cap3_3.yaml

!mobyle/program
name: cap3
version: '3'
title: CAP3
description: Contig Assembly Program
authors: Huang, X. and Madan, A. (1999)
inputs: !mobyle/inputparagraph
    children:
    - !mobyle/inputprogramparameter
        prompt: File of reads
        format: '" " + str( value )'
        simple: true
        argpos: 1
        mandatory: true
        name: seq
        command: false
        type: !mobyle/formattedtype
            format_terms: ['EDAM_format:2200']
            data_terms: ['EDAM_data:2977']
    - !mobyle/inputprogramparameter {comment: "CAP3 uses the same format of a quality\
            \ file as Phrap. \n          The sequence file and the corresponding quality\
            \ file must be arranged \n          in the same order in terms of reads,\
            \ where for each read, \n          the same name must be used in both\
            \ files and the number of bases must \n          be equal to the number\
            \ of quality values.", prompt: Quality value file, format: '("" , "ln
            -sf %s %s.qual && " %( value , seq ) )[value is not None and value !=
            seq + ".qual" ]', argpos: -10, name: qual_file, command: false}
    - !mobyle/inputprogramparameter {comment: "Each line of the constraint file specifies\
            \ one forward-reverse constraint of the form:ReadA   ReadB    MinDistance\
            \    MaxDistancewhere ReadA and ReadB are names of two reads, and MinDistance\
            \ and MaxDistance are \n          distances (integers) in base pairs.\
            \ The constraint is satisfied if ReadA in forward orientation \n     \
            \     occurs in a contig before ReadB in reverse orientation, or ReadB\
            \ in forward orientation occurs in \n          a contig before ReadA in\
            \ reverse orientation, and their distance is between MinDistance and \n\
            \          MaxDistance. CAP3 works better if a lot more constraints are\
            \ used.", prompt: Constraint file, format: '( "" , "ln -sf %s %s.con &&
            " %( value , seq ) )[value is not None ]', argpos: -5, name: con_file,
        command: false}
    - !mobyle/inputprogramparagraph
        comment: "<html:div xmlns:html=\"http://www.w3.org/1999/xhtml\"><html:p>CAP3\
            \ computes clipping \n    positions of each read using both base quality\
            \ values and similarity \n    information. Clipping of a poor end region\
            \ of a read f is controlled by \n    three parameters: quality value cutoff\
            \ qualcut, clipping range crange, \n    and depth of good coverage gdepth.\
            \ The value for qualcut can specified \n    with the \"-c\" option, the\
            \ value for crange with the \"-y\" option, and the \n    value for gdepth\
            \ with the \"-z\" option.</html:p><html:p>If there are quality values,\
            \ CAP3 computes two positions qualpos5 and \n    qualpos3 of read f such\
            \ that the region of read f from position qualpos5 \n    to position qualpos3\
            \ consists mostly of quality values greater than \n    qualcut. If there\
            \ are no quality values, then qualpos5 is set to 1 and \n    qualpos3\
            \ is set the length of read f. The range for the left clipping \n    position\
            \ of read f is from 1 to qualpos5 + crange. The range for the \n    right\
            \ clipping position of read f is from qualpos3 - crange to the end \n\
            \    of read f. The minimum depth of good coverage at the left and right\
            \ \n    clipping positions of read f is expected to be gdepth.</html:p><html:p>Let\
            \ realdepth5 be the maximum real depth of coverage for the initial \n\
            \    region of read f ending at position qualpos5 + crange. Let depth5\
            \ be the \n    smaller of realdepth5 and gdepth. If depth5 is 0, then\
            \ left clipping \n    position of read f is set to qualpos5 by CAP3. The\
            \ given value for the \n    parameter crange may be too small for read\
            \ f. CAP3 reports at the start \n    of a .info file that \"No overlap\
            \ is found in the given 5' clipping range \n    for read f.\" If there\
            \ are overlaps beyond the given 5' clipping range \n    for read f, CAP3\
            \ reports a new clipping range for each overlap. One of \n    the reported\
            \ range values can be used as a new value for the parameter \n    crange\
            \ for read f.</html:p><html:p>If depth5 is greater than 0, the left clipping\
            \ position of read f is the \n    smallest position x such that x is less\
            \ than qualpos5 + crange and the \n    region of read f beginning at position\
            \ x is similar to depth5 other \n    reads. The right clipping position\
            \ of read f is computed similarly by \n    CAP3. Larger values for the\
            \ parameters crange and gdepth result in more \n    aggressive clipping\
            \ of poor end regions. A larger value for crange \n    allows CAP3 to\
            \ search for the left clipping position in a larger area. A \n    larger\
            \ value for gdepth may cause CAP3 to clip more bases so that the \n  \
            \  resulting good portion of read f is similar to more reads.</html:p><html:p>The\
            \ user may provide specific values for the parameters crange and \n  \
            \  gdepth for individual reads in a file. Each line in the file has the\
            \ \n    following format: file has the following format:</html:p><html:pre><html:font\
            \ face=\"Verdana\" style=\"font-size: 9pt;\">ReadName     crange5    \
            \ gdepth5      crange3     gdepth3</html:font></html:pre><html:p>where\
            \ ReadName is the name \n    of a read, crange5 &amp; gdepth5 are values\
            \ for the 5' end, and crange3 &amp; \n    gdepth3 are for the 3' end.</html:p></html:div>"
        prompt: Clipping of poor regions
        name: clipping_poor_regions
        children:
        - !mobyle/inputprogramparameter
            comment: 'Default value: 12'
            prompt: Base quality cutoff for clipping (-c)
            format: ( "" , " -c "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: base_qual_cutoff_clipping
            command: false
            type: !mobyle/integertype {default: 12}
        - !mobyle/inputprogramparameter
            comment: 'Default value: 250'
            prompt: Clipping range (-y)
            format: ( "" , " -y "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: clipping_range
            command: false
            type: !mobyle/integertype {default: 250}
        - !mobyle/inputprogramparameter
            comment: 'Default value: 3'
            prompt: Minimum number of good reads at clip pos (-z)
            format: ( "" , " -z "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: good_reads
            command: false
            type: !mobyle/integertype {default: 3}
        - !mobyle/inputprogramparameter {comment: 'The user may provide specific values
                for the parameters crange and gdepth or individual reads in a file.Each
                line in the file has the following format:ReadName crange5 gdepth5
                crange3 gdepth3where ReadName is the name of a read, crange5 and gdepth5
                are values for the 5'' end, and crange3 and gdepth3 are for the 3''
                end.', prompt: File for clipping information (-w), format: '( "" ,
                " -w "+ str( value ) )[ value is not None ]', argpos: 10, name: clipping_file,
            command: false}
    - !mobyle/inputprogramparagraph
        comment: The program determines a minimum band of diagonals for an overlapping
            alignment between two sequence reads.The band is expanded by a number
            of bases specified by the user with option "-a".
        prompt: Band of diagonals
        name: band_diagonals
        children:
        - !mobyle/inputprogramparameter
            comment: 'The program determines a minimum band of diagonals for an overlapping
                alignment between two sequence reads.The band is expanded by a number
                of bases specified by the user with option "-a".Default value: 20'
            prompt: Band expansion size (-a)
            format: ( "" , " -a "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: band_expansion
            command: false
            type: !mobyle/integertype {default: 20}
    - !mobyle/inputprogramparagraph
        comment: Overlaps between reads are evaluated by many measures.The first measure
            is based on base quality.If an overlap contains lots of differences at
            bases of high quality, then the overlap is removed.Specifically,let b
            be the base quality cutoff value and let d be the maximum difference score.The
            values for the two parameters can be set using the "-b" and "-d" options.If
            the overlap contains a difference at bases of quality values q1 and q2,
            then the score at the difference is max(0, min(q1, q2) - b).The difference
            score of an overlap is the sum of scores at each difference.For example,
            an overlap contains two differences,one at bases of quality values 15
            and 30 and the other at bases of quality values 40 and 50.With b = 20,
            the difference score of the overlap is 0 + 20 = 20.If the difference score
            of an overlap exceeds d, then the overlap is removed. With b = 20,an overlap
            with 15 differences at bases of quality values 40 or higher has a difference
            score of at least 300 and is removed if d = 250.
        prompt: Quality difference score of an overlap
        name: overlap_score
        children:
        - !mobyle/inputprogramparameter
            prompt: Base quality cutoff for differences (-b)
            format: ( "" , " -b "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: base_qual_cutoff
            command: false
            type: !mobyle/integertype {default: 20}
        - !mobyle/inputprogramparameter
            prompt: Maximum qscore sum at differences (-d)
            format: ( "" , " -d "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: max_qscore
            command: false
            type: !mobyle/integertype {default: 200}
    - !mobyle/inputprogramparagraph
        comment: The second measure looks at the number of differences in an overlap.If
            the number of differences in an overlap is higher than expected, than
            the overlap is removed.Let an integer e be the maximum number of extra
            differences.Consider an overlap between reads f and g.Let d1 be the estimated
            number of sequencing errors for the region of f involved in the overlap
            and let r2 be that forthe region of g involved in the overlap.If the observed
            number of differences in the overlap is greater than r1 + r2 + e, then
            the overlap is removed.The value for the parameter e can be changed using
            the "-e" option.The expected number of differences in the overlap is about
            r1 + r2.Giving a smaller value to e causes more overlaps to be removed.
        prompt: Number of differences in an overlap
        name: nb_diff_overlap
        children:
        - !mobyle/inputprogramparameter
            prompt: Clearance between number of diff (-e)
            format: ( "" , " -e "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: clearance
            command: false
            type: !mobyle/integertype {default: 30}
    - !mobyle/inputprogramparagraph
        comment: The third measure is based on overlap similarity score.The similarity
            score of an overlapping alignment is defined using base quality values.Let
            m be the match score factor, let n be the mismatch score factor, and let
            g be the gap penalty factor.Values for these parameters can be set with
            the "-m", "-n", and "-g" options.A match at bases of quality values q1
            and q2 is given a score of m * min(q1,q2).A mismatch at bases of quality
            values q1 and q2 is given a score of n * min(q1,q2).A base of quality
            value q1 in a gap is given a score of -g * min(q1,q2),where q2 is the
            quality value of the base in the other sequence right before the gap.The
            score of a gap is the sum of scores of each base in the gap minus a gap
            open penalty.The similarity score of an overlapping alignment is the sum
            of scores of each match, each mismatch, and each gap.With m = 2, an overlap
            that consists of 25 matches at bases of quality value 10 has a score of
            500.If the similarity score of an overlap is less than the overlap similarity
            score cutoff s, then the overlap is removed.
        prompt: Similarity score of an overlap
        name: sim_score_overlap
        children:
        - !mobyle/inputprogramparameter
            prompt: Match score factor (-m)
            format: ( "" , " -m "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: match_score
            command: false
            type: !mobyle/integertype {default: 2}
        - !mobyle/inputprogramparameter
            prompt: Mismatch score factor (-n)
            format: ( "" , " -n "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: mismatch_score
            command: false
            type: !mobyle/integertype {default: -5}
        - !mobyle/inputprogramparameter
            prompt: Gap penalty factor (-g)
            format: ( "" , " -g "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: gap_penalty
            command: false
            type: !mobyle/integertype {default: 6}
    - !mobyle/inputprogramparagraph
        comment: The fourth requirement for an overlap is that the length in bp of
            the overlap is no less than the value of the minimum overlap length cutoff
            parameter.The value for this parameter can be changed with the "-o" option.The
            fifth requirement for an overlap is that the percent identity of the overlap
            is no less than the minimum percent identity cutoff.The value for this
            parameter can be changed with the "-p" option.A value of 75 for p means
            0.75 or 75%.
        prompt: Length and percent identity of an overlap
        name: percent_id_overlap
        children:
        - !mobyle/inputprogramparameter
            prompt: Overlap length cutoff (-o)
            format: ( "" , " -o "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: overlap_length
            command: false
            type: !mobyle/integertype {default: 40}
        - !mobyle/inputprogramparameter
            prompt: Overlap percent identity cutoff (-p)
            format: ( "" , " -p "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: overlap_identity
            command: false
            type: !mobyle/integertype {default: 80}
    - !mobyle/inputprogramparagraph
        comment: The program provides a parameter (-f option) for the user to reject
            overlaps with a long gap.Let an integer f be the maximum length of gaps
            allowed in any overlap. Then any overlap with a gap longer than f is rejected
            by the program.The value for this parameter can be changed using the "-f"
            option.Note that a small value for this parameter may cause the program
            to remove true overlaps and to produce incorrect results.The "-f" option
            may be used by the user to split reads from alternative splicing forms
            into separate contigs.Geo Pertea at TIGR suggested that this option be
            added to the program.
        prompt: Maximum length of gaps in an overlap
        name: max_len_gaps_overlap
        children:
        - !mobyle/inputprogramparameter
            prompt: Maximum gap length in any overlap (-f)
            format: ( "" , " -f "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: max_gap_length
            command: false
            type: !mobyle/integertype {default: 20}
    - !mobyle/inputprogramparagraph
        comment: The total length of the different overhang regions in an overlap
            is controlled with the -h option.TAn overhang region in an overlap is
            a different terminal region before or after the overlap.TThe overhang
            percent length of an overlap is 100 times the total length of the different
            overhang regions in the overlap divided by the length of the overlap.TOverlaps
            with an overhang percent length greater than the maximum cutoff are rejected.
        prompt: Overhang percent length of an overlap
        name: overhang_pcent_len_overlap
        children:
        - !mobyle/inputprogramparameter
            prompt: Maximum overhang percent length (-h)
            format: ( "" , " -h "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: max_overhang
            command: false
            type: !mobyle/integertype {default: 20}
    - !mobyle/inputprogramparameter
        prompt: Overlap similarity score cutoff (-s)
        format: ( "" , " -s "+ str( value ) )[ value is not None and value != vdef
            ]
        argpos: 10
        name: overlap_similarity
        command: false
        type: !mobyle/integertype {default: 900}
    - !mobyle/inputprogramparagraph
        comment: The "-r" option is used to let CAP3 know whether to consider reads
            in reverse orientation for assembly.The default value for the option is
            1, meaning that reads in reverse orientation are also considered for assembly.Specifying
            zero as "-r 0" instructs CAP3 to perform assembly of reads in forward
            orientation only.This option was suggested by Patrick Schnable's lab.
        prompt: Assembly of reads in forward orientation only
        name: assembly_fwd
        children:
        - !mobyle/inputprogramparameter
            prompt: Reverse orientation value (-r)
            format: ( "" , " -r "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: reverse_orientation
            command: false
            type: !mobyle/integertype {default: 1}
    - !mobyle/inputprogramparagraph
        comment: This parameter (option -t) allows the user to trade off the efficiency
            of the program for its accuracy.For a read f, the program computes overlaps
            between read f and other reads by considering short word matches between
            read f and other reads.A word match is examined to see if it can be extended
            into a long overlap.If read f has overlaps with many other reads, then
            read f has many short word matches with many other reads.This parameter
            gives an upper limit, for any word, on the number of word matches between
            read f and other reads that are considered by the program.Using a large
            value for this parameter allows the program to consider more word matches
            between read f and other reads, which can find more overlaps for read
            f, but slows down the program.Using a small vlaue for this parameter has
            the opposite effect.A large value may be used if the depth of coverage
            is high for the data set.For example, a value of 150 is used for a data
            set with a maximum depth of coverage of 30, and a value of 500 for a data
            set with a maximum depth of coverage of 100. Using a very large value
            may cause the program to run forever or run out of memory.
        prompt: Maximum number of word matches
        name: max_num_word_matches
        children:
        - !mobyle/inputprogramparameter
            prompt: Maximum number of word matches (-t)
            format: ( "" , " -t "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: word_matches
            command: false
            type: !mobyle/integertype {default: 300}
    - !mobyle/inputprogramparagraph
        comment: Corrections to an assembly are made using forward-reverse constraints.Let
            an integer u be the minimum number of constraints for correction.Consider
            an alternative overlap between two reads f and g.Assume that f is in contig
            C1 and that g is in contig C2.If the number of unsatisfied constraints
            that support the overlap between f and g is greater than the value of
            the u parameter plus the number of satisfied constraints that support
            the current joins involving f and g, then the current joins involving
            f and g are disconnected and the overlap between f and g is implemented.The
            value for this parameter can be changed with the "-u" option.Contigs that
            are linked by forward-reverse constraints are reported.The minimum number
            of constraints for reporting a link between two contigs is specified with
            the "-v" option.
        prompt: Forward-reverse constraints
        name: fwd_rev_const
        children:
        - !mobyle/inputprogramparameter
            prompt: Minimum number of constraints for correction (-u)
            format: ( "" , " -u "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: min_constraints_corr
            command: false
            type: !mobyle/integertype {default: 3}
        - !mobyle/inputprogramparameter
            prompt: Minimum number of constraints for linking (-v)
            format: ( "" , " -v "+ str( value ) )[ value is not None and value !=
                vdef ]
            argpos: 10
            name: min_constraints_linking
            command: false
            type: !mobyle/integertype {default: 2}
outputs: !mobyle/outputparagraph
    children:
    - !mobyle/outputprogramparameter {prompt: Assembly in ace format, filenames: '"*.cap.ace"',
        name: ace}
    - !mobyle/outputprogramparameter
        prompt: Contigs
        filenames: '"*.cap.contigs"'
        name: contig
        type: !mobyle/formattedtype
            format_terms: ['EDAM_format:2200']
            data_terms: ['EDAM_data:2977']
    - !mobyle/outputprogramparameter {prompt: Contig links, filenames: '"*.cap.contigs.links"',
        name: contig_link}
    - !mobyle/outputprogramparameter {prompt: Quality of contigs, filenames: '"*.cap.contigs.qual"',
        name: contig_qual}
    - !mobyle/outputprogramparameter {prompt: Assembly informations, filenames: '"*.cap.info"',
        name: info}
    - !mobyle/outputprogramparameter
        prompt: Singlets
        filenames: '"*.cap.singlets"'
        name: singlet
        type: !mobyle/formattedtype
            data_terms: ['EDAM_data:2977']
    - !mobyle/outputprogramparameter
        prompt: Standard output
        filenames: '"cap3.out"'
        name: stdout
        output_type: stdout
        type: !mobyle/formattedtype
            data_terms: ['EDAM_data:2048']
    - !mobyle/outputprogramparameter
        prompt: Standard error
        filenames: '"cap3.err"'
        name: stderr
        type: !mobyle/formattedtype
            data_terms: ['EDAM_data:2048']
operations: ['EDAM_operation:0310']
topics: ['EDAM_topic:0196']
references:
- {doi: null, label: 'Huang, X. and Madan, A. (1999) CAP3: A DNA Sequence Assembly
        Program. Genome Research, 9: 868-877.', url: null}
homepage_links: ['http://seq.cs.iastate.edu/']
command: cap3
env: {}
source_links: ['http://seq.cs.iastate.edu/cap3.html']