application: restrict [
  documentation: "Report restriction enzyme cleavage sites in
                  a nucleotide sequence"
  groups: "Nucleic:Restriction"
]

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

  seqall: sequence [
    parameter: "Y"
    type: "DNA"
  ]

  datafile: datafile [
    default: ""
    information: "Restriction enzyme data file (optional)"
    knowntype: "restriction enzyme data"
    nullok: "Y"
  ]

endsection: input

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

  integer: sitelen [
    standard: "Y"
    minimum: "2"
    maximum: "20"
    default: "4"
    information: "Minimum recognition site length"
    help: "This sets the minimum length of the restriction enzyme
           recognition site. Any enzymes with sites shorter than this will be
           ignored."
  ]

  string: enzymes [
    standard: "Y"
    default: "all"
    information: "Comma separated enzyme list"
    help: "The name 'all' reads in all enzyme names from the REBASE
           database. You can specify enzymes by giving their names with
           commas between then, such as: 'HincII,hinfI,ppiI,hindiii'. \
           The case of the names is not important. You can specify a file of
           enzyme names to read in by giving the name of the file holding the
           enzyme names with a '@' character in front of it, for example,
           '@enz.list'. \
           Blank lines and lines starting with a hash character or '!' are
           ignored and all other lines are concatenated together with a comma
           character ',' and then treated as the list of enzymes to search
           for. \
           An example of a file of enzyme names is: \
           ! my enzymes \
           HincII, ppiII \
           ! other enzymes \
           hindiii \
           HinfI \
           PpiI"
    knowntype: "enzyme list"
  ]

endsection: required

section: advanced [
  information: "Advanced section"
  type: "page"
]

  integer: min [
    minimum: "1"
    maximum: "1000"
    default: "1"
    information: "Minimum cuts per RE"
    help: "This sets the minimum number of cuts for any restriction
           enzyme that will be considered. Any enzymes that cut fewer times
           than this will be ignored."
  ]

  integer: max [
    minimum: "$(min)"
    maximum: "2000000000"
    default: "2000000000"
    information: "Maximum cuts per RE"
    help: "This sets the maximum number of cuts for any restriction
           enzyme that will be considered. Any enzymes that cut more times
           than this will be ignored."
  ]

  boolean: solofragment [
    default: "N"
    information: "List individual enzymes with their fragments"
    help: "This gives the fragment lengths of the forward sense strand
           produced by complete restriction by each restriction enzyme on
           its own. Results are added to the tail section of the report."
  ]

  boolean: single [
    default: "N"
    information: "Force single site only cuts"
    help: "If this is set then this forces the values of the mincuts
           and maxcuts qualifiers to both be 1. Any other value you may have
           set them to will be ignored."
  ]

  boolean: blunt [
    default: "Y"
    information: "Allow blunt end cutters"
    help: "This allows those enzymes which cut at the same position on
           the forward and reverse strands to be considered."
  ]

  boolean: sticky [
    default: "Y"
    information: "Allow sticky end cutters"
    help: "This allows those enzymes which cut at different positions
           on the forward and reverse strands, leaving an overhang, to be
           considered."
  ]

  boolean: ambiguity [
    default: "Y"
    information: "Allow ambiguous matches"
    help: "This allows those enzymes which have one or more 'N'
           ambiguity codes in their pattern to be considered"
  ]

  boolean: plasmid [
    default: "N"
    information: "Allow circular DNA"
    help: "If this is set then this allows searches for restriction
           enzyme recognition site and cut postions that span the end of the
           sequence to be considered."
  ]

  boolean: commercial [
    default: "Y"
    information: "Only enzymes with suppliers"
    help: "If this is set, then only those enzymes with a commercial
           supplier will be searched for. This qualifier is ignored if you
           have specified an explicit list of enzymes to search for, rather
           than searching through 'all' the enzymes in the REBASE database.
           It is assumed that, if you are asking for an explicit enzyme, then
           you probably know where to get it from and so all enzymes names
           that you have asked to be searched for, and which cut, will be
           reported whether or not they have a commercial supplier."
  ]

endsection: advanced

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

  boolean: limit [
    default: "Y"
    information: "Limits reports to one isoschizomer"
    help: "This limits the reporting of enzymes to just one enzyme
           from each group of isoschizomers. The enzyme chosen to represent
           an isoschizomer group is the prototype indicated in the data file
           'embossre.equ', which is created by the program 'rebaseextract'.
           If you prefer different prototypes to be used, make a copy of
           embossre.equ in your home directory and edit it. If this value is
           set to be false then all of the input enzymes will be reported.
           You might like to set this to false if you are supplying an
           explicit set of enzymes rather than searching 'all' of them."
  ]

  boolean: alphabetic [
    default: "N"
    information: "Sort output alphabetically"
  ]

  boolean: fragments [
    default: "N"
    information: "Show fragment lengths"
    help: "This gives the fragment lengths of the forward sense strand
           produced by complete restriction using all of the input enzymes
           together. Results are added to the tail section of the report."
  ]

  boolean: name [
    default: "N"
    information: "Show sequence name"
  ]

  report: outfile [
    parameter: "Y"
    rformat: "table"
    rscoreshow: "N"
    multiple: "Y"
    taglist: "str:enzyme=Enzyme_name str:site=Restriction_site
              int:5prime int:3prime int:5primerev int:3primerev"
    precision: "0"
  ]

endsection: output