application: diffseq [
  documentation: "Compare and report features of two similar sequences"
  groups: "Alignment:Differences"
  gui: "yes"
  batch: "yes"
  cpu: "medium"
  relations: "EDAM_topic:0182 Sequence alignment"
  relations: "EDAM_topic:0160 Sequence sites and features"
  relations: "EDAM_operation:0256 Feature comparison"
]

section: input [
  information: "Input section"
  type: "page"
]

  sequence: asequence [
    parameter: "Y"
    type: "any"
    features: "Y"
    relations: "EDAM_data:0849 Sequence record"
  ]

  sequence: bsequence [
    parameter: "Y"
    type: "@($(acdprotein) ? stopprotein : nucleotide)"
    features: "Y"
    relations: "EDAM_data:0849 Sequence record"
  ]

endsection: input

section: required [
  information: "Required section"
  type: "page"
]

  integer: wordsize [
    standard: "Y"
    default: "10"
    minimum: "2"
    information: "Word size"
    help: "The similar regions between the two sequences are found by
           creating a hash table of 'wordsize'd subsequences. 10 is a
           reasonable default. Making this value larger (20?) may speed up
           the program slightly, but will mean that any two differences
           within 'wordsize' of each other will be grouped as a single region
           of difference. This value may be made smaller (4?) to improve the
           resolution of nearby differences, but the program will go much
           slower."
    relations: "EDAM_data:1250 Word size"
  ]

endsection: required

section: additional [
  information: "Additional section"
  type: "page"
]

  boolean: globaldifferences [
    additional: "Y"
    default: "N"
    information: "Force reporting of differences at the start
                  and end"
    help: "Normally this program will find regions of identity that
           are the length of the specified word-size or greater and will then
           report the regions of difference between these matching regions.
           This works well and is what most people want if they are working
           with long overlapping nucleic acid sequences. You are usually not
           interested in the non-overlapping ends of these sequences. If you
           have protein sequences or short RNA sequences however, you will be
           interested in differences at the very ends . It this option is
           set to be true then the differences at the ends will also be
           reported."
    relations: "EDAM_data:2527 Parameter"
  ]

endsection: additional

section: output [
  information: "Output section"
  type: "page"
]

  report: outfile [
    parameter: "Y"
    rformat: "diffseq"
    taglist: "int:start int:end int:length str:name str:sequence
              str:first_feature str:second_feature"
    relations: "EDAM_data:1255 Feature record"
  ]

  featout: aoutfeat [
    parameter: "Y"
    default: "$(asequence.name).diffgff"
    help: "File for output of first sequence's features"
    type: "@($(acdprotein) ? protein : nucleotide)"
    relations: "EDAM_data:1255 Feature record"
  ]

  featout: boutfeat [
    parameter: "Y"
    default: "$(bsequence.name).diffgff"
    help: "File for output of second sequence's features"
    type: "@($(acdprotein) ? protein : nucleotide)"
    relations: "EDAM_data:1255 Feature record"
  ]

endsection: output