; oligo-analysis  -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/04/18/tmp_sequence_2026-04-18.211625_pHkZbY.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 Arabidopsis_thaliana.TAIR10.60 -pseudo 0.01 -l 7 -o $RSAT/public_html/tmp/www-data/2026/04/18/oligo-analysis_2026-04-18.211625_Igd2np_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/2026/04/18/tmp_sequence_2026-04-18.211625_pHkZbY.fasta.purged
; Input format                 	fasta
; Output file                  	$RSAT/public_html/tmp/www-data/2026/04/18/oligo-analysis_2026-04-18.211625_Igd2np_7nt.tab
; Discard overlapping matches
; Counted on both strands
; 	grouped by pairs of reverse complements
; Background model             	upstream-noorf
; Organism                     	Arabidopsis_thaliana.TAIR10.60
; Background estimation method 	Frequency file
; Expected frequency file      	$RSAT/public_html/data/genomes/Arabidopsis_thaliana.TAIR10.60/oligo-frequencies/7nt_upstream-noorf_Arabidopsis_thaliana.TAIR10.60-noov-2str.freq
; Pseudo-frequency             	0.01
; Pseudo-frequency per oligo   	1.220703125e-06
; Sequence type                	DNA
; Nb of sequences              	1
; Sum of sequence lengths      	3189
; 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      	3183
; total overlapping occurrences	46
; total non overlapping occ    	3137
; alphabet size                	4
; nb possible oligomers        	8192
; oligomers tested for significance	8192
; Sequences:
;	Armadillos	3189
;
; 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
agctgca	agctgca|tgcagct	0.0000589010981	5	0.19	1.6e-06	1.3e-02	1.87	1	0	30
ctgcagc	ctgcagc|gctgcag	0.0000289535981	4	0.09	2.8e-06	2.3e-02	1.64	2	0	24
cctctga	cctctga|tcagagg	0.0000433233648	4	0.14	1.3e-05	1.1e-01	0.96	3	0	24
ggacccc	ggacccc|ggggtcc	0.0000157666317	3	0.05	2e-05	1.7e-01	0.78	4	0	18
acagctc	acagctc|gagctgt	0.0000489102094	4	0.16	2.2e-05	1.8e-01	0.75	5	0	24
aagctga	aagctga|tcagctt	0.0001182172808	5	0.38	4.6e-05	3.8e-01	0.42	6	0	30
gctgcac	gctgcac|gtgcagc	0.0000214289741	3	0.07	5e-05	4.1e-01	0.39	7	0	18
accagcc	accagcc|ggctggt	0.0000282992829	3	0.09	0.00011	9.3e-01	0.03	8	0	18
cagctgc	cagctgc|gcagctg	0.0000288277683	3	0.09	0.00012	9.8e-01	0.01	9	2	18
; Host name	rsat
; Job started	2026-04-18.211626
; Job done	2026-04-18.211627
; Seconds	0.57
;	user	0.57
;	system	0.02
;	cuser	0.1
;	csystem	0.02