.\" Automatically generated by Pod::Man 4.11 (Pod::Simple 3.35) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' . ds C` . ds C' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is >0, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .\" .\" Avoid warning from groff about undefined register 'F'. .de IX .. .nr rF 0 .if \n(.g .if rF .nr rF 1 .if (\n(rF:(\n(.g==0)) \{\ . if \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . if !\nF==2 \{\ . nr % 0 . nr F 2 . \} . \} .\} .rr rF .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. . \" fudge factors for nroff and troff .if n \{\ . ds #H 0 . ds #V .8m . ds #F .3m . ds #[ \f1 . ds #] \fP .\} .if t \{\ . ds #H ((1u-(\\\\n(.fu%2u))*.13m) . ds #V .6m . ds #F 0 . ds #[ \& . ds #] \& .\} . \" simple accents for nroff and troff .if n \{\ . ds ' \& . ds ` \& . ds ^ \& . ds , \& . ds ~ ~ . ds / .\} .if t \{\ . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' .\} . \" troff and (daisy-wheel) nroff accents .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' .ds 8 \h'\*(#H'\(*b\h'-\*(#H' .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] .ds ae a\h'-(\w'a'u*4/10)'e .ds Ae A\h'-(\w'A'u*4/10)'E . \" corrections for vroff .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' . \" for low resolution devices (crt and lpr) .if \n(.H>23 .if \n(.V>19 \ \{\ . ds : e . ds 8 ss . ds o a . ds d- d\h'-1'\(ga . ds D- D\h'-1'\(hy . ds th \o'bp' . ds Th \o'LP' . ds ae ae . ds Ae AE .\} .rm #[ #] #H #V #F C .\" ======================================================================== .\" .IX Title "PRINSEQ-LITE 1" .TH PRINSEQ-LITE 1 "2020-11-09" "perl v5.30.3" "prinseq-lite" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" PRINSEQ \- PReprocessing and INformation of SEQuence data .SH "VERSION" .IX Header "VERSION" PRINSEQ-lite 0.20.4 .SH "SYNOPSIS" .IX Header "SYNOPSIS" perl prinseq\-lite.pl [\-h] [\-help] [\-version] [\-man] [\-verbose] [\-fastq input_fastq_file] [\-fasta input_fasta_file] [\-fastq2 input_fastq_file_2] [\-fasta2 input_fasta_file_2] [\-qual input_quality_file] [\-min_len int_value] [\-max_len int_value] [\-range_len ranges] [\-min_gc int_value] [\-max_gc int_value] [\-range_gc ranges] [\-min_qual_score int_value] [\-max_qual_score int_value] [\-min_qual_mean int_value] [\-max_qual_mean int_value] [\-ns_max_p int_value] [\-ns_max_n int_value] [\-noniupac] [\-seq_num int_value] [\-derep int_value] [\-derep_min int_value] [\-lc_method method_name] [\-lc_threshold int_value] [\-trim_to_len int_value] [\-trim_left int_value] [\-trim_right int_value] [\-trim_left_p int_value] [\-trim_right_p int_value] [\-trim_ns_left int_value] [\-trim_ns_right int_value] [\-trim_tail_left int_value] [\-trim_tail_right int_value] [\-trim_qual_left int_value] [\-trim_qual_right int_value] [\-trim_qual_type type] [\-trim_qual_rule rule] [\-trim_qual_window int_value] [\-trim_qual_step int_value] [\-seq_case case] [\-dna_rna type] [\-line_width int_value] [\-rm_header] [\-seq_id id_string] [\-out_format int_value] [\-out_good filename_prefix] [\-out_bad filename_prefix] [\-phred64] [\-stats_info] [\-stats_len] [\-stats_dinuc] [\-stats_tag] [\-stats_dupl] [\-stats_ns] [\-stats_assembly] [\-stats_all] [\-aa] [\-graph_data file] [\-graph_stats string] [\-qual_noscale] [\-no_qual_header] [\-exact_only] [\-log file] [\-custom_params string] [\-params file] [\-seq_id_mappings file] .SH "DESCRIPTION" .IX Header "DESCRIPTION" \&\s-1PRINSEQ\s0 will help you to preprocess your genomic or metagenomic sequence data in \s-1FASTA\s0 (and \s-1QUAL\s0) or \s-1FASTQ\s0 format. The lite version does not require any non-core perl modules for processing. .SH "OPTIONS" .IX Header "OPTIONS" .IP "\fB\-help\fR | \fB\-h\fR" 8 .IX Item "-help | -h" Print the help message; ignore other arguments. .IP "\fB\-man\fR" 8 .IX Item "-man" Print the full documentation; ignore other arguments. .IP "\fB\-version\fR" 8 .IX Item "-version" Print program version; ignore other arguments. .IP "\fB\-verbose\fR" 8 .IX Item "-verbose" Prints status and info messages during processing. .IP "\fB***** \s-1INPUT OPTIONS\s0 *****\fR" 8 .IX Item "***** INPUT OPTIONS *****" .PD 0 .IP "\fB\-fastq\fR " 8 .IX Item "-fastq " .PD Input file in \s-1FASTQ\s0 format that contains the sequence and quality data. Use stdin instead of a file name to read from \s-1STDIN\s0 (\-fasta stdin). This can be useful to process compressed files using Unix pipes. .IP "\fB\-fasta\fR " 8 .IX Item "-fasta " Input file in \s-1FASTA\s0 format that contains the sequence data. Use stdin instead of a file name to read from \s-1STDIN\s0 (\-fastq stdin). This can be useful to process compressed files using Unix pipes. .IP "\fB\-qual\fR " 8 .IX Item "-qual " Input file in \s-1QUAL\s0 format that contains the quality data. .IP "\fB\-fastq2\fR " 8 .IX Item "-fastq2 " For paired-end data only. Input file in \s-1FASTQ\s0 format that contains the sequence and quality data. The sequence identifiers for two matching paired-end sequences in separate files can be marked by /1 and /2, or _L and _R, or _left and _right, or must have the exact same identifier in both input files. The input sequences must be sorted by their sequence identifiers. Singletons are allowed in the input files. .IP "\fB\-fasta2\fR " 8 .IX Item "-fasta2 " For paired-end data only. Input file in \s-1FASTA\s0 format that contains the sequence data. The sequence identifiers for two matching paired-end sequences in separate files can be marked by /1 and /2, or _L and _R, or _left and _right, or must have the exact same identifier in both input files. The input sequences must be sorted by their sequence identifiers. Singletons are allowed in the input files. .IP "\fB\-params\fR " 8 .IX Item "-params " Input file in text format that contains \s-1PRINSEQ\s0 parameters. Each parameter should be specified on a new line and arguments should be separated by spaces or tabs. Comments can be specified on lines starting with the # sign. Can be combined with command line parameters. Parameters specified on the command line will overwrite the arguments in the file (if any). .IP "\fB\-si13\fR" 8 .IX Item "-si13" This option was replaced by option \-phred64. .IP "\fB\-phred64\fR" 8 .IX Item "-phred64" Quality data in \s-1FASTQ\s0 file is in Phred+64 format (http://en.wikipedia.org/wiki/FASTQ_format#Encoding). Not required for Illumina 1.8+, Sanger, Roche/454, Ion Torrent, PacBio data. .IP "\fB\-aa\fR" 8 .IX Item "-aa" Input is amino acid (protein) sequences instead of nucleic acid (\s-1DNA\s0 or \s-1RNA\s0) sequences. Allowed amino acid characters: ABCDEFGHIKLMNOPQRSTUVWYZXabcdefghiklmmopqrstuvwyzx*\- and allowed nucleic acid characters: ACGTURYKMSWBDHVNXacgturykmswbdhvnx\- .Sp The following options are ignored for \-aa: stats_dinuc,stats_tag,stats_ns,dna_rna .IP "\fB***** \s-1OUTPUT OPTIONS\s0 *****\fR" 8 .IX Item "***** OUTPUT OPTIONS *****" .PD 0 .IP "\fB\-out_format\fR " 8 .IX Item "-out_format " .PD To change the output format, use one of the following options. If not defined, the output format will be the same as the input format. .Sp 1 (\s-1FASTA\s0 only), 2 (\s-1FASTA\s0 and \s-1QUAL\s0), 3 (\s-1FASTQ\s0), 4 (\s-1FASTQ\s0 and \s-1FASTA\s0), or 5 (\s-1FASTQ, FASTA\s0 and \s-1QUAL\s0) .IP "\fB\-out_good\fR " 8 .IX Item "-out_good " By default, the output files are created in the same directory as the input file containing the sequence data with an additional \*(L"_prinseq_good_XXXX\*(R" in their name (where \s-1XXXX\s0 is replaced by random characters to prevent overwriting previous files). To change the output filename and location, specify the filename using this option. The file extension will be added automatically (either .fasta, .qual, or .fastq). For paired-end data, filenames contain additionally \*(L"_1\*(R", \*(L"_1_singletons\*(R", \*(L"_2\*(R", and \*(L"_2_singletons\*(R" before the file extension. Use \*(L"\-out_good null\*(R" to prevent the program from generating the output file(s) for data passing all filters. Use \*(L"\-out_good stdout\*(R" to write data passing all filters to \s-1STDOUT\s0 (only for \s-1FASTA\s0 or \s-1FASTQ\s0 output files). .Sp Example: use \*(L"file_passed\*(R" to generate the output file file_passed.fasta in the current directory .IP "\fB\-out_bad\fR " 8 .IX Item "-out_bad " By default, the output files are created in the same directory as the input file containing the sequence data with an additional \*(L"_prinseq_bad_XXXX\*(R" in their name (where \s-1XXXX\s0 is replaced by random characters to prevent overwriting previous files). To change the output filename and location, specify the filename using this option. The file extension will be added automatically (either .fasta, .qual, or .fastq). For paired-end data, filenames contain additionally \*(L"_1\*(R" and \*(L"_2\*(R" before the file extension. Use \*(L"\-out_bad null\*(R" to prevent the program from generating the output file(s) for data not passing any filter. Use \*(L"\-out_bad stdout\*(R" to write data not passing any filter to \s-1STDOUT\s0 (only for \s-1FASTA\s0 or \s-1FASTQ\s0 output files). .Sp Example: use \*(L"file_filtered\*(R" to generate the output file file_filtered.fasta in the current directory .Sp Example: \*(L"\-out_good stdout \-out_bad null\*(R" will write data passing filters to \s-1STDOUT\s0 and data not passing any filter will be ignored .IP "\fB\-log\fR " 8 .IX Item "-log " Log file to keep track of parameters, errors, etc. The log file name is optional. If no file name is given, the log file name will be \*(L"inputname.log\*(R". If the log file already exists, new content will be added to the file. .IP "\fB\-graph_data\fR " 8 .IX Item "-graph_data " File that contains the necessary information to generate the graphs similar to the ones in the web version. The file name is optional. If no file name is given, the file name will be \*(L"inputname.gd\*(R". If the file already exists, new content will overwrite the file. Use \*(L"\-out_good null \-out_bad null\*(R" to prevent generating any additional outputs. (See below for more options related to the graph data.) .Sp The graph data can be used as input for the prinseq\-graphs.pl file to generate the \s-1PNG\s0 graph files or an \s-1HTML\s0 report file. If you have trouble installing the required prinseq\-graphs.pl modules or want to see an output example report, upload the graph data file at: http://edwards.sdsu.edu/prinseq/ \-> Choose \*(L"Get Report\*(R" .IP "\fB\-graph_stats\fR " 8 .IX Item "-graph_stats " Use this option to select what statistics should be calculated and included in the graph_data file. This is useful if you e.g. do not need sequence complexity information, which requires a lot of computation. Requires to have graph_data specified. Default is all selected. .Sp Allowed option are (separate multiple by comma with no spaces): ld (Length distribution), gc (\s-1GC\s0 content distribution), qd (Base quality distribution), ns (Occurrence of N), pt (Poly\-A/T tails), ts (Tag sequence check), aq (Assembly quality measure), de (Sequence duplication \- exact only), da (Sequence duplication \- exact + 5'/3'), sc (Sequence complexity), dn (Dinucleotide odds ratios, includes the \s-1PCA\s0 plots) .Sp Example use: \-graph_stats ld,gc,qd,de .IP "\fB\-qual_noscale\fR" 8 .IX Item "-qual_noscale" Use this option if all your sequences are shorter than 100bp as they do not require to scale quality data to 100 data points in the graph. By default, quality scores of sequences shorter than 100bp or longer than 100bp are fit to 100 data points. (To retrieve this information and calculate the graph data would otherwise require to parse the data two times or store all the quality data in memory.) .IP "\fB\-no_qual_header\fR" 8 .IX Item "-no_qual_header" In order to reduce the file size, this option will generate an empty header line for the quality data in \s-1FASTQ\s0 files. Instead of +header, only the + sign will be output. The header of the sequence data will be left unchanged. This option applies to \s-1FASTQ\s0 output files only. .IP "\fB\-exact_only\fR" 8 .IX Item "-exact_only" Use this option to check for exact (forward and reverse) duplicates only when generating the graph data. This allows one to keep the memory requirements low for large input files and is faster. This option will automatically be applied when using \-derep options 1 and/or 4 only. Specify option \-derep 1 or \-derep 4 if you do not want to apply both at the same time. .IP "\fB\-seq_id_mappings\fR " 8 .IX Item "-seq_id_mappings " Text file containing the old and new (specified with \-seq_id) identifiers for later reference. This option is useful if e.g. a renamed sequence has to be identified based on the new sequence identifier. The file name is optional. If no file name is given, the file name will be \*(L"inputname_prinseq_good.ids\*(R" (only good sequences are renamed). If a file with the same name already exists, new content will overwrite the old file. The text file contains one sequence identifier pair per line, separated by tabs (old-tab-new). Requires option \-seq_id. .IP "\fB***** \s-1FILTER OPTIONS\s0 *****\fR" 8 .IX Item "***** FILTER OPTIONS *****" .PD 0 .IP "\fB\-min_len\fR " 8 .IX Item "-min_len " .PD Filter sequence shorter than min_len. .IP "\fB\-max_len\fR " 8 .IX Item "-max_len " Filter sequence longer than max_len. .IP "\fB\-range_len\fR " 8 .IX Item "-range_len " Filter sequence by length range. Multiple range values should be separated by comma without spaces. .Sp Example: \-range_len 50\-100,250\-300 .IP "\fB\-min_gc\fR " 8 .IX Item "-min_gc " Filter sequence with \s-1GC\s0 content below min_gc. .IP "\fB\-max_gc\fR " 8 .IX Item "-max_gc " Filter sequence with \s-1GC\s0 content above max_gc. .IP "\fB\-range_gc\fR " 8 .IX Item "-range_gc " Filter sequence by \s-1GC\s0 content range. Multiple range values should be separated by comma without spaces. .Sp Example: \-range_gc 50\-60,75\-90 .IP "\fB\-min_qual_score\fR " 8 .IX Item "-min_qual_score " Filter sequence with at least one quality score below min_qual_score. .IP "\fB\-max_qual_score\fR " 8 .IX Item "-max_qual_score " Filter sequence with at least one quality score above max_qual_score. .IP "\fB\-min_qual_mean\fR " 8 .IX Item "-min_qual_mean " Filter sequence with quality score mean below min_qual_mean. .IP "\fB\-max_qual_mean\fR " 8 .IX Item "-max_qual_mean " Filter sequence with quality score mean above max_qual_mean. .IP "\fB\-ns_max_p\fR " 8 .IX Item "-ns_max_p " Filter sequence with more than ns_max_p percentage of Ns. .IP "\fB\-ns_max_n\fR " 8 .IX Item "-ns_max_n " Filter sequence with more than ns_max_n Ns. .IP "\fB\-noniupac\fR" 8 .IX Item "-noniupac" Filter sequence with characters other than A, C, G, T or N. .IP "\fB\-seq_num\fR " 8 .IX Item "-seq_num " Only keep the first seq_num number of sequences (that pass all other filters). .IP "\fB\-derep\fR " 8 .IX Item "-derep " Type of duplicates to filter. Allowed values are 1, 2, 3, 4 and 5. Use integers for multiple selections (e.g. 124 to use type 1, 2 and 4). The order does not matter. Option 2 and 3 will set 1 and option 5 will set 4 as these are subsets of the other option. .Sp 1 (exact duplicate), 2 (5' duplicate), 3 (3' duplicate), 4 (reverse complement exact duplicate), 5 (reverse complement 5'/3' duplicate) .IP "\fB\-derep_min\fR " 8 .IX Item "-derep_min " This option specifies the number of allowed duplicates. If you want to remove sequence duplicates that occur more than x times, then you would specify x+1 as the \-derep_min values. For examples, to remove sequences that occur more than 5 times, you would specify \-derep_min 6. This option can only be used in combination with \-derep 1 and/or 4 (forward and/or reverse exact duplicates). [default : 2] .IP "\fB\-lc_method\fR " 8 .IX Item "-lc_method " Method to filter low complexity sequences. The current options are \*(L"dust\*(R" and \*(L"entropy\*(R". Use \*(L"\-lc_method dust\*(R" to calculate the complexity using the dust method. .IP "\fB\-lc_threshold\fR " 8 .IX Item "-lc_threshold " The threshold value (between 0 and 100) used to filter sequences by sequence complexity. The dust method uses this as maximum allowed score and the entropy method as minimum allowed value. .IP "\fB\-custom_params\fR " 8 .IX Item "-custom_params " Can be used to specify additional filters. The current set of possible rules is limited and has to follow the specifications below. The custom parameters have to be specified within quotes (either ' or "). .Sp Please separate parameter values with a space and separate new parameter sets with semicolon (;). Parameters are defined by two values: (1) the pattern (any combination of the letters \*(L"\s-1ACGTN\*(R"\s0), (2) the number of repeats or percentage of occurrence Percentage values are defined by a number followed by the %\-sign (without space). If no %\-sign is given, it is assumed that the given number specifies the number of repeats of the pattern. .Sp Examples: \*(L"\s-1AAT 10\*(R"\s0 (filters out sequences containing \s-1AATAATAATAATAATAATAATAATAATAAT\s0 anywhere in the sequence), \*(L"T 70%\*(R" (filters out sequences with more than 70% Ts in the sequence), \*(L"A 15\*(R" (filters out sequences containing \s-1AAAAAAAAAAAAAAA\s0 anywhere in the sequence), \*(L"\s-1AAT 10\s0;T 70%;A 15\*(R" (apply all three filters) .IP "\fB***** \s-1TRIM OPTIONS\s0 *****\fR" 8 .IX Item "***** TRIM OPTIONS *****" .PD 0 .IP "\fB\-trim_to_len\fR " 8 .IX Item "-trim_to_len " .PD Trim all sequence from the 3'\-end to result in sequence with this length. .IP "\fB\-trim_left\fR " 8 .IX Item "-trim_left " Trim sequence at the 5'\-end by trim_left positions. .IP "\fB\-trim_right\fR " 8 .IX Item "-trim_right " Trim sequence at the 3'\-end by trim_right positions. .IP "\fB\-trim_left_p\fR " 8 .IX Item "-trim_left_p " Trim sequence at the 5'\-end by trim_left_p percentage of read length. The trim length is rounded towards the lower integer (e.g. 143.6 is rounded to 143 positions). Use an integer between 1 and 100 for the percentage value. .IP "\fB\-trim_right_p\fR " 8 .IX Item "-trim_right_p " Trim sequence at the 3'\-end by trim_right_p percentage of read length. The trim length is rounded towards the lower integer (e.g. 143.6 is rounded to 143 positions). Use an integer between 1 and 100 for the percentage value. .IP "\fB\-trim_tail_left\fR " 8 .IX Item "-trim_tail_left " Trim poly\-A/T tail with a minimum length of trim_tail_left at the 5'\-end. .IP "\fB\-trim_tail_right\fR " 8 .IX Item "-trim_tail_right " Trim poly\-A/T tail with a minimum length of trim_tail_right at the 3'\-end. .IP "\fB\-trim_ns_left\fR " 8 .IX Item "-trim_ns_left " Trim poly-N tail with a minimum length of trim_ns_left at the 5'\-end. .IP "\fB\-trim_ns_right\fR " 8 .IX Item "-trim_ns_right " Trim poly-N tail with a minimum length of trim_ns_right at the 3'\-end. .IP "\fB\-trim_qual_left\fR " 8 .IX Item "-trim_qual_left " Trim sequence by quality score from the 5'\-end with this threshold score. .IP "\fB\-trim_qual_right\fR " 8 .IX Item "-trim_qual_right " Trim sequence by quality score from the 3'\-end with this threshold score. .IP "\fB\-trim_qual_type\fR " 8 .IX Item "-trim_qual_type " Type of quality score calculation to use. Allowed options are min, mean, max and sum. [default: min] .IP "\fB\-trim_qual_rule\fR " 8 .IX Item "-trim_qual_rule " Rule to use to compare quality score to calculated value. Allowed options are lt (less than), gt (greater than) and et (equal to). [default: lt] .IP "\fB\-trim_qual_window\fR " 8 .IX Item "-trim_qual_window " The sliding window size used to calculate quality score by type. To stop at the first base that fails the rule defined, use a window size of 1. [default: 1] .IP "\fB\-trim_qual_step\fR " 8 .IX Item "-trim_qual_step " Step size used to move the sliding window. To move the window over all quality scores without missing any, the step size should be less or equal to the window size. [default: 1] .IP "\fB***** \s-1REFORMAT OPTIONS\s0 *****\fR" 8 .IX Item "***** REFORMAT OPTIONS *****" .PD 0 .IP "\fB\-seq_case\fR " 8 .IX Item "-seq_case " .PD Changes sequence character case to upper or lower case. Allowed options are \*(L"upper\*(R" and \*(L"lower\*(R". Use this option to remove soft-masking from your sequences. .IP "\fB\-dna_rna\fR " 8 .IX Item "-dna_rna " Convert sequence between \s-1DNA\s0 and \s-1RNA.\s0 Allowed options are \*(L"dna\*(R" (convert from \s-1RNA\s0 to \s-1DNA\s0) and \*(L"rna\*(R" (convert from \s-1DNA\s0 to \s-1RNA\s0). .IP "\fB\-line_width\fR " 8 .IX Item "-line_width " Sequence characters per line. Use 0 if you want each sequence in a single line. Use 80 for line breaks every 80 characters. Note that this option only applies to \s-1FASTA\s0 output files, since \s-1FASTQ\s0 files store sequences without additional line breaks. [default: 60] .IP "\fB\-rm_header\fR" 8 .IX Item "-rm_header" Remove the sequence header. This includes everything after the sequence identifier (which is kept unchanged). .IP "\fB\-seq_id\fR " 8 .IX Item "-seq_id " Rename the sequence identifier. A counter is added to each identifier to assure its uniqueness. Use option \-seq_id_mappings to generate a file containing the old and new identifiers for later reference. .Sp Example: \*(L"mySeq_10\*(R" will generate the IDs (in \s-1FASTA\s0 format) >mySeq_101, >mySeq_102, >mySeq_103, ... .IP "\fB***** \s-1SUMMARY STATISTIC OPTIONS\s0 *****\fR" 8 .IX Item "***** SUMMARY STATISTIC OPTIONS *****" The summary statistic values are written to \s-1STDOUT\s0 in the form: \*(L"parameter_name statistic_name value\*(R" (without the quotes). For example, \*(L"stats_info reads 10000\*(R" or \*(L"stats_len max 500\*(R". Only one statistic is written per line and values are separated by tabs. .Sp If you specify any statistic option, no other output will be generated. To preprocess data, do not specify a statistics option. .IP "\fB\-stats_info\fR" 8 .IX Item "-stats_info" Outputs basic information such as number of reads (reads) and total bases (bases). .IP "\fB\-stats_len\fR" 8 .IX Item "-stats_len" Outputs minimum (min), maximum (max), range (range), mean (mean), standard deviation (stddev), mode (mode) and mode value (modeval), and median (median) for read length. .IP "\fB\-stats_dinuc\fR" 8 .IX Item "-stats_dinuc" Outputs the dinucleotide odds ratio for \s-1AA/TT\s0 (aatt), \s-1AC/GT\s0 (acgt), \s-1AG/CT\s0 (agct), \s-1AT\s0 (at), \s-1CA/TG\s0 (catg), \s-1CC/GG\s0 (ccgg), \s-1CG\s0 (cg), \s-1GA/TC\s0 (gatc), \s-1GC\s0 (gc) and \s-1TA\s0 (ta). .IP "\fB\-stats_tag\fR" 8 .IX Item "-stats_tag" Outputs the probability of a tag sequence at the 5'\-end (prob5) and 3'\-end (prob3) in percentage (0..100). Provides the number of predefined MIDs (midnum) and the \s-1MID\s0 sequences (midseq, separated by comma, only provided if midnum > 0) that occur in more than 34/100 (approx. 3%) of the reads. .IP "\fB\-stats_dupl\fR" 8 .IX Item "-stats_dupl" Outputs the number of exact duplicates (exact), 5' duplicates (5), 3' duplicates (3), exact duplicates with reverse complements (exactrevcom) and 5'/3' duplicates with reverse complements (revcomp), and total number of duplicates (total). The maximum number of duplicates is given under the value name with an additional \*(L"maxd\*(R" (e.g. exactmaxd or 5maxd). .IP "\fB\-stats_ns\fR" 8 .IX Item "-stats_ns" Outputs the number of reads with ambiguous base N (seqswithn), the maximum number of Ns per read (maxn) and the maximum percentage of Ns per read (maxp). The maxn and maxp value are not necessary from the same sequence. .IP "\fB\-stats_assembly\fR" 8 .IX Item "-stats_assembly" Outputs the N50, N90, etc contig sizes. The Nxx contig size is a weighted median that is defined as the length of the smallest contig C in the sorted list of all contigs where the cumulative length from the largest contig to contig C is at least xx% of the total length (sum of contig lengths). .IP "\fB\-stats_all\fR" 8 .IX Item "-stats_all" Outputs all available summary statistics. .IP "\fB***** \s-1ORDER OF PROCESSING\s0 *****\fR" 8 .IX Item "***** ORDER OF PROCESSING *****" The available options are processed in the following order: .Sp seq_num, trim_left, trim_right, trim_left_p, trim_right_p, trim_qual_left, trim_qual_right, trim_tail_left, trim_tail_right, trim_ns_left, trim_ns_right, trim_to_len, min_len, max_len, range_len, min_qual_score, max_qual_score, min_qual_mean, max_qual_mean, min_gc, max_gc, range_gc, ns_max_p, ns_max_n, noniupac, lc_method, derep, seq_id, seq_case, dna_rna, out_format .SH "AUTHOR" .IX Header "AUTHOR" Robert \s-1SCHMIEDER,\s0 \f(CW\*(C`\*(C'\fR .SH "BUGS" .IX Header "BUGS" If you find a bug please email me at \f(CW\*(C`\*(C'\fR or use http://sourceforge.net/tracker/?group_id=315449 so that I can make \s-1PRINSEQ\s0 better. .SH "COPYRIGHT" .IX Header "COPYRIGHT" Copyright (C) 2010\-2012 Robert \s-1SCHMIEDER\s0 .SH "LICENSE" .IX Header "LICENSE" This program is free software: you can redistribute it and/or modify it under the terms of the \s-1GNU\s0 General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. .PP This program is distributed in the hope that it will be useful, but \s-1WITHOUT ANY WARRANTY\s0; without even the implied warranty of \s-1MERCHANTABILITY\s0 or \s-1FITNESS FOR A PARTICULAR PURPOSE.\s0 See the \s-1GNU\s0 General Public License for more details. .PP You should have received a copy of the \s-1GNU\s0 General Public License along with this program. If not, see .