; oligo-analysis  -sort -v 1 -return occ,freq,mseq,proba,rank,zscore -l 6 -1str -noov -thosig 0 -thmssig 0 -org Saccharomyces_cerevisiae -bg intergenic -i data/utr3/orthologs/stricto/purged/YAL060W_utr3_500_ortho_purged.fasta -o data/utr3/orthologs/stricto/ORF-wise_oligos/YAL060W_utr3_500_ortho_oligos_6nt-1str-noov_osig0_msig0
; Citation: van Helden et al. (1998). J Mol Biol 281(5), 827-42. 
; Detection of over-represented words
; Oligomer length              	6
; Input file                   	data/utr3/orthologs/stricto/purged/YAL060W_utr3_500_ortho_purged.fasta
; Input format                 	fasta
; Output file                  	data/utr3/orthologs/stricto/ORF-wise_oligos/YAL060W_utr3_500_ortho_oligos_6nt-1str-noov_osig0_msig0
; Discard overlapping matches
; Counted on a single strand
; Background model             	intergenic
; Organism                     	Saccharomyces_cerevisiae
; Method                       	Frequency file
; Expected frequency file      	/Users/jvanheld/rsa-tools/data/genomes/Saccharomyces_cerevisiae/oligo-frequencies/6nt_intergenic_Saccharomyces_cerevisiae-1str.freq
; Sequence type                	DNA
; Nb of sequences              	6
; Sum of sequence lengths      	3000
; discarded occurrences        	85	 (contain other letters than ACGT)
; nb possible positions        	2885
; total oligo occurrences      	2475
; total overlapping occurrences	40
; total non overlapping occ    	2435
; alphabet size                	4
; nb possible oligomers        	4096
; threshold on occ sig         	0
; threshold on matching seq sig	0
; threshold on occ proba       	0.000244140625
; threshold on match. seq proba	0.000244140625
; Sequences:
;	cerevisiae_SGD_BDH1_YAL060W	500
;	paradoxus_MIT_459_YAL060W	500
;	mikatae_MIT_37_YAL060W	500
;	mikatae_WashU_Contig1893.3_YAL060W	500
;	kudriavzevii_WashU_Contig1874.1_YAL060W	500
;	bayanus_MIT_42_YAL060W	500
;
; column headers
;	1	seq            	oligomer sequence
;	2	id             	oligomer identifier
;	3	observed_freq  	observed relative frequency
;	4	expected_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	zscore         	z-score (normal)
;	11	ovl_occ        	number of overlapping occurrences (discarded from the count)
;	12	ms             	number of matching sequences
;	13	exp_ms         	expected number of matching sequences
;	14	ms_P           	matching sequence probability (binomial)
;	15	ms_E           	E-value for matching sequences (binomial)
;	16	ms_sig         	matching sequenc significance (binomial)
;	17	ms_freq        	observed matching sequence frequency
;	18	exp_msf        	expected matching sequence frequency
;	19	rank           	rank
;seq	id	observed_freq	expected_freq	occ	exp_occ	occ_P	occ_E	occ_sig	zscore	ovl_occ	ms	exp_ms	ms_P	ms_E	ms_sig	ms_freq	exp_msf	rank
gagctg	gagctg	0.0044444444444	0.0001099948446	11	0.31	4.9e-14	2.0e-10	9.70	19.16	0	4	0.32	0.00011	0.44	0.4	0.66667	0.05299	1
agctgc	agctgc	0.0028282828283	0.0001389408563	7	0.40	2.1e-07	8.7e-04	3.06	10.49	0	5	0.40	7.4e-06	0.03	1.5	0.83333	0.06647	2
tctaag	tctaag	0.0028282828283	0.0001934812363	7	0.55	1.9e-06	7.7e-03	2.11	8.68	0	5	0.55	3.5e-05	0.14	0.8	0.83333	0.09134	3
ccaaga	ccaaga	0.0028282828283	0.0002340056527	7	0.67	6.5e-06	2.7e-02	1.58	7.75	0	5	0.66	8.5e-05	0.35	0.5	0.83333	0.10939	4
ctaaga	ctaaga	0.0028282828283	0.0002376619910	7	0.68	7.2e-06	2.9e-02	1.53	7.68	0	5	0.67	9.2e-05	0.38	0.4	0.83333	0.11100	5
gctgcc	gctgcc	0.0016161616162	0.0000898849838	4	0.26	0.00015	6.1e-01	0.21	7.37	0	4	0.26	5e-05	0.21	0.7	0.66667	0.04352	6
acagac	acagac	0.0020202020202	0.0001459488381	5	0.42	7.4e-05	3.1e-01	0.52	7.09	0	5	0.42	9.3e-06	0.038	1.4	0.83333	0.06970	7
gaacag	gaacag	0.0024242424242	0.0002099347587	6	0.60	3.8e-05	1.6e-01	0.80	6.98	0	5	0.59	5.2e-05	0.21	0.7	0.83333	0.09871	8
gcgatg	gcgatg	0.0020202020202	0.0001526521250	5	0.44	9.2e-05	3.8e-01	0.42	6.91	0	5	0.44	1.2e-05	0.047	1.3	0.83333	0.07278	9
gagggg	gagggg	0.0016161616162	0.0001011586936	4	0.29	0.00023	9.5e-01	0.02	6.89	0	4	0.29	7.9e-05	0.32	0.5	0.66667	0.04884	10
gcaaag	gcaaag	0.0024242424242	0.0002510685649	6	0.72	0.00010	4.2e-01	0.38	6.24	0	5	0.70	0.00012	0.48	0.3	0.83333	0.11688	11
atgagc	atgagc	0.0020202020202	0.0001883014237	5	0.54	0.00024	9.9e-01	0.01	6.08	0	5	0.53	3.1e-05	0.13	0.9	0.83333	0.08901	12
ccaata	ccaata	0.0024242424242	0.0002781864074	6	0.79	0.00018	7.2e-01	0.14	5.84	0	5	0.77	0.00019	0.77	0.1	0.83333	0.12866	13
gaaagc	gaaagc	0.0024242424242	0.0002934211505	6	0.84	0.00023	9.6e-01	0.02	5.64	0	5	0.81	0.00024	0.99	0.0	0.83333	0.13521	14
; Job started 2004_04_02.113951
; Job done    2004_04_02.113952