; oligo-analysis  -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/08/11/retrieve-seq_2026-08-11.111650_gROdMH.fasta.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 6 -o $RSAT/public_html/tmp/www-data/2026/08/11/oligo-analysis_2026-08-11.111741_LrZudi_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/2026/08/11/retrieve-seq_2026-08-11.111650_gROdMH.fasta.fasta.purged
; Input format                 	fasta
; Output file                  	$RSAT/public_html/tmp/www-data/2026/08/11/oligo-analysis_2026-08-11.111741_LrZudi_6nt.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/6nt_upstream-noorf_Arabidopsis_thaliana.TAIR10.60-noov-2str.freq
; Pseudo-frequency             	0.01
; Pseudo-frequency per oligo   	4.80769230769231e-06
; Sequence type                	DNA
; Nb of sequences              	3
; Sum of sequence lengths      	2758
; 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      	2487
; total overlapping occurrences	30
; total non overlapping occ    	2457
; alphabet size                	4
; nb possible oligomers        	2080
; oligomers tested for significance	2080
; Sequences:
;	F6'H2	594
;	AT5G12270	463
;	F6'H1	1701
;
; 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
caacca	caacca|tggttg	0.0005378398762	10	1.34	1.5e-06	3.1e-03	2.51	1	0	50
ccacag	ccacag|ctgtgg	0.0001364277055	4	0.34	0.00042	8.8e-01	0.06	2	0	20
; Host name	rsat
; Job started	2026-08-11.111742
; Job done	2026-08-11.111742
; Seconds	0.29
;	user	0.29
;	system	0.02
;	cuser	0.11
;	csystem	0.01