; 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 8 -o $RSAT/public_html/tmp/www-data/2026/06/02/oligo-analysis_2026-06-02.224821_AMq79K_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/2026/06/02/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_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 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 18610
; total overlapping occurrences 52
; total non overlapping occ 18558
; alphabet size 4
; nb possible oligomers 32896
; oligomers tested for significance 32896
; 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
aggtggag aggtggag|ctccacct 0.0000281879880 9 0.52 5.2e-09 1.7e-04 3.77 1 0 63
actccacc actccacc|ggtggagt 0.0000213534416 7 0.40 2.2e-07 7.2e-03 2.14 2 0 49
gagtacgc gagtacgc|gcgtactc 0.0000095353720 5 0.18 1.3e-06 4.2e-02 1.38 3 0 35
gtggagta gtggagta|tactccac 0.0000202855437 6 0.38 2.9e-06 9.6e-02 1.02 4 0 42
atgtagtg atgtagtg|cactacat 0.0000204753923 6 0.38 3.1e-06 1.0e-01 1.00 5 0 42
catcacca catcacca|tggtgatg 0.0000326968900 7 0.61 3.6e-06 1.2e-01 0.93 6 0 49
caccacgg caccacgg|ccgtggtg 0.0000118847473 5 0.22 3.7e-06 1.2e-01 0.92 7 0 35
ctcctgca ctcctgca|tgcaggag 0.0000238452033 6 0.44 7.3e-06 2.4e-01 0.62 8 0 42
gcatcacc gcatcacc|ggtgatgc 0.0000144714332 5 0.27 9.4e-06 3.1e-01 0.51 9 0 35
caggtgga caggtgga|tccacctg 0.0000265742756 6 0.49 1.3e-05 4.4e-01 0.36 10 0 42
ggcctcca ggcctcca|tggaggcc 0.0000157054485 5 0.29 1.4e-05 4.6e-01 0.34 11 0 35
cggatcca cggatcca|tggatccg 0.0000157291796 5 0.29 1.4e-05 4.6e-01 0.34 12 0 35
gtactcca gtactcca|tggagtac 0.0000158478349 5 0.29 1.5e-05 4.8e-01 0.32 13 0 35
ggtgcgca ggtgcgca|tgcgcacc 0.0000159190281 5 0.30 1.5e-05 4.9e-01 0.31 14 0 35
; Host name rsat
; Job started 2026-06-02.224823
; Job done 2026-06-02.224825
; Seconds 2.53
; user 2.54
; system 0.05
; cuser 0.16
; csystem 0.03