application: skipredundant
[
  documentation: "Remove redundant sequences from an input set"
  groups: "Edit"
  gui: "yes"
  batch: "yes"
  cpu: "low"
]





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

toggle: feature 
[
    information: "Use feature information"
    help: "Sequence feature information will be retained if this option is set."
]

seqset: sequences
[
    parameter: "Y"
    type: "gapany"
    features: "$(feature)"
    aligned: "N"
]

matrixf: datafile 
[
    additional: "Y"
    information: "Matrix file"
    protein: "$(acdprotein)"
    help: "This is the scoring matrix file used when comparing
           sequences. By default it is the file 'EBLOSUM62' (for proteins) or
           the file 'EDNAFULL' (for nucleic sequences). These files are
           found in the 'data' directory of the EMBOSS installation."
]

endsection: input





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

list: mode 
[
    standard: "Y"
    default: "1"
    minimum: "1"
    maximum: "1"
    values: "1: Single threshold percentage sequence similarity,
             2: Outside a range of acceptable threshold percentage similarities"
    help: "This option specifies whether to remove redundancy at a
           single threshold percentage sequence similarity or remove redundancy
           outside a range of acceptable threshold percentage similarity. All
           permutations of pair-wise sequence alignments are calculated for
           each set of input sequences in turn using the EMBOSS
           implementation of the Needleman and Wunsch global alignment
           algorithm. Redundant sequences are removed in one of two modes as
           follows: (i) If a pair of proteins achieve greater than a
           threshold percentage sequence similarity (specified by the user)
           the shortest sequence is discarded. (ii) If a pair of proteins
           have a percentage sequence similarity that lies outside an
           acceptable range (specified by the user) the shortest sequence is
           discarded."
    delimiter: ","
    codedelimiter: ":"
    header: "Redundancy removal options"
    information: "Select number"
]

float: threshold 
[
    standard: "@($(mode)==1)"
    information: "The percentage sequence identity redundancy
                  threshold."
    help: "This option specifies the percentage sequence identity redundancy
           threshold. The percentage sequence identity redundancy threshold 
           determines the redundancy calculation. If a pair of proteins
           achieve greater than this threshold the shortest sequence is
           discarded."
    default: "95.0"
]

float: minthreshold
[
    standard: "@($(mode)==2)"
    information: "The % sequence identity redundancy threshold
                  (lower limit)."
    help: "This option specifies the percentage sequence identity redundancy
           threshold (lower limit). The percentage sequence identity redundancy
           threshold determines the redundancy calculation. If a pair of
           proteins have a percentage sequence similarity that lies outside
           an acceptable range the shortest sequence is discarded."
    default: "30.0"
]

float: maxthreshold
[
    standard: "@($(mode)==2)"
    information: "The percentage sequence identity redundancy threshold
                  (upper limit)."
    help: "This option specifies the percentage sequence identity redundancy
           threshold (upper limit). The percentage sequence identity redundancy
           threshold determines the redundancy calculation. If a pair of
           proteins have a percentage sequence similarity that lies outside
           an acceptable range the shortest sequence is discarded."
    default: "90.0"
]

float: gapopen 
[
    standard: "Y"
    information: "Gap opening penalty"
    minimum: "0.0"
    maximum: "100.0"
    default: "@($(acdprotein)? 10.0 : 10.0 )"
    valid: "Floating point number from 1.0 to 100.0"
    expected: "10.0 for any sequence"
    help: "The gap open penalty is the score taken away when a gap is
           created. The best value depends on the choice of comparison
           matrix. The default value assumes you are using the EBLOSUM62
           matrix for protein sequences, and the EDNAFULL matrix for
           nucleotide sequences."
]

float: gapextend 
[
    standard: "Y"
    information: "Gap extension penalty"
    minimum: "0.0"
    maximum: "10.0"
    default: "@($(acdprotein)? 0.5 : 0.5 )"
    valid: "Floating point number from 0.0 to 10.0"
    expected: "0.5 for any sequence"
    help: "The gap extension, penalty is added to the standard gap
           penalty for each base or residue in the gap. This is how long gaps
           are penalized. Usually you will expect a few long gaps rather
           than many short gaps, so the gap extension penalty should be lower
           than the gap penalty. An exception is where one or both sequences
           are single reads with possible sequencing errors in which case
           you would expect many single base gaps. You can get this result by
           setting the gap open penalty to zero (or very low) and using the
           gap extension penalty to control gap scoring."
]

endsection: required




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

toggle: keepredundant 
[
    information: "Retain redundant sequences."
    help: "This option specifies whether to retain redundant
           sequences. If this option is set a file of redundant 
           sequences is written."
    default: "N"
]

endsection: advanced





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

seqoutall: outseq 
[
    parameter: "Y"
    features:  "$(feature)"
    extension: "keep"
]

seqoutall: redundantoutseq
[
    parameter: "Y"
    features:  "$(feature)"
    extension: "redundant"
]

endsection: output