application: ememe [
  documentation: "Multiple EM for motif elicitation"
  groups: "Protein:Motifs"
  embassy: "memenew"
  wrapper: "Y"
  external: "meme MEME package http://meme.sdsc.edu/meme/"
  relations: "EDAM_topic:0158 Sequence motifs"
  relations: "EDAM_operation:0238 Sequence motif discovery"
]

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

  seqset: dataset [
    information: "Set of sequences (not a USA!)"
    parameter: "Y"
    type: "any"
    help: "User must provide the full filename of a set of sequences,
           not an indirect reference, e.g. a USA is NOT acceptable."
    aligned: "N"
    relations: "EDAM_data:0849 Sequence record"
  ]

  infile: bfile [
    additional: "Y"
    default: ""
    nullok: "Y"
    information: "MEME background Markov model file (optional)"
    help: "The name of the file containing the background model for
           sequences. The background model is the model of random sequences
           used by MEME. The background model is used by MEME 1) during EM as
           the 'null model', 2) for calculating the log likelihood ratio of
           a motif, 3) for calculating the significance (E-value) of a motif,
           and, 4) for creating the position-specific scoring matrix
           (log-odds matrix). See application documentation for more
           information."
    knowntype: "background markov model meme"
    relations:  "EDAM_data:1364 Hidden Markov model"
  ]

  infile: plibfile [
    additional: "Y"
    default: ""
    nullok: "Y"
    information: "MEME dirichlet prior file (optional)"
    help: "The name of the file containing the Dirichlet prior in the
           format of file prior30.plib"
    knowntype: "dirichlet prior meme"
    relations:  "EDAM_data:1347 Dirichlet distribution"
  ]

endsection: input

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

endsection: required

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

  selection: mod [
    additional: "Y"
    casesensitive: "N"
    default: "zoops"
    header: "Distribution of motifs"
    help: "If you know how occurrences of motifs are distributed in
           the training set sequences, you can specify it with these options.
           The default distribution of motif occurrences is assumed to be
           zero or one occurrence per sequence. oops : One Occurrence Per
           Sequence. MEME assumes that each sequence in the dataset contains
           exactly one occurrence of each motif. This option is the fastest
           and most sensitive but the motifs returned by MEME may be 'blurry'
           if any of the sequences is missing them. zoops : Zero or One
           Occurrence Per Sequence. MEME assumes that each sequence may
           contain at most one occurrence of each motif. This option is
           useful when you suspect that some motifs may be missing from some
           of the sequences. In that case, the motifs found will be more
           accurate than using the first option. This option takes more
           computer time than the first option (about twice as much) and is
           slightly less sensitive to weak motifs present in all of the
           sequences. anr : Any Number of Repetitions. MEME assumes each
           sequence may contain any number of non-overlapping occurrences of
           each motif. This option is useful when you suspect that motifs
           repeat multiple times within a single sequence. In that case, the
           motifs found will be much more accurate than using one of the
           other options. This option can also be used to discover repeats
           within a single sequence. This option takes the much more computer
           time than the first option (about ten times as much) and is
           somewhat less sensitive to weak motifs which do not repeat within
           a single sequence than the other two options."
    information: "Select motif distribution"
    maximum: "1"
    minimum: "1"
    delimiter: ","
    values: "oops, zoops, anr"
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: nmotifs [
    additional: "Y"
    default: "1"
    information: "Maximum number of motifs to find"
    help: "The number of *different* motifs to search for. MEME will
           search for and output <n> motifs."
    relations: "EDAM_data:1694 Number of output entities"
  ]

  boolean: text [
    additional: "Y"
    default: "N"
    information: "Output in text format (default is HTML)"
    help: "Default output is in HTML"
    relations: "EDAM_data:2527 Parameter"
  ]

  selection: prior [
    additional: "Y"
    casesensitive: "N"
    default: "dirichlet"
    minimum: "1"
    maximum: "1"
    header: "Prior"
    delimiter: ","
    values: "dirichlet, dmix, mega, megap, addone"
    information: "Prior to use"
    help: "The prior distribution on the model parameters. dirichlet:
           Simple Dirichlet prior. This is the default for -dna and -alph. It
           is based on the non-redundant database letter frequencies. dmix:
           Mixture of Dirichlets prior. This is the default for -protein.
           mega: Extremely low variance dmix; variance is scaled inversely
           with the size of the dataset. megap: Mega for all but last
           iteration of EM; dmix on last iteration. addone: Add +1 to each
           observed count."
    relations: "EDAM_data:2527 Parameter"
  ]

  float: evt [
    additional: "Y"
    default: "-1"
    information: "Threshold value of motif E-value at which to
                  stop searching."
    help: "Quit looking for motifs if E-value exceeds this value. Has
           an extremely high default so by default MEME never quits before
           -nmotifs <n> have been found. A value of -1 here is a
           shorthand for infinity."
    relations: "EDAM_data:1667 E-value"
    relations: "EDAM_data:2146 Threshold"
  ]

  integer: nsites [
    additional: "Y"
    default: "-1"
    information: "Number of sites for each motif"
    help: "These switches are ignored if mod = oops. The (expected)
           number of occurrences of each motif. If a value for -nsites is
           specified, only that number of occurrences is tried. Otherwise,
           numbers of occurrences between -minsites and -maxsites are tried
           as initial guesses for the number of motif occurrences. If a value
           is not specified for -minsites and maxsites then the default
           hardcoded into MEME, as opposed to the default value given in the
           ACD file, is used. The hardcoded default value of -minsites is
           equal to sqrt(number sequences). The hardcoded default value of
           -maxsites is equal to the number of sequences (zoops) or MIN(5*
           num.sequences, 50) (anr). A value of -1 here represents nsites
           being unspecified."
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: minsites [
    additional: "Y"
    default: "-1"
    information: "Minimum number of sites for each motif"
    help: "These switches are ignored if mod = oops. The (expected)
           number of occurrences of each motif. If a value for -nsites is
           specified, only that number of occurrences is tried. Otherwise,
           numbers of occurrences between -minsites and -maxsites are tried
           as initial guesses for the number of motif occurrences. If a value
           is not specified for -minsites and maxsites then the default
           hardcoded into MEME, as opposed to the default value given in the
           ACD file, is used. The hardcoded default value of -minsites is
           equal to sqrt(number sequences). The hardcoded default value of
           -maxsites is equal to the number of sequences (zoops) or MIN(5 *
           num.sequences, 50) (anr). A value of -1 here represents minsites
           being unspecified."
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: maxsites [
    additional: "Y"
    default: "-1"
    information: "Maximum number of sites for each motif"
    help: "These switches are ignored if mod = oops. The (expected)
           number of occurrences of each motif. If a value for -nsites is
           specified, only that number of occurrences is tried. Otherwise,
           numbers of occurrences between -minsites and -maxsites are tried
           as initial guesses for the number of motif occurrences. If a value
           is not specified for -minsites and maxsites then the default
           hardcoded into MEME, as opposed to the default value given in the
           ACD file, is used. The hardcoded default value of -minsites is
           equal to sqrt(number sequences). The hardcoded default value of
           -maxsites is equal to the number of sequences (zoops) or MIN(5 *
           num.sequences, 50) (anr). A value of -1 here represents maxsites
           being unspecified."
    relations: "EDAM_data:2527 Parameter"
  ]

  float: wnsites [
    additional: "Y"
    default: "0.8"
    information: "Weight on expected number of sites"
    help: "The weight of the prior on nsites. This controls how strong
           the bias towards motifs with exactly nsites sites (or between
           minsites and maxsites sites) is. It is a number in the range
           [0..1). The larger it is, the stronger the bias towards motifs
           with exactly nsites occurrences is."
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: w [
    additional: "Y"
    default: "-1"
    information: "Motif width"
    help: "The width of the motif(s) to search for. If -w is given,
           only that width is tried. Otherwise, widths between -minw and
           -maxw are tried. Note: if width is less than the length of the
           shortest sequence in the dataset, width is reset by MEME to that
           value. A value of -1 here represents -w being unspecified."
    relations: "EDAM_data:1249 Sequence length"
  ]

  integer: minw [
    additional: "Y"
    default: "8"
    information: "Minumum motif width"
    help: "The width of the motif(s) to search for. If -w is given,
           only that width is tried. Otherwise, widths between -minw and
           -maxw are tried. Note: if width is less than the length of the
           shortest sequence in the dataset, width is reset by MEME to that
           value."
    relations: "EDAM_data:1249 Sequence length"
  ]

  integer: maxw [
    additional: "Y"
    default: "50"
    information: "Maximum motif width"
    help: "The width of the motif(s) to search for. If -w is given,
           only that width is tried. Otherwise, widths between -minw and
           -maxw are tried. Note: if width is less than the length of the
           shortest sequence in the dataset, width is reset by MEME to that
           value."
    relations: "EDAM_data:1249 Sequence length"
  ]

  boolean: nomatrim [
    additional: "Y"
    default: "N"
    information: "Do not adjust motif width using multiple
                  alignment."
    help: "The -nomatrim, -wg, -ws and -noendgaps switches control
           trimming (shortening) of motifs using the multiple alignment
           method. Specifying -nomatrim causes MEME to skip this and causes
           the other switches to be ignored. The pairwise alignment is
           controlled by the switches -wg (gap cost), -ws (space cost) and
           -noendgaps (do not penalize endgaps). See application
           documentation for further information."
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: wg [
    additional: "Y"
    default: "11"
    information: "Gap opening cost for multiple alignments"
    help: "The -nomatrim, -wg, -ws and -noendgaps switches control
           trimming (shortening) of motifs using the multiple alignment
           method. Specifying -nomatrim causes MEME to skip this and causes
           the other switches to be ignored. The pairwise alignment is
           controlled by the switches -wg (gap cost), -ws (space cost) and
           -noendgaps (do not penalize endgaps). See application
           documentation for further information."
    relations: "EDAM_data:1397 Gap opening penalty"
  ]

  integer: ws [
    additional: "Y"
    default: "1"
    information: "Gap extension cost for multiple alignments"
    help: "The -nomatrim, -wg, -ws and -noendgaps switches control
           trimming (shortening) of motifs using the multiple alignment
           method. Specifying -nomatrim causes MEME to skip this and causes
           the other switches to be ignored. The pairwise alignment is
           controlled by the switches -wg (gap cost), -ws (space cost) and
           -noendgaps (do not penalize endgaps). See application
           documentation for further information."
    relations: "EDAM_data:1398 Gap extension penalty"
  ]

  boolean: noendgaps [
    additional: "Y"
    default: "N"
    information: "Do not penalise end gaps in multiple
                  alignments"
    help: "The -nomatrim, -wg, -ws and -noendgaps switches control
           trimming (shortening) of motifs using the multiple alignment
           method. Specifying -nomatrim causes MEME to skip this and causes
           the other switches to be ignored. The pairwise alignment is
           controlled by the switches -wg (gap cost), -ws (space cost) and
           -noendgaps (do not penalise endgaps). See application
           documentation for further information."
    relations: "EDAM_data:2527 Parameter"
  ]

  boolean: revcomp [
    additional: "Y"
    default: "N"
    information: "Allow sites on + or - DNA strands"
    help: "Motif occurrences may be on the given DNA strand or on its
           reverse complement. The default is to look for DNA motifs only on
           the strand given in the training set."
    relations: "EDAM_data:2527 Parameter"
  ]

  boolean: pal [
    additional: "Y"
    default: "N"
    information: "Look for palindromes (requires input sequence to
                  be dna)"
    help: "Choosing -pal causes MEME to look for palindromes in DNA
           datasets. MEME averages the letter frequencies in corresponding
           columns of the motif (PSPM) together. For instance, if the width
           of the motif is 10, columns 1 and 10, 2 and 9, 3 and 8, etc., are
           averaged together. The averaging combines the frequency of A in
           one column with T in the other, and the frequency of C in one
           column with G in the other."
    relations: "EDAM_data:2527 Parameter"
  ]

  boolean: nostatus [
    additional: "Y"
    default: "Y"
    information: "Do not print progress reports to terminal"
    help: "Set this option to prevent progress reports to the
           terminal."
    relations: "EDAM_data:2527 Parameter"
  ]

endsection: additional

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

  integer: maxiter [
    default: "50"
    information: "Maximum EM iterations to run"
    help: "The number of iterations of EM to run from any starting
           point. EM is run for <n> iterations or until convergence (see
           -distance, below) from each starting point."
    relations: "EDAM_data:1693 Number of iterations"
  ]

  float: distance [
    default: "0.001"
    information: "EM convergence criterion"
    help: "The convergence criterion. MEME stops iterating EM when the
           change in the motif frequency matrix is less than <a>. (Change is
           the euclidean distance between two successive frequency
           matrices.)"
    relations: "EDAM_data:2527 Parameter"
  ]

  float: b [
    default: "-1.0"
    information: "Strength of the prior"
    help: "The strength of the prior on model parameters. A value of 0
           means use intrinsic strength of prior if prior = dmix. The
           default values are 0.01 if prior = dirichlet or 0 if prior = dmix.
           These defaults are hardcoded into MEME (the value of the default
           in the ACD file is not used). A value of -1 here represents -b
           being unspecified."
    relations: "EDAM_data:2527 Parameter"
  ]

  float: spfuzz [
    default: "-1.0"
    information: "Fuzziness of sequence to theta mapping"
    help: "The fuzziness of the mapping. Possible values are greater
           than 0. Meaning depends on -spmap, see below. See the application
           documentation for more information. A value of -1.0 here
           represents -spfuzz being unspecified."
    relations: "EDAM_data:2527 Parameter"
  ]

  selection: spmap [
    casesensitive: "N"
    default: "default"
    minimum: "1"
    maximum: "1"
    header: "Starting point seq to theta mapping type"
    delimiter: ","
    values: "uni, pam, default"
    information: "Select type of mapping"
    help: "The type of mapping function to use. uni: Use prior when
           converting a substring to an estimate of theta. Default -spfuzz
           <a>: 0.5. pam: Use columns of PAM <a> matrix when converting a
           substring to an estimate of theta. Default -spfuzz <a>: 120 (PAM
           120). See the application documentation for more information."
    relations: "EDAM_data:2527 Parameter"
  ]

  string: cons [
    default: ""
    information: "Consensus sequence to start EM from"
    help: "Override the sampling of starting points and just use a
           starting point derived from <string>. This is useful when an
           actual occurrence of a motif is known and can be used as the
           starting point for finding the motif. See the application
           documentation for more information."
    knowntype: "sequence"
    relations:  "EDAM_format:1209 consensus"
  ]

  integer: maxsize [
    default: "-1"
    information: "Maximum dataset size in characters (-1 = use meme default)."
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: p [
    default: "0"
    information: "Use parallel version with <p> processors"
    help: "Only values of >0 will be applied. The -p <np> argument
           causes a version of MEME compiled for a parallel CPU architecture
           to be run. (By placing <np> in quotes you may pass installation
           specific switches to the 'mpirun' command. The number of
           processors to run on must be the first argument following -p)."
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: time [
    default: "0"
    information: "Quit before <time> CPU seconds consumed"
    help: "Only values of more than 0 will be applied."
    relations: "EDAM_data:2527 Parameter"
  ]

  string: sf [
    default: ""
    information: "Print <sf> as name of sequence file"
    knowntype: "sequence id output"
    relations:  "EDAM_identifier:1050 File name"
  ]

  integer: heapsize [
    default: "64"
    information: "Maximum size of heap used during a branching search"
    help: "The search for good EM starting points can be improved by
           using a branching search. A branching search begins with a
           fixed-size heap of best EM starts identified during the search
           of subsequences from the dataset. These starts are also called
           seeds. The fixed-size heap of seeds is used as the branch-heap
           during the first iteration of branching search. See the
           application documentation for more information."
    relations: "EDAM_data:2527 Parameter"
  ]

  boolean: xbranch [
    default: "N"
    information: "Perform x-branching"
    help: "The search for good EM starting points can be improved by
           using a branching search. A branching search begins with a
           fixed-size heap of best EM starts identified during the search
           of subsequences from the dataset. These starts are also called
           seeds. The fixed-size heap of seeds is used as the branch-heap
           during the first iteration of branching search. See the
           application documentation for more information."
    relations: "EDAM_data:2527 Parameter"
  ]

  boolean: wbranch [
    default: "N"
    information: "Perform width branching"
    help: "The search for good EM starting points can be improved by
           using a branching search. A branching search begins with a
           fixed-size heap of best EM starts identified during the search
           of subsequences from the dataset. These starts are also called
           seeds. The fixed-size heap of seeds is used as the branch-heap
           during the first iteration of branching search. See the
           application documentation for more information."
    relations: "EDAM_data:2527 Parameter"
  ]

  integer: bfactor [
    default: "3"
    information: "Number of iterations in the branching search"
    help: "The search for good EM starting points can be improved by
           using a branching search. A branching search begins with a
           fixed-size heap of best EM starts identified during the search
           of subsequences from the dataset. These starts are also called
           seeds. The fixed-size heap of seeds is used as the branch-heap
           during the first iteration of branching search. See the
           application documentation for more information."
    relations: "EDAM_data:1693 Number of iterations"
  ]

endsection: advanced

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

  outdir: outdir [
    parameter: "Y"
    information: "MEME program output file output directory"
    knowntype: "meme output"
    default: "."
    create: "Y"
    relations:  "EDAM_data:1298 Sequence features (motifs)"
  ]

endsection: output