; oligo-analysis -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/06/02/tmp_sequence_2026-06-02.224821_NB57iH.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/2026/06/02/oligo-analysis_2026-06-02.224821_AMq79K_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/2026/06/02/tmp_sequence_2026-06-02.224821_NB57iH.purged
; Input format fasta
; Output file $RSAT/public_html/tmp/www-data/2026/06/02/oligo-analysis_2026-06-02.224821_AMq79K_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 26
; Sum of sequence lengths 19526
; 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 18662
; total overlapping occurrences 149
; total non overlapping occ 18513
; alphabet size 4
; nb possible oligomers 2080
; oligomers tested for significance 2080
; Sequences:
; FBgn0002284|Prosbeta6 751
; FBgn0002787|Rpn8 751
; FBgn0010590|Prosbeta1 751
; FBgn0011327|Uch-L5 751
; FBgn0015283|Rpn10 751
; FBgn0017556|Prosalpha4T2 751
; FBgn0029745|Rpn13R 751
; FBgn0029812|Prosbeta2R1 751
; FBgn0030370|Uch-L5R 751
; FBgn0031442|Prosbeta4R1 751
; FBgn0031443|Prosbeta4R2 751
; FBgn0032492|Prosalpha6T 751
; FBgn0033886|Rpn13 751
; FBgn0034842|Prosbeta5R1 751
; FBgn0036224|Rpt4R 751
; FBgn0036465|Rpn12R 751
; FBgn0037296|Prosbeta2R2 751
; FBgn0037742|Rpt3R 751
; FBgn0039788|Rpt6R 751
; FBgn0050382|Prosalpha1R 751
; FBgn0051742|Prosbeta5R2 751
; FBgn0250746|Prosbeta7 751
; FBgn0261394|Prosalpha3 751
; FBgn0261395|Prosalpha3T 751
; FBgn0263121|Prosalpha1 751
; FBgn0265606|Prosalpha4T1 751
;
; 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
ctccac ctccac|gtggag 0.0003865288153 30 7.21 2e-10 4.1e-07 6.39 1 0 150
ccacgg ccacgg|ccgtgg 0.0001993766997 21 3.72 5.4e-10 1.1e-06 5.95 2 0 105
accacg accacg|cgtggt 0.0001986421194 20 3.71 2.9e-09 6.1e-06 5.22 3 1 100
gcatca gcatca|tgatgc 0.0003539229263 25 6.60 3.6e-08 7.5e-05 4.12 4 0 125
cctgga cctgga|tccagg 0.0002412240834 19 4.50 3e-07 6.3e-04 3.20 5 0 95
ccagga ccagga|tcctgg 0.0003060804192 21 5.71 6.8e-07 1.4e-03 2.85 6 0 105
caggag caggag|ctcctg 0.0002841614895 20 5.30 8.4e-07 1.7e-03 2.76 7 0 100
acctgg acctgg|ccaggt 0.0002151820252 17 4.02 1.2e-06 2.5e-03 2.61 8 0 85
cacctg cacctg|caggtg 0.0003545390260 22 6.62 1.9e-06 3.9e-03 2.41 9 0 110
cggatc cggatc|gatccg 0.0002328356497 17 4.35 3.3e-06 7.0e-03 2.16 10 1 85
ggtgga ggtgga|tccacc 0.0003693728098 22 6.89 3.5e-06 7.4e-03 2.13 11 0 110
gctcca gctcca|tggagc 0.0004294188290 24 8.01 3.8e-06 7.9e-03 2.10 12 0 120
gctgga gctgga|tccagc 0.0004300823210 24 8.03 3.9e-06 8.1e-03 2.09 13 0 120
cctcca cctcca|tggagg 0.0003034027554 19 5.66 8e-06 1.7e-02 1.78 14 0 95
gcctcc gcctcc|ggaggc 0.0002520769156 17 4.70 9.2e-06 1.9e-02 1.72 15 0 85
atgacc atgacc|ggtcat 0.0002538067339 17 4.74 1e-05 2.1e-02 1.68 16 0 85
ctccag ctccag|ctggag 0.0003101087630 19 5.79 1.1e-05 2.2e-02 1.65 17 0 95
accagg accagg|cctggt 0.0002315323620 16 4.32 1.2e-05 2.6e-02 1.59 18 0 80
ctggaa ctggaa|ttccag 0.0005358144987 26 10.00 1.8e-05 3.6e-02 1.44 19 0 130
aggagg aggagg|cctcct 0.0002954882445 18 5.51 1.9e-05 4.1e-02 1.39 20 0 90
cctgca cctgca|tgcagg 0.0003563636287 20 6.65 2.2e-05 4.6e-02 1.34 21 0 100
gatcca gatcca|tggatc 0.0002986398311 18 5.57 2.2e-05 4.6e-02 1.33 22 0 90
acggtg acggtg|caccgt 0.0001916991503 14 3.58 2.3e-05 4.9e-02 1.31 23 0 70
caccga caccga|tcggtg 0.0003580697509 20 6.68 2.3e-05 4.9e-02 1.31 24 0 100
atccag atccag|ctggat 0.0003310798471 19 6.18 2.6e-05 5.4e-02 1.27 25 0 95
cgatcc cgatcc|ggatcg 0.0002759152327 17 5.15 2.8e-05 5.9e-02 1.23 26 0 85
ccagca ccagca|tgctgg 0.0005520463548 26 10.30 2.9e-05 6.0e-02 1.22 27 0 130
ggcacc ggcacc|ggtgcc 0.0002217458561 15 4.14 2.9e-05 6.1e-02 1.22 28 0 75
caaggg caaggg|cccttg 0.0002492570749 16 4.65 3e-05 6.2e-02 1.21 29 0 80
catgga catgga|tccatg 0.0003058908501 18 5.71 3e-05 6.3e-02 1.20 30 1 90
caccag caccag|ctggtg 0.0003362219096 19 6.27 3.2e-05 6.6e-02 1.18 31 0 95
aggtgg aggtgg|ccacct 0.0003453212274 19 6.44 4.5e-05 9.4e-02 1.03 32 0 95
gccacc gccacc|ggtggc 0.0004430678059 22 8.27 5.3e-05 1.1e-01 0.95 33 1 110
atcgcc atcgcc|ggcgat 0.0003857942349 20 7.20 6.4e-05 1.3e-01 0.87 34 0 100
gaccac gaccac|gtggtc 0.0002706309934 16 5.05 7.7e-05 1.6e-01 0.79 35 0 80
ggatcc ggatcc|ggatcc 0.0001142601640 10 2.13 7.8e-05 1.6e-01 0.79 36 0 50
gcacca gcacca|tggtgc 0.0003615056912 19 6.75 8.1e-05 1.7e-01 0.77 37 0 95
atcctg atcctg|caggat 0.0003015070642 17 5.63 8.3e-05 1.7e-01 0.77 38 0 85
agcatc agcatc|gatgct 0.0003320750850 18 6.20 8.5e-05 1.8e-01 0.75 39 0 90
accgga accgga|tccggt 0.0001919835039 13 3.58 9.5e-05 2.0e-01 0.70 40 0 65
gagtac gagtac|gtactc 0.0002191866730 14 4.09 9.6e-05 2.0e-01 0.70 41 0 70
gatggc gatggc|gccatc 0.0004370252901 21 8.16 0.00012 2.5e-01 0.60 42 0 105
ctggta ctggta|taccag 0.0002528825843 15 4.72 0.00012 2.6e-01 0.59 43 0 75
ccggcg ccggcg|cgccgg 0.0002251581003 14 4.20 0.00013 2.6e-01 0.58 44 1 70
ccagcg ccagcg|cgctgg 0.0003751309718 19 7.00 0.00013 2.7e-01 0.57 45 0 95
cggtga cggtga|tcaccg 0.0002260348575 14 4.22 0.00013 2.7e-01 0.56 46 0 70
cggcac cggcac|gtgccg 0.0002840430088 16 5.30 0.00013 2.8e-01 0.56 47 0 80
cttgtc cttgtc|gacaag 0.0003446577355 18 6.43 0.00013 2.8e-01 0.56 48 0 90
ctgggc ctgggc|gcccag 0.0003481884604 18 6.50 0.00015 3.1e-01 0.51 49 0 90
cgtgga cgtgga|tccacg 0.0002577876854 15 4.81 0.00015 3.1e-01 0.50 50 0 75
; Host name rsat
; Job started 2026-06-02.224821
; Job done 2026-06-02.224822
; Seconds 0.24
; user 0.24
; system 0.02
; cuser 0.11
; csystem 0.01