; oligo-analysis  -v 1 -sort -i $RSAT/public_html/tmp/www-data/2026/07/10/tmp_sequence_2026-07-10.105849_MwFmTr.fasta.purged -format fasta -lth occ_sig 0 -uth rank 50 -return freq,occ,proba,rank,ratio,zscore -2str -noov -quick_if_possible -seqtype dna -bg upstream-noorf -org Homo_sapiens_GRCh38 -pseudo 0.01 -l 4 -o $RSAT/public_html/tmp/www-data/2026/07/10/oligo-analysis_2026-07-10.105849_yMrI9W_4nt.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              	4
; Input file                   	$RSAT/public_html/tmp/www-data/2026/07/10/tmp_sequence_2026-07-10.105849_MwFmTr.fasta.purged
; Input format                 	fasta
; Output file                  	$RSAT/public_html/tmp/www-data/2026/07/10/oligo-analysis_2026-07-10.105849_yMrI9W_4nt.tab
; Discard overlapping matches
; Counted on both strands
; 	grouped by pairs of reverse complements
; Background model             	upstream-noorf
; Organism                     	Homo_sapiens_GRCh38
; Background estimation method 	Frequency file
; Expected frequency file      	$RSAT/public_html/data/genomes/Homo_sapiens_GRCh38/oligo-frequencies/4nt_upstream-noorf_Homo_sapiens_GRCh38-noov-2str.freq
; Pseudo-frequency             	0.01
; Pseudo-frequency per oligo   	7.35294117647059e-05
; Sequence type                	DNA
; Nb of sequences              	5062
; Sum of sequence lengths      	1399185
; 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      	1186561
; total overlapping occurrences	44037
; total non overlapping occ    	1142524
; alphabet size                	4
; nb possible oligomers        	136
; oligomers tested for significance	136
;
; column headers
;	1	seq            	oligomer sequence
;	2	id             	oligomer identifier
;	3	obs_freq       	observed relative frequency
;	4	exp_freq       	expected relative frequency
;	5	occ            	observed occurrences
;	6	exp_occ        	expected occurrences
;	7	occ_P          	occurrence probability (binomial)
;	8	occ_E          	E-value for occurrences (binomial)
;	9	occ_sig        	occurrence significance (binomial)
;	10	rank           	rank
;	11	ovl_occ        	number of overlapping occurrences (discarded from the count)
;	12	forbocc        	forbidden positions (to avoid self-overlap)
;	13	zscore         	z-score (Gaussian approximation)
;	14	exp_var        	estimation of the variance on occurrences
;	15	ratio          	observed/expected ratio
#seq	id	obs_freq	exp_freq	occ	exp_occ	occ_P	occ_E	occ_sig	rank	ovl_occ	forbocc	zscore	exp_var	ratio
ccgc	ccgc|gcgg	0.0106071242861	0.0027877686570	12586	3307.86	0	0e+00	350.00	1	1116	37758	161.32	3307.858	3.8049
cccg	cccg|cggg	0.0104335133213	0.0032878994693	12380	3901.29	0	0e+00	350.00	2	760	37140	135.75	3901.293	3.1733
cgcc	cgcc|ggcg	0.0102169210011	0.0033514748720	12123	3976.73	0	0e+00	350.00	3	1128	36369	129.18	3976.729	3.0485
cggc	cggc|gccg	0.0081378032819	0.0024277739276	9656	2880.70	0	0e+00	350.00	4	1158	28968	126.23	2880.702	3.3520
cgcg	cgcg|cgcg	0.0037756170985	0.0007447827586	4480	883.73	0	0e+00	350.00	5	1004	13440	120.97	883.730	5.0694
cgga	cgga|tccg	0.0062171266374	0.0018482367403	7377	2193.05	0	0e+00	350.00	6	275	22131	110.70	2193.046	3.3638
agcg	agcg|cgct	0.0062533658194	0.0019033684787	7420	2258.46	0	0e+00	350.00	7	278	22260	108.61	2258.463	3.2854
gcgc	gcgc|gcgc	0.0045408537783	0.0012202293268	5388	1447.88	0	0e+00	350.00	8	1066	16164	103.55	1447.877	3.7213
cgca	cgca|tgcg	0.0054771731078	0.0017084024734	6499	2027.12	0	0e+00	350.00	9	288	19497	99.32	2027.124	3.2060
ccgg	ccgg|ccgg	0.0049116733147	0.0015379841764	5828	1824.91	0	0e+00	350.00	10	0	17484	93.71	1824.912	3.1936
cgac	cgac|gtcg	0.0037916297603	0.0010606045480	4499	1258.47	0	0e+00	350.00	11	95	13497	91.35	1258.472	3.5750
gcga	gcga|tcgc	0.0049310570632	0.0016340766693	5851	1938.93	0	0e+00	350.00	12	124	17553	88.84	1938.932	3.0176
acgc	acgc|gcgt	0.0050844415079	0.0017116649615	6033	2030.99	0	0e+00	350.00	13	129	18099	88.80	2030.995	2.9705
gccc	gccc|gggc	0.0141846900412	0.0073316745028	16831	8699.48	0	0e+00	350.00	14	759	50493	87.18	8699.479	1.9347
accg	accg|cggt	0.0045231555731	0.0014742147491	5367	1749.25	0	0e+00	350.00	15	95	16101	86.50	1749.246	3.0682
cgtc	cgtc|gacg	0.0046377725208	0.0015337443790	5503	1819.88	0	0e+00	350.00	16	253	16509	86.34	1819.881	3.0238
ccga	ccga|tcgg	0.0051198379182	0.0018350574380	6075	2177.41	0	0e+00	350.00	17	0	18225	83.53	2177.408	2.7900
cccc	cccc|gggg	0.0123356489890	0.0064110132776	14637	7607.06	0	0e+00	350.00	18	4624	43911	80.60	7607.058	1.9241
cgag	cgag|ctcg	0.0057881558555	0.0023630703077	6868	2803.93	0	0e+00	350.00	19	200	20604	76.75	2803.927	2.4494
acgg	acgg|ccgt	0.0047397478933	0.0018014768054	5624	2137.56	0	0e+00	350.00	20	0	16872	75.41	2137.562	2.6310
aacg	aacg|cgtt	0.0038067996504	0.0013793870095	4517	1636.73	0	0e+00	350.00	21	131	13551	71.19	1636.727	2.7598
cacg	cacg|cgtg	0.0053979525705	0.0024918307988	6405	2956.71	0	0e+00	350.00	22	322	19215	63.42	2956.709	2.1663
cgaa	cgaa|ttcg	0.0034654771225	0.0013510953445	4112	1603.16	0	0e+00	350.00	23	94	12336	62.66	1603.157	2.5649
ggcc	ggcc|ggcc	0.0068340355026	0.0038889302736	8109	4614.45	0	0e+00	350.00	24	0	24327	51.44	4614.453	1.7573
aggg	aggg|ccct	0.0134843467803	0.0090085431169	16000	10689.19	0	0e+00	350.00	25	0	48000	51.37	10689.186	1.4968
ggac	ggac|gtcc	0.0081487593137	0.0050367152895	9669	5976.37	0	0e+00	350.00	26	0	29007	47.77	5976.370	1.6179
acga	acga|tcgt	0.0028746941792	0.0013461728678	3411	1597.32	0	0e+00	350.00	27	35	10233	45.38	1597.316	2.1355
cgta	cgta|tacg	0.0022164895020	0.0009479984036	2630	1124.86	2e-319	3e-317	316.57	28	157	7890	44.88	1124.858	2.3381
gagc	gagc|gctc	0.0098216610861	0.0068096835825	11654	8080.10	2e-306	2e-304	303.68	29	419	34962	39.76	8080.105	1.4423
ggga	ggga|tccc	0.0138138705048	0.0102143486822	16391	12119.95	5e-300	6e-298	297.21	30	0	49173	38.80	12119.948	1.3524
accc	accc|gggt	0.0095595590956	0.0067400502998	11343	7997.48	3e-273	3e-271	270.47	31	0	34029	37.41	7997.481	1.4183
acgt	acgt|acgt	0.0019788278900	0.0009084964269	2348	1077.99	4e-245	6e-243	242.24	32	0	7044	38.68	1077.986	2.1781
gacc	gacc|ggtc	0.0073026165532	0.0051155180322	8665	6069.87	3e-216	4e-214	213.42	33	0	25995	33.31	6069.874	1.4275
ctcc	ctcc|ggag	0.0145420252309	0.0114687107067	17255	13608.32	2e-200	2e-198	197.61	34	665	51765	31.26	13608.325	1.2680
cctc	cctc|gagg	0.0138568518601	0.0110413391293	16442	13101.22	1e-175	2e-173	172.76	35	627	49326	29.19	13101.222	1.2550
atcg	atcg|cgat	0.0021591810282	0.0012314037082	2562	1461.14	2e-149	3e-147	146.57	36	85	7686	28.80	1461.136	1.7534
ctgc	ctgc|gcag	0.0112939832002	0.0092424577695	13401	10966.74	5e-113	7e-111	110.19	37	1013	40203	23.24	10966.740	1.2220
ccac	ccac|gtgg	0.0106467345547	0.0087252240456	12633	10353.01	3e-105	5e-103	102.34	38	327	37899	22.41	10353.011	1.2202
tcga	tcga|tcga	0.0012776418574	0.0006976994493	1516	827.86	6e-102	9e-100	99.06	39	0	4548	23.92	827.863	1.8312
ggaa	ggaa|ttcc	0.0118679107100	0.0099528609744	14082	11809.68	9.6e-93	1.3e-90	89.88	40	0	42246	20.91	11809.677	1.1924
agcc	agcc|ggct	0.0112518446165	0.0095189069318	13351	11294.76	6.4e-80	8.7e-78	77.06	41	0	40053	19.35	11294.764	1.1821
cttc	cttc|gaag	0.0105447591822	0.0089888819548	12512	10665.86	1.1e-68	1.5e-66	65.82	42	267	37536	17.88	10665.857	1.1731
gcac	gcac|gtgc	0.0073127298133	0.0061167857105	8677	7257.94	2.4e-59	3.3e-57	56.49	43	280	26031	16.66	7257.939	1.1955
ccca	ccca|tggg	0.0136200330198	0.0119844784667	16161	14220.31	4.5e-58	6.1e-56	55.21	44	0	48483	16.27	14220.315	1.1365
cagc	cagc|gctg	0.0115771544826	0.0100927886606	13737	11975.71	1.5e-56	2.0e-54	53.70	45	927	41211	16.09	11975.709	1.1471
cacc	cacc|ggtg	0.0096067543093	0.0085711972364	11399	10170.25	1.8e-33	2.4e-31	30.62	46	317	34197	12.18	10170.248	1.1208
gcca	gcca|tggc	0.0094617975814	0.0084799625454	11227	10061.99	1.2e-30	1.6e-28	27.78	47	408	33681	11.61	10061.993	1.1158
aagg	aagg|cctt	0.0101663547007	0.0091946486643	12063	10910.01	5.7e-28	7.7e-26	25.11	48	0	36189	11.04	10910.012	1.1057
acac	acac|gtgt	0.0078175500459	0.0070330562304	9276	8345.15	5e-24	6.8e-22	21.17	49	1360	27828	10.19	8345.150	1.1115
aggc	aggc|gcct	0.0110310384380	0.0101047032099	13089	11989.85	1.4e-23	1.9e-21	20.72	50	568	39267	10.04	11989.847	1.0917
; Host name	rsat
; Job started	2026-07-10.105855
; Job done	2026-07-10.105855
; Seconds	0.46
;	user	0.46
;	system	0.03
;	cuser	0.27
;	csystem	0.03
