Mercurial > repos > greg > meme_fimo
changeset 6:4df8e9f58a53 draft default tip
Uploaded
| author | greg |
|---|---|
| date | Wed, 06 Jul 2016 10:25:06 -0400 |
| parents | e85346ab5054 |
| children | |
| files | fimo.xml fimo_wrapper.py test-data/fimo_output_html_1.html test-data/fimo_output_html_2.html test-data/fimo_output_xml_1.xml test-data/fimo_output_xml_2.xml test-data/meme_output_html_1.html test-data/meme_output_html_2.html test-data/meme_output_txt_1.txt test-data/meme_output_txt_2.txt test-data/meme_output_xml_2.xml test-data/motif1.gff tool_dependencies.xml |
| diffstat | 13 files changed, 1929 insertions(+), 24 deletions(-) [+] |
line wrap: on
line diff
--- a/fimo.xml Thu Jun 16 08:07:03 2016 -0400 +++ b/fimo.xml Wed Jul 06 10:25:06 2016 -0400 @@ -1,8 +1,8 @@ -<tool id="meme_fimo" name="FIMO" version="4.11.0.3"> +<tool id="meme_fimo" name="FIMO" version="4.11.1.0"> <description>- Scan a set of sequences for motifs.</description> <requirements> - <requirement type="package" version="6.9.3">imagemagick</requirement> - <requirement type="package" version="4.11.0">meme</requirement> + <requirement type="package" version="1.3.20">graphicsmagick</requirement> + <requirement type="package" version="4.11.1">meme</requirement> </requirements> <command> <![CDATA[ @@ -117,7 +117,10 @@ <option value="yes">Yes</option> </param> <when value="yes"> - <param name="remove_duplicate_coords" type="boolean" truevalue="yes" falsevalue="no" label="Remove duplicate entries in unique GFF coordinates?" help="Remove duplicate entries as defined by the unique GFF coordinates" /> + <param name="remove_duplicate_coords" type="select" label="Remove duplicate entries in unique GFF coordinates?" help="Remove duplicate entries as defined by the unique GFF coordinates"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> </when> <when value="no"/> </conditional> @@ -178,7 +181,7 @@ </actions> </data> <data format="tabular" name="gff_outfile" label="${tool.name} on ${on_string} (almost-gff)"> - <filter>options_type['output_separate_motifs'] == 'no'</filter> + <filter>options_type['options_type_selector'] == 'basic' or (options_type['options_type_selector'] == 'advanced' and options_type['output_separate_motifs'] == 'no')</filter> <actions> <conditional name="fasta_type.fasta_type_selector"> <when value="cached"> @@ -193,7 +196,7 @@ </data> <collection name="motifs" type="list" label="Motifs: ${tool.name} on ${on_string}"> <discover_datasets pattern="(?P<designation>.*)" directory="output" ext="gff" visible="false" /> - <filter>options_type['output_separate_motifs'] == 'yes'</filter> + <filter>options_type['options_type_selector'] == 'advanced' and options_type['output_separate_motifs'] == 'yes'</filter> </collection> <data format="cisml" name="xml_outfile" label="${tool.name} on ${on_string} (xml)"> <actions>
--- a/fimo_wrapper.py Thu Jun 16 08:07:03 2016 -0400 +++ b/fimo_wrapper.py Wed Jul 06 10:25:06 2016 -0400 @@ -56,13 +56,13 @@ parser.add_argument('--max_strand', action='store_true', help='If matches on both strands at a given position satisfy the output threshold, only report the match for the strand with the higher score') parser.add_argument('--max_stored_scores', dest='max_stored_scores', type=int, help='Maximum score count to store') parser.add_argument('--motif', dest='motifs', action='append', default=[], help='Specify motif by id') -parser.add_argument('--output_separate_motifs', default="no", help='Output one dataset per motif') +parser.add_argument('--output_separate_motifs', dest='output_separate_motifs', default='no', help='Output one dataset per motif') parser.add_argument('--motif_pseudo', dest='motif_pseudo', type=float, default=0.1, help='Pseudocount to add to counts in motif matrix') parser.add_argument('--no_qvalue', action='store_true', help='Do not compute a q-value for each p-value') parser.add_argument('--norc', action='store_true', help='Do not score the reverse complement DNA strand') parser.add_argument('--output_path', dest='output_path', help='Output files directory') -parser.add_argument('--parse_genomic_coord', default='no', help='Check each sequence header for UCSC style genomic coordinates') -parser.add_argument('--remove_duplicate_coords', default='no', help='Remove duplicate entries in unique GFF coordinates') +parser.add_argument('--parse_genomic_coord', dest='parse_genomic_coord', default='no', help='Check each sequence header for UCSC style genomic coordinates') +parser.add_argument('--remove_duplicate_coords', dest='remove_duplicate_coords', default='no', help='Remove duplicate entries in unique GFF coordinates') parser.add_argument('--qv_thresh', action='store_true', help='Use q-values for the output threshold') parser.add_argument('--thresh', dest='thresh', type=float, help='p-value threshold') parser.add_argument('--gff_output', dest='gff_output', help='Gff output file')
--- a/test-data/fimo_output_html_1.html Thu Jun 16 08:07:03 2016 -0400 +++ b/test-data/fimo_output_html_1.html Wed Jul 06 10:25:06 2016 -0400 @@ -41,12 +41,10 @@ <hr> <div style="padding-left: 0.75in; line-height: 1em; font-family: monospace;"> <p> - DATABASE /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2541.dat <br /> Database contains 1 sequences, 5386 residues </p> <p> - MOTIFS /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2540.dat (Protein) <table> <thead> <tr> @@ -98,3 +96,5 @@ probability of a random sequence of the same length as the motif matching that position of the sequence with as good or better a score. </li> +<li> +The score for the match of a position in a sequence to a motif
--- a/test-data/fimo_output_html_2.html Thu Jun 16 08:07:03 2016 -0400 +++ b/test-data/fimo_output_html_2.html Wed Jul 06 10:25:06 2016 -0400 @@ -96,3 +96,5 @@ probability of a random sequence of the same length as the motif matching that position of the sequence with as good or better a score. </li> +<li> +The score for the match of a position in a sequence to a motif
--- a/test-data/fimo_output_xml_1.xml Thu Jun 16 08:07:03 2016 -0400 +++ b/test-data/fimo_output_xml_1.xml Wed Jul 06 10:25:06 2016 -0400 @@ -4,11 +4,7 @@ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation= xmlns:fimo="http://noble.gs.washington.edu/schema/fimo" > -<command-line>fimo --o /Users/gvk/work/git_workspace/galaxy/database/job_working_directory/001/1973/dataset_2713_files --verbosity 1 /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2540.dat /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2541.dat</command-line> <settings> -<setting name="output directory">/Users/gvk/work/git_workspace/galaxy/database/job_working_directory/001/1973/dataset_2713_files</setting> -<setting name="MEME file name">/Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2540.dat</setting> -<setting name="sequence file name">/Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2541.dat</setting> <setting name="allow clobber">false</setting> <setting name="compute q-values">true</setting> <setting name="parse genomic coord.">false</setting>
--- a/test-data/fimo_output_xml_2.xml Thu Jun 16 08:07:03 2016 -0400 +++ b/test-data/fimo_output_xml_2.xml Wed Jul 06 10:25:06 2016 -0400 @@ -4,14 +4,9 @@ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation= xmlns:fimo="http://noble.gs.washington.edu/schema/fimo" > -<command-line>fimo --alpha 1.000000 --max-stored-scores 100000 --motif-pseudo 0.100000 --no-qvalue --thresh 0.000100 --o /Users/gvk/work/git_workspace/galaxy/database/job_working_directory/001/1978/dataset_2738_files --verbosity 1 /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2540.dat /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2541.dat</command-line> <settings> -<setting name="output directory">/Users/gvk/work/git_workspace/galaxy/database/job_working_directory/001/1978/dataset_2738_files</setting> -<setting name="MEME file name">/Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2540.dat</setting> -<setting name="sequence file name">/Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2541.dat</setting> <setting name="allow clobber">false</setting> <setting name="compute q-values">false</setting> -<setting name="parse genomic coord.">false</setting> <setting name="text only">false</setting> <setting name="scan both strands">false</setting> <setting name="output threshold">0.0001</setting>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/meme_output_html_1.html Wed Jul 06 10:25:06 2016 -0400 @@ -0,0 +1,97 @@ +<!DOCTYPE HTML> +<html> + <head> + <meta charset="UTF-8"> + <title>MEME</title> + <script> + // @JSON_VAR data + var data = { + "program": "MEME", + "version": "4.11.0", + "release": "Thu Nov 26 17:48:49 2015 +1000", + "stop_reason": "Stopped because requested number of motifs (1) found.", + "cmd": [ + "meme", + "-nostatus" + ], + "options": { + "mod": "zoops", + "revcomp": false, + "nmotifs": 1, + "minw": 8, + "maxw": 50, + "minsites": 2, + "maxsites": 30, + "wnsites": 0.8, + "spmap": "pam", + "spfuzz": 120, + "maxwords": -1, + "prior": "megap", + "b": 7500, + "maxiter": 50, + "distance": 1e-05, + "wg": 11, + "ws": 1, + "noendgaps": false, + "substring": true + }, + "alphabet": { + "name": "Protein", + "like": "protein", + "ncore": 20, + "symbols": [ + { + "symbol": "A", + "name": "Alanine", + "colour": "0000CC" + }, { + "symbol": "C", + "name": "Cysteine", + "colour": "0000CC" + }, { + "symbol": "D", + "name": "Aspartic acid", + "colour": "FF00FF" + }, { + "symbol": "E", + "name": "Glutamic acid", + "colour": "FF00FF" + }, { + "symbol": "F", + "name": "Phenylalanine", + "colour": "0000CC" + }, { + "symbol": "G", + "name": "Glycine", + "colour": "FFB300" + }, { + "symbol": "H", + "name": "Histidine", + "colour": "FFCCCC" + }, { + "symbol": "I", + "name": "Isoleucine", + "colour": "0000CC" + }, { + "symbol": "K", + "name": "Lysine", + "colour": "CC0000" + }, { + "symbol": "L", + "name": "Leucine", + "colour": "0000CC" + }, { + "symbol": "M", + "name": "Methionine", + "colour": "0000CC" + }, { + "symbol": "N", + "name": "Asparagine", + "colour": "008000" + }, { + "symbol": "P", + "name": "Proline", + "colour": "FFFF00" + }, { + "symbol": "Q", + "name": "Glutamine",
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/meme_output_html_2.html Wed Jul 06 10:25:06 2016 -0400 @@ -0,0 +1,91 @@ +<!DOCTYPE HTML> +<html> + <head> + <meta charset="UTF-8"> + <title>MEME</title> + <script> + // @JSON_VAR data + var data = { + "program": "MEME", + "version": "4.11.0", + "release": "Thu Nov 26 17:48:49 2015 +1000", + "stop_reason": "Stopped because requested number of motifs (1) found.", + "cmd": [ + "meme", + ], + "options": { + "mod": "zoops", + "revcomp": false, + "nmotifs": 1, + "minw": 8, + "maxw": 50, + "minsites": 2, + "maxsites": 30, + "wnsites": 0.8, + "spmap": "uni", + "spfuzz": 0.5, + "maxwords": -1, + "prior": "dirichlet", + "b": 0.01, + "maxiter": 50, + "distance": 0.001, + "wg": 11, + "ws": 1, + "noendgaps": false, + "substring": true + }, + "alphabet": { + "name": "DNA", + "like": "dna", + "ncore": 4, + "symbols": [ + { + "symbol": "A", + "name": "Adenine", + "colour": "CC0000", + "complement": "T" + }, { + "symbol": "C", + "name": "Cytosine", + "colour": "0000CC", + "complement": "G" + }, { + "symbol": "G", + "name": "Guanine", + "colour": "FFB300", + "complement": "C" + }, { + "symbol": "T", + "aliases": "U", + "name": "Thymine", + "colour": "008000", + "complement": "A" + }, { + "symbol": "N", + "aliases": "X.", + "name": "Any base", + "equals": "ACGT" + }, { + "symbol": "V", + "name": "Not T", + "equals": "ACG" + }, { + "symbol": "H", + "name": "Not G", + "equals": "ACT" + }, { + "symbol": "D", + "name": "Not C", + "equals": "AGT" + }, { + "symbol": "B", + "name": "Not A", + "equals": "CGT" + }, { + "symbol": "M", + "name": "Amino", + "equals": "AC" + }, { + "symbol": "R", + "name": "Purine", + "equals": "AG"
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/meme_output_txt_1.txt Wed Jul 06 10:25:06 2016 -0400 @@ -0,0 +1,325 @@ +******************************************************************************** +MEME - Motif discovery tool +******************************************************************************** +MEME version 4.11.0 (Release date: Thu Nov 26 17:48:49 2015 +1000) + +For further information on how to interpret these results or to get +a copy of the MEME software please access http://meme-suite.org . + +This file may be used as input to the MAST algorithm for searching +sequence databases for matches to groups of motifs. MAST is available +for interactive use and downloading at http://meme-suite.org . +******************************************************************************** + + +******************************************************************************** +REFERENCE +******************************************************************************** +If you use this program in your research, please cite: + +Timothy L. Bailey and Charles Elkan, +"Fitting a mixture model by expectation maximization to discover +motifs in biopolymers", Proceedings of the Second International +Conference on Intelligent Systems for Molecular Biology, pp. 28-36, +AAAI Press, Menlo Park, California, 1994. +******************************************************************************** + + +******************************************************************************** +TRAINING SET +******************************************************************************** +DATAFILE= +ALPHABET= ACDEFGHIKLMNPQRSTVWY +Sequence name Weight Length Sequence name Weight Length +------------- ------ ------ ------------- ------ ------ +chr21_19617074_19617124_ 1.0000 50 chr21_26934381_26934431_ 1.0000 50 +chr21_28217753_28217803_ 1.0000 50 chr21_31710037_31710087_ 1.0000 50 +chr21_31744582_31744632_ 1.0000 50 chr21_31768316_31768366_ 1.0000 50 +chr21_31914206_31914256_ 1.0000 50 chr21_31933633_31933683_ 1.0000 50 +chr21_31962741_31962791_ 1.0000 50 chr21_31964683_31964733_ 1.0000 50 +chr21_31973364_31973414_ 1.0000 50 chr21_31992870_31992920_ 1.0000 50 +chr21_32185595_32185645_ 1.0000 50 chr21_32202076_32202126_ 1.0000 50 +chr21_32253899_32253949_ 1.0000 50 chr21_32410820_32410870_ 1.0000 50 +chr21_36411748_36411798_ 1.0000 50 chr21_37838750_37838800_ 1.0000 50 +chr21_45705687_45705737_ 1.0000 50 chr21_45971413_45971463_ 1.0000 50 +chr21_45978668_45978718_ 1.0000 50 chr21_45993530_45993580_ 1.0000 50 +chr21_46020421_46020471_ 1.0000 50 chr21_46031920_46031970_ 1.0000 50 +chr21_46046964_46047014_ 1.0000 50 chr21_46057197_46057247_ 1.0000 50 +chr21_46086869_46086919_ 1.0000 50 chr21_46102103_46102153_ 1.0000 50 +chr21_47517957_47518007_ 1.0000 50 chr21_47575506_47575556_ 1.0000 50 +******************************************************************************** + +******************************************************************************** +COMMAND LINE SUMMARY +******************************************************************************** +This information can also be useful in the event you wish to report a +problem with the MEME software. + +command: meme + +model: mod= zoops nmotifs= 1 evt= inf +object function= E-value of product of p-values +width: minw= 8 maxw= 50 +width: wg= 11 ws= 1 endgaps= yes +nsites: minsites= 2 maxsites= 30 wnsites= 0.8 +theta: spmap= pam spfuzz= 120 +global: substring= yes branching= no wbranch= no +em: prior= megap b= 7500 maxiter= 50 + distance= 1e-05 +data: n= 1500 N= 30 shuffle= -1 + +sample: seed= 0 ctfrac= -1 maxwords= -1 +Dirichlet mixture priors file: prior30.plib +Letter frequencies in dataset: +A 0.294 C 0.231 D 0.000 E 0.000 F 0.000 G 0.257 H 0.000 I 0.000 K 0.000 +L 0.000 M 0.000 N 0.000 P 0.000 Q 0.000 R 0.000 S 0.000 T 0.217 V 0.000 +W 0.000 Y 0.000 +Background letter frequencies (from dataset with add-one prior applied): +A 0.291 C 0.229 D 0.001 E 0.001 F 0.001 G 0.255 H 0.001 I 0.001 K 0.001 +L 0.001 M 0.001 N 0.001 P 0.001 Q 0.001 R 0.001 S 0.001 T 0.215 V 0.001 +W 0.001 Y 0.001 +******************************************************************************** + + +******************************************************************************** +MOTIF 1 MEME width = 11 sites = 25 llr = 239 E-value = 2.4e-011 +******************************************************************************** +-------------------------------------------------------------------------------- + Motif 1 Description +-------------------------------------------------------------------------------- +Simplified A 2323:a:a8a8 +pos.-specific C ::3:::::::: +probability D ::::::::::: +matrix E ::::::::::: + F ::::::::::: + G 7746::::::1 + H ::::::::::: + I ::::::::::: + K ::::::::::: + L ::::::::::: + M ::::::::::: + N ::::::::::: + P ::::::::::: + Q ::::::::::: + R ::::::::::: + S ::::::::::: + T 1:2:a:a:2:: + V ::::::::::: + W ::::::::::: + Y ::::::::::: + + bits 10.6 + 9.5 + 8.5 + 7.4 +Relative 6.3 +Entropy 5.3 +(13.8 bits) 4.2 + 3.2 + 2.1 * ** + 1.1 ** ******** + 0.0 ----------- + +Multilevel GGGGTATAAAA +consensus AACA T +sequence + + +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 sites sorted by position p-value +-------------------------------------------------------------------------------- +Sequence name Start P-value Site +------------- ----- --------- ----------- +chr21_46046964_46047014_ 13 1.06e-06 AAGGCCAGGA GGGGTATAAAA GCCTGAGAGC +chr21_46057197_46057247_ 37 3.41e-06 ACAGGCCCTG GGCATATAAAA GCC +chr21_45971413_45971463_ 10 3.41e-06 CAGGCCCTG GGCATATAAAA GCCCCAGCAG +chr21_31964683_31964733_ 14 3.41e-06 GATTCACTGA GGCATATAAAA GGCCCTCTGC +chr21_45993530_45993580_ 8 4.00e-06 CCAAGGA GGAGTATAAAA GCCCCACAAA +chr21_32202076_32202126_ 14 5.01e-06 CCACCAGCTT GAGGTATAAAA AGCCCTGTAC +chr21_46031920_46031970_ 16 6.06e-06 ATACCCAGGG AGGGTATAAAA CCTCAGCAGC +chr21_32410820_32410870_ 22 8.67e-06 AATCACTGAG GATGTATAAAA GTCCCAGGGA +chr21_32185595_32185645_ 19 8.67e-06 CACCAGAGCT GGGATATATAA AGAAGGTTCT +chr21_31992870_31992920_ 17 8.67e-06 CACTATTGAA GATGTATAAAA TTTCATTTGC +chr21_46020421_46020471_ 3 1.21e-05 GA GACATATAAAA GCCAACATCC +chr21_47517957_47518007_ 33 1.59e-05 CCGGCGGGGC GGGGTATAAAG GGGGCGG +chr21_45978668_45978718_ 5 1.59e-05 CAGA GGGGTATAAAG GTTCCGACCA +chr21_31914206_31914256_ 16 1.68e-05 CCCACTACTT AGAGTATAAAA TCATTCTGAG +chr21_32253899_32253949_ 20 2.03e-05 CACCAGCAAG GATATATAAAA GCTCAGGAGT +chr21_31744582_31744632_ 13 3.06e-05 CAGGTCTAAG AGCATATATAA CTTGGAGTCC +chr21_19617074_19617124_ 40 3.06e-05 CCTCGGGACG TGGGTATATAA +chr21_45705687_45705737_ 38 3.82e-05 CGTGGTCGCG GGGGTATAACA GC +chr21_31768316_31768366_ 1 3.82e-05 . AACGTATATAA ATGGTCCTGT +chr21_47575506_47575556_ 31 4.02e-05 GCTGCCGGTG AGCGTATAAAG GCCCTGGCG +chr21_26934381_26934431_ 28 5.52e-05 AGTCACAAGT GAGTTATAAAA GGGTCGCACG +chr21_31710037_31710087_ 15 5.94e-05 CCCAGGTTTC TGAGTATATAA TCGCCGCACC +chr21_36411748_36411798_ 23 6.78e-05 AGTTTCAGTT GGCATCtaaaa attatataac +chr21_31933633_31933683_ 3 2.08e-04 TC AGAGTATATAT AAATGTTCCT +chr21_31962741_31962791_ 14 4.05e-04 TATAACTCAG GTTGGATAAAA TAATTTGTAC +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 block diagrams +-------------------------------------------------------------------------------- +SEQUENCE NAME POSITION P-VALUE MOTIF DIAGRAM +------------- ---------------- ------------- +chr21_46046964_46047014_ 1.1e-06 12_[1]_27 +chr21_46057197_46057247_ 3.4e-06 36_[1]_3 +chr21_45971413_45971463_ 3.4e-06 9_[1]_30 +chr21_31964683_31964733_ 3.4e-06 13_[1]_26 +chr21_45993530_45993580_ 4e-06 7_[1]_32 +chr21_32202076_32202126_ 5e-06 13_[1]_26 +chr21_46031920_46031970_ 6.1e-06 15_[1]_24 +chr21_32410820_32410870_ 8.7e-06 21_[1]_18 +chr21_32185595_32185645_ 8.7e-06 18_[1]_21 +chr21_31992870_31992920_ 8.7e-06 16_[1]_23 +chr21_46020421_46020471_ 1.2e-05 2_[1]_37 +chr21_47517957_47518007_ 1.6e-05 32_[1]_7 +chr21_45978668_45978718_ 1.6e-05 4_[1]_35 +chr21_31914206_31914256_ 1.7e-05 15_[1]_24 +chr21_32253899_32253949_ 2e-05 19_[1]_20 +chr21_31744582_31744632_ 3.1e-05 12_[1]_27 +chr21_19617074_19617124_ 3.1e-05 39_[1] +chr21_45705687_45705737_ 3.8e-05 37_[1]_2 +chr21_31768316_31768366_ 3.8e-05 [1]_39 +chr21_47575506_47575556_ 4e-05 30_[1]_9 +chr21_26934381_26934431_ 5.5e-05 27_[1]_12 +chr21_31710037_31710087_ 5.9e-05 14_[1]_25 +chr21_36411748_36411798_ 6.8e-05 22_[1]_17 +chr21_31933633_31933683_ 0.00021 2_[1]_37 +chr21_31962741_31962791_ 0.0004 13_[1]_26 +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 in BLOCKS format +-------------------------------------------------------------------------------- +BL MOTIF 1 width=11 seqs=25 +chr21_46046964_46047014_ ( 13) GGGGTATAAAA 1 +chr21_46057197_46057247_ ( 37) GGCATATAAAA 1 +chr21_45971413_45971463_ ( 10) GGCATATAAAA 1 +chr21_31964683_31964733_ ( 14) GGCATATAAAA 1 +chr21_45993530_45993580_ ( 8) GGAGTATAAAA 1 +chr21_32202076_32202126_ ( 14) GAGGTATAAAA 1 +chr21_46031920_46031970_ ( 16) AGGGTATAAAA 1 +chr21_32410820_32410870_ ( 22) GATGTATAAAA 1 +chr21_32185595_32185645_ ( 19) GGGATATATAA 1 +chr21_31992870_31992920_ ( 17) GATGTATAAAA 1 +chr21_46020421_46020471_ ( 3) GACATATAAAA 1 +chr21_47517957_47518007_ ( 33) GGGGTATAAAG 1 +chr21_45978668_45978718_ ( 5) GGGGTATAAAG 1 +chr21_31914206_31914256_ ( 16) AGAGTATAAAA 1 +chr21_32253899_32253949_ ( 20) GATATATAAAA 1 +chr21_31744582_31744632_ ( 13) AGCATATATAA 1 +chr21_19617074_19617124_ ( 40) TGGGTATATAA 1 +chr21_45705687_45705737_ ( 38) GGGGTATAACA 1 +chr21_31768316_31768366_ ( 1) AACGTATATAA 1 +chr21_47575506_47575556_ ( 31) AGCGTATAAAG 1 +chr21_26934381_26934431_ ( 28) GAGTTATAAAA 1 +chr21_31710037_31710087_ ( 15) TGAGTATATAA 1 +chr21_36411748_36411798_ ( 23) GGCATCTAAAA 1 +chr21_31933633_31933683_ ( 3) AGAGTATATAT 1 +chr21_31962741_31962791_ ( 14) GTTGGATAAAA 1 +// + +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 position-specific scoring matrix +-------------------------------------------------------------------------------- +log-odds matrix: alength= 20 w= 11 n= 1200 bayes= 5.33554 E= 2.4e-011 + -32 -680 91 77 7 138 -20 55 64 107 11 150 142 72 87 396 -148 221 -140 -36 + -11 -680 89 76 7 137 -21 55 63 107 10 149 141 71 87 396 -239 220 -140 -36 + -79 41 4 21 -7 44 -62 42 -5 99 0 99 138 52 42 399 -46 223 -173 -68 + 11 -677 48 47 -2 127 -43 46 27 101 3 124 138 60 62 397 -235 220 -160 -55 + -596 -820 12 -21 -53 -267 -74 37 16 44 -37 98 31 9 19 319 212 127 -193 -95 + 165 -261 70 110 77 -521 -4 147 95 201 90 121 124 91 107 425 -527 314 -95 8 + -838 -990 -89 -149 -151 -841 -161 -117 -113 -66 -209 -68 -69 -129 -91 111 221 -55 -255 -173 + 176 -858 -79 -103 -115 -717 -148 -95 -108 -17 -162 -61 -12 -95 -69 193 -737 52 -240 -153 + 134 -686 0 16 -12 -553 -68 44 -8 96 -9 88 124 41 36 384 11 216 -177 -71 + 165 -261 70 110 77 -521 -4 147 95 201 90 121 124 91 107 425 -527 314 -95 8 + 147 -614 89 129 93 -121 12 160 113 217 108 144 144 111 125 447 -241 332 -81 22 +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 position-specific probability matrix +-------------------------------------------------------------------------------- +letter-probability matrix: alength= 20 w= 11 nsites= 25 E= 2.4e-011 + 0.240000 0.000000 0.000000 0.000000 0.000000 0.680000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.080000 0.000000 0.000000 0.000000 + 0.280000 0.000000 0.000000 0.000000 0.000000 0.680000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.040000 0.000000 0.000000 0.000000 + 0.160000 0.320000 0.000000 0.000000 0.000000 0.360000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.160000 0.000000 0.000000 0.000000 + 0.320000 0.000000 0.000000 0.000000 0.000000 0.640000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.040000 0.000000 0.000000 0.000000 + 0.000000 0.000000 0.000000 0.000000 0.000000 0.040000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.960000 0.000000 0.000000 0.000000 + 0.960000 0.040000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 + 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 + 1.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 + 0.760000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.240000 0.000000 0.000000 0.000000 + 0.960000 0.040000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 + 0.840000 0.000000 0.000000 0.000000 0.000000 0.120000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.040000 0.000000 0.000000 0.000000 +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 regular expression +-------------------------------------------------------------------------------- +[GA][GA][GC][GA]TATA[AT]AA +-------------------------------------------------------------------------------- + + + + +Time + +******************************************************************************** + + +******************************************************************************** +SUMMARY OF MOTIFS +******************************************************************************** + +-------------------------------------------------------------------------------- + Combined block diagrams: non-overlapping sites with p-value < 0.0001 +-------------------------------------------------------------------------------- +SEQUENCE NAME COMBINED P-VALUE MOTIF DIAGRAM +------------- ---------------- ------------- +chr21_19617074_19617124_ 1.22e-03 39_[1(3.06e-05)] +chr21_26934381_26934431_ 2.21e-03 27_[1(5.52e-05)]_12 +chr21_28217753_28217803_ 7.29e-01 50 +chr21_31710037_31710087_ 2.37e-03 14_[1(5.94e-05)]_25 +chr21_31744582_31744632_ 1.22e-03 12_[1(3.06e-05)]_27 +chr21_31768316_31768366_ 1.53e-03 [1(3.82e-05)]_39 +chr21_31914206_31914256_ 6.70e-04 15_[1(1.68e-05)]_24 +chr21_31933633_31933683_ 1.81e-03 4_[1(4.54e-05)]_35 +chr21_31962741_31962791_ 1.61e-02 50 +chr21_31964683_31964733_ 1.36e-04 13_[1(3.41e-06)]_26 +chr21_31973364_31973414_ 1.99e-01 50 +chr21_31992870_31992920_ 3.47e-04 16_[1(8.67e-06)]_23 +chr21_32185595_32185645_ 3.47e-04 18_[1(8.67e-06)]_21 +chr21_32202076_32202126_ 2.01e-04 13_[1(5.01e-06)]_26 +chr21_32253899_32253949_ 8.11e-04 19_[1(2.03e-05)]_20 +chr21_32410820_32410870_ 3.47e-04 21_[1(8.67e-06)]_18 +chr21_36411748_36411798_ 2.71e-03 22_[1(6.78e-05)]_17 +chr21_37838750_37838800_ 8.23e-02 50 +chr21_45705687_45705737_ 1.53e-03 37_[1(3.82e-05)]_2 +chr21_45971413_45971463_ 1.36e-04 9_[1(3.41e-06)]_30 +chr21_45978668_45978718_ 6.37e-04 4_[1(1.59e-05)]_35 +chr21_45993530_45993580_ 1.60e-04 7_[1(4.00e-06)]_32 +chr21_46020421_46020471_ 4.83e-04 2_[1(1.21e-05)]_37 +chr21_46031920_46031970_ 2.43e-04 15_[1(6.06e-06)]_24 +chr21_46046964_46047014_ 4.26e-05 12_[1(1.06e-06)]_27 +chr21_46057197_46057247_ 1.36e-04 36_[1(3.41e-06)]_3 +chr21_46086869_46086919_ 4.30e-02 50 +chr21_46102103_46102153_ 4.30e-02 50 +chr21_47517957_47518007_ 6.37e-04 32_[1(1.59e-05)]_7 +chr21_47575506_47575556_ 1.61e-03 30_[1(4.02e-05)]_9 +-------------------------------------------------------------------------------- + +******************************************************************************** + + +******************************************************************************** +Stopped because requested number of motifs (1) found. +******************************************************************************** + +CPU: + +********************************************************************************
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/meme_output_txt_2.txt Wed Jul 06 10:25:06 2016 -0400 @@ -0,0 +1,319 @@ +******************************************************************************** +MEME - Motif discovery tool +******************************************************************************** +MEME version 4.11.0 (Release date: Thu Nov 26 17:48:49 2015 +1000) + +For further information on how to interpret these results or to get +a copy of the MEME software please access http://meme-suite.org . + +This file may be used as input to the MAST algorithm for searching +sequence databases for matches to groups of motifs. MAST is available +for interactive use and downloading at http://meme-suite.org . +******************************************************************************** + + +******************************************************************************** +REFERENCE +******************************************************************************** +If you use this program in your research, please cite: + +Timothy L. Bailey and Charles Elkan, +"Fitting a mixture model by expectation maximization to discover +motifs in biopolymers", Proceedings of the Second International +Conference on Intelligent Systems for Molecular Biology, pp. 28-36, +AAAI Press, Menlo Park, California, 1994. +******************************************************************************** + + +******************************************************************************** +TRAINING SET +******************************************************************************** +DATAFILE= Galaxy_FASTA_Input +ALPHABET= ACGT +Sequence name Weight Length Sequence name Weight Length +------------- ------ ------ ------------- ------ ------ +chr21_19617074_19617124_ 1.0000 50 chr21_26934381_26934431_ 1.0000 50 +chr21_28217753_28217803_ 1.0000 50 chr21_31710037_31710087_ 1.0000 50 +chr21_31744582_31744632_ 1.0000 50 chr21_31768316_31768366_ 1.0000 50 +chr21_31914206_31914256_ 1.0000 50 chr21_31933633_31933683_ 1.0000 50 +chr21_31962741_31962791_ 1.0000 50 chr21_31964683_31964733_ 1.0000 50 +chr21_31973364_31973414_ 1.0000 50 chr21_31992870_31992920_ 1.0000 50 +chr21_32185595_32185645_ 1.0000 50 chr21_32202076_32202126_ 1.0000 50 +chr21_32253899_32253949_ 1.0000 50 chr21_32410820_32410870_ 1.0000 50 +chr21_36411748_36411798_ 1.0000 50 chr21_37838750_37838800_ 1.0000 50 +chr21_45705687_45705737_ 1.0000 50 chr21_45971413_45971463_ 1.0000 50 +chr21_45978668_45978718_ 1.0000 50 chr21_45993530_45993580_ 1.0000 50 +chr21_46020421_46020471_ 1.0000 50 chr21_46031920_46031970_ 1.0000 50 +chr21_46046964_46047014_ 1.0000 50 chr21_46057197_46057247_ 1.0000 50 +chr21_46086869_46086919_ 1.0000 50 chr21_46102103_46102153_ 1.0000 50 +chr21_47517957_47518007_ 1.0000 50 chr21_47575506_47575556_ 1.0000 50 +******************************************************************************** + +******************************************************************************** +COMMAND LINE SUMMARY +******************************************************************************** +This information can also be useful in the event you wish to report a +problem with the MEME software. + +command: meme + +model: mod= zoops nmotifs= 1 evt= inf +object function= E-value of product of p-values +width: minw= 8 maxw= 50 +width: wg= 11 ws= 1 endgaps= yes +nsites: minsites= 2 maxsites= 30 wnsites= 0.8 +theta: spmap= uni spfuzz= 0.5 +global: substring= yes branching= no wbranch= no +em: prior= dirichlet b= 0.01 maxiter= 50 + distance= 0.001 +data: n= 1500 N= 30 shuffle= -1 +strands: + +sample: seed= 0 ctfrac= -1 maxwords= -1 +Dirichlet mixture priors file: +Letter frequencies in dataset: +A 0.294 C 0.231 G 0.257 T 0.217 +Background letter frequencies (from dataset with add-one prior applied): +A 0.294 C 0.231 G 0.257 T 0.217 +******************************************************************************** + + +******************************************************************************** +MOTIF 1 MEME width = 11 sites = 30 llr = 254 E-value = 5.1e-040 +******************************************************************************** +-------------------------------------------------------------------------------- + Motif 1 Description +-------------------------------------------------------------------------------- +Simplified A 3313:9:a798 +pos.-specific C 1:3::1:::1: +probability G 6756::::::2 +matrix T 1:11a1a:3:: + + bits 2.2 * + 2.0 * * + 1.8 * * + 1.5 * ** * +Relative 1.3 * ** * +Entropy 1.1 ****** +(12.2 bits) 0.9 * ******* + 0.7 * ******* + 0.4 ** ******** + 0.2 *********** + 0.0 ----------- + +Multilevel GGGGTATAAAA +consensus AACA T +sequence + +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 sites sorted by position p-value +-------------------------------------------------------------------------------- +Sequence name Start P-value Site +------------- ----- --------- ----------- +chr21_46046964_46047014_ 13 4.51e-07 AAGGCCAGGA GGGGTATAAAA GCCTGAGAGC +chr21_46031920_46031970_ 16 2.22e-06 ATACCCAGGG AGGGTATAAAA CCTCAGCAGC +chr21_32202076_32202126_ 14 2.74e-06 CCACCAGCTT GAGGTATAAAA AGCCCTGTAC +chr21_46057197_46057247_ 37 4.86e-06 ACAGGCCCTG GGCATATAAAA GCC +chr21_45993530_45993580_ 8 4.86e-06 CCAAGGA GGAGTATAAAA GCCCCACAAA +chr21_45971413_45971463_ 10 4.86e-06 CAGGCCCTG GGCATATAAAA GCCCCAGCAG +chr21_31964683_31964733_ 14 4.86e-06 GATTCACTGA GGCATATAAAA GGCCCTCTGC +chr21_47517957_47518007_ 33 6.48e-06 CCGGCGGGGC GGGGTATAAAG GGGGCGG +chr21_45978668_45978718_ 5 6.48e-06 CAGA GGGGTATAAAG GTTCCGACCA +chr21_32185595_32185645_ 19 6.48e-06 CACCAGAGCT GGGATATATAA AGAAGGTTCT +chr21_32410820_32410870_ 22 1.38e-05 AATCACTGAG GATGTATAAAA GTCCCAGGGA +chr21_31992870_31992920_ 17 1.38e-05 CACTATTGAA GATGTATAAAA TTTCATTTGC +chr21_19617074_19617124_ 40 1.41e-05 CCTCGGGACG TGGGTATATAA +chr21_31914206_31914256_ 16 1.61e-05 CCCACTACTT AGAGTATAAAA TCATTCTGAG +chr21_46020421_46020471_ 3 1.95e-05 GA GACATATAAAA GCCAACATCC +chr21_32253899_32253949_ 18 1.95e-05 CCCACCAGCA AGGATATATAA AAGCTCAGGA +chr21_45705687_45705737_ 38 2.16e-05 CGTGGTCGCG GGGGTATAACA GC +chr21_47575506_47575556_ 31 3.04e-05 GCTGCCGGTG AGCGTATAAAG GCCCTGGCG +chr21_31744582_31744632_ 13 3.04e-05 CAGGTCTAAG AGCATATATAA CTTGGAGTCC +chr21_31768316_31768366_ 1 3.67e-05 . AACGTATATAA ATGGTCCTGT +chr21_26934381_26934431_ 28 3.93e-05 AGTCACAAGT GAGTTATAAAA GGGTCGCACG +chr21_31933633_31933683_ 5 5.65e-05 TCAG AGTATATATAA ATGTTCCTGT +chr21_31710037_31710087_ 15 6.24e-05 CCCAGGTTTC TGAGTATATAA TCGCCGCACC +chr21_36411748_36411798_ 23 7.15e-05 AGTTTCAGTT GGCATCtaaaa attatataac +chr21_46102103_46102153_ 37 1.39e-04 TGCCTGGGTC CAGGTATAAAG GCT +chr21_46086869_46086919_ 38 1.39e-04 TGCCTGGGCC CAGGTATAAAG GC +chr21_37838750_37838800_ 3 4.81e-04 ga tggttttataa ggggcctcac +chr21_31962741_31962791_ 14 8.57e-04 TATAACTCAG GTTGGATAAAA TAATTTGTAC +chr21_31973364_31973414_ 8 1.47e-03 aaactta aaactctataa acttaaaact +chr21_28217753_28217803_ 27 2.64e-03 GGTGGGGGTG GGGGTTTCACT GGTCCACTAT +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 block diagrams +-------------------------------------------------------------------------------- +SEQUENCE NAME POSITION P-VALUE MOTIF DIAGRAM +------------- ---------------- ------------- +chr21_46046964_46047014_ 4.5e-07 12_[+1]_27 +chr21_46031920_46031970_ 2.2e-06 15_[+1]_24 +chr21_32202076_32202126_ 2.7e-06 13_[+1]_26 +chr21_46057197_46057247_ 4.9e-06 36_[+1]_3 +chr21_45993530_45993580_ 4.9e-06 7_[+1]_32 +chr21_45971413_45971463_ 4.9e-06 9_[+1]_30 +chr21_31964683_31964733_ 4.9e-06 13_[+1]_26 +chr21_47517957_47518007_ 6.5e-06 32_[+1]_7 +chr21_45978668_45978718_ 6.5e-06 4_[+1]_35 +chr21_32185595_32185645_ 6.5e-06 18_[+1]_21 +chr21_32410820_32410870_ 1.4e-05 21_[+1]_18 +chr21_31992870_31992920_ 1.4e-05 16_[+1]_23 +chr21_19617074_19617124_ 1.4e-05 39_[+1] +chr21_31914206_31914256_ 1.6e-05 15_[+1]_24 +chr21_46020421_46020471_ 1.9e-05 2_[+1]_37 +chr21_32253899_32253949_ 1.9e-05 17_[+1]_22 +chr21_45705687_45705737_ 2.2e-05 37_[+1]_2 +chr21_47575506_47575556_ 3e-05 30_[+1]_9 +chr21_31744582_31744632_ 3e-05 12_[+1]_27 +chr21_31768316_31768366_ 3.7e-05 [+1]_39 +chr21_26934381_26934431_ 3.9e-05 27_[+1]_12 +chr21_31933633_31933683_ 5.6e-05 4_[+1]_35 +chr21_31710037_31710087_ 6.2e-05 14_[+1]_25 +chr21_36411748_36411798_ 7.1e-05 22_[+1]_17 +chr21_46102103_46102153_ 0.00014 36_[+1]_3 +chr21_46086869_46086919_ 0.00014 37_[+1]_2 +chr21_37838750_37838800_ 0.00048 2_[+1]_37 +chr21_31962741_31962791_ 0.00086 13_[+1]_26 +chr21_31973364_31973414_ 0.0015 7_[+1]_32 +chr21_28217753_28217803_ 0.0026 26_[+1]_13 +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 in BLOCKS format +-------------------------------------------------------------------------------- +BL MOTIF 1 width=11 seqs=30 +chr21_46046964_46047014_ ( 13) GGGGTATAAAA 1 +chr21_46031920_46031970_ ( 16) AGGGTATAAAA 1 +chr21_32202076_32202126_ ( 14) GAGGTATAAAA 1 +chr21_46057197_46057247_ ( 37) GGCATATAAAA 1 +chr21_45993530_45993580_ ( 8) GGAGTATAAAA 1 +chr21_45971413_45971463_ ( 10) GGCATATAAAA 1 +chr21_31964683_31964733_ ( 14) GGCATATAAAA 1 +chr21_47517957_47518007_ ( 33) GGGGTATAAAG 1 +chr21_45978668_45978718_ ( 5) GGGGTATAAAG 1 +chr21_32185595_32185645_ ( 19) GGGATATATAA 1 +chr21_32410820_32410870_ ( 22) GATGTATAAAA 1 +chr21_31992870_31992920_ ( 17) GATGTATAAAA 1 +chr21_19617074_19617124_ ( 40) TGGGTATATAA 1 +chr21_31914206_31914256_ ( 16) AGAGTATAAAA 1 +chr21_46020421_46020471_ ( 3) GACATATAAAA 1 +chr21_32253899_32253949_ ( 18) AGGATATATAA 1 +chr21_45705687_45705737_ ( 38) GGGGTATAACA 1 +chr21_47575506_47575556_ ( 31) AGCGTATAAAG 1 +chr21_31744582_31744632_ ( 13) AGCATATATAA 1 +chr21_31768316_31768366_ ( 1) AACGTATATAA 1 +chr21_26934381_26934431_ ( 28) GAGTTATAAAA 1 +chr21_31933633_31933683_ ( 5) AGTATATATAA 1 +chr21_31710037_31710087_ ( 15) TGAGTATATAA 1 +chr21_36411748_36411798_ ( 23) GGCATCTAAAA 1 +chr21_46102103_46102153_ ( 37) CAGGTATAAAG 1 +chr21_46086869_46086919_ ( 38) CAGGTATAAAG 1 +chr21_37838750_37838800_ ( 3) TGGTTTTATAA 1 +chr21_31962741_31962791_ ( 14) GTTGGATAAAA 1 +chr21_31973364_31973414_ ( 8) AAACTCTATAA 1 +chr21_28217753_28217803_ ( 27) GGGGTTTCACT 1 +// + +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 position-specific scoring matrix +-------------------------------------------------------------------------------- +log-odds matrix: alength= 4 w= 11 n= 1200 bayes= 5.2854 E= 5.1e-040 + -14 -179 114 -112 + 3 -1155 137 -270 + -114 20 86 -71 + 3 -279 122 -170 + -1155 -1155 -295 215 + 156 -179 -1155 -170 + -1155 -1155 -1155 220 + 172 -279 -1155 -1155 + 125 -1155 -1155 46 + 167 -179 -1155 -1155 + 144 -1155 -63 -270 +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 position-specific probability matrix +-------------------------------------------------------------------------------- +letter-probability matrix: alength= 4 w= 11 nsites= 30 E= 5.1e-040 + 0.266667 0.066667 0.566667 0.100000 + 0.300000 0.000000 0.666667 0.033333 + 0.133333 0.266667 0.466667 0.133333 + 0.300000 0.033333 0.600000 0.066667 + 0.000000 0.000000 0.033333 0.966667 + 0.866667 0.066667 0.000000 0.066667 + 0.000000 0.000000 0.000000 1.000000 + 0.966667 0.033333 0.000000 0.000000 + 0.700000 0.000000 0.000000 0.300000 + 0.933333 0.066667 0.000000 0.000000 + 0.800000 0.000000 0.166667 0.033333 +-------------------------------------------------------------------------------- + +-------------------------------------------------------------------------------- + Motif 1 regular expression +-------------------------------------------------------------------------------- +[GA][GA][GC][GA]TATA[AT]AA +-------------------------------------------------------------------------------- + + + + +Time + +******************************************************************************** + + +******************************************************************************** +SUMMARY OF MOTIFS +******************************************************************************** + +-------------------------------------------------------------------------------- + Combined block diagrams: non-overlapping sites with p-value < 0.0001 +-------------------------------------------------------------------------------- +SEQUENCE NAME COMBINED P-VALUE MOTIF DIAGRAM +------------- ---------------- ------------- +chr21_19617074_19617124_ 5.63e-04 39_[+1(1.41e-05)] +chr21_26934381_26934431_ 1.57e-03 27_[+1(3.93e-05)]_12 +chr21_28217753_28217803_ 1.00e-01 50 +chr21_31710037_31710087_ 2.49e-03 14_[+1(6.24e-05)]_25 +chr21_31744582_31744632_ 1.22e-03 12_[+1(3.04e-05)]_27 +chr21_31768316_31768366_ 1.47e-03 [+1(3.67e-05)]_39 +chr21_31914206_31914256_ 6.45e-04 15_[+1(1.61e-05)]_24 +chr21_31933633_31933683_ 2.26e-03 4_[+1(5.65e-05)]_35 +chr21_31962741_31962791_ 3.37e-02 50 +chr21_31964683_31964733_ 1.95e-04 13_[+1(4.86e-06)]_26 +chr21_31973364_31973414_ 5.73e-02 50 +chr21_31992870_31992920_ 5.52e-04 16_[+1(1.38e-05)]_23 +chr21_32185595_32185645_ 2.59e-04 18_[+1(6.48e-06)]_21 +chr21_32202076_32202126_ 1.10e-04 13_[+1(2.74e-06)]_26 +chr21_32253899_32253949_ 7.78e-04 17_[+1(1.95e-05)]_22 +chr21_32410820_32410870_ 5.52e-04 21_[+1(1.38e-05)]_18 +chr21_36411748_36411798_ 2.85e-03 22_[+1(7.15e-05)]_17 +chr21_37838750_37838800_ 1.90e-02 50 +chr21_45705687_45705737_ 8.63e-04 37_[+1(2.16e-05)]_2 +chr21_45971413_45971463_ 1.95e-04 9_[+1(4.86e-06)]_30 +chr21_45978668_45978718_ 2.59e-04 4_[+1(6.48e-06)]_35 +chr21_45993530_45993580_ 1.95e-04 7_[+1(4.86e-06)]_32 +chr21_46020421_46020471_ 7.78e-04 2_[+1(1.95e-05)]_37 +chr21_46031920_46031970_ 8.89e-05 15_[+1(2.22e-06)]_24 +chr21_46046964_46047014_ 1.80e-05 12_[+1(4.51e-07)]_27 +chr21_46057197_46057247_ 1.95e-04 36_[+1(4.86e-06)]_3 +chr21_46086869_46086919_ 5.54e-03 50 +chr21_46102103_46102153_ 5.54e-03 50 +chr21_47517957_47518007_ 2.59e-04 32_[+1(6.48e-06)]_7 +chr21_47575506_47575556_ 1.22e-03 30_[+1(3.04e-05)]_9 +-------------------------------------------------------------------------------- + +******************************************************************************** + + +******************************************************************************** +Stopped because requested number of motifs (1) found. +******************************************************************************** + +CPU: + +********************************************************************************
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/meme_output_xml_2.xml Wed Jul 06 10:25:06 2016 -0400 @@ -0,0 +1,977 @@ +<?xml version='1.0' encoding='UTF-8' standalone='yes'?> +<!-- Document definition --> +<!DOCTYPE MEME[ +<!ELEMENT MEME ( + training_set, + model, + motifs, + scanned_sites_summary? +)> +<!ATTLIST MEME + version CDATA #REQUIRED + release CDATA #REQUIRED +> +<!-- Training-set elements --> +<!ELEMENT training_set (alphabet, ambigs, sequence*, letter_frequencies)> +<!ATTLIST training_set datafile CDATA #REQUIRED length CDATA #REQUIRED> +<!ELEMENT alphabet (letter*)> +<!ATTLIST alphabet name CDATA #REQUIRED> +<!ELEMENT ambigs (letter*)> +<!ELEMENT letter EMPTY> +<!ATTLIST letter id ID #REQUIRED> +<!ATTLIST letter symbol CDATA #REQUIRED> +<!ATTLIST letter equals CDATA #IMPLIED> +<!ATTLIST letter aliases CDATA #IMPLIED> +<!ATTLIST letter complement CDATA #IMPLIED> +<!ATTLIST letter name CDATA #IMPLIED> +<!ATTLIST letter colour CDATA #IMPLIED> +<!ELEMENT sequence EMPTY> +<!ATTLIST sequence id ID #REQUIRED + name CDATA #REQUIRED + length CDATA #REQUIRED + weight CDATA #REQUIRED +> +<!ELEMENT letter_frequencies (alphabet_array)> + +<!-- Model elements --> +<!ELEMENT model ( + command_line, + host, + type, + nmotifs, + evalue_threshold, + object_function, + min_width, + max_width, + minic, + wg, + ws, + endgaps, + minsites, + maxsites, + wnsites, + prob, + spmap, + spfuzz, + prior, + beta, + maxiter, + distance, + num_sequences, + num_positions, + seed, + seqfrac, + strands, + priors_file, + reason_for_stopping, + background_frequencies +)> +<!ELEMENT command_line (#PCDATA)*> +<!ELEMENT host (#PCDATA)*> +<!ELEMENT type (#PCDATA)*> +<!ELEMENT nmotifs (#PCDATA)*> +<!ELEMENT evalue_threshold (#PCDATA)*> +<!ELEMENT object_function (#PCDATA)*> +<!ELEMENT min_width (#PCDATA)*> +<!ELEMENT max_width (#PCDATA)*> +<!ELEMENT minic (#PCDATA)*> +<!ELEMENT wg (#PCDATA)*> +<!ELEMENT ws (#PCDATA)*> +<!ELEMENT endgaps (#PCDATA)*> +<!ELEMENT minsites (#PCDATA)*> +<!ELEMENT maxsites (#PCDATA)*> +<!ELEMENT wnsites (#PCDATA)*> +<!ELEMENT prob (#PCDATA)*> +<!ELEMENT spmap (#PCDATA)*> +<!ELEMENT spfuzz (#PCDATA)*> +<!ELEMENT prior (#PCDATA)*> +<!ELEMENT beta (#PCDATA)*> +<!ELEMENT maxiter (#PCDATA)*> +<!ELEMENT distance (#PCDATA)*> +<!ELEMENT num_sequences (#PCDATA)*> +<!ELEMENT num_positions (#PCDATA)*> +<!ELEMENT seed (#PCDATA)*> +<!ELEMENT seqfrac (#PCDATA)*> +<!ELEMENT strands (#PCDATA)*> +<!ELEMENT priors_file (#PCDATA)*> +<!ELEMENT reason_for_stopping (#PCDATA)*> +<!ELEMENT background_frequencies (alphabet_array)> +<!ATTLIST background_frequencies source CDATA #REQUIRED> + +<!-- Motif elements --> +<!ELEMENT motifs (motif*)> +<!ELEMENT motif (scores, probabilities, regular_expression?, contributing_sites)> +<!ATTLIST motif id ID #REQUIRED + name CDATA #REQUIRED + width CDATA #REQUIRED + sites CDATA #REQUIRED + llr CDATA #REQUIRED + ic CDATA #REQUIRED + re CDATA #REQUIRED + bayes_threshold CDATA #REQUIRED + e_value CDATA #REQUIRED + elapsed_time CDATA #REQUIRED + url CDATA "" +> +<!ELEMENT scores (alphabet_matrix)> +<!ELEMENT probabilities (alphabet_matrix)> +<!ELEMENT regular_expression (#PCDATA)*> + +<!-- Contributing site elements --> +<!-- Contributing sites are motif occurences found during the motif discovery phase --> +<!ELEMENT contributing_sites (contributing_site*)> +<!ELEMENT contributing_site (left_flank, site, right_flank)> +<!ATTLIST contributing_site sequence_id IDREF #REQUIRED + position CDATA #REQUIRED + strand (plus|minus|none) 'none' + pvalue CDATA #REQUIRED +> +<!-- The left_flank contains the sequence for 10 bases to the left of the motif start --> +<!ELEMENT left_flank (#PCDATA)> +<!-- The site contains the sequence for the motif instance --> +<!ELEMENT site (letter_ref*)> +<!-- The right_flank contains the sequence for 10 bases to the right of the motif end --> +<!ELEMENT right_flank (#PCDATA)> + +<!-- Scanned site elements --> +<!-- Scanned sites are motif occurences found during the sequence scan phase --> +<!ELEMENT scanned_sites_summary (scanned_sites*)> +<!ATTLIST scanned_sites_summary p_thresh CDATA #REQUIRED> +<!ELEMENT scanned_sites (scanned_site*)> +<!ATTLIST scanned_sites sequence_id IDREF #REQUIRED + pvalue CDATA #REQUIRED + num_sites CDATA #REQUIRED> +<!ELEMENT scanned_site EMPTY> +<!ATTLIST scanned_site motif_id IDREF #REQUIRED + strand (plus|minus|none) 'none' + position CDATA #REQUIRED + pvalue CDATA #REQUIRED> + +<!-- Utility elements --> +<!-- A reference to a letter in the alphabet --> +<!ELEMENT letter_ref EMPTY> +<!ATTLIST letter_ref letter_id IDREF #REQUIRED> +<!-- A alphabet-array contains one floating point value for each letter in an alphabet --> +<!ELEMENT alphabet_array (value*)> +<!ELEMENT value (#PCDATA)> +<!ATTLIST value letter_id IDREF #REQUIRED> + +<!-- A alphabet_matrix contains one alphabet_array for each position in a motif --> +<!ELEMENT alphabet_matrix (alphabet_array*)> + +]> +<!-- Begin document body --> +<MEME version="4.11.0" release="Thu Nov 26 17:48:49 2015 +1000"> +<training_set datafile="Galaxy_FASTA_Input" length="30"> +<alphabet name="DNA" like="dna"> +<letter id="A" symbol="A" complement="T" name="Adenine" colour="CC0000"/> +<letter id="C" symbol="C" complement="G" name="Cytosine" colour="0000CC"/> +<letter id="G" symbol="G" complement="C" name="Guanine" colour="FFB300"/> +<letter id="T" symbol="T" aliases="U" complement="A" name="Thymine" colour="008000"/> +<letter id="N" symbol="N" aliases="X." equals="ACGT" name="Any base"/> +<letter id="V" symbol="V" equals="ACG" name="Not T"/> +<letter id="H" symbol="H" equals="ACT" name="Not G"/> +<letter id="D" symbol="D" equals="AGT" name="Not C"/> +<letter id="B" symbol="B" equals="CGT" name="Not A"/> +<letter id="M" symbol="M" equals="AC" name="Amino"/> +<letter id="R" symbol="R" equals="AG" name="Purine"/> +<letter id="W" symbol="W" equals="AT" name="Weak"/> +<letter id="S" symbol="S" equals="CG" name="Strong"/> +<letter id="Y" symbol="Y" equals="CT" name="Pyrimidine"/> +<letter id="K" symbol="K" equals="GT" name="Keto"/> +</alphabet> +<sequence id="sequence_0" name="chr21_19617074_19617124_+" length="50" weight="1.000000" /> +<sequence id="sequence_1" name="chr21_26934381_26934431_+" length="50" weight="1.000000" /> +<sequence id="sequence_2" name="chr21_28217753_28217803_-" length="50" weight="1.000000" /> +<sequence id="sequence_3" name="chr21_31710037_31710087_-" length="50" weight="1.000000" /> +<sequence id="sequence_4" name="chr21_31744582_31744632_-" length="50" weight="1.000000" /> +<sequence id="sequence_5" name="chr21_31768316_31768366_+" length="50" weight="1.000000" /> +<sequence id="sequence_6" name="chr21_31914206_31914256_-" length="50" weight="1.000000" /> +<sequence id="sequence_7" name="chr21_31933633_31933683_-" length="50" weight="1.000000" /> +<sequence id="sequence_8" name="chr21_31962741_31962791_-" length="50" weight="1.000000" /> +<sequence id="sequence_9" name="chr21_31964683_31964733_+" length="50" weight="1.000000" /> +<sequence id="sequence_10" name="chr21_31973364_31973414_+" length="50" weight="1.000000" /> +<sequence id="sequence_11" name="chr21_31992870_31992920_+" length="50" weight="1.000000" /> +<sequence id="sequence_12" name="chr21_32185595_32185645_-" length="50" weight="1.000000" /> +<sequence id="sequence_13" name="chr21_32202076_32202126_-" length="50" weight="1.000000" /> +<sequence id="sequence_14" name="chr21_32253899_32253949_-" length="50" weight="1.000000" /> +<sequence id="sequence_15" name="chr21_32410820_32410870_-" length="50" weight="1.000000" /> +<sequence id="sequence_16" name="chr21_36411748_36411798_-" length="50" weight="1.000000" /> +<sequence id="sequence_17" name="chr21_37838750_37838800_-" length="50" weight="1.000000" /> +<sequence id="sequence_18" name="chr21_45705687_45705737_+" length="50" weight="1.000000" /> +<sequence id="sequence_19" name="chr21_45971413_45971463_-" length="50" weight="1.000000" /> +<sequence id="sequence_20" name="chr21_45978668_45978718_-" length="50" weight="1.000000" /> +<sequence id="sequence_21" name="chr21_45993530_45993580_+" length="50" weight="1.000000" /> +<sequence id="sequence_22" name="chr21_46020421_46020471_+" length="50" weight="1.000000" /> +<sequence id="sequence_23" name="chr21_46031920_46031970_+" length="50" weight="1.000000" /> +<sequence id="sequence_24" name="chr21_46046964_46047014_+" length="50" weight="1.000000" /> +<sequence id="sequence_25" name="chr21_46057197_46057247_+" length="50" weight="1.000000" /> +<sequence id="sequence_26" name="chr21_46086869_46086919_-" length="50" weight="1.000000" /> +<sequence id="sequence_27" name="chr21_46102103_46102153_-" length="50" weight="1.000000" /> +<sequence id="sequence_28" name="chr21_47517957_47518007_+" length="50" weight="1.000000" /> +<sequence id="sequence_29" name="chr21_47575506_47575556_-" length="50" weight="1.000000" /> +<letter_frequencies> +<alphabet_array> +<value letter_id="A">0.294</value> +<value letter_id="C">0.231</value> +<value letter_id="G">0.257</value> +<value letter_id="T">0.217</value> +</alphabet_array> +</letter_frequencies> +</training_set> +<model> +<command_line>meme /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2490.dat -o /Users/gvk/work/git_workspace/galaxy/database/job_working_directory/001/1929/dataset_2578_files -nostatus -sf Galaxy_FASTA_Input -dna -mod zoops -nmotifs 1 -wnsites 0.8 -minw 8 -maxw 50 -wg 11 -ws 1 -maxiter 50 -distance 0.001 -prior dirichlet -b 0.01 -plib /Users/gvk/work/git_workspace/galaxy/database/files/002/dataset_2577.dat -spmap uni -spfuzz 0.5 </command_line> +<host>MacBook-Pro-2.local</host> +<type>zoops</type> +<nmotifs>1</nmotifs> +<evalue_threshold>inf</evalue_threshold> +<object_function>E-value of product of p-values</object_function> +<use_llr>0</use_llr> +<min_width>8</min_width> +<max_width>50</max_width> +<wg>11</wg> +<ws>1</ws> +<endgaps>yes</endgaps> +<substring>yes</substring> +<minsites>2</minsites> +<maxsites>30</maxsites> +<wnsites>0.8</wnsites> +<spmap>uni</spmap> +<spfuzz>0.5</spfuzz> +<prior>dirichlet</prior> +<beta>0.01</beta> +<maxiter>50</maxiter> +<distance>0.001</distance> +<num_sequences>30</num_sequences> +<num_positions>1500</num_positions> +<seed>0</seed> +<ctfrac>-1</ctfrac> +<maxwords>-1</maxwords> +<strands>forward</strands> +<priors_file>dataset_2577.dat</priors_file> +<reason_for_stopping>Stopped because requested number of motifs (1) found.</reason_for_stopping> +<background_frequencies source="dataset with add-one prior applied"> +<alphabet_array> +<value letter_id="A">0.294</value> +<value letter_id="C">0.231</value> +<value letter_id="G">0.257</value> +<value letter_id="T">0.217</value> +</alphabet_array> +</background_frequencies> +</model> +<motifs> +<motif id="motif_1" name="1" width="11" sites="30" ic="13.0" re="12.2" llr="254" e_value="5.1e-040" bayes_threshold="5.2854" elapsed_time="0.168106"> +<scores> +<alphabet_matrix> +<alphabet_array> +<value letter_id="A">-14</value> +<value letter_id="C">-179</value> +<value letter_id="G">114</value> +<value letter_id="T">-112</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">3</value> +<value letter_id="C">-1155</value> +<value letter_id="G">137</value> +<value letter_id="T">-270</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">-114</value> +<value letter_id="C">20</value> +<value letter_id="G">86</value> +<value letter_id="T">-71</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">3</value> +<value letter_id="C">-279</value> +<value letter_id="G">122</value> +<value letter_id="T">-170</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">-1155</value> +<value letter_id="C">-1155</value> +<value letter_id="G">-295</value> +<value letter_id="T">215</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">156</value> +<value letter_id="C">-179</value> +<value letter_id="G">-1155</value> +<value letter_id="T">-170</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">-1155</value> +<value letter_id="C">-1155</value> +<value letter_id="G">-1155</value> +<value letter_id="T">220</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">172</value> +<value letter_id="C">-279</value> +<value letter_id="G">-1155</value> +<value letter_id="T">-1155</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">125</value> +<value letter_id="C">-1155</value> +<value letter_id="G">-1155</value> +<value letter_id="T">46</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">167</value> +<value letter_id="C">-179</value> +<value letter_id="G">-1155</value> +<value letter_id="T">-1155</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">144</value> +<value letter_id="C">-1155</value> +<value letter_id="G">-63</value> +<value letter_id="T">-270</value> +</alphabet_array> +</alphabet_matrix> +</scores> +<probabilities> +<alphabet_matrix> +<alphabet_array> +<value letter_id="A">0.266667</value> +<value letter_id="C">0.066667</value> +<value letter_id="G">0.566667</value> +<value letter_id="T">0.100000</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.300000</value> +<value letter_id="C">0.000000</value> +<value letter_id="G">0.666667</value> +<value letter_id="T">0.033333</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.133333</value> +<value letter_id="C">0.266667</value> +<value letter_id="G">0.466667</value> +<value letter_id="T">0.133333</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.300000</value> +<value letter_id="C">0.033333</value> +<value letter_id="G">0.600000</value> +<value letter_id="T">0.066667</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.000000</value> +<value letter_id="C">0.000000</value> +<value letter_id="G">0.033333</value> +<value letter_id="T">0.966667</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.866667</value> +<value letter_id="C">0.066667</value> +<value letter_id="G">0.000000</value> +<value letter_id="T">0.066667</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.000000</value> +<value letter_id="C">0.000000</value> +<value letter_id="G">0.000000</value> +<value letter_id="T">1.000000</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.966667</value> +<value letter_id="C">0.033333</value> +<value letter_id="G">0.000000</value> +<value letter_id="T">0.000000</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.700000</value> +<value letter_id="C">0.000000</value> +<value letter_id="G">0.000000</value> +<value letter_id="T">0.300000</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.933333</value> +<value letter_id="C">0.066667</value> +<value letter_id="G">0.000000</value> +<value letter_id="T">0.000000</value> +</alphabet_array> +<alphabet_array> +<value letter_id="A">0.800000</value> +<value letter_id="C">0.000000</value> +<value letter_id="G">0.166667</value> +<value letter_id="T">0.033333</value> +</alphabet_array> +</alphabet_matrix> +</probabilities> +<regular_expression> +[GA][GA][GC][GA]TATA[AT]AA +</regular_expression> +<contributing_sites> +<contributing_site sequence_id="sequence_24" position="12" strand="plus" pvalue="4.51e-07" > +<left_flank>AAGGCCAGGA</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GCCTGAGAGC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_23" position="15" strand="plus" pvalue="2.22e-06" > +<left_flank>ATACCCAGGG</left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>CCTCAGCAGC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_13" position="13" strand="plus" pvalue="2.74e-06" > +<left_flank>CCACCAGCTT</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>AGCCCTGTAC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_25" position="36" strand="plus" pvalue="4.86e-06" > +<left_flank>ACAGGCCCTG</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GCC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_21" position="7" strand="plus" pvalue="4.86e-06" > +<left_flank>CCAAGGA</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GCCCCACAAA</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_19" position="9" strand="plus" pvalue="4.86e-06" > +<left_flank>CAGGCCCTG</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GCCCCAGCAG</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_9" position="13" strand="plus" pvalue="4.86e-06" > +<left_flank>GATTCACTGA</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GGCCCTCTGC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_28" position="32" strand="plus" pvalue="6.48e-06" > +<left_flank>CCGGCGGGGC</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +</site> +<right_flank>GGGGCGG</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_20" position="4" strand="plus" pvalue="6.48e-06" > +<left_flank>CAGA</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +</site> +<right_flank>GTTCCGACCA</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_12" position="18" strand="plus" pvalue="6.48e-06" > +<left_flank>CACCAGAGCT</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>AGAAGGTTCT</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_15" position="21" strand="plus" pvalue="1.38e-05" > +<left_flank>AATCACTGAG</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GTCCCAGGGA</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_11" position="16" strand="plus" pvalue="1.38e-05" > +<left_flank>CACTATTGAA</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>TTTCATTTGC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_0" position="39" strand="plus" pvalue="1.41e-05" > +<left_flank>CCTCGGGACG</left_flank> +<site> +<letter_ref letter_id="T"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank></right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_6" position="15" strand="plus" pvalue="1.61e-05" > +<left_flank>CCCACTACTT</left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>TCATTCTGAG</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_22" position="2" strand="plus" pvalue="1.95e-05" > +<left_flank>GA</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GCCAACATCC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_14" position="17" strand="plus" pvalue="1.95e-05" > +<left_flank>CCCACCAGCA</left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>AAGCTCAGGA</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_18" position="37" strand="plus" pvalue="2.16e-05" > +<left_flank>CGTGGTCGCG</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_29" position="30" strand="plus" pvalue="3.04e-05" > +<left_flank>GCTGCCGGTG</left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +</site> +<right_flank>GCCCTGGCG</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_4" position="12" strand="plus" pvalue="3.04e-05" > +<left_flank>CAGGTCTAAG</left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>CTTGGAGTCC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_5" position="0" strand="plus" pvalue="3.67e-05" > +<left_flank></left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>ATGGTCCTGT</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_1" position="27" strand="plus" pvalue="3.93e-05" > +<left_flank>AGTCACAAGT</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>GGGTCGCACG</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_7" position="4" strand="plus" pvalue="5.65e-05" > +<left_flank>TCAG</left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>ATGTTCCTGT</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_3" position="14" strand="plus" pvalue="6.24e-05" > +<left_flank>CCCAGGTTTC</left_flank> +<site> +<letter_ref letter_id="T"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>TCGCCGCACC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_16" position="22" strand="plus" pvalue="7.15e-05" > +<left_flank>AGTTTCAGTT</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>attatataac</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_27" position="36" strand="plus" pvalue="1.39e-04" > +<left_flank>TGCCTGGGTC</left_flank> +<site> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +</site> +<right_flank>GCT</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_26" position="37" strand="plus" pvalue="1.39e-04" > +<left_flank>TGCCTGGGCC</left_flank> +<site> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="G"/> +</site> +<right_flank>GC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_17" position="2" strand="plus" pvalue="4.81e-04" > +<left_flank>ga</left_flank> +<site> +<letter_ref letter_id="T"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>ggggcctcac</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_8" position="13" strand="plus" pvalue="8.57e-04" > +<left_flank>TATAACTCAG</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>TAATTTGTAC</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_10" position="7" strand="plus" pvalue="1.47e-03" > +<left_flank>aaactta</left_flank> +<site> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="A"/> +</site> +<right_flank>acttaaaact</right_flank> +</contributing_site> +<contributing_site sequence_id="sequence_2" position="26" strand="plus" pvalue="2.64e-03" > +<left_flank>GGTGGGGGTG</left_flank> +<site> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="G"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="T"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="A"/> +<letter_ref letter_id="C"/> +<letter_ref letter_id="T"/> +</site> +<right_flank>GGTCCACTAT</right_flank> +</contributing_site> +</contributing_sites> +</motif> +</motifs> +<scanned_sites_summary p_thresh="0.0001"> +<scanned_sites sequence_id="sequence_0" pvalue="5.63e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="39" pvalue="1.41e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_1" pvalue="1.57e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="27" pvalue="3.93e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_2" pvalue="1.00e-01" num_sites="0"></scanned_sites> +<scanned_sites sequence_id="sequence_3" pvalue="2.49e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="14" pvalue="6.24e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_4" pvalue="1.22e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="12" pvalue="3.04e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_5" pvalue="1.47e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="0" pvalue="3.67e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_6" pvalue="6.45e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="15" pvalue="1.61e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_7" pvalue="2.26e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="4" pvalue="5.65e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_8" pvalue="3.37e-02" num_sites="0"></scanned_sites> +<scanned_sites sequence_id="sequence_9" pvalue="1.95e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="13" pvalue="4.86e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_10" pvalue="5.73e-02" num_sites="0"></scanned_sites> +<scanned_sites sequence_id="sequence_11" pvalue="5.52e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="16" pvalue="1.38e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_12" pvalue="2.59e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="18" pvalue="6.48e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_13" pvalue="1.10e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="13" pvalue="2.74e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_14" pvalue="7.78e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="17" pvalue="1.95e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_15" pvalue="5.52e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="21" pvalue="1.38e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_16" pvalue="2.85e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="22" pvalue="7.15e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_17" pvalue="1.90e-02" num_sites="0"></scanned_sites> +<scanned_sites sequence_id="sequence_18" pvalue="8.63e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="37" pvalue="2.16e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_19" pvalue="1.95e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="9" pvalue="4.86e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_20" pvalue="2.59e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="4" pvalue="6.48e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_21" pvalue="1.95e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="7" pvalue="4.86e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_22" pvalue="7.78e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="2" pvalue="1.95e-05"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_23" pvalue="8.89e-05" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="15" pvalue="2.22e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_24" pvalue="1.80e-05" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="12" pvalue="4.51e-07"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_25" pvalue="1.95e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="36" pvalue="4.86e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_26" pvalue="5.54e-03" num_sites="0"></scanned_sites> +<scanned_sites sequence_id="sequence_27" pvalue="5.54e-03" num_sites="0"></scanned_sites> +<scanned_sites sequence_id="sequence_28" pvalue="2.59e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="32" pvalue="6.48e-06"/> +</scanned_sites> +<scanned_sites sequence_id="sequence_29" pvalue="1.22e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="plus" position="30" pvalue="3.04e-05"/> +</scanned_sites> +</scanned_sites_summary> +</MEME>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/motif1.gff Wed Jul 06 10:25:06 2016 -0400 @@ -0,0 +1,100 @@ +##gff-version 3 +phiX174 fimo polypeptide_motif 1 11 78.3 + . Name=1;ID=1-57-phiX174;pvalue=1.46e-08;sequence=GAGTTTTATCG; +phiX174 fimo polypeptide_motif 3 13 57.5 + . Name=1;ID=1-471-phiX174;pvalue=1.79e-06;sequence=GTTTTATCGCT; +phiX174 fimo polypeptide_motif 7 17 45 + . Name=1;ID=1-1378-phiX174;pvalue=3.18e-05;sequence=TATCGCTTCCA; +phiX174 fimo polypeptide_motif 10 20 53.9 + . Name=1;ID=1-605-phiX174;pvalue=4.1e-06;sequence=CGCTTCCATGA; +phiX174 fimo polypeptide_motif 17 27 40.2 + . Name=1;ID=1-1887-phiX174;pvalue=9.55e-05;sequence=ATGACGCAGAA; +phiX174 fimo polypeptide_motif 18 28 45.3 + . Name=1;ID=1-1349-phiX174;pvalue=2.98e-05;sequence=TGACGCAGAAG; +phiX174 fimo polypeptide_motif 19 29 55.8 + . Name=1;ID=1-527-phiX174;pvalue=2.6e-06;sequence=GACGCAGAAGT; +phiX174 fimo polypeptide_motif 21 31 41.5 + . Name=1;ID=1-1705-phiX174;pvalue=7.07e-05;sequence=CGCAGAAGTTA; +phiX174 fimo polypeptide_motif 22 32 44.6 + . Name=1;ID=1-1404-phiX174;pvalue=3.44e-05;sequence=GCAGAAGTTAA; +phiX174 fimo polypeptide_motif 24 34 79.1 + . Name=1;ID=1-53-phiX174;pvalue=1.23e-08;sequence=AGAAGTTAACA; +phiX174 fimo polypeptide_motif 25 35 45.3 + . Name=1;ID=1-1347-phiX174;pvalue=2.97e-05;sequence=GAAGTTAACAC; +phiX174 fimo polypeptide_motif 26 36 59.2 + . Name=1;ID=1-417-phiX174;pvalue=1.19e-06;sequence=AAGTTAACACT; +phiX174 fimo polypeptide_motif 30 40 44.7 + . Name=1;ID=1-1399-phiX174;pvalue=3.4e-05;sequence=TAACACTTTCG; +phiX174 fimo polypeptide_motif 37 47 72.4 + . Name=1;ID=1-98-phiX174;pvalue=5.79e-08;sequence=TTCGGATATTT; +phiX174 fimo polypeptide_motif 39 49 65.3 + . Name=1;ID=1-213-phiX174;pvalue=2.92e-07;sequence=CGGATATTTCT; +phiX174 fimo polypeptide_motif 41 51 55.3 + . Name=1;ID=1-548-phiX174;pvalue=2.97e-06;sequence=GATATTTCTGA; +phiX174 fimo polypeptide_motif 43 53 58.4 + . Name=1;ID=1-442-phiX174;pvalue=1.43e-06;sequence=TATTTCTGATG; +phiX174 fimo polypeptide_motif 46 56 53.7 + . Name=1;ID=1-617-phiX174;pvalue=4.23e-06;sequence=TTCTGATGAGT; +phiX174 fimo polypeptide_motif 50 60 45.4 + . Name=1;ID=1-1333-phiX174;pvalue=2.86e-05;sequence=GATGAGTCGAA; +phiX174 fimo polypeptide_motif 51 61 48.4 + . Name=1;ID=1-1094-phiX174;pvalue=1.44e-05;sequence=ATGAGTCGAAA; +phiX174 fimo polypeptide_motif 52 62 83.9 + . Name=1;ID=1-22-phiX174;pvalue=4.06e-09;sequence=TGAGTCGAAAA; +phiX174 fimo polypeptide_motif 53 63 53.9 + . Name=1;ID=1-601-phiX174;pvalue=4.03e-06;sequence=GAGTCGAAAAA; +phiX174 fimo polypeptide_motif 54 64 62.9 + . Name=1;ID=1-297-phiX174;pvalue=5.16e-07;sequence=AGTCGAAAAAT; +phiX174 fimo polypeptide_motif 55 65 52.8 + . Name=1;ID=1-675-phiX174;pvalue=5.26e-06;sequence=GTCGAAAAATT; +phiX174 fimo polypeptide_motif 56 66 41.4 + . Name=1;ID=1-1713-phiX174;pvalue=7.2e-05;sequence=TCGAAAAATTA; +phiX174 fimo polypeptide_motif 58 68 43.4 + . Name=1;ID=1-1500-phiX174;pvalue=4.56e-05;sequence=GAAAAATTATC; +phiX174 fimo polypeptide_motif 59 69 59.6 + . Name=1;ID=1-409-phiX174;pvalue=1.1e-06;sequence=AAAAATTATCT; +phiX174 fimo polypeptide_motif 61 71 61.8 + . Name=1;ID=1-329-phiX174;pvalue=6.52e-07;sequence=AAATTATCTTG; +phiX174 fimo polypeptide_motif 63 73 59.2 + . Name=1;ID=1-419-phiX174;pvalue=1.2e-06;sequence=ATTATCTTGAT; +phiX174 fimo polypeptide_motif 65 75 53.3 + . Name=1;ID=1-643-phiX174;pvalue=4.66e-06;sequence=TATCTTGATAA; +phiX174 fimo polypeptide_motif 66 76 51.8 + . Name=1;ID=1-737-phiX174;pvalue=6.54e-06;sequence=ATCTTGATAAA; +phiX174 fimo polypeptide_motif 67 77 73.2 + . Name=1;ID=1-89-phiX174;pvalue=4.78e-08;sequence=TCTTGATAAAG; +phiX174 fimo polypeptide_motif 69 79 63.8 + . Name=1;ID=1-268-phiX174;pvalue=4.15e-07;sequence=TTGATAAAGCA; +phiX174 fimo polypeptide_motif 71 81 40.2 + . Name=1;ID=1-1882-phiX174;pvalue=9.49e-05;sequence=GATAAAGCAGG; +phiX174 fimo polypeptide_motif 73 83 45.4 + . Name=1;ID=1-1334-phiX174;pvalue=2.87e-05;sequence=TAAAGCAGGAA; +phiX174 fimo polypeptide_motif 74 84 50.9 + . Name=1;ID=1-832-phiX174;pvalue=8.05e-06;sequence=AAAGCAGGAAT; +phiX174 fimo polypeptide_motif 76 86 52.2 + . Name=1;ID=1-710-phiX174;pvalue=5.96e-06;sequence=AGCAGGAATTA; +phiX174 fimo polypeptide_motif 78 88 51.8 + . Name=1;ID=1-741-phiX174;pvalue=6.65e-06;sequence=CAGGAATTACT; +phiX174 fimo polypeptide_motif 79 89 45 + . Name=1;ID=1-1369-phiX174;pvalue=3.16e-05;sequence=AGGAATTACTA; +phiX174 fimo polypeptide_motif 80 90 43.3 + . Name=1;ID=1-1511-phiX174;pvalue=4.63e-05;sequence=GGAATTACTAC; +phiX174 fimo polypeptide_motif 81 91 59.8 + . Name=1;ID=1-402-phiX174;pvalue=1.05e-06;sequence=GAATTACTACT; +phiX174 fimo polypeptide_motif 82 92 46.9 + . Name=1;ID=1-1205-phiX174;pvalue=2.03e-05;sequence=AATTACTACTG; +phiX174 fimo polypeptide_motif 88 98 41.2 + . Name=1;ID=1-1744-phiX174;pvalue=7.51e-05;sequence=TACTGCTTGTT; +phiX174 fimo polypeptide_motif 91 101 53.6 + . Name=1;ID=1-621-phiX174;pvalue=4.33e-06;sequence=TGCTTGTTTAC; +phiX174 fimo polypeptide_motif 92 102 44.8 + . Name=1;ID=1-1388-phiX174;pvalue=3.31e-05;sequence=GCTTGTTTACG; +phiX174 fimo polypeptide_motif 93 103 43.2 + . Name=1;ID=1-1525-phiX174;pvalue=4.82e-05;sequence=CTTGTTTACGA; +phiX174 fimo polypeptide_motif 95 105 61.9 + . Name=1;ID=1-327-phiX174;pvalue=6.5e-07;sequence=TGTTTACGAAT; +phiX174 fimo polypeptide_motif 96 106 42.9 + . Name=1;ID=1-1553-phiX174;pvalue=5.08e-05;sequence=GTTTACGAATT; +phiX174 fimo polypeptide_motif 98 108 45.4 + . Name=1;ID=1-1340-phiX174;pvalue=2.9e-05;sequence=TTACGAATTAA; +phiX174 fimo polypeptide_motif 99 109 73.5 + . Name=1;ID=1-88-phiX174;pvalue=4.48e-08;sequence=TACGAATTAAA; +phiX174 fimo polypeptide_motif 100 110 53 + . Name=1;ID=1-661-phiX174;pvalue=4.99e-06;sequence=ACGAATTAAAT; +phiX174 fimo polypeptide_motif 102 112 75.6 + . Name=1;ID=1-72-phiX174;pvalue=2.75e-08;sequence=GAATTAAATCG; +phiX174 fimo polypeptide_motif 104 114 52.2 + . Name=1;ID=1-713-phiX174;pvalue=6.05e-06;sequence=ATTAAATCGAA; +phiX174 fimo polypeptide_motif 106 116 59.6 + . Name=1;ID=1-407-phiX174;pvalue=1.09e-06;sequence=TAAATCGAAGT; +phiX174 fimo polypeptide_motif 112 122 41.6 + . Name=1;ID=1-1683-phiX174;pvalue=6.85e-05;sequence=GAAGTGGACTG; +phiX174 fimo polypeptide_motif 114 124 45.3 + . Name=1;ID=1-1342-phiX174;pvalue=2.92e-05;sequence=AGTGGACTGCT; +phiX174 fimo polypeptide_motif 118 128 56.2 + . Name=1;ID=1-512-phiX174;pvalue=2.38e-06;sequence=GACTGCTGGCG; +phiX174 fimo polypeptide_motif 122 132 51.4 + . Name=1;ID=1-774-phiX174;pvalue=7.15e-06;sequence=GCTGGCGGAAA; +phiX174 fimo polypeptide_motif 123 133 43.1 + . Name=1;ID=1-1533-phiX174;pvalue=4.93e-05;sequence=CTGGCGGAAAA; +phiX174 fimo polypeptide_motif 124 134 48.6 + . Name=1;ID=1-1085-phiX174;pvalue=1.38e-05;sequence=TGGCGGAAAAT; +phiX174 fimo polypeptide_motif 125 135 68.3 + . Name=1;ID=1-146-phiX174;pvalue=1.49e-07;sequence=GGCGGAAAATG; +phiX174 fimo polypeptide_motif 126 136 46.4 + . Name=1;ID=1-1243-phiX174;pvalue=2.27e-05;sequence=GCGGAAAATGA; +phiX174 fimo polypeptide_motif 128 138 58.3 + . Name=1;ID=1-446-phiX174;pvalue=1.48e-06;sequence=GGAAAATGAGA; +phiX174 fimo polypeptide_motif 129 139 43.2 + . Name=1;ID=1-1522-phiX174;pvalue=4.78e-05;sequence=GAAAATGAGAA; +phiX174 fimo polypeptide_motif 130 140 54.1 + . Name=1;ID=1-595-phiX174;pvalue=3.92e-06;sequence=AAAATGAGAAA; +phiX174 fimo polypeptide_motif 131 141 76 + . Name=1;ID=1-68-phiX174;pvalue=2.49e-08;sequence=AAATGAGAAAA; +phiX174 fimo polypeptide_motif 132 142 51.2 + . Name=1;ID=1-800-phiX174;pvalue=7.57e-06;sequence=AATGAGAAAAT; +phiX174 fimo polypeptide_motif 133 143 56.2 + . Name=1;ID=1-513-phiX174;pvalue=2.41e-06;sequence=ATGAGAAAATT; +phiX174 fimo polypeptide_motif 134 144 41.1 + . Name=1;ID=1-1761-phiX174;pvalue=7.83e-05;sequence=TGAGAAAATTC; +phiX174 fimo polypeptide_motif 135 145 50.3 + . Name=1;ID=1-910-phiX174;pvalue=9.39e-06;sequence=GAGAAAATTCG; +phiX174 fimo polypeptide_motif 136 146 43.3 + . Name=1;ID=1-1517-phiX174;pvalue=4.66e-05;sequence=AGAAAATTCGA; +phiX174 fimo polypeptide_motif 139 149 54.2 + . Name=1;ID=1-588-phiX174;pvalue=3.75e-06;sequence=AAATTCGACCT; +phiX174 fimo polypeptide_motif 141 151 42.2 + . Name=1;ID=1-1625-phiX174;pvalue=6.01e-05;sequence=ATTCGACCTAT; +phiX174 fimo polypeptide_motif 143 153 50 + . Name=1;ID=1-938-phiX174;pvalue=9.94e-06;sequence=TCGACCTATCC; +phiX174 fimo polypeptide_motif 145 155 44.6 + . Name=1;ID=1-1403-phiX174;pvalue=3.42e-05;sequence=GACCTATCCTT; +phiX174 fimo polypeptide_motif 155 165 51.3 + . Name=1;ID=1-787-phiX174;pvalue=7.35e-06;sequence=TGCGCAGCTCG; +phiX174 fimo polypeptide_motif 157 167 51.1 + . Name=1;ID=1-807-phiX174;pvalue=7.68e-06;sequence=CGCAGCTCGAG; +phiX174 fimo polypeptide_motif 159 169 44.5 + . Name=1;ID=1-1420-phiX174;pvalue=3.56e-05;sequence=CAGCTCGAGAA; +phiX174 fimo polypeptide_motif 160 170 40 + . Name=1;ID=1-1921-phiX174;pvalue=9.89e-05;sequence=AGCTCGAGAAG; +phiX174 fimo polypeptide_motif 166 176 60.9 + . Name=1;ID=1-365-phiX174;pvalue=8.02e-07;sequence=AGAAGCTCTTA; +phiX174 fimo polypeptide_motif 168 178 62.3 + . Name=1;ID=1-311-phiX174;pvalue=5.87e-07;sequence=AAGCTCTTACT; +phiX174 fimo polypeptide_motif 181 191 49.9 + . Name=1;ID=1-946-phiX174;pvalue=1.01e-05;sequence=GCGACCTTTCG; +phiX174 fimo polypeptide_motif 187 197 52.5 + . Name=1;ID=1-694-phiX174;pvalue=5.64e-06;sequence=TTTCGCCATCA; +phiX174 fimo polypeptide_motif 191 201 46.6 + . Name=1;ID=1-1232-phiX174;pvalue=2.2e-05;sequence=GCCATCAACTA; +phiX174 fimo polypeptide_motif 194 204 76.4 + . Name=1;ID=1-67-phiX174;pvalue=2.29e-08;sequence=ATCAACTAACG; +phiX174 fimo polypeptide_motif 201 211 40.1 + . Name=1;ID=1-1908-phiX174;pvalue=9.77e-05;sequence=AACGATTCTGT; +phiX174 fimo polypeptide_motif 203 213 63 + . Name=1;ID=1-291-phiX174;pvalue=5e-07;sequence=CGATTCTGTCA; +phiX174 fimo polypeptide_motif 205 215 53.8 + . Name=1;ID=1-610-phiX174;pvalue=4.16e-06;sequence=ATTCTGTCAAA; +phiX174 fimo polypeptide_motif 206 216 59.1 + . Name=1;ID=1-421-phiX174;pvalue=1.23e-06;sequence=TTCTGTCAAAA; +phiX174 fimo polypeptide_motif 207 217 68 + . Name=1;ID=1-153-phiX174;pvalue=1.58e-07;sequence=TCTGTCAAAAA; +phiX174 fimo polypeptide_motif 209 219 49.6 + . Name=1;ID=1-988-phiX174;pvalue=1.09e-05;sequence=TGTCAAAAACT; +phiX174 fimo polypeptide_motif 210 220 40.8 + . Name=1;ID=1-1810-phiX174;pvalue=8.33e-05;sequence=GTCAAAAACTG; +phiX174 fimo polypeptide_motif 213 223 59.7 + . Name=1;ID=1-404-phiX174;pvalue=1.06e-06;sequence=AAAAACTGACG; +phiX174 fimo polypeptide_motif 223 233 42 + . Name=1;ID=1-1654-phiX174;pvalue=6.36e-05;sequence=GCGTTGGATGA; +phiX174 fimo polypeptide_motif 225 235 61.4 + . Name=1;ID=1-349-phiX174;pvalue=7.16e-07;sequence=GTTGGATGAGG; +phiX174 fimo polypeptide_motif 227 237 40.3 + . Name=1;ID=1-1874-phiX174;pvalue=9.32e-05;sequence=TGGATGAGGAG; +phiX174 fimo polypeptide_motif 228 238 49.9 + . Name=1;ID=1-947-phiX174;pvalue=1.01e-05;sequence=GGATGAGGAGA; +phiX174 fimo polypeptide_motif 229 239 45 + . Name=1;ID=1-1370-phiX174;pvalue=3.16e-05;sequence=GATGAGGAGAA; +phiX174 fimo polypeptide_motif 230 240 44.8 + . Name=1;ID=1-1395-phiX174;pvalue=3.33e-05;sequence=ATGAGGAGAAG;
--- a/tool_dependencies.xml Thu Jun 16 08:07:03 2016 -0400 +++ b/tool_dependencies.xml Wed Jul 06 10:25:06 2016 -0400 @@ -1,9 +1,9 @@ <?xml version="1.0"?> <tool_dependency> - <package name="imagemagick" version="6.9.3"> - <repository changeset_revision="1cb6eed50cd2" name="package_imagemagick_6_9_3" owner="iuc" prior_installation_required="True" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + <package name="graphicsmagick" version="1.3.20"> + <repository changeset_revision="25002de17a97" name="package_graphicsmagick_1_3_20" owner="iuc" prior_installation_required="True" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> - <package name="meme" version="4.11.0"> - <repository changeset_revision="1c44baf77b0e" name="package_meme_4_11_0" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + <package name="meme" version="4.11.1"> + <repository changeset_revision="fd41eab672cd" name="package_meme_4_11_1" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> </tool_dependency>