LOCUS HS2ST1-pGEn2 6291 bp DNA circular 29-SEP-2016 FEATURES Location/Qualifiers CDS 129..1108 /dnas_title="AmpR" /label=AmpR /vntifkey="4" rep_origin 1137..1804 /dnas_title="Col E1 origin" /label=Col E1 origin /vntifkey="33" misc_feature 1998..2127 /note="5'ITR" misc_feature 2208..2790 /note="CMV Promoter" misc_feature 2828..2960 /note="Artificial Intron" misc_recomb complement(3839..3867) /label=attB1 /note="attB1 site" /note="recognized as attB1" misc_feature 4919..5460 /note="WPRE" misc_recomb 4881..4903 /label=attB2 /note="attB2 site" /note="recognized as attB2" misc_feature complement(5467..5681) /note="BGH pA" misc_feature complement(5769..5898) /note="3'-ITR" misc_feature 2982..3056 /note="TCM signal sequence" misc_feature 3060..3083 /note="His tag" misc_feature 3084..3134 /note="AviTag" misc_feature 3135..3830 /note="Superfolder GFP" misc_feature 2976..2981 /note="Kozak seq" CDS 3868..4880 /label=HS2ST1 misc_feature 3870..3890 /note="TEV site" misc_feature 3891..4877 /note="OPTIMIZED HS2ST1 coding region" vector join(4889..6291,1..3857) /source="pGEn2-DEST" /type="Destination Vector" clone 3858..4888 /source="HS2ST1-pDONR" /type="Entry Clone" source 1..6291 /dnas_title="HS2ST1-pGEn2" ORIGIN 1 GTGGCACTTT TCGGGGAAAT GTGCGCGGAA CCCCTATTTG TTTATTTTTC TAAATACATT 61 CAAATATGTA TCCGCTCATG AGACAATAAC CCTGATAAAT GCTTCAATAA TATTGAAAAA 121 GGAAGAGTAT GAGTATTCAA CATTTCCGTG TCGCCCTTAT TCCCTTTTTT GCGGCATTTT 181 GCCTTCCTGT TTTTGCTCAC CCAGAAACGC TGGTGAAAGT AAAAGATGCT GAAGATCAGT 241 TGGGTGCACG AGTGGGTTAC ATCGAACTGG ATCTCAACAG CGGTAAGATC CTTGAGAGTT 301 TTCGCCCCGA AGAACGTTTT CCAATGATGA GCACTTTTAA AGTTCTGCTA TGTGGCGCGG 361 TATTATCCCG TATTGACGCC GGGCAAGAGC AACTCGGTCG CCGCATACAC TATTCTCAGA 421 ATGACTTGGT TGAGTACTCA CCAGTCACAG AAAAGCATCT TACGGATGGC ATGACAGTAA 481 GAGAATTATG CAGTGCTGCC ATAACCATGA GTGATAACAC TGCGGCCAAC TTACTTCTGA 541 CAACGATCGG AGGACCGAAG GAGCTAACCG CTTTTTTGCA CAACATGGGG GATCATGTAA 601 CTCGCCTTGA TCGTTGGGAA CCGGAGCTGA ATGAAGCCAT ACCAAACGAC GAGCGTGACA 661 CCACGATGCC TGTAGCAATG GCAACAACGT TGCGCAAACT ATTAACTGGC GAACTACTTA 721 CTCTAGCTTC CCGGCAACAA TTAATAGACT GGATGGAGGC GGATAAAGTT GCAGGACCAC 781 TTCTGCGCTC GGCCCTTCCG GCTGGCTGGT TTATTGCTGA TAAATCTGGA GCCGGTGAGC 841 GTGGTTCTCG CGGTATCATT GCAGCACTGG GGCCAGATGG TAAGCCCTCC CGTATCGTAG 901 TTATCTACAC GACGGGGAGT CAGGCAACTA TGGATGAACG AAATAGACAG ATCGCTGAGA 961 TAGGTGCCTC ACTGATTAAG CATTGGTAAC TGTCAGACCA AGTTTACTCA TATATACTTT 1021 AGATTGATTT AAAACTTCAT TTTTAATTTA AAAGGATCTA GGTGAAGATC CTTTTTGATA 1081 ATCTCATGAC CAAAATCCCT TAACGTGAGT TTTCGTTCCA CTGAGCGTCA GACCCCGTAG 1141 AAAAGATCAA AGGATCTTCT TGAGATCCTT TTTTTCTGCG CGTAATCTGC TGCTTGCAAA 1201 CAAAAAAACC ACCGCTACCA GCGGTGGTTT GTTTGCCGGA TCAAGAGCTA CCAACTCTTT 1261 TTCCGAAGGT AACTGGCTTC AGCAGAGCGC AGATACCAAA TACTGTTCTT CTAGTGTAGC 1321 CGTAGTTAGG CCACCACTTC AAGAACTCTG TAGCACCGCC TACATACCTC GCTCTGCTAA 1381 TCCTGTTACC AGTGGCTGCT GCCAGTGGCG ATAAGTCGTG TCTTACCGGG TTGGACTCAA 1441 GACGATAGTT ACCGGATAAG GCGCAGCGGT CGGGCTGAAC GGGGGGTTCG TGCACACAGC 1501 CCAGCTTGGA GCGAACGACC TACACCGAAC TGAGATACCT ACAGCGTGAG CTATGAGAAA 1561 GCGCCACGCT TCCCGAAGGG AGAAAGGCGG ACAGGTATCC GGTAAGCGGC AGGGTCGGAA 1621 CAGGAGAGCG CACGAGGGAG CTTCCAGGGG GAAACGCCTG GTATCTTTAT AGTCCTGTCG 1681 GGTTTCGCCA CCTCTGACTT GAGCGTCGAT TTTTGTGATG CTCGTCAGGG GGGCGGAGCC 1741 TATGGAAAAA CGCCAGCAAC GCGGCCTTTT TACGGTTCCT GGCCTTTTGC TGGCCTTTTG 1801 CTCATTAGGC ACCCCAGGCT TTACCCGAAC GACCGAGCGC AGCGAGTCAG TGAGCGAGGA 1861 AGCGGAGAGC GCCCAATACG CAAGGAAACA GCTATGACCA TGTTAATGCA GCTGGCACGA 1921 CAGGTTTCCC GACTGGAAAG CGGGCAGTGA GCGGAAGGCC CATGAGGCCA GTTAATTAAG 1981 AGGTACCTTA ATTAAGGCTG CGCGCTCGCT CGCTCACTGA GGCCGCCCGG GCAAAGCCCG 2041 GGCGTCGGGC GACCTTTGGT CGCCCGGCCT CAGTGAGCGA GCGAGCGCGC AGAGAGGGAG 2101 TGGCCAACTC CATCACTAGG GGTTCCTTGT AGTTAATGAT TAACCCGCCA TGCTACTTAT 2161 CTACGTAGCC ATGCTCTAGG AAGATCGCAA TTCGCCCTTA AGCTAGCTAG TTATTAATAG 2221 TAATCAATTA CGGGGTCATT AGTTCATAGC CCATATATGG AGTTCCGCGT TACATAACTT 2281 ACGGTAAATG GCCCGCCTGG CTGACCGCCC AACGACCCCC GCCCATTGAC GTCAATAATG 2341 ACGTATGTTC CCATAGTAAC GCCAATAGGG ACTTTCCATT GACGTCAATG GGTGGAGTAT 2401 TTACGGTAAA CTGCCCACTT GGCAGTACAT CAAGTGTATC ATATGCCAAG TACGCCCCCT 2461 ATTGACGTCA ATGACGGTAA ATGGCCCGCC TGGCATTATG CCCAGTACAT GACCTTATGG 2521 GACTTTCCTA CTTGGCAGTA CATCTACGTA TTAGTCATCG CTATTACCAT GGTGATGCGG 2581 TTTTGGCAGT ACATCAATGG GCGTGGATAG CGGTTTGACT CACGGGGATT TCCAAGTCTC 2641 CACCCCATTG ACGTCAATGG GAGTTTGTTT TGGCACCAAA ATCAACGGGA CTTTCCAAAA 2701 TGTCGTAACA ACTCCGCCCC ATTGACGCAA ATGGGCGGTA GGCGTGTACG GTGGGAGGTC 2761 TATATAAGCA GAGCTGGTTT AGTGAACCGT CAGATCCTGC AGAAGTTGGT CGTGAGGCAC 2821 TGGGCAGGTA AGTATCAAGG TTACAAGACA GGTTTAAGGA GACCAATAGA AACTGGGCTT 2881 GTCGAGACAG AGAAGACTCT TGCGTTTCTG ATAGGCACCT ATTGGTCTTA CTGACATCCA 2941 CTTTGCCTTT CTCTCCACAG GTGTCCAgcg gccgcGCCAC cATGAGACTG CTGACCGCCC 3001 TGTTCGCCTA CTTCATCGTG GCCCTGATCC TGGCCTTCAG CGTGTCCGCC AAGAGCATGC 3061 ACCACCACCA TCACCATCAT CACATGAGCG GCCTGAACGA CATCTTCGAG GCCCAGAAAA 3121 TCGAGTGGCA CGAGATGAGC AAGGGCGAGG AACTGTTCAC CGGCGTGGTG CCCATCCTGG 3181 TGGAACTGGA CGGCGACGTG AACGGCCACA AGTTCTCTGT GCGGGGCGAG GGCGAGGGGG 3241 ACGCCACAAA TGGCAAGCTG ACCCTGAAGT TCATCTGCAC CACCGGAAAG CTGCCCGTGC 3301 CCTGGCCTAC CCTGGTCACA ACCCTGACCT ACGGCGTGCA GTGCTTCAGC AGATACCCCG 3361 ACCACATGAA GCGGCACGAT TTCTTCAAGA GCGCCATGCC CGAGGGCTAC GTGCAAGAAC 3421 GGACCATCAG CTTCAAGGAC GACGGCACCT ACAAGACCAG AGCCGAAGTG AAGTTCGAGG 3481 GCGACACCCT GGTCAACCGG ATCGAGCTGA AGGGCATCGA CTTCAAAGAG GACGGCAACA 3541 TCCTGGGCCA CAAGCTCGAG TACAACTTCA ACAGCCACAA CGTGTACATC ACCGCCGACA 3601 AGCAGAAGAA CGGCATCAAG GCCAACTTCA AGATCCGGCA CAACGTGGAA GATGGCAGCG 3661 TGCAGCTGGC CGACCACTAC CAGCAGAACA CCCCCATCGG CGACGGCCCC GTGCTGCTGC 3721 CCGACAATCA CTACCTGAGC ACCCAGAGCG TGCTGAGCAA GGACCCCAAC GAGAAGCGGG 3781 ACCACATGGT GCTGCTGGAA TTTGTGACCG CCGCTGGCAT CACCCACGGC GAATTCgcAT 3841 CAACAAGTTT GTACAAAAAA GCAGGCTCTG AGAACCTGTA TTTTCAAGGC AACCAGATCC 3901 AGAAGCTGGA AGAGAGCAGA AGCAAGCTGG AACGGGCCAT TGCCCGGCAC GAAGTGCGGG 3961 AAATCGAGCA GAGACACACC ATGGACGGCC CCAGACAGGA CGCCACCCTG GACGAGGAAG 4021 AGGACATGGT CATCATCTAC AACCGGGTGC CCAAGACCGC CAGCACCAGC TTCACCAATA 4081 TCGCCTACGA CCTGTGCGCC AAGAACAAGT ACCACGTGCT GCACATCAAC ACCACAAAGA 4141 ACAACCCCGT GATGAGCCTG CAGGACCAGG TGCGCTTCGT GAAGAACATC ACCAGCTGGA 4201 AAGAGATGAA GCCCGGCTTC TACCACGGCC ACGTGTCCTA CCTGGACTTC GCCAAGTTCG 4261 GCGTGAAGAA GAAGCCCATC TACATCAACG TGATCCGGGA CCCCATCGAG CGGCTGGTGT 4321 CCTACTACTA CTTCCTGAGA TTCGGCGACG ACTACAGACC CGGCCTGCGG AGAAGAAAGC 4381 AGGGCGACAA GAAAACCTTC GACGAGTGCG TGGCCGAGGG CGGCTCTGAT TGTGCCCCTG 4441 AGAAACTGTG GCTGCAGATC CCATTCTTCT GCGGCCACAG CAGCGAGTGC TGGAACGTGG 4501 GAAGCAGATG GGCCATGGAC CAGGCCAAGT ACAACCTGAT CAACGAGTAC TTCCTCGTGG 4561 GCGTGACCGA GGAACTGGAA GATTTCATCA TGCTGCTGGA AGCCGCCCTG CCCCGGTTCT 4621 TTAGAGGCGC CACAGAGCTG TACCGGACCG GCAAGAAGTC CCACCTGAGA AAGACCACCG 4681 AGAAGAAGCT GCCCACCAAG CAGACAATCG CCAAGCTGCA GCAGAGCGAC ATCTGGAAGA 4741 TGGAAAACGA GTTCTACGAG TTCGCCCTGG AACAGTTTCA GTTCATCCGG GCCCACGCCG 4801 TGCGCGAGAA AGACGGCGAT CTGTATATCC TGGCCCAGAA CTTCTTCTAC GAGAAGATCT 4861 ACCCCAAGAG CAACTAGGAC CCAGCTTTCT TGTACAAAGT GGTTGATAGC TTGGATCCAA 4921 TCAACCTCTG GATTACAAAA TTTGTGAAAG ATTGACTGGT ATTCTTAACT ATGTTGCTCC 4981 TTTTACGCTA TGTGGATACG CTGCTTTAAT GCCTTTGTAT CATGCTATTG CTTCCCGTAT 5041 GGCTTTCATT TTCTCCTCCT TGTATAAATC CTGGTTGCTG TCTCTTTATG AGGAGTTGTG 5101 GCCCGTTGTC AGGCAACGTG GCGTGGTGTG CACTGTGTTT GCTGACGCAA CCCCCACTGG 5161 TTGGGGCATT GCCACCACCT GTCAGCTCCT TTCCGGGACT TTCGCTTTCC CCCTCCCTAT 5221 TGCCACGGCG GAACTCATCG CCGCCTGCCT TGCCCGCTGC TGGACAGGGG CTCGGCTGTT 5281 GGGCACTGAC AATTCCGTGG TGTTGTCGGG GAAGCTGACG TCCTTTCCAT GGCTGCTCGC 5341 CTGTGTTGCC ACCTGGATTC TGCGCGGGAC GTCCTTCTGC TACGTCCCTT CGGCCCTCAA 5401 TCCAGCGGAC CTTCCTTCCC GCGGCCTGCT GCCGGCTCTG CGGCCTCTTC CGCGTCTTCG 5461 AGATCTGCCT CGACTGTGCC TTCTAGTTGC CAGCCATCTG TTGTTTGCCC CTCCCCCGTG 5521 CCTTCCTTGA CCCTGGAAGG TGCCACTCCC ACTGTCCTTT CCTAATAAAA TGAGGAAATT 5581 GCATCGCATT GTCTGAGTAG GTGTCATTCT ATTCTGGGGG GTGGGGTGGG GCAGGACAGC 5641 AAGGGGGAGG ATTGGGAAGA CAATAGCAGG CATGCTGGGG ACTCGAGTTA AGGGCGAATT 5701 GCCGATTAGG ATCTTCCTAG AGCATGGCTA CGTAGATAAG TAGCATGGCG GGTTAATCAT 5761 TAACTACAAG GAACCCCTAG TGATGGAGTT GGCCACTCCC TCTCTGCGCG CTCGCTCGCT 5821 CACTGAGGCC GGGCGACCAA AGGTCGCCCG ACGCCCGGGC TTTGCCCGGG CGGCCTCAGT 5881 GAGCGAGCGA GCGCGCAGCC TTAATTAAGA GCTCATGGCG CGCCTAGGCC TTGACGGCCT 5941 TCCGCCAATT CGCCCTATAG TGAGTCGTAT TACGTCGCGC TCACTGGCCG TCGTTTTACA 6001 ACGTCGTGAC TGGGAAAACC CTGGCGTTAC CCAACTTAAT CGCCTTGCAG CACATCCCCC 6061 TTTCGCCAGC TGGCGTAATA GCGAAGAGGC CCGCACCGAA ACGCCCTTCC CAACAGTTGC 6121 GCAGCCTGAA TGGCGAATGG GAGCGCCCTG TAGCGGCCAC TCAACCCTAT CTCGGTCTAT 6181 TCTTTTGATT TATAAGGGAT TTTGCCGATT TCGGCCTATT GGTTAAAAAA TGAGCTGATT 6241 TAACAAAAAT TTAACGCGAA TTTTAACAAA ATATTAACGC TTACAATTTA G //