"Fossies" - the Fresh Open Source Software Archive

Member "augustus-3.3.3/config/species/amphimedon/amphimedon_parameters.cfg" (22 May 2019, 6892 Bytes) of package /linux/misc/augustus-3.3.3.tar.gz:


As a special service "Fossies" has tried to format the requested text file into HTML format (style: standard) with prefixed line numbers. Alternatively you can here view or download the uninterpreted source code file. See also the latest Fossies "Diffs" side-by-side code changes report for "amphimedon_parameters.cfg": 3.3.2_vs_3.3.3.

    1 #
    2 # amphimedon parameters. 
    3 # Amphimedon queenslandica (formerly Reniera sp.)
    4 # Mario Stanke (mstanke@gwdg.de)
    5 # date : 21.1.2008
    6 #
    7 
    8 #
    9 # Properties for augustus
   10 #------------------------------------
   11 /augustus/verbosity 3     # 0-3, 0: only print the necessary
   12 maxDNAPieceSize    200000 # maximum segment that is predicted in one piece
   13 stopCodonExcludedFromCDS false # make this 'true' if the CDS includes the stop codon (training and prediction)
   14 
   15 # gff output options:
   16 protein             on    # output predicted protein sequence
   17 codingseq           off   # output the coding sequence
   18 cds                 on    # output 'cds' as feature for exons
   19 start               on    # output start codons (translation start)
   20 stop                on    # output stop codons  (translation stop)
   21 introns             on    # output introns
   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 
   26 checkExAcc          off   # internal parameter for extrinsic accuracy
   27 
   28 # alternative transcripts and posterior probabilities
   29 sample                      100   # the number of sampling iterations
   30 alternatives-from-sampling  false # output alternative transcripts
   31 alternatives-from-evidence  false # output alternative transcripts (based on  hints)
   32 minexonintronprob           0.08  # minimal posterior probability of all (coding) exons
   33 minmeanexonintronprob       0.4   # minimal geometric mean of the posterior probs of introns and exons
   34 maxtracks                   -1    # maximum number of reported transcripts per gene (-1: no limit)
   35 keep_viterbi                true  # set to true if all Viterbi transcripts should be reported
   36 uniqueCDS                   true  # don't report transcripts that differ only in the UTR
   37 UTR                         off   # predict untranslated regions
   38 
   39 #
   40 # 
   41 # The rest of the file contains mainly meta parameters used for training.
   42 #
   43 
   44 # global constants
   45 # ----------------------------
   46 
   47 /Constant/trans_init_window           8
   48 /Constant/ass_upwindow_size           30
   49 /Constant/ass_start                   2
   50 /Constant/ass_end                     1
   51 /Constant/dss_start                   2
   52 /Constant/dss_end                     3
   53 /Constant/init_coding_len	      1
   54 /Constant/intterm_coding_len	      5
   55 /Constant/tss_upwindow_size           45
   56 /Constant/decomp_num_at               1
   57 /Constant/decomp_num_gc               1
   58 /Constant/gc_range_min		      0.32   # This range has an effect only when decomp_num_steps>1. 
   59 /Constant/gc_range_max                0.73   # States the minimal and maximal percentage of c or g
   60 /Constant/decomp_num_steps            1
   61 /Constant/min_coding_len              201    # no gene with a coding sequence shorter than this is predicted
   62 /Constant/probNinCoding               0.23
   63 /Constant/amberprob                   0.20   # Prob(stop codon = tag), if 0 tag is assumed to code for amino acid
   64 /Constant/ochreprob                   0.51   # Prob(stop codon = taa), if 0 taa is assumed to code for amino acid
   65 /Constant/opalprob                    0.29   # Prob(stop codon = tga), if 0 tga is assumed to code for amino acid
   66 /Constant/subopt_transcript_threshold 0.7
   67 /Constant/almost_identical_maxdiff    10
   68 
   69 # type of weighing, one of  1 = equalWeights, 2 = gcContentClasses, 3 = multiNormalKernel
   70 /BaseCount/weighingType    3
   71 # file with the weight matrix (only for multiNormalKernel type weighing)
   72 /BaseCount/weightMatrixFile   amphimedon_weightmatrix.txt # change this to your species if at all necessary
   73 
   74 # Properties for IGenicModel
   75 # ----------------------------
   76 /IGenicModel/verbosity      0
   77 /IGenicModel/infile         amphimedon_igenic_probs.pbl   # change this and the other five filenames *_probs.pbl below to your species
   78 /IGenicModel/outfile        amphimedon_igenic_probs.pbl
   79 /IGenicModel/patpseudocount 0.5
   80 /IGenicModel/k              4        # order of the Markov chain for content model, keep equal to /ExonModel/k
   81 
   82 # Properties for ExonModel
   83 # ----------------------------
   84 /ExonModel/verbosity          3
   85 /ExonModel/infile             amphimedon_exon_probs.pbl
   86 /ExonModel/outfile            amphimedon_exon_probs.pbl
   87 /ExonModel/patpseudocount     1.90625
   88 /ExonModel/minPatSum          233.3
   89 /ExonModel/k                  4       # order of the Markov chain for content model
   90 /ExonModel/etorder	      2
   91 /ExonModel/etpseudocount      3
   92 /ExonModel/exonlengthD        2000    # beyond this the distribution is geometric
   93 /ExonModel/maxexonlength      15000
   94 /ExonModel/slope_of_bandwidth 0.084375
   95 /ExonModel/minwindowcount     6
   96 /ExonModel/tis_motif_memory   2
   97 /ExonModel/tis_motif_radius   2
   98  
   99 # Properties for IntronModel
  100 # ----------------------------
  101 /IntronModel/verbosity          0
  102 /IntronModel/infile             amphimedon_intron_probs.pbl
  103 /IntronModel/outfile            amphimedon_intron_probs.pbl
  104 /IntronModel/patpseudocount     5.0
  105 /IntronModel/k                  4     # order of the Markov chain for content model, keep equal to /ExonModel/k
  106 /IntronModel/slope_of_bandwidth 0.4
  107 /IntronModel/minwindowcount     4
  108 /IntronModel/asspseudocount     0.01525
  109 /IntronModel/dsspseudocount     0.0005
  110 /IntronModel/dssneighborfactor  0.00173
  111 #/IntronModel/splicefile         amphimedon_splicefile.txt # this optional file contains additional windows around splice sites for training, uncomment if you have one
  112 /IntronModel/sf_with_motif	false           # if true the splice file is also used to train the branch point region
  113 /IntronModel/d                  950
  114 /IntronModel/ass_motif_memory   2
  115 /IntronModel/ass_motif_radius   4
  116 
  117 # Properties for UtrModel
  118 # ----------------------------
  119 /UtrModel/verbosity             3
  120 /UtrModel/infile                amphimedon_utr_probs.pbl
  121 /UtrModel/outfile               amphimedon_utr_probs.pbl
  122 /UtrModel/k                     4
  123 /UtrModel/utr5patternweight     0.875
  124 /UtrModel/utr3patternweight     0.875
  125 /UtrModel/patpseudocount        1
  126 /UtrModel/tssup_k               3
  127 /UtrModel/tssup_patpseudocount  1
  128 /UtrModel/slope_of_bandwidth    0.25
  129 /UtrModel/minwindowcount        3
  130 /UtrModel/exonlengthD           800
  131 /UtrModel/maxexonlength         1200
  132 /UtrModel/max3singlelength      1200
  133 /UtrModel/max3termlength        1200
  134 /UtrModel/tss_start             8
  135 /UtrModel/tss_end               3
  136 /UtrModel/tata_start            2
  137 /UtrModel/tata_end              10
  138 /UtrModel/tata_pseudocount      5
  139 /UtrModel/d_tss_tata_min        26      # minimal distance between start of tata box (if existent) and tss 
  140 /UtrModel/d_tss_tata_max        37      # maximal distance between start of tata box (if existent) and tss
  141 /UtrModel/d_polyasig_cleavage   14      # the transcription end is predicted this many bases after the polyadenylation signal
  142 /UtrModel/d_polya_cleavage_min  6
  143 /UtrModel/d_polya_cleavage_max  18
  144 /UtrModel/prob_polya            0.75