Debian Codegraph @

config/species/zebrafish/zebrafish_parameters.cfg

raw
1 #
2 # zebrafish parameters. (Danio rerio)
3 #
4 # date : May 2nd, 2014
5 #
6
7 #
8 # Properties for augustus
9 #------------------------------------
10 /augustus/verbosity 3 # 0-3, 0: only print the necessary
11 maxDNAPieceSize 1000000 # maximum segment that is predicted in one piece
12 stopCodonExcludedFromCDS true # make this 'true' if the CDS does not include the stop codon (training and prediction)
13
14 # gff output options:
15 protein on # output predicted protein sequence
16 codingseq off # output the coding sequence
17 exonnames off # output 'single', 'initial', 'terminal' or 'internal' for CDS
18 cds on # output 'cds' as feature for exons
19 introns off # output introns
20 start on # output start codons (translation start)
21 stop on # output stop codons (translation stop)
22 tss on # output transcription start site
23 tts on # output transcription termination site
24 print_utr off # output 5'UTR and 3'UTR lines in addition to exon lines
25 gff3 off # output in gff3 format (with exon IDs and Parents)
26
27 checkExAcc off # internal parameter for extrinsic accuracy
28
29 # alternative transcripts and posterior probabilities
30 sample 100 # the number of sampling iterations
31 alternatives-from-sampling false # output alternative suboptimal transcripts
32 alternatives-from-evidence false # output alternative transcripts based on explicit evidence from hints
33 minexonintronprob 0.08 # minimal posterior probability of all (coding) exons
34 minmeanexonintronprob 0.4 # minimal geometric mean of the posterior probs of introns and exons
35 maxtracks -1 # maximum number of reported transcripts per gene (-1: no limit)
36 keep_viterbi true # set to true if all Viterbi transcripts should be reported
37 uniqueCDS true # don't report transcripts that differ only in the UTR
38 UTR off # predict untranslated regions
39
40 #
41 #
42 # The rest of the file contains mainly meta parameters used for training.
43 #
44
45 # global constants
46 # ----------------------------
47
48 /Constant/trans_init_window 22
49 /Constant/ass_upwindow_size 33
50 /Constant/ass_start 3
51 /Constant/ass_end 2
52 /Constant/dss_start 3
53 /Constant/dss_end 4
54 /Constant/init_coding_len 15
55 /Constant/intterm_coding_len 5
56 /Constant/tss_upwindow_size 45
57 /Constant/decomp_num_at 1
58 /Constant/decomp_num_gc 1
59 /Constant/gc_range_min 0.30 # This range has an effect only when decomp_num_steps>1.
60 /Constant/gc_range_max 0.50 # States the minimal and maximal percentage of c or g
61 /Constant/decomp_num_steps 2 # I recommend keeping this to 1 for most species.
62 /Constant/min_coding_len 201 # no gene with a coding sequence shorter than this is predicted
63 /Constant/probNinCoding 0.23 # divide this by .25 to get a malus for making one masked letter part of the coding sequence
64 /Constant/amberprob 0.18 # Prob(stop codon = tag), if 0 tag is assumed to code for amino acid
65 /Constant/ochreprob 0.35 # Prob(stop codon = taa), if 0 taa is assumed to code for amino acid
66 /Constant/opalprob 0.48 # Prob(stop codon = tga), if 0 tga is assumed to code for amino acid
67 /Constant/subopt_transcript_threshold 0.86
68 /Constant/almost_identical_maxdiff 10
69
70 # type of weighing, one of 1 = equalWeights, 2 = gcContentClasses, 3 = multiNormalKernel
71 /BaseCount/weighingType 3
72 # file with the weight matrix (only for multiNormalKernel type weighing)
73 /BaseCount/weightMatrixFile zebrafish_weightmatrix.txt # change this to your species if at all necessary
74
75 # Properties for IGenicModel
76 # ----------------------------
77 /IGenicModel/verbosity 0
78 /IGenicModel/infile zebrafish_igenic_probs.pbl # change this and the other five filenames *_probs.pbl below to your species
79 /IGenicModel/outfile zebrafish_igenic_probs.pbl
80 /IGenicModel/patpseudocount 5.0
81 /IGenicModel/k 4 # order of the Markov chain for content model, keep equal to /ExonModel/k
82
83 # Properties for ExonModel
84 # ----------------------------
85 /ExonModel/verbosity 3
86 /ExonModel/infile zebrafish_exon_probs.pbl
87 /ExonModel/outfile zebrafish_exon_probs.pbl
88 /ExonModel/patpseudocount 5.0
89 /ExonModel/minPatSum 233.3
90 /ExonModel/k 4 # order of the Markov chain for content model
91 /ExonModel/etorder 2
92 /ExonModel/etpseudocount 3
93 /ExonModel/exonlengthD 3000 # beyond this the distribution is geometric
94 /ExonModel/maxexonlength 15000
95 /ExonModel/slope_of_bandwidth 0.2
96 /ExonModel/minwindowcount 10
97 /ExonModel/tis_motif_memory 3
98 /ExonModel/tis_motif_radius 2
99
100 # Properties for IntronModel
101 # ----------------------------
102 /IntronModel/verbosity 0
103 /IntronModel/infile zebrafish_intron_probs.pbl
104 /IntronModel/outfile zebrafish_intron_probs.pbl
105 /IntronModel/patpseudocount 5.0
106 /IntronModel/k 4 # order of the Markov chain for content model, keep equal to /ExonModel/k
107 /IntronModel/slope_of_bandwidth 0.4
108 /IntronModel/minwindowcount 4
109 /IntronModel/asspseudocount 0.00266
110 /IntronModel/dsspseudocount 0.0005
111 /IntronModel/dssneighborfactor 0.00173
112 #/IntronModel/splicefile zebrafish_splicefile.txt # this optional file contains additional windows around splice sites for training, uncomment if you have one
113 /IntronModel/sf_with_motif false # if true the splice file is also used to train the branch point region
114 /IntronModel/d 586 # constraint: this must be larger than 4 + /Constant/dss_end + /Constant/ass_upwindow_size + /Constant/ass_start
115 /IntronModel/ass_motif_memory 3
116 /IntronModel/ass_motif_radius 3
117
118 # Properties for UtrModel
119 # ----------------------------
120 /UtrModel/verbosity 3
121 /UtrModel/infile zebrafish_utr_probs.pbl
122 /UtrModel/outfile zebrafish_utr_probs.pbl
123 /UtrModel/k 4
124 /UtrModel/utr5patternweight 0.3
125 /UtrModel/utr3patternweight 0.07
126 /UtrModel/patpseudocount 1
127 /UtrModel/tssup_k 0
128 /UtrModel/tssup_patpseudocount 1
129 /UtrModel/slope_of_bandwidth 0.1
130 /UtrModel/minwindowcount 3
131 /UtrModel/exonlengthD 1000
132 /UtrModel/maxexonlength 1500
133 /UtrModel/max3singlelength 3500
134 /UtrModel/max3termlength 3500
135 /UtrModel/tss_start 8
136 /UtrModel/tss_end 5
137 /UtrModel/tata_start 2
138 /UtrModel/tata_end 10
139 /UtrModel/tata_pseudocount 2
140 /UtrModel/d_tss_tata_min 26 # minimal distance between start of tata box (if existent) and tss
141 /UtrModel/d_tss_tata_max 37 # maximal distance between start of tata box (if existent) and tss
142 /UtrModel/polyasig_consensus aataaa # polyadenylation signal training not fully automated yet
143 /UtrModel/d_polyasig_cleavage 22 # the transcription end is predicted this many bases after the polyadenylation signal
144 /UtrModel/d_polya_cleavage_min 7
145 /UtrModel/d_polya_cleavage_max 19
146 /UtrModel/prob_polya 0.4
147 /UtrModel/tts_motif_memory 1