Debian Codegraph @

config/species/pisaster/pisaster_parameters.cfg

raw
1 #
2 # pisaster parameters. (Pisaster ochraceus, ochre starfish)
3 #
4 # date : 2018
5 #
6
7 #
8 # Properties for augustus
9 #------------------------------------
10 /augustus/verbosity 3 # 0-3, 0: only print the necessary
11 maxDNAPieceSize 500000 # maximum segment that is predicted in one piece
12 stopCodonExcludedFromCDS false # 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 cds on # output 'cds' as feature for exons
18 start on # output start codons (translation start)
19 stop on # output stop codons (translation stop)
20 introns on # output introns
21 tss on # output transcription start site
22 tts on # output transcription termination site
23 print_utr off # output 5'UTR and 3'UTR lines in addition to exon lines
24
25 checkExAcc off # internal parameter for extrinsic accuracy
26
27 # alternative transcripts and posterior probabilities
28 sample 100 # the number of sampling iterations
29 alternatives-from-sampling false # output alternative suboptimal transcripts
30 alternatives-from-evidence false # output alternative transcripts based on explicit evidence from hints
31 minexonintronprob 0.08 # minimal posterior probability of all (coding) exons
32 minmeanexonintronprob 0.4 # minimal geometric mean of the posterior probs of introns and exons
33 maxtracks -1 # maximum number of reported transcripts per gene (-1: no limit)
34 keep_viterbi true # set to true if all Viterbi transcripts should be reported
35 uniqueCDS true # don't report transcripts that differ only in the UTR
36 UTR off # predict untranslated regions
37
38 #
39 #
40 # The rest of the file contains mainly meta parameters used for training.
41 #
42
43 # global constants
44 # ----------------------------
45
46 /Constant/trans_init_window 25
47 /Constant/ass_upwindow_size 50
48 /Constant/ass_start 3
49 /Constant/ass_end 2
50 /Constant/dss_start 1
51 /Constant/dss_end 4
52 /Constant/init_coding_len 0
53 /Constant/intterm_coding_len 6
54 /Constant/tss_upwindow_size 45
55 /Constant/decomp_num_at 1
56 /Constant/decomp_num_gc 1
57 /Constant/gc_range_min 0.32 # This range has an effect only when decomp_num_steps>1.
58 /Constant/gc_range_max 0.73 # States the minimal and maximal percentage of c or g
59 /Constant/decomp_num_steps 1 # I recommend keeping this to 1 for most species.
60 /Constant/min_coding_len 201 # no gene with a coding sequence shorter than this is predicted
61 /Constant/probNinCoding 0.23 # divide this by .25 to get a malus for making one masked letter part of the coding sequence
62 /Constant/amberprob 0.243 # Prob(stop codon = tag), if 0 tag is assumed to code for amino acid
63 /Constant/ochreprob 0.374 # Prob(stop codon = taa), if 0 taa is assumed to code for amino acid
64 /Constant/opalprob 0.383 # Prob(stop codon = tga), if 0 tga is assumed to code for amino acid
65 /Constant/subopt_transcript_threshold 0.7
66 /Constant/almost_identical_maxdiff 10
67
68 # type of weighing, one of 1 = equalWeights, 2 = gcContentClasses, 3 = multiNormalKernel
69 /BaseCount/weighingType 3
70 # file with the weight matrix (only for multiNormalKernel type weighing)
71 /BaseCount/weightMatrixFile pisaster_weightmatrix.txt # change this to your species if at all necessary
72
73 # Properties for IGenicModel
74 # ----------------------------
75 /IGenicModel/verbosity 0
76 /IGenicModel/infile pisaster_igenic_probs.pbl # change this and the other five filenames *_probs.pbl below to your species
77 /IGenicModel/outfile pisaster_igenic_probs.pbl
78 /IGenicModel/patpseudocount 5.0
79 /IGenicModel/k 4 # order of the Markov chain for content model, keep equal to /ExonModel/k
80
81 # Properties for ExonModel
82 # ----------------------------
83 /ExonModel/verbosity 3
84 /ExonModel/infile pisaster_exon_probs.pbl
85 /ExonModel/outfile pisaster_exon_probs.pbl
86 /ExonModel/patpseudocount 1.625
87 /ExonModel/minPatSum 287.5
88 /ExonModel/k 4 # order of the Markov chain for content model
89 /ExonModel/etorder 2
90 /ExonModel/etpseudocount 3
91 /ExonModel/exonlengthD 2000 # beyond this the distribution is geometric
92 /ExonModel/maxexonlength 15000
93 /ExonModel/slope_of_bandwidth 0.05
94 /ExonModel/minwindowcount 1
95 /ExonModel/tis_motif_memory 1
96 /ExonModel/tis_motif_radius 0
97
98 # Properties for IntronModel
99 # ----------------------------
100 /IntronModel/verbosity 0
101 /IntronModel/infile pisaster_intron_probs.pbl
102 /IntronModel/outfile pisaster_intron_probs.pbl
103 /IntronModel/patpseudocount 3.75
104 /IntronModel/k 4 # order of the Markov chain for content model, keep equal to /ExonModel/k
105 /IntronModel/slope_of_bandwidth 0.4
106 /IntronModel/minwindowcount 4
107 /IntronModel/asspseudocount 0.007875
108 /IntronModel/dsspseudocount 0.0005
109 /IntronModel/dssneighborfactor 0.007525
110 #/IntronModel/splicefile pisaster_splicefile.txt # this optional file contains additional windows around splice sites for training, uncomment if you have one
111 /IntronModel/sf_with_motif false # if true the splice file is also used to train the branch point region
112 /IntronModel/d 950 # constraint: this must be larger than 4 + /Constant/dss_end + /Constant/ass_upwindow_size + /Constant/ass_start
113 /IntronModel/ass_motif_memory 2
114 /IntronModel/ass_motif_radius 2
115
116 # Properties for UtrModel
117 # ----------------------------
118 /UtrModel/verbosity 3
119 /UtrModel/infile pisaster_utr_probs.pbl
120 /UtrModel/outfile pisaster_utr_probs.pbl
121 /UtrModel/k 4
122 /UtrModel/utr5patternweight 0.5
123 /UtrModel/utr3patternweight 0.5
124 /UtrModel/patpseudocount 1
125 /UtrModel/tssup_k 0
126 /UtrModel/tssup_patpseudocount 1
127 /UtrModel/slope_of_bandwidth 0.2375
128 /UtrModel/minwindowcount 3
129 /UtrModel/exonlengthD 800
130 /UtrModel/maxexonlength 1800
131 /UtrModel/max3singlelength 2000
132 /UtrModel/max3termlength 1500
133 /UtrModel/tss_start 8
134 /UtrModel/tss_end 5
135 /UtrModel/tata_start 2
136 /UtrModel/tata_end 10
137 /UtrModel/tata_pseudocount 2
138 /UtrModel/d_tss_tata_min 26 # minimal distance between start of tata box (if existent) and tss
139 /UtrModel/d_tss_tata_max 37 # maximal distance between start of tata box (if existent) and tss
140 /UtrModel/polyasig_consensus aataaa # polyadenylation signal training not fully automated yet
141 /UtrModel/d_polyasig_cleavage 14 # the transcription end is predicted this many bases after the polyadenylation signal
142 /UtrModel/d_polya_cleavage_min 7
143 /UtrModel/d_polya_cleavage_max 19
144 /UtrModel/prob_polya 0.4
145 /UtrModel/tts_motif_memory 1