{"id":2717,"date":"2019-04-08T15:22:52","date_gmt":"2019-04-08T07:22:52","guid":{"rendered":"http:\/\/www.chenlianfu.com\/?p=2717"},"modified":"2019-04-12T10:21:06","modified_gmt":"2019-04-12T02:21:06","slug":"%e6%a3%80%e6%b5%8b%e5%85%a8%e5%9f%ba%e5%9b%a0%e7%bb%84%e5%ba%8f%e5%88%97%e4%b8%ad%e7%9a%84%e7%ab%af%e7%b2%92%e5%ba%8f%e5%88%97","status":"publish","type":"post","link":"http:\/\/www.chenlianfu.com\/?p=2717","title":{"rendered":"\u68c0\u6d4b\u5168\u57fa\u56e0\u7ec4\u5e8f\u5217\u4e2d\u7684\u7aef\u7c92\u5e8f\u5217"},"content":{"rendered":"\n<p>\u4f7f\u7528\u4e09\u4ee3\u6d4b\u5e8f\u6570\u636e\u80fd\u83b7\u5f97\u8f83\u597d\u7684\u3001\u751a\u81f3\u5b8c\u6574\u7684\u57fa\u56e0\u7ec4\u5e8f\u5217\u3002\u901a\u8fc7\u68c0\u6d4b\u57fa\u56e0\u7ec4\u5e8f\u5217\u4e24\u7aef\u7684\u5c5e\u4e8e\u7aef\u7c92\uff08Telomere\uff09\u7684\u7279\u5b9a\u7684\u91cd\u590d\u5e8f\u5217\uff0c\u53ef\u4ee5\u77e5\u9053\u57fa\u56e0\u7ec4\u7ec4\u88c5\u662f\u5426\u5f97\u5230\u5b8c\u6574\u7684\u67d3\u8272\u4f53\u6c34\u5e73\u7684\u5e8f\u5217\u3002\u82e5\u5728\u5e8f\u5217\u4e2d\u95f4\u68c0\u6d4b\u5230\u7aef\u7c92\u5e8f\u5217\uff0c\u53ef\u4ee5\u77e5\u9053\u57fa\u56e0\u7ec4\u7ec4\u88c5\u8fc7\u7a0b\u4e2d\u5bf9Contigs\u6709\u9519\u8bef\u7684\u8fde\u63a5\u3002<\/p>\n\n\n\n<p>\u5728\u67d3\u8272\u4f53\u5e8f\u5217\u9996\u5c3e\u5b58\u5728\u7aef\u7c92\u5e8f\u5217\u3002<a rel=\"noreferrer noopener\" aria-label=\"\u5728\u4eba\u7c7b\u4e2d\uff0c\u7aef\u7c92\u5e8f\u5217\u7531\u91cd\u590d\u5355\u5143TTAGGG\uff0c\u91cd\u590d\u7ea62500\u6b21\u7ec4\u6210\u3002\uff08\u5728\u65b0\u7a97\u53e3\u6253\u5f00\uff09\" href=\"https:\/\/en.wikipedia.org\/wiki\/Telomere\" target=\"_blank\">\u5728\u4eba\u7c7b\u4e2d\uff0c\u7aef\u7c92\u5e8f\u5217\u7531\u91cd\u590d\u5355\u5143TTAGGG\uff0c\u4e32\u8054\u91cd\u590d\u7ea62500\u6b21\u7ec4\u6210\u3002<\/a> \u4e0d\u540c\u7684\u7269\u79cd\uff0c\u7aef\u7c92\u7684\u91cd\u590d\u5355\u5143\u53ef\u80fd\u4e0d\u4e00\u6837\uff0c\u53ef\u4ee5\u5728<a rel=\"noreferrer noopener\" aria-label=\"\u7aef\u7c92\u6570\u636e\u5e93\uff08\u5728\u65b0\u7a97\u53e3\u6253\u5f00\uff09\" href=\"http:\/\/telomerase.asu.edu\/sequences_telomere.html\" target=\"_blank\">\u7aef\u7c92\u6570\u636e\u5e93<\/a>\u4e2d\u67e5\u8be2\u3002 \u6211\u5bf9\u4e00\u79cd\u5b50\u56ca\u83cc\u4f7f\u7528PacBio\u6d4b\u5e8f\u6570\u636e\u8fdb\u884c\u4e86\u57fa\u56e0\u7ec4\u7ec4\u88c5\uff0c\u5f97\u523012\u6761\u5e8f\u5217\uff0c\u53d1\u73b0\u5927\u90e8\u5206\u5e8f\u5217\u9996\u5c3e\u5747\u51fa\u73b0\u4e86TTAGGG\/CCCTAA\u7684\u4e32\u8054\u91cd\u590d\u5e8f\u5217\u3002\u6211\u5bf9\u4e00\u79cd\u6606\u866b\u7269\u79cdPacBio\u7ec4\u88c5\u57fa\u56e0\u7ec4\u5e8f\u5217\u8fdb\u884c\u5206\u6790\uff0c\u53d1\u73b0\u5e8f\u5217\u9996\u5c3e\u51fa\u73b0\u4e00\u4e9b\u957f\u5ea6\u8f83\u957f\u5fae\u536b\u661f\u91cd\u590d\u5e8f\u5217\uff0c\u800c\u6ca1\u6709\u56fa\u5b9a\u7684\u91cd\u590d\u5355\u5143\uff0c\u8fd9\u548c\u7aef\u7c92\u6570\u636e\u5e93\u4e2d\u7684\u7ed3\u679c\u4e00\u81f4\u3002<\/p>\n\n\n\n<p>\u7f16\u5199Perl\u7a0b\u5e8f\u5bf9\u5168\u57fa\u56e0\u7ec4\u5e8f\u5217\u7684\u7aef\u7c92\u5e8f\u5217\u8fdb\u884c\u641c\u7d22\uff0c\u67e5\u770b\u57fa\u56e0\u7ec4\u5e8f\u5217\u7684\u5b8c\u6574\u60c5\u51b5\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>#!\/usr\/bin\/perl\nuse strict;\nuse Getopt::Long;\n\nmy $usage = &lt;&lt;USAGE;\nUsage:\n    $0 genome.fasta > telomere_info.txt\n\n    \u5927\u90e8\u5206\u7269\u79cd\u7aef\u7c92\u5e8f\u5217\u7684\u91cd\u590d\u5355\u5143\u662fTTAGGG\/CCCTAA\u3002\u672c\u7a0b\u5e8f\u80fd\u5728\u57fa\u56e0\u7ec4\u4e2d\u5bfb\u627e\u7aef\u7c92\u91cd\u590d\u5355\u5143\u7684\u4e32\u8054\u91cd\u590d\u5e8f\u5217\uff0c\u5e76\u7ed9\u51fa\u4f4d\u70b9\u4fe1\u606f\u3002\n\n    --split-length &lt;int>    default: 100000\n    --overlap-length &lt;int>    default: 10000\n    \u7a0b\u5e8f\u4f1a\u5c06\u6bcf\u6761\u5e8f\u5217\u6253\u65ad\u540e\u8fdb\u884c\u91cd\u590d\u5355\u5143\u641c\u7d22\u3002\u8fd9\u4e24\u4e2a\u53c2\u6570\u8bbe\u7f6e\u6253\u65ad\u7684\u5e8f\u5217\u957f\u5ea6\u548c\u76f8\u90bb\u4e24\u5e8f\u5217\u4e4b\u95f4\u7684\u91cd\u53e0\u957f\u5ea6\u3002\n\n    --repeat-unit &lt;string>    default: TTAGGG\n    \u8bbe\u7f6e\u91cd\u590d\u5355\u5143\u78b1\u57fa\u5e8f\u5217\uff0c\u8be5\u91cd\u590d\u5355\u5143\u7684\u53cd\u5411\u4e92\u8865\u4e5f\u5c06\u4f5c\u4e3a\u91cd\u590d\u5355\u5143\u8fdb\u884c\u641c\u7d22\u3002\u53ef\u4ee5\u5728\u7aef\u7c92\u6570\u636e\u5e93\uff08http:\/\/telomerase.asu.edu\/sequences_telomere.html\uff09\u4e2d\u5bfb\u627e\u76ee\u6807\u7aef\u7c92\u91cd\u590d\u5355\u5143\u3002\n    vertebrate sp.      TTAGGG\n    plants sp.          TTTAGGG\n    Pezizomycotina      TTAGGG\n\n    --min-repeat-num &lt;int>    default: 4\n    \u8bbe\u7f6e\u91cd\u590d\u5355\u5143\u6700\u5c0f\u91cd\u590d\u6b21\u6570\u3002\n\n\nUSAGE\nif (@ARGV==0){die $usage}\n\nmy ($splitLength, $overlapLength, $repeatunit, $minRepeatNum);\nGetOptions(\n    \"split-length:i\" => \\$splitLength,\n    \"overlap-length:i\" => \\$overlapLength,\n    \"repeat-unit:s\" => \\$repeatunit,\n    \"min-repeat-num:s\" => \\$minRepeatNum,\n);\n$splitLength ||= 100000;\n$overlapLength ||= 10000;\n$repeatunit ||= \"TTAGGG\";\n$repeatunit = uc($repeatunit);\nmy $repeatunit_reverse = reverse $repeatunit;\n$repeatunit_reverse =~ tr\/ATCG\/TAGC\/;\n$minRepeatNum ||= 4;\n\n# \u8bfb\u53d6\u57fa\u56e0\u7ec4\u5e8f\u5217\nopen IN, $ARGV[0] or die \"Can not open file $ARGV[0], $!\\n\";\nmy (%seq, $seq_id);\nwhile (&lt;IN>) {\n    chomp;\n    if (m\/^>(\\S+)\/) {\n        $seq_id = $1;\n    }\n    else {\n        $_ = uc($_);\n        $seq{$seq_id} .= $_;\n    }\n}\nclose IN;\n\n# \u5c06\u57fa\u56e0\u7ec4\u5e8f\u5217\u6253\u65ad\nmy (%seq_split, %seq_length);\nforeach my $id (keys %seq) {\n    my $seq = $seq{$id};\n    my $length = length($seq);\n    $seq_length{$id} = $length;\n    my $pos = 0;\n    while ($pos &lt; $length) {\n        $seq_split{$id}{$pos} = substr($seq, $pos, $splitLength + $overlapLength);\n        $pos += $splitLength;\n    }\n}\n\nprint \"SeqID\\tSeqLength\\tStart\\tEnd\\tLength\\tType\\n\";\nforeach my $id (sort keys %seq_split) {\n    foreach my $pos (sort {$a &lt;=> $b} keys %{$seq_split{$id}}) {\n        my $seq = $seq_split{$id}{$pos};\n        while ($seq =~ m\/(($repeatunit){$minRepeatNum,})\/g) {\n            my $length = length($1);\n            my $end = pos($seq);\n            $end = $end + $pos;\n            my $start = $end - $length + 1;\n            print \"$id\\t$seq_length{$id}\\t$start\\t$end\\t$length\\t$repeatunit\\n\";\n        }\n        while ($seq =~ m\/(($repeatunit_reverse){$minRepeatNum,})\/g) {\n            my $length = length($1);\n            my $end = pos($seq);\n            $end = $end + $pos;\n            my $start = $end - $length + 1;\n            print \"$id\\t$seq_length{$id}\\t$start\\t$end\\t$length\\t$repeatunit_reverse\\n\";\n        }\n    }\n}\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>\u4f7f\u7528\u4e09\u4ee3\u6d4b\u5e8f\u6570\u636e\u80fd\u83b7\u5f97\u8f83\u597d\u7684\u3001\u751a\u81f3\u5b8c\u6574\u7684\u57fa\u56e0\u7ec4\u5e8f\u5217\u3002\u901a\u8fc7\u68c0\u6d4b\u57fa\u56e0\u7ec4\u5e8f\u5217\u4e24\u7aef\u7684\u5c5e\u4e8e &hellip; <a href=\"http:\/\/www.chenlianfu.com\/?p=2717\">\u7ee7\u7eed\u9605\u8bfb <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts\/2717"}],"collection":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2717"}],"version-history":[{"count":7,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts\/2717\/revisions"}],"predecessor-version":[{"id":2796,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts\/2717\/revisions\/2796"}],"wp:attachment":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2717"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2717"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2717"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}