; oligo-analysis -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/08/21/tmp_sequence_2026-08-21.210800_isBj8Q.fasta.purged -format fasta -lth occ_sig 0 -uth rank 50 -return occ,proba,rank -2str -noov -quick_if_possible -seqtype dna -bg upstream-noorf -org Drosophila_melanogaster -pseudo 0.01 -l 6 -o $RSAT/public_html/tmp/www-data/2026/08/21/oligo-analysis_2026-08-21.210800_pcU8kP_6nt.tab
; Citation: van Helden et al. (1998). J Mol Biol 281(5), 827-42.
; Program version 1.169
; Quick counting mode
; Detection of over-represented words (right-tail test)
; Oligomer length 6
; Input file $RSAT/public_html/tmp/www-data/2026/08/21/tmp_sequence_2026-08-21.210800_isBj8Q.fasta.purged
; Input format fasta
; Output file $RSAT/public_html/tmp/www-data/2026/08/21/oligo-analysis_2026-08-21.210800_pcU8kP_6nt.tab
; Discard overlapping matches
; Counted on both strands
; grouped by pairs of reverse complements
; Background model upstream-noorf
; Organism Drosophila_melanogaster
; Background estimation method Frequency file
; Expected frequency file $RSAT/public_html/data/genomes/Drosophila_melanogaster/oligo-frequencies/6nt_upstream-noorf_Drosophila_melanogaster-noov-2str.freq
; Pseudo-frequency 0.01
; Pseudo-frequency per oligo 4.80769230769231e-06
; Sequence type DNA
; Nb of sequences 37
; Sum of sequence lengths 45655
; discarded residues NA (quick mode) (other letters than ACGT)
; discarded occurrences NA (quick mode) (contain discarded residues)
; nb possible positions NA (quick mode)
; total oligo occurrences 45492
; total overlapping occurrences 982
; total non overlapping occ 44510
; alphabet size 4
; nb possible oligomers 2080
; oligomers tested for significance 2080
; Sequences:
; chr2R:12374957-12377245(.) 2288
; chr3L:19845033-19848421(.) 3388
; chr3R:9263708-9264530(.) 822
; chrX:12496696-12497519(.) 823
; chrX:7195637-7196623(.) 986
; chrX:7225872-7226648(.) 776
; chr3L:14550559-14551321(.) 762
; chr3L:5975670-5977117(.) 1447
; chr3L:21034239-21035187(.) 948
; chr3L:21058520-21059519(.) 999
; chr3L:21067506-21068157(.) 651
; chr3R:4196948-4197885(.) 937
; chr2R:21871562-21872466(.) 904
; chr2L:14688433-14689698(.) 1265
; chr2R:8161000-8161640(.) 640
; chrX:22854575-22855626(.) 1051
; chr3R:14740504-14741806(.) 1302
; chr3R:14749205-14749940(.) 735
; chr2L:8898214-8899277(.) 1063
; chr2R:12978871-12981585(.) 2714
; chr3L:1947429-1947995(.) 566
; chr2L:20757615-20759169(.) 1554
; chr2L:20759686-20760643(.) 957
; chr3L:21129679-21131795(.) 2116
; chr3L:21099861-21100280(.) 419
; chr3L:2766018-2767173(.) 1155
; chr3L:11707848-11708598(.) 750
; chr2R:18611474-18612076(.) 602
; chr2R:18582454-18583873(.) 1419
; chr2R:20581564-20582738(.) 1174
; chr3L:10659246-10661255(.) 2009
; chrX:15162354-15163474(.) 1120
; chr3L:3416943-3419182(.) 2239
; chr3L:18625845-18626329(.) 484
; chr3L:18640156-18641658(.) 1502
; chr3R:28584754-28586443(.) 1689
; chr3L:11196886-11198285(.) 1399
;
; column headers
; 1 seq oligomer sequence
; 2 id oligomer identifier
; 3 exp_freq expected relative frequency
; 4 occ observed occurrences
; 5 exp_occ expected occurrences
; 6 occ_P occurrence probability (binomial)
; 7 occ_E E-value for occurrences (binomial)
; 8 occ_sig occurrence significance (binomial)
; 9 rank rank
; 10 ovl_occ number of overlapping occurrences (discarded from the count)
; 11 forbocc forbidden positions (to avoid self-overlap)
#seq id exp_freq occ exp_occ occ_P occ_E occ_sig rank ovl_occ forbocc
agagag agagag|ctctct 0.0006161207180 77 28.03 2e-14 4.3e-11 10.37 1 34 385
gagaga gagaga|tctctc 0.0005456720930 63 24.82 1e-10 2.1e-07 6.68 2 36 315
agagcg agagcg|cgctct 0.0004543471686 49 20.67 8.2e-08 1.7e-04 3.77 3 0 245
cgtcgc cgtcgc|gcgacg 0.0002890191982 36 13.15 1.5e-07 3.2e-04 3.50 4 0 180
cgagag cgagag|ctctcg 0.0003538518379 39 16.10 9.5e-07 2.0e-03 2.70 5 0 195
cgacga cgacga|tcgtcg 0.0003211511644 36 14.61 1.7e-06 3.5e-03 2.46 6 2 180
agcgcg agcgcg|cgcgct 0.0002422430174 30 11.02 1.7e-06 3.6e-03 2.44 7 2 150
ctcgca ctcgca|tgcgag 0.0003805810841 40 17.31 2.2e-06 4.5e-03 2.35 8 0 200
gagagc gagagc|gctctc 0.0004985878624 48 22.68 2.4e-06 5.1e-03 2.29 9 0 240
agcggg agcggg|cccgct 0.0002738773646 32 12.46 2.7e-06 5.5e-03 2.26 10 0 160
ggcgac ggcgac|gtcgcc 0.0003146110297 34 14.31 6.8e-06 1.4e-02 1.85 11 0 170
acacac acacac|gtgtgt 0.0010811574699 83 49.18 6.8e-06 1.4e-02 1.85 12 52 415
cacaca cacaca|tgtgtg 0.0012730251174 94 57.91 8e-06 1.7e-02 1.78 13 61 470
cagcga cagcga|tcgctg 0.0005687758298 51 25.87 8.3e-06 1.7e-02 1.76 14 0 255
gcgaga gcgaga|tctcgc 0.0003774058012 38 17.17 9.8e-06 2.0e-02 1.69 15 0 190
acagcg acagcg|cgctgt 0.0003535437881 36 16.08 1.3e-05 2.7e-02 1.57 16 0 180
cgcgag cgcgag|ctcgcg 0.0001910356583 24 8.69 1.4e-05 2.9e-02 1.53 17 0 120
cctctc cctctc|gagagg 0.0003015070642 32 13.72 1.7e-05 3.6e-02 1.44 18 0 160
gtgaga gtgaga|tctcac 0.0003194687384 33 14.53 2.2e-05 4.6e-02 1.34 19 0 165
agcgaa agcgaa|ttcgct 0.0007154075455 58 32.55 3.6e-05 7.5e-02 1.13 20 0 290
cgtcga cgtcga|tcgacg 0.0002598492496 28 11.82 4.3e-05 9.0e-02 1.05 21 4 140
gagcgc gagcgc|gcgctc 0.0002963886978 30 13.48 7.1e-05 1.5e-01 0.83 22 2 150
aaagag aaagag|ctcttt 0.0008083675036 62 36.77 9.1e-05 1.9e-01 0.72 23 0 310
agaggg agaggg|ccctct 0.0002868154571 29 13.05 9.5e-05 2.0e-01 0.71 24 0 145
cgacgc cgacgc|gcgtcg 0.0002469348532 26 11.23 0.00011 2.4e-01 0.63 25 1 130
gcgagc gcgagc|gctcgc 0.0003387573966 32 15.41 0.00014 3.0e-01 0.52 26 0 160
cgtctc cgtctc|gagacg 0.0002005852029 22 9.13 0.00021 4.4e-01 0.36 27 0 110
gcggca gcggca|tgccgc 0.0005026399024 42 22.87 0.00021 4.4e-01 0.36 28 0 210
cggtaa cggtaa|ttaccg 0.0002464846265 25 11.21 0.00026 5.5e-01 0.26 29 0 125
aacagc aacagc|gctgtt 0.0007426107145 56 33.78 0.00029 6.0e-01 0.22 30 1 280
ccgctc ccgctc|gagcgg 0.0003530698653 32 16.06 0.00029 6.1e-01 0.21 31 0 160
acactc acactc|gagtgt 0.0004473094149 38 20.35 0.00030 6.2e-01 0.21 32 0 190
gcgcga gcgcga|tcgcgc 0.0002356080982 24 10.72 0.00032 6.7e-01 0.17 33 1 120
cgagac cgagac|gtctcg 0.0001937607145 21 8.81 0.00034 7.0e-01 0.15 34 1 105
aaacaa aaacaa|ttgttt 0.0023713175208 145 107.88 0.00038 7.8e-01 0.11 35 9 725
acgcgc acgcgc|gcgcgt 0.0002242576470 23 10.20 0.00039 8.1e-01 0.09 36 2 115
actctc actctc|gagagt 0.0003306533166 30 15.04 0.00044 9.1e-01 0.04 37 0 150
acgtcg acgtcg|cgacgt 0.0001988079923 21 9.04 0.00047 9.7e-01 0.01 38 4 105
; Host name rsat
; Job started 2026-08-21.210801
; Job done 2026-08-21.210801
; Seconds 0.29
; user 0.29
; system 0.02
; cuser 0.09
; csystem 0
; oligo-analysis -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/08/21/tmp_sequence_2026-08-21.210800_isBj8Q.fasta.purged -format fasta -lth occ_sig 0 -uth rank 50 -return occ,proba,rank -2str -noov -quick_if_possible -seqtype dna -bg upstream-noorf -org Drosophila_melanogaster -pseudo 0.01 -l 7 -o $RSAT/public_html/tmp/www-data/2026/08/21/oligo-analysis_2026-08-21.210800_pcU8kP_7nt.tab
; Citation: van Helden et al. (1998). J Mol Biol 281(5), 827-42.
; Program version 1.169
; Quick counting mode
; Detection of over-represented words (right-tail test)
; Oligomer length 7
; Input file $RSAT/public_html/tmp/www-data/2026/08/21/tmp_sequence_2026-08-21.210800_isBj8Q.fasta.purged
; Input format fasta
; Output file $RSAT/public_html/tmp/www-data/2026/08/21/oligo-analysis_2026-08-21.210800_pcU8kP_7nt.tab
; Discard overlapping matches
; Counted on both strands
; grouped by pairs of reverse complements
; Background model upstream-noorf
; Organism Drosophila_melanogaster
; Background estimation method Frequency file
; Expected frequency file $RSAT/public_html/data/genomes/Drosophila_melanogaster/oligo-frequencies/7nt_upstream-noorf_Drosophila_melanogaster-noov-2str.freq
; Pseudo-frequency 0.01
; Pseudo-frequency per oligo 1.220703125e-06
; Sequence type DNA
; Nb of sequences 37
; Sum of sequence lengths 45655
; discarded residues NA (quick mode) (other letters than ACGT)
; discarded occurrences NA (quick mode) (contain discarded residues)
; nb possible positions NA (quick mode)
; total oligo occurrences 45433
; total overlapping occurrences 904
; total non overlapping occ 44529
; alphabet size 4
; nb possible oligomers 8192
; oligomers tested for significance 8192
; Sequences:
; chr2R:12374957-12377245(.) 2288
; chr3L:19845033-19848421(.) 3388
; chr3R:9263708-9264530(.) 822
; chrX:12496696-12497519(.) 823
; chrX:7195637-7196623(.) 986
; chrX:7225872-7226648(.) 776
; chr3L:14550559-14551321(.) 762
; chr3L:5975670-5977117(.) 1447
; chr3L:21034239-21035187(.) 948
; chr3L:21058520-21059519(.) 999
; chr3L:21067506-21068157(.) 651
; chr3R:4196948-4197885(.) 937
; chr2R:21871562-21872466(.) 904
; chr2L:14688433-14689698(.) 1265
; chr2R:8161000-8161640(.) 640
; chrX:22854575-22855626(.) 1051
; chr3R:14740504-14741806(.) 1302
; chr3R:14749205-14749940(.) 735
; chr2L:8898214-8899277(.) 1063
; chr2R:12978871-12981585(.) 2714
; chr3L:1947429-1947995(.) 566
; chr2L:20757615-20759169(.) 1554
; chr2L:20759686-20760643(.) 957
; chr3L:21129679-21131795(.) 2116
; chr3L:21099861-21100280(.) 419
; chr3L:2766018-2767173(.) 1155
; chr3L:11707848-11708598(.) 750
; chr2R:18611474-18612076(.) 602
; chr2R:18582454-18583873(.) 1419
; chr2R:20581564-20582738(.) 1174
; chr3L:10659246-10661255(.) 2009
; chrX:15162354-15163474(.) 1120
; chr3L:3416943-3419182(.) 2239
; chr3L:18625845-18626329(.) 484
; chr3L:18640156-18641658(.) 1502
; chr3R:28584754-28586443(.) 1689
; chr3L:11196886-11198285(.) 1399
;
; column headers
; 1 seq oligomer sequence
; 2 id oligomer identifier
; 3 exp_freq expected relative frequency
; 4 occ observed occurrences
; 5 exp_occ expected occurrences
; 6 occ_P occurrence probability (binomial)
; 7 occ_E E-value for occurrences (binomial)
; 8 occ_sig occurrence significance (binomial)
; 9 rank rank
; 10 ovl_occ number of overlapping occurrences (discarded from the count)
; 11 forbocc forbidden positions (to avoid self-overlap)
#seq id exp_freq occ exp_occ occ_P occ_E occ_sig rank ovl_occ forbocc
ctctctc ctctctc|gagagag 0.0002405671104 38 10.93 1.4e-10 1.1e-06 5.95 1 30 228
agagaga agagaga|tctctct 0.0002461195105 36 11.18 3e-09 2.4e-05 4.62 2 27 216
cgcgacg cgcgacg|cgtcgcg 0.0000513821293 13 2.33 1.1e-06 9.3e-03 2.03 3 0 78
cacacac cacacac|gtgtgtg 0.0005539929748 52 25.17 1.9e-06 1.6e-02 1.81 4 44 312
ggcgacc ggcgacc|ggtcgcc 0.0000539210472 13 2.45 1.9e-06 1.6e-02 1.80 5 0 78
cagcgaa cagcgaa|ttcgctg 0.0001949852280 25 8.86 6.6e-06 5.4e-02 1.26 6 0 150
ccctctc ccctctc|gagaggg 0.0001009740784 17 4.59 6.7e-06 5.5e-02 1.26 7 0 102
ctctcac ctctcac|gtgagag 0.0001021367604 17 4.64 7.8e-06 6.4e-02 1.20 8 0 102
cgctctc cgctctc|gagagcg 0.0001846397305 24 8.39 8e-06 6.6e-02 1.18 9 0 144
ctgccgc ctgccgc|gcggcag 0.0001450848121 20 6.59 2e-05 1.6e-01 0.80 10 1 120
ctcgcac ctcgcac|gtgcgag 0.0001162550426 17 5.28 3.9e-05 3.2e-01 0.50 11 0 102
agataca agataca|tgtatct 0.0002175507512 25 9.88 3.9e-05 3.2e-01 0.50 12 1 150
aagagag aagagag|ctctctt 0.0002207303308 25 10.03 4.9e-05 4.0e-01 0.40 13 0 150
acacaca acacaca|tgtgtgt 0.0005979613393 50 27.17 5.5e-05 4.5e-01 0.35 14 43 300
gcgacga gcgacga|tcgtcgc 0.0000859303962 14 3.90 5.9e-05 4.9e-01 0.31 15 0 84
aacaaaa aacaaaa|ttttgtt 0.0009838768710 73 44.70 6.3e-05 5.1e-01 0.29 16 2 438
cactctc cactctc|gagagtg 0.0001213328785 17 5.51 6.5e-05 5.3e-01 0.27 17 0 102
gagatac gagatac|gtatctc 0.0000866896987 14 3.94 6.5e-05 5.3e-01 0.27 18 0 84
cgcgctc cgcgctc|gagcgcg 0.0000688935448 12 3.13 0.00011 8.6e-01 0.06 19 0 72
cgaaaaa cgaaaaa|tttttcg 0.0004553548252 40 20.69 0.00011 8.7e-01 0.06 20 0 240
agagcgg agagcgg|ccgctct 0.0001032519861 15 4.69 0.00012 9.4e-01 0.03 21 0 90
ctctttc ctctttc|gaaagag 0.0002058052896 23 9.35 0.00012 9.5e-01 0.02 22 0 138
; Host name rsat
; Job started 2026-08-21.210802
; Job done 2026-08-21.210802
; Seconds 0.85
; user 0.85
; system 0.02
; cuser 0.13
; csystem 0.02
; oligo-analysis -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/08/21/tmp_sequence_2026-08-21.210800_isBj8Q.fasta.purged -format fasta -lth occ_sig 0 -uth rank 50 -return occ,proba,rank -2str -noov -quick_if_possible -seqtype dna -bg upstream-noorf -org Drosophila_melanogaster -pseudo 0.01 -l 8 -o $RSAT/public_html/tmp/www-data/2026/08/21/oligo-analysis_2026-08-21.210800_pcU8kP_8nt.tab
; Citation: van Helden et al. (1998). J Mol Biol 281(5), 827-42.
; Program version 1.169
; Quick counting mode
; Detection of over-represented words (right-tail test)
; Oligomer length 8
; Input file $RSAT/public_html/tmp/www-data/2026/08/21/tmp_sequence_2026-08-21.210800_isBj8Q.fasta.purged
; Input format fasta
; Output file $RSAT/public_html/tmp/www-data/2026/08/21/oligo-analysis_2026-08-21.210800_pcU8kP_8nt.tab
; Discard overlapping matches
; Counted on both strands
; grouped by pairs of reverse complements
; Background model upstream-noorf
; Organism Drosophila_melanogaster
; Background estimation method Frequency file
; Expected frequency file $RSAT/public_html/data/genomes/Drosophila_melanogaster/oligo-frequencies/8nt_upstream-noorf_Drosophila_melanogaster-noov-2str.freq
; Pseudo-frequency 0.01
; Pseudo-frequency per oligo 3.03988326848249e-07
; Sequence type DNA
; Nb of sequences 37
; Sum of sequence lengths 45655
; discarded residues NA (quick mode) (other letters than ACGT)
; discarded occurrences NA (quick mode) (contain discarded residues)
; nb possible positions NA (quick mode)
; total oligo occurrences 45398
; total overlapping occurrences 473
; total non overlapping occ 44925
; alphabet size 4
; nb possible oligomers 32896
; oligomers tested for significance 32896
; Sequences:
; chr2R:12374957-12377245(.) 2288
; chr3L:19845033-19848421(.) 3388
; chr3R:9263708-9264530(.) 822
; chrX:12496696-12497519(.) 823
; chrX:7195637-7196623(.) 986
; chrX:7225872-7226648(.) 776
; chr3L:14550559-14551321(.) 762
; chr3L:5975670-5977117(.) 1447
; chr3L:21034239-21035187(.) 948
; chr3L:21058520-21059519(.) 999
; chr3L:21067506-21068157(.) 651
; chr3R:4196948-4197885(.) 937
; chr2R:21871562-21872466(.) 904
; chr2L:14688433-14689698(.) 1265
; chr2R:8161000-8161640(.) 640
; chrX:22854575-22855626(.) 1051
; chr3R:14740504-14741806(.) 1302
; chr3R:14749205-14749940(.) 735
; chr2L:8898214-8899277(.) 1063
; chr2R:12978871-12981585(.) 2714
; chr3L:1947429-1947995(.) 566
; chr2L:20757615-20759169(.) 1554
; chr2L:20759686-20760643(.) 957
; chr3L:21129679-21131795(.) 2116
; chr3L:21099861-21100280(.) 419
; chr3L:2766018-2767173(.) 1155
; chr3L:11707848-11708598(.) 750
; chr2R:18611474-18612076(.) 602
; chr2R:18582454-18583873(.) 1419
; chr2R:20581564-20582738(.) 1174
; chr3L:10659246-10661255(.) 2009
; chrX:15162354-15163474(.) 1120
; chr3L:3416943-3419182(.) 2239
; chr3L:18625845-18626329(.) 484
; chr3L:18640156-18641658(.) 1502
; chr3R:28584754-28586443(.) 1689
; chr3L:11196886-11198285(.) 1399
;
; column headers
; 1 seq oligomer sequence
; 2 id oligomer identifier
; 3 exp_freq expected relative frequency
; 4 occ observed occurrences
; 5 exp_occ expected occurrences
; 6 occ_P occurrence probability (binomial)
; 7 occ_E E-value for occurrences (binomial)
; 8 occ_sig occurrence significance (binomial)
; 9 rank rank
; 10 ovl_occ number of overlapping occurrences (discarded from the count)
; 11 forbocc forbidden positions (to avoid self-overlap)
#seq id exp_freq occ exp_occ occ_P occ_E occ_sig rank ovl_occ forbocc
gagagaga gagagaga|tctctctc 0.0001161115781 24 5.27 2.2e-09 7.3e-05 4.14 1 18 168
cacacaca cacacaca|tgtgtgtg 0.0003553206980 40 16.13 4e-07 1.3e-02 1.88 2 33 280
agagagag agagagag|ctctctct 0.0001281906895 19 5.82 1.2e-05 3.8e-01 0.42 3 24 133
aaacaaaa aaacaaaa|ttttgttt 0.0005055145987 46 22.95 1.5e-05 4.9e-01 0.31 4 2 322
cgagatac cgagatac|gtatctcg 0.0000180073617 7 0.82 2.4e-05 7.8e-01 0.11 5 0 49
; Host name rsat
; Job started 2026-08-21.210803
; Job done 2026-08-21.210806
; Seconds 2.98
; user 2.98
; system 0.07
; cuser 0.2
; csystem 0.02