_sidebar_layout":"default_layout","_locale":"ja","_original_post":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/?p=1529","footnotes":""},"categories":[7],"tags":[],"class_list":["post-1529","post","type-post","status-publish","format-standard","hentry","category-protocol","ja"],"_links":{"self":[{"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=\/wp\/v2\/posts\/1529","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1529"}],"version-history":[{"count":6,"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=\/wp\/v2\/posts\/1529\/revisions"}],"predecessor-version":[{"id":1696,"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=\/wp\/v2\/posts\/1529\/revisions\/1696"}],"wp:attachment":[{"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1529"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1529"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/home.hiroshima-u.ac.jp\/~tigawa\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1529"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}