; oligo-analysis  -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/07/01/retrieve-seq_2026-07-01.093439_kIh5Jb.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/2026/07/01/oligo-analysis_2026-07-01.093605_ZJHi28_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/2026/07/01/retrieve-seq_2026-07-01.093439_kIh5Jb.fasta.fasta.purged
; Input format                 	fasta
; Output file                  	$RSAT/public_html/tmp/www-data/2026/07/01/oligo-analysis_2026-07-01.093605_ZJHi28_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              	26
; Sum of sequence lengths      	9167
; 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      	9047
; total overlapping occurrences	207
; total non overlapping occ    	8840
; alphabet size                	4
; nb possible oligomers        	2080
; oligomers tested for significance	2080
; Sequences:
;	HSP17.8	24
;	HSP70-5	72
;	AT1G29660	500
;	HSP17.6C	173
;	AT1G66080	500
;	CLPB1	224
;	ROSY1	500
;	AT2G20560	36
;	HAC1	419
;	HSFA2	158
;	HSP17.6B	316
;	AT2G38610	500
;	MED37C	453
;	DTX19	500
;	SAP12	500
;	CDC48D	500
;	AT4G24480	500
;	HSP23.6	500
;	MED37D	500
;	HSP17.6	500
;	HSP17.7	110
;	CYP705A5	500
;	FKBP65	304
;	HSP23.5	155
;	HSP90-1	223
;	EIL5	500
;
; 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
atgggc	atgggc|gcccat	0.0003372091028	15	3.05	8.2e-07	1.7e-03	2.77	1	0	75
aaaact	aaaact|agtttt	0.0021189117916	39	19.17	4.5e-05	9.4e-02	1.03	2	0	195
ggccca	ggccca|tgggcc	0.0003203392479	12	2.90	5.1e-05	1.1e-01	0.97	3	2	60
; Host name	rsat
; Job started	2026-07-01.093606
; Job done	2026-07-01.093606
; Seconds	0.28
;	user	0.28
;	system	0.01
;	cuser	0.1
;	csystem	0.02