From 29dc4b30fc93a7fde77793033b43fdf30f6abbcd Mon Sep 17 00:00:00 2001 From: Eric Boittier <ericdavid.boittier@unibas.ch> Date: Wed, 23 Nov 2022 10:45:09 +0100 Subject: [PATCH] cleaning dir --- .DS_Store | Bin 6148 -> 0 bytes .../8ec9a00bfd09b3190ac6b22251dbb1aa95a0579d | 0 .../bac1bbdfef47272490e8c91d5267120512437532 | 7 - .idea/workspace.xml | 45 - .ipynb_checkpoints/cdna-checkpoint.ipynb | 1186 ----------------- .../copy_numbers-checkpoint.csv | 0 6 files changed, 1238 deletions(-) delete mode 100644 .DS_Store delete mode 100644 .idea/sonarlint/issuestore/8/e/8ec9a00bfd09b3190ac6b22251dbb1aa95a0579d delete mode 100644 .idea/sonarlint/issuestore/b/a/bac1bbdfef47272490e8c91d5267120512437532 delete mode 100644 .idea/workspace.xml delete mode 100644 .ipynb_checkpoints/cdna-checkpoint.ipynb delete mode 100644 .ipynb_checkpoints/copy_numbers-checkpoint.csv diff --git a/.DS_Store b/.DS_Store deleted file mode 100644 index 6c9f8365e9980ee838b8131f3248f0ab755fcf1f..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 6148 zcmZQzU|@7AO)+F(5MW?n;9!8zEL;p&0Z1N%F(jFwBHSSJKxTO6<R>TP<R?K5gi4Q6 zqaiRF0)sRJKzWyiA(<hCA&(&uE&n<)Ffi!-2LrI{;p&pgiwmInd`D72PG)h5fx$IK zCT12^Hg*nn4sMRv;Eeq8;F83W(qgB?qG%8=BtJhV3C2!L3d>9_j~5Ve&d)1J%*;zI z0x1d3Oi4{jEQ$%w%uC5Hcgio#ODP8Hg-UR6a&X2ANK{uFnHlORm>8PY>L^rO8X4#) zm>8SY)^c))D(hPZ#b@W_=H+*RUChA92%#Bxp)`!@W?*1|`=>0pC@&{JFC9{jF>t}c zgF%lWlc9j2k|B>F2{mjOLHd!yMt~uiAs?(Zo*|E+lp&WPi6NDth@qH4k0F_%n4t_! z|4+2AWn;)>$Yn@mNM}f8C`MJwupXb<fsPAfBU2p(V{>B);{wJ1Xz{_x5X9ih;K<;@ z;LG63pvREQkb)XQjIwAU#KI85kjhZZP=czC2^7P~vBttsf=wMp?7~vb@S>r4g9B6s z3@@LJ`erl)Mnizo5CD}A3eY;y0ZKPOXpj^GBLf4t3&04fN}-l9g8BgvH6X1ZH6X1Z z8l;th5yS$^gS9d+GO&PkGJ?Ay3=E9mE(wSRYiD3&0BdJpWB_Z2SLloo?F@_%?F@|2 z9ttC<M*}h+qMd;eq8)6<C@~rWqalC@0cHqO0960GGBDuk|3g%blA|Fo8Un*I1Q=Od zf?b?Il_n1Ff$CaNeVPE32i5+d>X;E!Peb&9lz?TKAOngLU=BnMq!m={gR5dj21rdl Q+7N(+&?r3`0`w070FKw-#sB~S diff --git a/.idea/sonarlint/issuestore/8/e/8ec9a00bfd09b3190ac6b22251dbb1aa95a0579d b/.idea/sonarlint/issuestore/8/e/8ec9a00bfd09b3190ac6b22251dbb1aa95a0579d deleted file mode 100644 index e69de29..0000000 diff --git a/.idea/sonarlint/issuestore/b/a/bac1bbdfef47272490e8c91d5267120512437532 b/.idea/sonarlint/issuestore/b/a/bac1bbdfef47272490e8c91d5267120512437532 deleted file mode 100644 index 73a7b14..0000000 --- a/.idea/sonarlint/issuestore/b/a/bac1bbdfef47272490e8c91d5267120512437532 +++ /dev/null @@ -1,7 +0,0 @@ - -�python:S101"bRename class "cDNA_Gen" to match the regular expression ^_?([A-Z_][a-zA-Z0-9]*|[a-z_][a-z0-9_]*)$.(����8Ų���0 -}python:S1186&"YAdd a nested comment explaining why this method is empty, or complete the implementation.(���������8Ȳ���0 -xpython:S1186)"YAdd a nested comment explaining why this method is empty, or complete the implementation.(����8ɲ���0 -}python:S1186;"YAdd a nested comment explaining why this method is empty, or complete the implementation.(���������8ʲ���0 -�python:S101M"cRename class "GTF_entry" to match the regular expression ^_?([A-Z_][a-zA-Z0-9]*|[a-z_][a-z0-9_]*)$.(։�������8ʲ���0 -;python:S2772a"Remove this unneeded "pass".(�۾8ʲ���0 \ No newline at end of file diff --git a/.idea/workspace.xml b/.idea/workspace.xml deleted file mode 100644 index 8a987c1..0000000 --- a/.idea/workspace.xml +++ /dev/null @@ -1,45 +0,0 @@ -<?xml version="1.0" encoding="UTF-8"?> -<project version="4"> - <component name="ChangeListManager"> - <list default="true" id="4a8c5eec-e14f-46f8-83f6-218471f8c20b" name="Changes" comment="" /> - <option name="SHOW_DIALOG" value="false" /> - <option name="HIGHLIGHT_CONFLICTS" value="true" /> - <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" /> - <option name="LAST_RESOLUTION" value="IGNORE" /> - </component> - <component name="Git.Settings"> - <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" /> - </component> - <component name="MarkdownSettingsMigration"> - <option name="stateVersion" value="1" /> - </component> - <component name="ProjectId" id="2GzM5DMpjLKSe0zWWtlaBWfsqTD" /> - <component name="ProjectLevelVcsManager" settingsEditedManually="true" /> - <component name="ProjectViewState"> - <option name="hideEmptyMiddlePackages" value="true" /> - <option name="showLibraryContents" value="true" /> - </component> - <component name="PropertiesComponent"><![CDATA[{ - "keyToString": { - "RunOnceActivity.OpenProjectViewOnStart": "true", - "RunOnceActivity.ShowReadmeOnStart": "true", - "WebServerToolWindowFactoryState": "false", - "last_opened_file_path": "/Users/ericboittier/Documents/github/cdna-generator" - } -}]]></component> - <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" /> - <component name="TaskManager"> - <task active="true" id="Default" summary="Default task"> - <changelist id="4a8c5eec-e14f-46f8-83f6-218471f8c20b" name="Changes" comment="" /> - <created>1667386773933</created> - <option name="number" value="Default" /> - <option name="presentableId" value="Default" /> - <updated>1667386773933</updated> - <workItem from="1667386779377" duration="1232000" /> - </task> - <servers /> - </component> - <component name="TypeScriptGeneratedFilesManager"> - <option name="version" value="3" /> - </component> -</project> \ No newline at end of file diff --git a/.ipynb_checkpoints/cdna-checkpoint.ipynb b/.ipynb_checkpoints/cdna-checkpoint.ipynb deleted file mode 100644 index fff378b..0000000 --- a/.ipynb_checkpoints/cdna-checkpoint.ipynb +++ /dev/null @@ -1,1186 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 1, - "id": "451af95e-82e7-4c64-a4f2-391d7ad5b8c1", - "metadata": {}, - "outputs": [], - "source": [ - "import sys\n", - "\n", - "def translate(res):\n", - " translate_dict = {\"A\": \"T\", \"U\": \"A\", \"G\": \"C\", \"C\":\"G\"}\n", - " if res not in translate_dict.keys():\n", - " print(\"cDNA residue not A,T,U or G \")\n", - " sys.exit(1)\n", - " return translate_dict[res]\n", - "\n", - "class cDNA_Gen:\n", - " def __init__(self, \n", - " fasta, \n", - " gtf, \n", - " cpn, \n", - " output_fasta = \"cDNA.fasta\",\n", - " output_csv = \"cDNA.csv\"\n", - " ):\n", - " # inputs\n", - " self.fasta = fasta\n", - " self.gtf = gtf\n", - " self.cpn = cpn\n", - " self.output_fasta = output_fasta\n", - " self.output_csv = output_csv\n", - " # variables\n", - " self.prime_sites = []\n", - " self.fasta_seq = \"\"\n", - " self.fasta_id = \"\"\n", - " self.copy_numbers = {}\n", - " \n", - " self.run()\n", - " \n", - " def run(self):\n", - " self.read_fasta()\n", - " self.read_gtf()\n", - " \n", - " def order_priming_sites(self):\n", - " pass\n", - " \n", - " def generate_cdna(self):\n", - " pass\n", - " \n", - " \n", - " def read_fasta(self):\n", - " fasta = open(self.fasta).readlines()\n", - " self.fasta_id = fasta[0]\n", - " print(fasta[0])\n", - " self.fasta_seq = \"\".join([_.rstrip() for _ in fasta[1:]])\n", - " \n", - " \n", - " def read_gtf(self):\n", - " with open(self.gtf) as gtf_file:\n", - " gtf_lines = gtf_file.readlines()\n", - " for line in gtf_lines[:1000]:\n", - " if not line.startswith(\"#\"):\n", - " temp_gtf = GTF_entry(line)\n", - " temp_gtf.set_sequence(self.fasta_seq)\n", - " self.prime_sites.append(temp_gtf)\n", - "\n", - " def write_fasta(self):\n", - " pass\n", - " \n", - " def read_copy_numbers(self):\n", - " with open(self.cpn) as cpn_file:\n", - " cpn_lines = cpn_file.readlines()\n", - " for line in cpn_lines:\n", - " csv = line.split(\",\")\n", - " trans_id = csv[0]\n", - " if trans_id:\n", - " gene_id = csv[1]\n", - " count = csv[2]\n", - " self.copy_numbers[gene_id] = count\n", - " \n", - " \n", - " def return_output(self):\n", - " return self.output_fasta, self.output_csv\n", - " \n", - "\n", - "class GTF_entry:\n", - " def __init__(self, string):\n", - " self.string = string\n", - " self.values = self.string.split(\"\\t\")\n", - " self.start = int(self.values[3])\n", - " self.end = int(self.values[4])\n", - " self.score = float(0.5) #self.values[5]\n", - " self.sequence = \"no sequence set\"\n", - " self.length = self.end - self.start\n", - " \n", - " def __repr__(self):\n", - " return self.sequence[:10] + \"...\" + f\" len={self.length} score={self.score}\"\n", - " \n", - " def set_sequence(self, full_sequence):\n", - " self.sequence = full_sequence[self.start:self.end]\n", - " \n", - " \n", - "if __name__ == \"__main__\":\n", - " import argparse\n", - " pass\n", - " \n", - " " - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "id": "84d36302-f645-43a9-a5a6-b4f3d913f734", - "metadata": {}, - "outputs": [], - "source": [ - "fasta = \"/Users/ericboittier/Downloads/Homo_sapiens.GRCh38.dna.primary_assembly.fa\"\n", - "gtf = \"/Users/ericboittier/Downloads/Homo_sapiens.GRCh38.107.gtf\"" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "c7a3c6f2-c8f3-466e-80aa-05ae982680f1", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - ">1 dna:chromosome chromosome:GRCh38:1:1:248956422:1 REF\n", - "\n" - ] - } - ], - "source": [ - "cdna_gen = cDNA_Gen(fasta, gtf, gtf)" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "f03693e4-82e8-4a48-9163-1146941ac095", - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "[TTTCGCCTGC... len=26083 score=0.5,\n", - " TTTCGCCTGC... len=26083 score=0.5,\n", - " TTTCGCCTGC... len=324 score=0.5,\n", - " TGTCGTGGCT... len=204 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " TTACGCCAAG... len=76 score=0.5,\n", - " TTACGCCAAG... len=76 score=0.5,\n", - " AGTATGAGGC... len=101 score=0.5,\n", - " AGTATGAGGC... len=101 score=0.5,\n", - " GGGCCCAGTA... len=59 score=0.5,\n", - " GGGCCCAGTA... len=59 score=0.5,\n", - " AACTTCTCAA... len=69 score=0.5,\n", - " AACTTCTCAA... len=69 score=0.5,\n", - " CACCGTGGAG... len=165 score=0.5,\n", - " CACCGTGGAG... len=165 score=0.5,\n", - " ACGGCTGGCA... len=69 score=0.5,\n", - " ACGGCTGGCA... len=69 score=0.5,\n", - " TGGCTGGGCT... len=155 score=0.5,\n", - " TGGCTGGGCT... len=155 score=0.5,\n", - " TCAGCCGGCG... len=56 score=0.5,\n", - " TCAGCCGGCG... len=56 score=0.5,\n", - " CCAGCCTGGA... len=125 score=0.5,\n", - " CCAGCCTGGA... len=125 score=0.5,\n", - " AACTCGCCCT... len=124 score=0.5,\n", - " AACTCGCCCT... len=124 score=0.5,\n", - " CTCCTGCTCT... len=51 score=0.5,\n", - " CTCCTGCTCT... len=51 score=0.5,\n", - " AGGAGATAAG... len=70 score=0.5,\n", - " AGGAGATAAG... len=70 score=0.5,\n", - " TTCATGCTGG... len=167 score=0.5,\n", - " TTCATGCTGG... len=167 score=0.5,\n", - " CGCCTGAAGC... len=108 score=0.5,\n", - " CGCCTGAAGC... len=108 score=0.5,\n", - " CCACGGCATA... len=2363 score=0.5,\n", - " CCACGGCATA... len=329 score=0.5,\n", - " AG... len=2 score=0.5,\n", - " TTTCGCCTGC... len=119 score=0.5,\n", - " CACTGGCTAG... len=2030 score=0.5,\n", - " AGTGTCACTC... len=19822 score=0.5,\n", - " AGTGTCACTC... len=719 score=0.5,\n", - " GGGCCCAGTA... len=59 score=0.5,\n", - " AACTTCTCAA... len=69 score=0.5,\n", - " CACCGTGGAG... len=165 score=0.5,\n", - " ACGGCTGGCA... len=69 score=0.5,\n", - " TGGCTGGGCT... len=155 score=0.5,\n", - " TCAGCCGGCG... len=56 score=0.5,\n", - " CCAGCCTGGA... len=125 score=0.5,\n", - " AACTCGCCCT... len=124 score=0.5,\n", - " CTCCTGCTCT... len=51 score=0.5,\n", - " AGGAGATAAG... len=70 score=0.5,\n", - " TTCATGCTGG... len=167 score=0.5,\n", - " CGCCTGAAGC... len=108 score=0.5,\n", - " CCACGGCATA... len=2363 score=0.5,\n", - " GGGCCCAGTA... len=3613 score=0.5,\n", - " GGGCCCAGTA... len=59 score=0.5,\n", - " AACTTCTCAA... len=69 score=0.5,\n", - " CACCGTGGAG... len=165 score=0.5,\n", - " ACGGCTGGCA... len=117 score=0.5,\n", - " AATAAGCCAG... len=12717 score=0.5,\n", - " AATAAGCCAG... len=1686 score=0.5,\n", - " TCAGCCGGCG... len=56 score=0.5,\n", - " CCAGCCTGGA... len=125 score=0.5,\n", - " AACTCGCCCT... len=124 score=0.5,\n", - " CTCCTGCTCT... len=51 score=0.5,\n", - " AGGAGATAAG... len=70 score=0.5,\n", - " CCCAGTCACG... len=119 score=0.5,\n", - " TTCATGCTGG... len=167 score=0.5,\n", - " CGCCTGAAGC... len=108 score=0.5,\n", - " CCACGGCATA... len=717 score=0.5,\n", - " GCCGGCCTTG... len=11632 score=0.5,\n", - " GCCGGCCTTG... len=602 score=0.5,\n", - " TCAGCCGGCG... len=453 score=0.5,\n", - " AACTCGCCCT... len=124 score=0.5,\n", - " AGGAGATAAG... len=1467 score=0.5,\n", - " CCACGGCATA... len=716 score=0.5,\n", - " CTGGCCACCG... len=24417 score=0.5,\n", - " CTGGCCACCG... len=305 score=0.5,\n", - " TGTCGTGGCT... len=204 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " TTACGCCAAG... len=76 score=0.5,\n", - " TTACGCCAAG... len=76 score=0.5,\n", - " AACTTCTCAA... len=41 score=0.5,\n", - " AACTTCTCAA... len=41 score=0.5,\n", - " CGTCCGAGCA... len=37 score=0.5,\n", - " CGTCCGAGCA... len=37 score=0.5,\n", - " ACGGCTGGCA... len=69 score=0.5,\n", - " ACGGCTGGCA... len=69 score=0.5,\n", - " TGGCTGGGCT... len=155 score=0.5,\n", - " TGGCTGGGCT... len=155 score=0.5,\n", - " TCAGCCGGCG... len=56 score=0.5,\n", - " TCAGCCGGCG... len=56 score=0.5,\n", - " CCAGCCTGGA... len=125 score=0.5,\n", - " CCAGCCTGGA... len=125 score=0.5,\n", - " AACTCGCCCT... len=124 score=0.5,\n", - " AACTCGCCCT... len=122 score=0.5,\n", - " CTCCTGCTCT... len=51 score=0.5,\n", - " AGGAGATAAG... len=70 score=0.5,\n", - " TTCATGCTGG... len=167 score=0.5,\n", - " CGCCTGAAGC... len=108 score=0.5,\n", - " CCACGGCATA... len=716 score=0.5,\n", - " CTGGCCACCG... len=100 score=0.5,\n", - " G... len=1 score=0.5,\n", - " CTCCTGCTCT... len=51 score=0.5,\n", - " AGGAGATAAG... len=70 score=0.5,\n", - " TTCATGCTGG... len=167 score=0.5,\n", - " CGCCTGAAGC... len=108 score=0.5,\n", - " CCACGGCATA... len=716 score=0.5,\n", - " CACCCCCGGC... len=8215 score=0.5,\n", - " CACCCCCGGC... len=8215 score=0.5,\n", - " CACCCCCGGC... len=121 score=0.5,\n", - " AAGGGGACCC... len=203 score=0.5,\n", - " TTGACCTTCA... len=371 score=0.5,\n", - " TTGACCTTCA... len=371 score=0.5,\n", - " TTGACCTTCA... len=371 score=0.5,\n", - " AAGAAGCCTG... len=702 score=0.5,\n", - " AAGAAGCCTG... len=702 score=0.5,\n", - " AAGAAGCCTG... len=702 score=0.5,\n", - " TGACCCACCA... len=546 score=0.5,\n", - " TGACCCACCA... len=546 score=0.5,\n", - " TGACCCACCA... len=546 score=0.5,\n", - " ATTGGAGGAA... len=1478 score=0.5,\n", - " ATTGGAGGAA... len=1478 score=0.5,\n", - " ATTGGAGGAA... len=50 score=0.5,\n", - " TGTGTGGTGA... len=84 score=0.5,\n", - " TCAGAGCCCA... len=77 score=0.5,\n", - " CAGGGCCATC... len=161 score=0.5,\n", - " AGTAGGCCTC... len=193 score=0.5,\n", - " AAATGCCGTC... len=2973 score=0.5,\n", - " AAATGCCGTC... len=2973 score=0.5,\n", - " AAATGCCGTC... len=90 score=0.5,\n", - " AGCCACCCCA... len=125 score=0.5,\n", - " AGAACGGCAT... len=408 score=0.5,\n", - " GTGTCCAAAC... len=369453 score=0.5,\n", - " GTGTCCAAAC... len=365174 score=0.5,\n", - " GTGTCCAAAC... len=128 score=0.5,\n", - " TGCGATCCAA... len=36 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " AGATCTCCGA... len=137 score=0.5,\n", - " AGATCTCCGA... len=137 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " AGGGTAGAAA... len=87 score=0.5,\n", - " AGGGTAGAAA... len=87 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " CATATGCAAT... len=665 score=0.5,\n", - " CATATGCAA... len=9 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " GTGTCCAAAC... len=91 score=0.5,\n", - " GCTGTCCCTT... len=652 score=0.5,\n", - " ATGCTGGGGA... len=117408 score=0.5,\n", - " ATGCTGGGGA... len=113 score=0.5,\n", - " TGACGGTGAC... len=466 score=0.5,\n", - " AAGATAGTGT... len=366224 score=0.5,\n", - " AAGATAGTGT... len=99 score=0.5,\n", - " TGCGATCCAA... len=36 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " TCTCCGAAGA... len=134 score=0.5,\n", - " TCTCCGAAGA... len=134 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " AGGGTAGAAA... len=87 score=0.5,\n", - " AGGGTAGAAA... len=87 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " TGTGCTGAGG... len=174 score=0.5,\n", - " TGTGCTGAGG... len=174 score=0.5,\n", - " GTTCTCTGGA... len=1687 score=0.5,\n", - " GTTCTCTGGA... len=74 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " AAGATAGTGT... len=62 score=0.5,\n", - " GGGCTGGGCA... len=1609 score=0.5,\n", - " CTGCTTCTGG... len=365131 score=0.5,\n", - " CTGCTTCTGG... len=85 score=0.5,\n", - " TGCGATCCAA... len=36 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " AGATCTCCGA... len=137 score=0.5,\n", - " AGATCTCCGA... len=137 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " GTAGAAAAGC... len=84 score=0.5,\n", - " GTAGAAAAGC... len=84 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " CATATGCAAT... len=665 score=0.5,\n", - " CATATGCAA... len=9 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " CTGCTTCTGG... len=48 score=0.5,\n", - " GCTGTCCCTT... len=652 score=0.5,\n", - " GTGTGTGGCT... len=369418 score=0.5,\n", - " GTGTGTGGCT... len=93 score=0.5,\n", - " TGCGATCCAA... len=36 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " TGACGGTGAC... len=349 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " TCTCCGAAGA... len=134 score=0.5,\n", - " TCTCCGAAGA... len=134 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " AGGGTAGAAA... len=87 score=0.5,\n", - " AGGGTAGAAA... len=87 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " TGTGCTGAGG... len=174 score=0.5,\n", - " TGTGCTGAGG... len=174 score=0.5,\n", - " CATATGCAAT... len=4944 score=0.5,\n", - " CATATGCAAT... len=131 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " GTGTGTGGCT... len=56 score=0.5,\n", - " GGGCTGGGCA... len=4809 score=0.5,\n", - " AGCACAAGGC... len=195994 score=0.5,\n", - " AGCACAAGGC... len=164 score=0.5,\n", - " AAATACTGAC... len=50 score=0.5,\n", - " TCTCCGAAGA... len=134 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " AGGGTAGAAA... len=87 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " TGTGCTGAGG... len=174 score=0.5,\n", - " CATATGCAAT... len=248 score=0.5,\n", - " CAAAGGTAGG... len=142786 score=0.5,\n", - " CAAAG... len=5 score=0.5,\n", - " CAAAG... len=5 score=0.5,\n", - " TCTCCGAAGA... len=134 score=0.5,\n", - " TCTCCGAAGA... len=134 score=0.5,\n", - " TGAAAGTGAA... len=242 score=0.5,\n", - " TGAAAGTGAA... len=17 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " GGAAAATTGG... len=221 score=0.5,\n", - " TTTACTATAA... len=37802 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " TTTACTATAA... len=102 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " GGAGCCCACG... len=207 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " CTGGAGCAGC... len=147 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGTTCACGGA... len=153 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " TGAGGTCTGC... len=1416 score=0.5,\n", - " GTAGAAAAGC... len=84 score=0.5,\n", - " GTAGAAAAGC... len=84 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TGTCAGCCAT... len=169 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TACTGTGGGA... len=77 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " TGTGCTGAGG... len=174 score=0.5,\n", - " TGTGCTGAGG... len=174 score=0.5,\n", - " CATATGCAAT... len=616 score=0.5,\n", - " CATATGCAAT... len=131 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " GGGCTGGGCA... len=481 score=0.5,\n", - " GCCGGCCCCG... len=9176 score=0.5,\n", - " GCCGGCCCCG... len=140 score=0.5,\n", - " TGTAAGTACT... len=169 score=0.5,\n", - " GAGCCAGCAC... len=174 score=0.5,\n", - " GCGGACATGC... len=236 score=0.5,\n", - " CATATGCAAT... len=418 score=0.5,\n", - " ACAGGCGCCC... len=856 score=0.5,\n", - " ACAGGCGCCC... len=534 score=0.5,\n", - " GAGCCAGCAC... len=21 score=0.5,\n", - " TTAATCCCCT... len=1043 score=0.5,\n", - " TTAATCCCCT... len=1043 score=0.5,\n", - " TTAATCCCCT... len=1043 score=0.5,\n", - " TTGTTTGCTT... len=5466 score=0.5,\n", - " TTGTTTGCTT... len=5466 score=0.5,\n", - " TTTCTTCTGT... len=452 score=0.5,\n", - " AAAATCCCTG... len=628 score=0.5,\n", - " TGTGCAGCTT... len=65 score=0.5,\n", - " TTGTTTGCTT... len=76 score=0.5,\n", - " TTTACCAAGT... len=9833 score=0.5,\n", - " TTTACCAAGT... len=8600 score=0.5,\n", - " CGCCAGGCTG... len=173 score=0.5,\n", - " CGCCAGGCTG... len=111 score=0.5,\n", - " AT... len=2 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TGCGGTGAGA... len=235 score=0.5,\n", - " TGCGGTGAGA... len=235 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " TTTACCAAGT... len=1870 score=0.5,\n", - " CGGTAGTGCC... len=65 score=0.5,\n", - " CA... len=2 score=0.5,\n", - " GCCGCGGGTT... len=61 score=0.5,\n", - " TTTACCAAGT... len=1801 score=0.5,\n", - " GATTTTACCT... len=8590 score=0.5,\n", - " CGCCAGGCTG... len=173 score=0.5,\n", - " CGCCAGGCTG... len=111 score=0.5,\n", - " AT... len=2 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TGCGGTGAGA... len=175 score=0.5,\n", - " TGCGGTGAGA... len=175 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " GATTTTACCT... len=1860 score=0.5,\n", - " CGGTAGTGCC... len=65 score=0.5,\n", - " CA... len=2 score=0.5,\n", - " GCCGCGGGTT... len=61 score=0.5,\n", - " GATTTTACCT... len=1791 score=0.5,\n", - " GAAAGGTGAC... len=8395 score=0.5,\n", - " CGCCAGGCTG... len=65 score=0.5,\n", - " CGCCAGGCTG... len=65 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TGCGGTGAGA... len=175 score=0.5,\n", - " TGCGGTGAGA... len=175 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " CCCAGGACCT... len=803 score=0.5,\n", - " CGGTAGTGCC... len=65 score=0.5,\n", - " CA... len=2 score=0.5,\n", - " TTGACTAACC... len=278 score=0.5,\n", - " GAAAGGTGAC... len=310 score=0.5,\n", - " CCCAGGACCT... len=734 score=0.5,\n", - " TTGACTAACC... len=278 score=0.5,\n", - " GAAAGGTGAC... len=310 score=0.5,\n", - " TAAAGATGCC... len=7702 score=0.5,\n", - " CGCCAGGCTG... len=149 score=0.5,\n", - " CGCCAGGCTG... len=111 score=0.5,\n", - " AT... len=2 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TACGTGATCC... len=406 score=0.5,\n", - " TGCGGTGAGA... len=175 score=0.5,\n", - " TGCGGTGAGA... len=175 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " TTGCTGCTGC... len=135 score=0.5,\n", - " TAAAGATGCC... len=990 score=0.5,\n", - " CGGTAGTGCC... len=59 score=0.5,\n", - " CA... len=2 score=0.5,\n", - " GCCGCGGGTT... len=37 score=0.5,\n", - " TAAAGATGCC... len=927 score=0.5,\n", - " AGAACAGGTG... len=6017 score=0.5,\n", - " CGCCAGGCTG... len=144 score=0.5,\n", - " CGCCAGGCTG... len=111 score=0.5,\n", - " AT... len=2 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGATCCCCGT... len=402 score=0.5,\n", - " TGATCCCCGT... len=402 score=0.5,\n", - " TGCGGTGAGA... len=175 score=0.5,\n", - " GTCCTCTCCG... len=30 score=0.5,\n", - " CA... len=2 score=0.5,\n", - " AGAACAGGTG... len=101 score=0.5,\n", - " GCCGCGGGTT... len=32 score=0.5,\n", - " TGCGGTGAGA... len=141 score=0.5,\n", - " AGAACAGGTG... len=101 score=0.5,\n", - " AGGCAGGCGA... len=5267 score=0.5,\n", - " TGAATGGCTG... len=200 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " AGGCAGGCGA... len=328 score=0.5,\n", - " AGGCAGGCGA... len=89 score=0.5,\n", - " AT... len=2 score=0.5,\n", - " TGAATGGCTG... len=200 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " CAGCGCCGCG... len=238 score=0.5,\n", - " CTGCTGCTCA... len=1421 score=0.5,\n", - " AGCCCCCCGG... len=326 score=0.5,\n", - " CTGCTGCTCA... len=275 score=0.5,\n", - " CGTGTGGTGA... len=2232 score=0.5,\n", - " TTAGCGTGAG... len=206 score=0.5,\n", - " AGGCCAGAGG... len=74 score=0.5,\n", - " TA... len=2 score=0.5,\n", - " CGGGCCAGCT... len=190 score=0.5,\n", - " CGTGTGGTGA... len=254 score=0.5,\n", - " TTAGCGTGAG... len=128 score=0.5,\n", - " CGGGCCAGCT... len=190 score=0.5,\n", - " CGTGTGGTGA... len=254 score=0.5,\n", - " TGCAGTGTCA... len=3759 score=0.5,\n", - " CGCCAGGCTG... len=123 score=0.5,\n", - " CGCCAGGCTG... len=111 score=0.5,\n", - " AT... len=2 score=0.5,\n", - " TTAGCGTGAG... len=238 score=0.5,\n", - " AGGCCAGAGG... len=106 score=0.5,\n", - " TA... len=2 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGCAGTGTCA... len=103 score=0.5,\n", - " GCCGCGGGTT... len=11 score=0.5,\n", - " TTAGCGTGAG... len=128 score=0.5,\n", - " TGCAAGTGTG... len=80 score=0.5,\n", - " TGCAGTGTCA... len=103 score=0.5,\n", - " TTGCCCTCTT... len=2406 score=0.5,\n", - " TTGCCCTCTT... len=2406 score=0.5,\n", - " TTGCCCTCTT... len=2406 score=0.5,\n", - " GAAGCGGAGG... len=213 score=0.5,\n", - " GAAGCGGAGG... len=213 score=0.5,\n", - " TGTTCGCCGA... len=1542 score=0.5,\n", - " TGTTCGCCGA... len=1542 score=0.5,\n", - " TGTTCGCCGA... len=1542 score=0.5,\n", - " AAATCACGTT... len=101817 score=0.5,\n", - " AAATCACGTT... len=6869 score=0.5,\n", - " TTCCTCAATG... len=129 score=0.5,\n", - " AAATCACGTT... len=1161 score=0.5,\n", - " GTCTAAAATT... len=10903 score=0.5,\n", - " TTGGTTGTGT... len=149 score=0.5,\n", - " TCGAGGCAGC... len=901 score=0.5,\n", - " TAAGTCGCAG... len=84 score=0.5,\n", - " GTCTAAAATT... len=1112 score=0.5,\n", - " CATTGCAAAA... len=101537 score=0.5,\n", - " CCCATCCCCT... len=336 score=0.5,\n", - " TTGGTTGTGT... len=134 score=0.5,\n", - " TCGAGGCAGC... len=901 score=0.5,\n", - " CATTGCAAAA... len=881 score=0.5,\n", - " ACACATATAT... len=10292 score=0.5,\n", - " TTGGTTGTGT... len=149 score=0.5,\n", - " TCGAGGCAGC... len=901 score=0.5,\n", - " ACACATATAT... len=501 score=0.5,\n", - " CCCAATTTTG... len=456 score=0.5,\n", - " CCCAATTTTG... len=456 score=0.5,\n", - " GGAAAAATAT... len=34487 score=0.5,\n", - " TTCAAGTTTG... len=157 score=0.5,\n", - " TTTTCCTGGA... len=104 score=0.5,\n", - " TTGGTTGTGT... len=149 score=0.5,\n", - " GGAAAAATAT... len=5189 score=0.5,\n", - " AGGGCTGGTG... len=1696 score=0.5,\n", - " AGGGCTGGTG... len=1696 score=0.5,\n", - " AGGGCTGGTG... len=1696 score=0.5,\n", - " CTCCTCCCGG... len=81894 score=0.5,\n", - " CTCCTCCCGG... len=81894 score=0.5,\n", - " CTCCTCCCGG... len=1416 score=0.5,\n", - " TGGAGGCGGC... len=968 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " TCTCCTCTGA... len=125 score=0.5,\n", - " TCTCCTCTGA... len=125 score=0.5,\n", - " GCCTGGGCTG... len=115 score=0.5,\n", - " GCCTGGGCTG... len=115 score=0.5,\n", - " TTCTACTCCT... len=262 score=0.5,\n", - " TTCTACTCCT... len=262 score=0.5,\n", - " CACCTCCTCC... len=292 score=0.5,\n", - " CACCTCCTCC... len=292 score=0.5,\n", - " AGCTGGAGTT... len=230 score=0.5,\n", - " AGCTGGAGTT... len=230 score=0.5,\n", - " TCGAAGACCT... len=3636 score=0.5,\n", - " TCGAAGACCT... len=185 score=0.5,\n", - " AG... len=2 score=0.5,\n", - " CTCCTCCCGG... len=447 score=0.5,\n", - " TTCCGTGCCT... len=3447 score=0.5,\n", - " GCGGCTGTGC... len=70559 score=0.5,\n", - " GCGGCTGTGC... len=190 score=0.5,\n", - " TCTCCTCTGA... len=60 score=0.5,\n", - " GGGGGGCGCG... len=55380 score=0.5,\n", - " GGGGGGCGCG... len=75 score=0.5,\n", - " TCTCCTCTGA... len=125 score=0.5,\n", - " GCCTGGGCTG... len=91 score=0.5,\n", - " TGTCTGGCCT... len=722 score=0.5,\n", - " TGTCTGGCCT... len=462 score=0.5,\n", - " CACCTCCTCC... len=75 score=0.5,\n", - " CATGAATTCA... len=336 score=0.5,\n", - " CATGAATTCA... len=336 score=0.5,\n", - " CATGAATTCA... len=336 score=0.5,\n", - " GCAAGTTCAT... len=1031 score=0.5,\n", - " GCAAGTTCAT... len=1031 score=0.5,\n", - " GCAAGTTCAT... len=216 score=0.5,\n", - " GTGAAAGTTT... len=197 score=0.5,\n", - " GAAGACTCCT... len=423 score=0.5,\n", - " GAAGACTCCT... len=423 score=0.5,\n", - " GAAGACTCCT... len=423 score=0.5,\n", - " TTTGACCTCC... len=4477 score=0.5,\n", - " TTTGACCTCC... len=4353 score=0.5,\n", - " GCTTTCCCGC... len=37 score=0.5,\n", - " TCCCGAGAAG... len=638 score=0.5,\n", - " TTCAATACTG... len=53 score=0.5,\n", - " TCCTGCACCC... len=143 score=0.5,\n", - " TCCTCATCGT... len=175 score=0.5,\n", - " TTTGACCTCC... len=594 score=0.5,\n", - " CGCCATCCTC... len=4339 score=0.5,\n", - " GCTTTCCCGC... len=37 score=0.5,\n", - " TCCCGAGAAG... len=638 score=0.5,\n", - " TCCTGCACCC... len=143 score=0.5,\n", - " CGCCATCCTC... len=580 score=0.5,\n", - " TTGCTCACTT... len=1880 score=0.5,\n", - " GCTTTCCCGC... len=161 score=0.5,\n", - " TCCCGAGAAG... len=638 score=0.5,\n", - " TTGCTCACTT... len=184 score=0.5,\n", - " TTGCTCACTT... len=1880 score=0.5,\n", - " TCCCGAGAAG... len=1067 score=0.5,\n", - " TTGCTCACTT... len=184 score=0.5,\n", - " ATCTTGTTGA... len=371 score=0.5,\n", - " ATCTTGTTGA... len=371 score=0.5,\n", - " ATCTTGTTGA... len=371 score=0.5,\n", - " TCCCCCACAC... len=158470 score=0.5,\n", - " TCCCCCACAC... len=64284 score=0.5,\n", - " TCCCCCACAC... len=292 score=0.5,\n", - " CAAGCTCTAC... len=47 score=0.5,\n", - " TTTCAGAGCC... len=103 score=0.5,\n", - " TTGCCACGGC... len=359 score=0.5,\n", - " GTCAGGCCTC... len=155808 score=0.5,\n", - " GTCAGGCCTC... len=52 score=0.5,\n", - " TGGCGTCCTC... len=35 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " CAAGCTCTAC... len=47 score=0.5,\n", - " CAAGCTCTAC... len=47 score=0.5,\n", - " TTGCCACGGC... len=84 score=0.5,\n", - " TTGCCACGGC... len=84 score=0.5,\n", - " GCTGACAGAT... len=128 score=0.5,\n", - " GCTGACAGAT... len=128 score=0.5,\n", - " TCCCGCAGGC... len=85 score=0.5,\n", - " TCCCGCAGGC... len=85 score=0.5,\n", - " AATACCTGCT... len=102 score=0.5,\n", - " AATACCTGCT... len=102 score=0.5,\n", - " GACTCAGTTA... len=97 score=0.5,\n", - " GACTCAGTTA... len=97 score=0.5,\n", - " CCACCACATC... len=91 score=0.5,\n", - " CCACCACATC... len=91 score=0.5,\n", - " AGGCAGTTCC... len=1227 score=0.5,\n", - " AGGCAGTTCC... len=453 score=0.5,\n", - " AG... len=2 score=0.5,\n", - " GTCAGGCCTC... len=16 score=0.5,\n", - " GCTGCGCCTG... len=770 score=0.5,\n", - " AGGCAGAGCA... len=148304 score=0.5,\n", - " AGGCAGAGCA... len=20 score=0.5,\n", - " AGGCAGAGCA... len=20 score=0.5,\n", - " CAAGCTCTAC... len=47 score=0.5,\n", - " CAAGCTCTAC... len=47 score=0.5,\n", - " TTGCCACGGC... len=84 score=0.5,\n", - " TTGCCACGGC... len=84 score=0.5,\n", - " GCTGACAGAT... len=128 score=0.5,\n", - " GCTGACAGAT... len=128 score=0.5,\n", - " TCCCGCAGGC... len=85 score=0.5,\n", - " TCCCGCAGGC... len=85 score=0.5,\n", - " AATACCTGCT... len=267 score=0.5,\n", - " AATACCTGCT... len=110 score=0.5,\n", - " AA... len=2 score=0.5,\n", - " GACTCCATCA... len=153 score=0.5,\n", - " ATGGGTGCGC... len=401 score=0.5,\n", - " ATGGGTGCGC... len=172 score=0.5,\n", - " TTGCCACGGC... len=76 score=0.5,\n", - " CATCCAGATG... len=22535 score=0.5,\n", - " CATCCAGATG... len=22528 score=0.5,\n", - " CATCCAGATG... len=148 score=0.5,\n", - " ACAGTGCCTG... len=957 score=0.5,\n", - " AGGGAGGCCC... len=12204 score=0.5,\n", - " AGGGAGGCCC... len=125 score=0.5,\n", - " ATAGTGCACA... len=122 score=0.5,\n", - " TCTTGGCTCC... len=297 score=0.5,\n", - " TTTGGAGTAA... len=366 score=0.5,\n", - " TTGCCAAAAG... len=11873 score=0.5,\n", - " TTGCCAAAAG... len=81 score=0.5,\n", - " ATAGTGCACA... len=122 score=0.5,\n", - " TCTTGGCTCC... len=297 score=0.5,\n", - " AAATAATCAC... len=95 score=0.5,\n", - " AGCTTTGGAG... len=82 score=0.5,\n", - " CCAACAGCGA... len=22503 score=0.5,\n", - " CCAACAGCGA... len=116 score=0.5,\n", - " ATAGTGCACA... len=122 score=0.5,\n", - " ACAGTGCCTG... len=964 score=0.5,\n", - " TGGGTGTCTG... len=22520 score=0.5,\n", - " TGGGTGTCTG... len=140 score=0.5,\n", - " ATAGTGCACA... len=122 score=0.5,\n", - " ACAGTGCCTG... len=138 score=0.5,\n", - " CCTCGGGGGA... len=309 score=0.5,\n", - " AGGGAGGCCC... len=22505 score=0.5,\n", - " AGGGAGGCCC... len=125 score=0.5,\n", - " TCAATCAAAG... len=128 score=0.5,\n", - " ACAGTGCCTG... len=957 score=0.5,\n", - " ACAGCGATGG... len=13578 score=0.5,\n", - " ACAGCGATGG... len=113 score=0.5,\n", - " ATAGTGCACA... len=122 score=0.5,\n", - " AAATAATCAC... len=95 score=0.5,\n", - " AATTGGCTCA... len=1197 score=0.5,\n", - " CCACAAGGGA... len=22517 score=0.5,\n", - " CCACAAGGGA... len=130 score=0.5,\n", - " ACAGTGCCTG... len=964 score=0.5,\n", - " GGGAGAGGAG... len=12662 score=0.5,\n", - " GGGAGAGGAG... len=12662 score=0.5,\n", - " GGGAGAGGAG... len=322 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " TTTATCCTGA... len=100 score=0.5,\n", - " GGTCTTGAAT... len=695 score=0.5,\n", - " TTACTGGAGT... len=12636 score=0.5,\n", - " TTACTGGAGT... len=581 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " TCAGATAAAT... len=427 score=0.5,\n", - " TTTATCCTGA... len=100 score=0.5,\n", - " GGTCTTGAAT... len=693 score=0.5,\n", - " GCAGTGTGTT... len=12645 score=0.5,\n", - " GCAGTGTGTT... len=307 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " CCTGAGACCG... len=133 score=0.5,\n", - " TTTATCCTGA... len=100 score=0.5,\n", - " GGTCTTGAAT... len=693 score=0.5,\n", - " GCAGTGTGTT... len=12645 score=0.5,\n", - " GCAGTGTGTT... len=307 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " TCAGATAAAT... len=427 score=0.5,\n", - " TTTATCCTGA... len=100 score=0.5,\n", - " GGTCTTGAAT... len=693 score=0.5,\n", - " GTGTCTCCAC... len=8378 score=0.5,\n", - " GTGTCTCCAC... len=237 score=0.5,\n", - " GCATTAGTTC... len=311 score=0.5,\n", - " TTTATCCTGA... len=100 score=0.5,\n", - " GGTCTTGAAT... len=695 score=0.5,\n", - " GCATTTTTCT... len=4800 score=0.5,\n", - " GCATTTTTCT... len=551 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " GCCTTCTTCC... len=159 score=0.5,\n", - " CCATTATGCC... len=5967 score=0.5,\n", - " CCATTATGCC... len=210 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " ACCCCCCATT... len=285 score=0.5,\n", - " TACACGGAGC... len=9134 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " GCATTAGTTC... len=311 score=0.5,\n", - " GGTCTTGAAT... len=693 score=0.5,\n", - " AGGCATTTTT... len=6028 score=0.5,\n", - " AGGCATTTTT... len=270 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " TTCTCTCCAT... len=309 score=0.5,\n", - " CCAGCGCAAT... len=4785 score=0.5,\n", - " CCAGCGCAAT... len=253 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " GCCTTCTTCC... len=159 score=0.5,\n", - " CCATTATGCC... len=12548 score=0.5,\n", - " CCATTATGCC... len=210 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " GCATTAGTTC... len=311 score=0.5,\n", - " TTTATCCTGA... len=100 score=0.5,\n", - " GGTCTTGAAT... len=693 score=0.5,\n", - " ACCAGCGCAA... len=12592 score=0.5,\n", - " ACCAGCGCAA... len=537 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " TTTATCCTGA... len=100 score=0.5,\n", - " GGTCTTGAAT... len=693 score=0.5,\n", - " CTCTTAACCA... len=6017 score=0.5,\n", - " CTCTTAACCA... len=543 score=0.5,\n", - " TACACGGAGC... len=34 score=0.5,\n", - " TGTCTCCACA... len=236 score=0.5,\n", - " TTCTCTCCAT... len=308 score=0.5,\n", - " TAATAATCAC... len=162 score=0.5,\n", - " TAATAATCAC... len=162 score=0.5,\n", - " TAATAATCAC... len=162 score=0.5,\n", - " TGCCCCAACT... len=206 score=0.5,\n", - " TGCCCCAACT... len=206 score=0.5,\n", - " TGCCCCAACT... len=206 score=0.5,\n", - " TGGCACATGC... len=681 score=0.5,\n", - " TGGCACATGC... len=681 score=0.5,\n", - " TGGCACATGC... len=681 score=0.5,\n", - " TTATGTCAGG... len=4440 score=0.5,\n", - " TTATGTCAGG... len=4440 score=0.5,\n", - " ATCAAACACC... len=166 score=0.5,\n", - " TATCTTCATC... len=47 score=0.5,\n", - " TGTAATCCCA... len=122 score=0.5,\n", - " TTATGTCAGG... len=110 score=0.5,\n", - " CCCTTTGCTG... len=79552 score=0.5,\n", - " CCCTTTGCTG... len=53824 score=0.5,\n", - " CCCTTTGCTG... len=57 score=0.5,\n", - " TGTGTGATGC... len=291 score=0.5,\n", - " TGATGGCTCC... len=114 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " CTCCATCGAC... len=70 score=0.5,\n", - " CTCCATCGAC... len=70 score=0.5,\n", - " CCCTTTGCTG... len=57 score=0.5,\n", - " TGTGTGATGC... len=176 score=0.5,\n", - " ACGGGCGGGC... len=38067 score=0.5,\n", - " ACGGGCGGGC... len=203 score=0.5,\n", - " TGGAAGAGCC... len=42 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " CTCCATCGAC... len=244 score=0.5,\n", - " CTCCATCGAC... len=244 score=0.5,\n", - " GGCTGAAGCA... len=128 score=0.5,\n", - " GGCTGAAGCA... len=128 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " TGCCCTGAAC... len=107 score=0.5,\n", - " TGCCCTGAAC... len=107 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " TCAAGCAGGC... len=798 score=0.5,\n", - " TCAAGCAGGC... len=798 score=0.5,\n", - " TAGGAACTGA... len=1909 score=0.5,\n", - " TAGGAAC... len=7 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " ACGGGCGGGC... len=160 score=0.5,\n", - " AGCGGCGAGT... len=1898 score=0.5,\n", - " CGGCTGCGTC... len=29210 score=0.5,\n", - " CGGCTGCGTC... len=397 score=0.5,\n", - " TGTCTGGTCC... len=123 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " CTCCATCGAC... len=244 score=0.5,\n", - " CTCCATCGAC... len=244 score=0.5,\n", - " GGCTGAAGCA... len=128 score=0.5,\n", - " GGCTGAAGCA... len=128 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " TGCCCTGAAC... len=107 score=0.5,\n", - " TGCCCTGAAC... len=107 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " TCAAGCAGGC... len=297 score=0.5,\n", - " TCAAGCAGGC... len=297 score=0.5,\n", - " CACCCGCCCC... len=1603 score=0.5,\n", - " CACCCGCCCC... len=1288 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " CGGCTGCGTC... len=273 score=0.5,\n", - " CGTCAGTGGT... len=311 score=0.5,\n", - " ACAGGGAACG... len=26440 score=0.5,\n", - " ACAGGGAACG... len=888 score=0.5,\n", - " GGCTGAAGCA... len=128 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " TGCCCTGAAC... len=107 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " TCAAGCAGGC... len=3418 score=0.5,\n", - " GCGCGCACCT... len=25388 score=0.5,\n", - " GCGCGCACCT... len=90 score=0.5,\n", - " GCGCGCACCT... len=90 score=0.5,\n", - " GGCTGAAGCA... len=128 score=0.5,\n", - " GGCTGAAGCA... len=128 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " TCAAGCAGGC... len=297 score=0.5,\n", - " TCAAGCAGGC... len=297 score=0.5,\n", - " CACCCGCCCC... len=1354 score=0.5,\n", - " CACCCGCCCC... len=1288 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " CGTCAGTGGT... len=62 score=0.5,\n", - " TGGGGGAACC... len=7746 score=0.5,\n", - " TGGGGGAACC... len=865 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " CTACAGACAC... len=5887 score=0.5,\n", - " GTGGGGGCCA... len=6881 score=0.5,\n", - " GTGGGGGCCA... len=181 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " TCAAGCAGGC... len=297 score=0.5,\n", - " TAGGAACTGA... len=26 score=0.5,\n", - " CACCCGCCCC... len=1606 score=0.5,\n", - " TCCTTTGCTC... len=29243 score=0.5,\n", - " TCCTTTGCTC... len=423 score=0.5,\n", - " TGTCTGGTCC... len=123 score=0.5,\n", - " TG... len=2 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " GGAGCGGTGC... len=146 score=0.5,\n", - " CTCCATCGAC... len=243 score=0.5,\n", - " CTCCATCGAC... len=243 score=0.5,\n", - " TGGCTGAAGC... len=129 score=0.5,\n", - " TGGCTGAAGC... len=129 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " AAGCGGACAC... len=170 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " TGGCGGGTGT... len=93 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " CTTCACCAAC... len=203 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " GGACTGCTGG... len=120 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " TACCCAGTGA... len=171 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " GGAAGAAGCT... len=107 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " CATCCACCAA... len=143 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " GCAAGGCTGA... len=92 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " AGAAGGGCAG... len=82 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GCGACCCGGC... len=97 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " GGCGTCCAGC... len=182 score=0.5,\n", - " TGCCCTGAAC... len=107 score=0.5,\n", - " TGCCCTGAAC... len=107 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " CGTGTTCAAC... len=124 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " TCATCGACCC... len=84 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " GTTCAACCCC... len=146 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " CTACAGACAC... len=79 score=0.5,\n", - " TCAAGCAGGC... len=297 score=0.5,\n", - " TCAAGCAGGC... len=297 score=0.5,\n", - " CACCCGCCCC... len=1610 score=0.5,\n", - " CACCCGCCCC... len=1288 score=0.5,\n", - " GA... len=2 score=0.5,\n", - " TCCTTTGCTC... len=299 score=0.5,\n", - " CGTCAGTGGT... len=318 score=0.5,\n", - " TTTACCTCTG... len=9344 score=0.5,\n", - " TTTACCTCTG... len=9344 score=0.5,\n", - " CTCTGTGTCC... len=191 score=0.5,\n", - " TGCTTCTGAA... len=135 score=0.5,\n", - " TTTACCTCTG... len=135 score=0.5,\n", - " CACAGAAGTC... len=76638 score=0.5,\n", - " CACAGAAGTC... len=76638 score=0.5,\n", - " CACAGAAGTC... len=177 score=0.5,\n", - " CAATACTGAA... len=842 score=0.5]" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "cdna_gen.prime_sites" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "871cd34d-3291-446e-8173-7b444d768865", - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.9.13" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/.ipynb_checkpoints/copy_numbers-checkpoint.csv b/.ipynb_checkpoints/copy_numbers-checkpoint.csv deleted file mode 100644 index e69de29..0000000 -- GitLab