| Previous changeset 17:d7a6ea1e3b9d (2021-11-27) Next changeset 19:01f5d04846c4 (2024-08-29) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/meme commit 03235f29be6368f58bc730a20d87a13cf215310f" |
|
modified:
fimo.xml macros.xml test-data/dreme_output_test1.html test-data/dreme_output_test1.txt test-data/dreme_output_test1.xml test-data/dreme_output_test2.html test-data/dreme_output_test2.txt test-data/dreme_output_test2.xml test-data/fimo_output_test1.gff test-data/fimo_output_test1.html test-data/fimo_output_test1.xml test-data/fimo_output_test2.gff test-data/fimo_output_test2.html test-data/fimo_output_test2.txt test-data/fimo_output_test2.xml test-data/fimo_output_test3.html test-data/fimo_output_test3.txt test-data/fimo_output_test3.xml test-data/meme_output_test1.html test-data/meme_output_test1.txt test-data/meme_output_test1.xml test-data/meme_output_test2.html test-data/meme_output_test2.txt test-data/meme_output_test2.xml |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d fimo.xml --- a/fimo.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/fimo.xml Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,4 +1,4 @@ -<tool id="meme_fimo" name="FIMO" version="@TOOL_VERSION@.0"> +<tool id="meme_fimo" name="FIMO" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"> <description>- Scan a set of sequences for motifs</description> <xrefs> <xref type="bio.tools">meme_fimo</xref> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d macros.xml --- a/macros.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/macros.xml Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,9 +1,10 @@ <?xml version='1.0' encoding='UTF-8'?> <macros> - <token name="@TOOL_VERSION@">5.0.5</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@TOOL_VERSION@">5.4.1</token> <xml name="requirements"> <requirements> - <requirement type="package" version="5.0.5">meme</requirement> + <requirement type="package" version="@TOOL_VERSION@">meme</requirement> <yield/> </requirements> </xml> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/dreme_output_test1.html --- a/test-data/dreme_output_test1.html Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/dreme_output_test1.html Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| b'@@ -1,113 +1,100 @@\n-<!DOCTYPE HTML>\n-<html>\n- <head>\n- <meta charset="UTF-8">\n- <title>DREME</title>\n- <script>\n- // @JSON_VAR data\n- var data = {\n- "program": "dreme",\n- "version": "5.0.5",\n- "cmd": [\n- "dreme", "-o", "./dreme_out", "-p",\n- "-norc", "-rna", "-s", "1"\n- ],\n- "options": {\n- "revcomp": false,\n- "ngen": 100,\n- "add_pv_thresh": 0.01,\n- "seed": 1,\n- "stop": {\n- "evalue": "0.05"\n- "alphabet": {\n- "name": "RNA",\n- "like": "rna",\n- "ncore": 4,\n- "symbols": [\n- "background": {\n- "freqs": [0.221, 0.245, 0.221, 0.312]\n- "control_db": {\n- "name": "shuffled positive sequences",\n- "from": "shuffled",\n- "count": 1000,\n- "freqs": [0.221, 0.245, 0.221, 0.312]\n- "motifs": [\n- "db": 0,\n- "id": "UUYUCY",\n- "alt": "DREME-1",\n- "len": 6,\n- "nsites": 459,\n- "evalue": "1.2e-013",\n- "p": 387,\n- "n": 210,\n- "pvalue": "2.6e-018",\n- "unerased_evalue": "1.2e-013",\n- "pwm": [\n- [0.000000, 0.000000, 0.000000, 1.000000], \n- [0.000000, 0.000000, 0.000000, 1.000000], \n- [0.000000, 0.294118, 0.000000, 0.705882], \n- [0.000000, 0.000000, 0.000000, 1.000000], \n- [0.000000, 1.000000, 0.000000, 0.000000], \n- [0.000000, 0.474946, 0.000000, 0.525054]\n- "matches": [\n- "seq": "UUUUCC",\n- "p": 147,\n- "n": 75,\n- "pvalue": "1.8e-007",\n- "evalue": "8.1e-003"\n- }, {\n- "seq": "UUUUCU",\n- "p": 155,\n- "n": 94,\n- "pvalue": "2.2e-005",\n- "evalue": "1.0e+000"\n- "seq": "UUCUCU",\n- "p": 94,\n- "n": 51,\n- "pvalue": "1.3e-004",\n- "evalue": "6.1e+000"\n- "seq": "UUCUCC",\n- "p": 75,\n- "n": 42,\n- "pvalue": "1.1e-003",\n- "evalue": "5.0e+001"\n- <script>\n-var site_url = "http://meme-suite.org";\n-</script>\n-/* dreme output specific css */\n-/* program settings */\n-</style>\n- </head>\n- <body data-scrollpad="true">\n- The name of the motif uses the IUPAC codes for nucleotides which has \n- a different letter to represent each of the 15 possible combinations.\n- The name is itself a representation of the motif though the position\n- weight matrix is not directly equivalent as it is generated from the\n- sites found that matched the letters given in the name.\n- <p>The E-value is the enrichment p-value times the number of candidate \n- motifs tested.</p>\n- <p>The enrichment p-value is calculated using Fisher\'s Exact Test for \n- enrichment of the motif in the positive sequences.</p>\n- <p>Note that the counts used in Fisher\'s Exact Test are made after \n- erasing sites that match previously found motifs.</p>\n- <p>The E-value of the motif calculated without erasing the sites of \n- previously found motifs.</p>\n- <p>Show more information on the motif.</p>\n- <p>Submit your motif to another MEME Suite program or download your motif.</p>\n- <h5>Supported Programs</h5>\n- <dt>Tomtom</dt>\n- <dd>Tomtom is a tool for searching for similar known motifs. \n- <dt>MAST</dt>\n- <dd>MAST is a tool for searching biological sequence databases for \n- sequences that contain one or more of a group of known motifs.\n- <dt>FIMO</dt>\n- <dd>FIMO is a tool for searching biological sequence databases for \n- sequences that contain one or more known motifs.\n- <dt>GOMo</dt>\n- <dd>GOMo is a tool for ident'..b' <th>Alphabet <div class="help" data-topic="pop_seq_alph"></div></th>\n+ <th>Sequence Count <div class="help" data-topic="pop_seq_count"></div></th>\n+ </tr>\n+ <tr>\n+ <td id="ins_seq_source"></td>\n+ <td id="ins_seq_alphabet"></td>\n+ <td id="ins_seq_count"></td>\n+ </tr>\n+ </table>\n+ <script>\n+ {\n+ var db = data.sequence_db;\n+ $("ins_seq_source").innerHTML = db.file;\n+ $("ins_seq_alphabet").innerHTML = current_alphabet.get_alphabet_name();\n+ $("ins_seq_count").innerHTML = db.count;\n+ }\n+ </script>\n+ <h4>Control Sequences</h4>\n+ <table id="seq_info" class="inputs">\n+ <tr><th>Source <div class="help" data-topic="pop_seq_source"></div></th>\n+ <th>Sequence Count <div class="help" data-topic="pop_seq_count"></div></th>\n+ </tr>\n+ <tr>\n+ <td id="ins_cseq_source"></td>\n+ <td id="ins_cseq_count"></td>\n+ </tr>\n+ </table>\n+ <script>\n+ {\n+ var db = data.control_db;\n+ if (db.from == "shuffled") {\n+ $("ins_cseq_source").innerHTML = "Shuffled Sequences";\n+ } else {\n+ $("ins_cseq_source").innerHTML = db.file;\n+ }\n+ $("ins_cseq_count").innerHTML = db.count;\n+ }\n+ </script>\n+ <h4>Background</h4>\n+ <span id="alpha_bg"></span>\n+ <script>\n+ {\n+ $("alpha_bg").appendChild(make_alpha_bg_table(current_alphabet, data.control_db.freqs));\n+ }\n+ </script>\n+ <h4>Other Settings</h4>\n+ <table id="tbl_settings" class="inputs hide_advanced">\n+ <tr>\n+ <th>Strand Handling</th>\n+ <td id="opt_strand">\n+ <span class="strand_none">This alphabet only has one strand</span>\n+ <span class="strand_given">Only the given strand is processed</span>\n+ <span class="strand_both">Both the given and reverse complement strands are processed</span>\n+ </td>\n+ </tr>\n+ <tr><th># REs to Generalize</th><td id="opt_ngen"></td></tr>\n+ <tr><th>Shuffle Seed</th><td id="opt_seed"></td></tr>\n+ <tr><th>E-value Threshold</th><td id="opt_stop_evalue"></td></tr>\n+ <tr><th>Max Motif Count</th><td id="opt_stop_count"></td></tr>\n+ <tr><th>Max Run Time</th><td id="opt_stop_time"></td></tr>\n+ </table>\n+ <script>\n+ {\n+ $("opt_strand").className = (current_alphabet.has_complement() ? (data.options.revcomp ? "both" : "given") : "none");\n+ $("opt_ngen").innerHTML = data.options.ngen;\n+ $("opt_seed").innerHTML = data.options.seed;\n+ $("opt_stop_evalue").innerHTML = data.options.stop.evalue;\n+ $("opt_stop_count").innerHTML = (typeof data.options.stop.count == "number" ? data.options.stop.count : "No maximum motif count.");\n+ $("opt_stop_time").innerHTML = (typeof data.options.stop.time == "number" ? data.options.stop.time + " seconds." : "No maximum running time.");\n+ }\n+ </script>\n+ </div>\n+ <!-- list information on this program -->\n+ <div id="info_sec" class="bar" style="position:relative">\n+ <div style="position: absolute; right: 0;"><a href="#inputs_sec">Previous</a> <a href="#">Top</a></div>\n+ <div class="subsection">\n+ <h5 id="version">DREME version</h5>\n+ <span id="ins_version"></span> \n+ (Release date: <span id="ins_release"></span>)<br>\n+ </div>\n+ <script>\n+ $("ins_version").innerHTML = data["version"];\n+ $("ins_release").innerHTML = data["release"];\n+ </script>\n+ <div class="subsection" id="reference"> <script>print_citation("reference", "DREME");</script> </div>\n+ <div class="subsection">\n+ <h5 id="command">Command line</h5>\n+ <textarea id="cmd" rows="3" style="width:100%;" readonly="readonly">\n+ </textarea>\n+ <script>$("cmd").value = data["cmd"].join(" ");</script>\n+ </div>\n+ </div>\n+ \n </body>\n </html>\n' |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/dreme_output_test1.txt --- a/test-data/dreme_output_test1.txt Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/dreme_output_test1.txt Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,36 +1,12 @@ -# DREME 5.0.5 -# negatives: 1000 from shuffled positives +MOTIF UUYUCY DREME-1 -MEME version 5.0.5 -ALPHABET "RNA" RNA-LIKE -A "Adenine" CC0000 -C "Cytosine" 0000CC -G "Guanine" FFB300 -U "Uracil" 008000 -N "Any base" = ACGU -X = ACGU -. = ACGU -V "Not U" = ACG -H "Not G" = ACU -D "Not C" = AGU -B "Not A" = CGU -M "Amino" = AC -R "Purine" = AG -W "Weak" = AU -S "Strong" = CG -Y "Pyrimidine" = CU -K "Keto" = GU -T = U -END ALPHABET -Background letter frequencies (from dataset): -A 0.221 C 0.245 G 0.221 U 0.312 -MOTIF UUYUCY DREME-1 # Word Pos Neg P-value E-value # BEST UUYUCY 387 210 2.6e-018 1.2e-013 # UUUUCC 147 75 1.8e-007 8.1e-003 # UUUUCU 155 94 2.2e-005 1.0e+000 # UUCUCU 94 51 1.3e-004 6.1e+000 # UUCUCC 75 42 1.1e-003 5.0e+001 + letter-probability matrix: alength= 4 w= 6 nsites= 459 E= 1.2e-013 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 1.000000 @@ -38,21 +14,29 @@ 0.000000 0.000000 0.000000 1.000000 0.000000 1.000000 0.000000 0.000000 0.000000 0.474946 0.000000 0.525054 + + MOTIF YAGG DREME-2 + # Word Pos Neg P-value E-value # BEST YAGG 600 416 1.1e-016 5.1e-012 # CAGG 441 304 1.5e-010 6.6e-006 # UAGG 232 165 1.1e-004 4.7e+000 + letter-probability matrix: alength= 4 w= 4 nsites= 793 E= 5.1e-012 0.000000 0.692308 0.000000 0.307692 1.000000 0.000000 0.000000 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 1.000000 0.000000 + + MOTIF GAAGAW DREME-3 + # Word Pos Neg P-value E-value # BEST GAAGAW 81 22 8.2e-010 3.4e-005 # GAAGAU 45 7 2.4e-008 9.9e-004 # GAAGAA 40 16 7.9e-004 3.3e+001 + letter-probability matrix: alength= 4 w= 6 nsites= 89 E= 3.4e-005 0.000000 0.000000 1.000000 0.000000 1.000000 0.000000 0.000000 0.000000 @@ -60,13 +44,17 @@ 0.000000 0.000000 1.000000 0.000000 1.000000 0.000000 0.000000 0.000000 0.494382 0.000000 0.000000 0.505618 + + MOTIF SMUGGA DREME-4 + # Word Pos Neg P-value E-value # BEST SMUGGA 110 47 9.1e-008 3.7e-003 # GAUGGA 22 6 1.7e-003 7.1e+001 # GCUGGA 33 14 3.6e-003 1.5e+002 # CCUGGA 32 15 8.6e-003 3.5e+002 # CAUGGA 29 13 9.1e-003 3.7e+002 + letter-probability matrix: alength= 4 w= 6 nsites= 119 E= 3.7e-003 0.000000 0.529412 0.470588 0.000000 0.428571 0.571429 0.000000 0.000000 @@ -74,4 +62,3 @@ 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 1.000000 0.000000 1.000000 0.000000 0.000000 0.000000 -# Stopping reason: E-value threshold exceeded |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/dreme_output_test1.xml --- a/test-data/dreme_output_test1.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/dreme_output_test1.xml Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,30 +1,3 @@ -<dreme version="5.0.5" release="Mon Mar 18 20:12:19 2019 -0700"> - <model> - <negatives name="shuffled positive sequences" count="1000" from="shuffled"/> - <alphabet name="RNA" like="rna"> - <letter id="A" symbol="A" name="Adenine" colour="CC0000"/> - <letter id="C" symbol="C" name="Cytosine" colour="0000CC"/> - <letter id="G" symbol="G" name="Guanine" colour="FFB300"/> - <letter id="U" symbol="U" aliases="T" name="Uracil" colour="008000"/> - <letter id="N" symbol="N" aliases="X." equals="ACGU" name="Any base"/> - <letter id="V" symbol="V" equals="ACG" name="Not U"/> - <letter id="H" symbol="H" equals="ACU" name="Not G"/> - <letter id="D" symbol="D" equals="AGU" name="Not C"/> - <letter id="B" symbol="B" equals="CGU" 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="AU" name="Weak"/> - <letter id="S" symbol="S" equals="CG" name="Strong"/> - <letter id="Y" symbol="Y" equals="CU" name="Pyrimidine"/> - <letter id="K" symbol="K" equals="GU" name="Keto"/> - </alphabet> - <strands>none</strands> - <background A="0.221" C="0.245" G="0.221" U="0.312" from="dataset"/> - <stop evalue="0.05"/> - <ngen>100</ngen> - <add_pv_thresh>0.01</add_pv_thresh> - <seed>1</seed> - </model> <motifs> <motif id="m01" alt="DREME-1" seq="UUYUCY" length="6" nsites="459" p="387" n="210" pvalue="2.6e-018" evalue="1.2e-013" unerased_evalue="1.2e-013"> <pos A="0.000000" C="0.000000" G="0.000000" U="1.000000"/> @@ -68,5 +41,4 @@ <match seq="CCUGGA" p="32" n="15" pvalue="8.6e-003" evalue="3.5e+002"/> <match seq="CAUGGA" p="29" n="13" pvalue="9.1e-003" evalue="3.7e+002"/> </motif> - </motifs> -</dreme> + </motifs> \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/dreme_output_test2.html --- a/test-data/dreme_output_test2.html Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/dreme_output_test2.html Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| b'@@ -1,167 +1,50 @@\n-<!DOCTYPE HTML>\n-<html>\n- <head>\n- <meta charset="UTF-8">\n- <title>DREME</title>\n- <script>\n- // @JSON_VAR data\n- var data = {\n- "program": "dreme",\n- "version": "5.0.5",\n- "release": "Mon Mar 18 20:12:19 2019 -0700",\n- "cmd": [\n- "dreme", "-o", "./dreme_out", "-p",\n- "-norc", "-rna", "-s", "1", "-e", "1e-05", "-g", "100", "-mink",\n- "4", "-maxk", "10"\n- ],\n- "options": {\n- "revcomp": false,\n- "ngen": 100,\n- "add_pv_thresh": 0.01,\n- "seed": 1,\n- "stop": {\n- "evalue": "1e-05"\n- }\n- },\n- "alphabet": {\n- "name": "RNA",\n- "like": "rna",\n- "ncore": 4,\n- "symbols": [\n- {\n- "symbol": "A",\n- "name": "Adenine",\n- "colour": "CC0000"\n- }, {\n- "symbol": "C",\n- "name": "Cytosine",\n- "colour": "0000CC"\n- "symbol": "G",\n- "name": "Guanine",\n- "colour": "FFB300"\n- "symbol": "U",\n- "aliases": "T",\n- "name": "Uracil",\n- "colour": "008000"\n- "symbol": "N",\n- "aliases": "X.",\n- "name": "Any base",\n- "equals": "ACGU"\n- "symbol": "V",\n- "name": "Not U",\n- "equals": "ACG"\n- "symbol": "H",\n- "name": "Not G",\n- "equals": "ACU"\n- "symbol": "D",\n- "name": "Not C",\n- "equals": "AGU"\n- "symbol": "B",\n- "name": "Not A",\n- "equals": "CGU"\n- "symbol": "M",\n- "name": "Amino",\n- "equals": "AC"\n- "symbol": "R",\n- "name": "Purine",\n- "equals": "AG"\n- "symbol": "W",\n- "name": "Weak",\n- "equals": "AU"\n- "symbol": "S",\n- "name": "Strong",\n- "equals": "CG"\n- "symbol": "Y",\n- "name": "Pyrimidine",\n- "equals": "CU"\n- "symbol": "K",\n- "name": "Keto",\n- "equals": "GU"\n- "background": {\n- "freqs": [0.221, 0.245, 0.221, 0.312]\n- "sequence_db": {\n- "count": 1000\n- "control_db": {\n- "name": "shuffled positive sequences",\n- "from": "shuffled",\n- "count": 1000,\n- "freqs": [0.221, 0.245, 0.221, 0.312]\n- "motifs": [\n- "db": 0,\n- "id": "UUYUCY",\n- "alt": "DREME-1",\n- "len": 6,\n- "nsites": 459,\n- "evalue": "3.3e-013",\n- "p": 387,\n- "n": 210,\n- "pvalue": "2.6e-018",\n- "unerased_evalue": "3.3e-013",\n- "pwm": [\n- [0.000000, 0.000000, 0.000000, 1.000000], \n- [0.000000, 0.000000, 0.000000, 1.000000], \n- [0.000000, 0.294118, 0.000000, 0.705882], \n- [0.000000, 0.000000, 0.000000, 1.000000], \n- [0.000000, 1.000000, 0.000000, 0.000000], \n- [0.000000, 0.474946, 0.000000, 0.525054]\n- "matches": [\n- "seq": "UUUUCC",\n- "p": 147,\n- "n": 75,\n- "pvalue": "1.8e-007",\n- "evalue": "2.2e-002"\n- </script>\n-var site_url = "http://meme-suite.org";\n-//======================================================================\n-// end RasterizedAlphabet\n-//======================================================================\n-//======================================================================\n-// start LogoMetrics object\n-//======================================================================\n- * Initialise and display the download popup.\n-</style>\n- </head>\n- <body data-scrollpad="true">\n- <!'..b'ch previously found motifs.</p>\n- <p>The E-value of the motif calculated without erasing the sites of \n- previously found motifs.</p>\n- <p>Show more information on the motif.</p>\n- <p>Submit your motif to another MEME Suite program or download your motif.</p>\n- <h5>Supported Programs</h5>\n- <dt>Tomtom</dt>\n- <dd>Tomtom is a tool for searching for similar known motifs. \n- <dt>MAST</dt>\n- <dd>MAST is a tool for searching biological sequence databases for \n- sequences that contain one or more of a group of known motifs.\n- <dt>FIMO</dt>\n- <dd>FIMO is a tool for searching biological sequence databases for \n- sequences that contain one or more known motifs.\n- <dt>GOMo</dt>\n- <dd>GOMo is a tool for identifying possible roles (Gene Ontology \n- terms) for DNA binding motifs.\n- <dt>SpaMo</dt>\n- <dd>SpaMo is a tool for inferring possible transcription factor\n- complexes by finding motifs with enriched spacings.\n- <!-- Page starts here -->\n- <h1>DREME</h1>\n- <h2>Discriminative Regular Expression Motif Elicitation</h2>\n- For further information on how to interpret these results please access\n- To get a copy of the MEME software please access \n- If you use DREME in your research please cite the following paper:<br />\n- Timothy L. Bailey, "DREME: Motif discovery in transcription factor ChIP-seq data", <i>Bioinformatics</i>, <b>27</b>(12):1653-1659, 2011.\n+ <h4>Other Settings</h4>\n+ <table id="tbl_settings" class="inputs hide_advanced">\n+ <tr>\n+ <th>Strand Handling</th>\n+ <td id="opt_strand">\n+ <span class="strand_none">This alphabet only has one strand</span>\n+ <span class="strand_given">Only the given strand is processed</span>\n+ <span class="strand_both">Both the given and reverse complement strands are processed</span>\n+ </td>\n+ </tr>\n+ <tr><th># REs to Generalize</th><td id="opt_ngen"></td></tr>\n+ <tr><th>Shuffle Seed</th><td id="opt_seed"></td></tr>\n+ <tr><th>E-value Threshold</th><td id="opt_stop_evalue"></td></tr>\n+ <tr><th>Max Motif Count</th><td id="opt_stop_count"></td></tr>\n+ <tr><th>Max Run Time</th><td id="opt_stop_time"></td></tr>\n+ </table>\n+ <script>\n+ {\n+ $("opt_strand").className = (current_alphabet.has_complement() ? (data.options.revcomp ? "both" : "given") : "none");\n+ $("opt_ngen").innerHTML = data.options.ngen;\n+ $("opt_seed").innerHTML = data.options.seed;\n+ $("opt_stop_evalue").innerHTML = data.options.stop.evalue;\n+ $("opt_stop_count").innerHTML = (typeof data.options.stop.count == "number" ? data.options.stop.count : "No maximum motif count.");\n+ $("opt_stop_time").innerHTML = (typeof data.options.stop.time == "number" ? data.options.stop.time + " seconds." : "No maximum running time.");\n+ }\n+ </script>\n+ </div>\n+ <!-- list information on this program -->\n+ <div id="info_sec" class="bar" style="position:relative">\n+ <div style="position: absolute; right: 0;"><a href="#inputs_sec">Previous</a> <a href="#">Top</a></div>\n+ <div class="subsection">\n+ <h5 id="version">DREME version</h5>\n+ <span id="ins_version"></span> \n+ (Release date: <span id="ins_release"></span>)<br>\n+ </div>\n+ <script>\n+ $("ins_version").innerHTML = data["version"];\n+ $("ins_release").innerHTML = data["release"];\n+ </script>\n+ <div class="subsection" id="reference"> <script>print_citation("reference", "DREME");</script> </div>\n+ <div class="subsection">\n+ <h5 id="command">Command line</h5>\n+ <textarea id="cmd" rows="3" style="width:100%;" readonly="readonly">\n+ </textarea>\n+ <script>$("cmd").value = data["cmd"].join(" ");</script>\n+ </div>\n+ </div>\n+ \n </body>\n </html>\n' |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/dreme_output_test2.txt --- a/test-data/dreme_output_test2.txt Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/dreme_output_test2.txt Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,7 +1,3 @@ -# DREME 5.0.5 -# negatives: 1000 from shuffled positives - -MEME version 5.0.5 ALPHABET "RNA" RNA-LIKE A "Adenine" CC0000 C "Cytosine" 0000CC @@ -22,15 +18,20 @@ K "Keto" = GU T = U END ALPHABET + Background letter frequencies (from dataset): A 0.221 C 0.245 G 0.221 U 0.312 + + MOTIF UUYUCY DREME-1 + # Word Pos Neg P-value E-value # BEST UUYUCY 387 210 2.6e-018 3.3e-013 # UUUUCC 147 75 1.8e-007 2.2e-002 # UUUUCU 155 94 2.2e-005 2.8e+000 # UUCUCU 94 51 1.3e-004 1.7e+001 # UUCUCC 75 42 1.1e-003 1.4e+002 + letter-probability matrix: alength= 4 w= 6 nsites= 459 E= 3.3e-013 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 1.000000 @@ -38,14 +39,17 @@ 0.000000 0.000000 0.000000 1.000000 0.000000 1.000000 0.000000 0.000000 0.000000 0.474946 0.000000 0.525054 + + MOTIF YAGG DREME-2 + # Word Pos Neg P-value E-value # BEST YAGG 600 416 1.1e-016 1.4e-011 # CAGG 441 304 1.5e-010 1.8e-005 # UAGG 232 165 1.1e-004 1.3e+001 + letter-probability matrix: alength= 4 w= 4 nsites= 793 E= 1.4e-011 0.000000 0.692308 0.000000 0.307692 1.000000 0.000000 0.000000 0.000000 0.000000 0.000000 1.000000 0.000000 -0.000000 0.000000 1.000000 0.000000 -# Stopping reason: E-value threshold exceeded +0.000000 0.000000 1.000000 0.000000 \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/dreme_output_test2.xml --- a/test-data/dreme_output_test2.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/dreme_output_test2.xml Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,30 +1,3 @@ -<dreme version="5.0.5" release="Mon Mar 18 20:12:19 2019 -0700"> - <model> - <negatives name="shuffled positive sequences" count="1000" from="shuffled"/> - <alphabet name="RNA" like="rna"> - <letter id="A" symbol="A" name="Adenine" colour="CC0000"/> - <letter id="C" symbol="C" name="Cytosine" colour="0000CC"/> - <letter id="G" symbol="G" name="Guanine" colour="FFB300"/> - <letter id="U" symbol="U" aliases="T" name="Uracil" colour="008000"/> - <letter id="N" symbol="N" aliases="X." equals="ACGU" name="Any base"/> - <letter id="V" symbol="V" equals="ACG" name="Not U"/> - <letter id="H" symbol="H" equals="ACU" name="Not G"/> - <letter id="D" symbol="D" equals="AGU" name="Not C"/> - <letter id="B" symbol="B" equals="CGU" 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="AU" name="Weak"/> - <letter id="S" symbol="S" equals="CG" name="Strong"/> - <letter id="Y" symbol="Y" equals="CU" name="Pyrimidine"/> - <letter id="K" symbol="K" equals="GU" name="Keto"/> - </alphabet> - <strands>none</strands> - <background A="0.221" C="0.245" G="0.221" U="0.312" from="dataset"/> - <stop evalue="1e-05"/> - <ngen>100</ngen> - <add_pv_thresh>0.01</add_pv_thresh> - <seed>1</seed> - </model> <motifs> <motif id="m01" alt="DREME-1" seq="UUYUCY" length="6" nsites="459" p="387" n="210" pvalue="2.6e-018" evalue="3.3e-013" unerased_evalue="3.3e-013"> <pos A="0.000000" C="0.000000" G="0.000000" U="1.000000"/> @@ -46,5 +19,4 @@ <match seq="CAGG" p="441" n="304" pvalue="1.5e-010" evalue="1.8e-005"/> <match seq="UAGG" p="232" n="165" pvalue="1.1e-004" evalue="1.3e+001"/> </motif> - </motifs> -</dreme> + </motifs> \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test1.gff --- a/test-data/fimo_output_test1.gff Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test1.gff Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,12 +1,12 @@ ##gff-version 3 -chrM fimo nucleotide_motif 6529 6536 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-1-chrM;pvalue=2.18e-05;qvalue= 0.142;sequence=TACTAACA; -chrM fimo nucleotide_motif 7741 7748 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-2-chrM;pvalue=2.18e-05;qvalue= 0.142;sequence=TACTAACA; -chrM fimo nucleotide_motif 13656 13663 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-3-chrM;pvalue=2.18e-05;qvalue= 0.142;sequence=TACTAACA; -chrM fimo nucleotide_motif 13740 13747 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-4-chrM;pvalue=2.18e-05;qvalue= 0.142;sequence=TACTAACA; -chrM fimo nucleotide_motif 2299 2306 46.6 - . Name=TACTAAYM_chrM-;Alias=MEME-1;ID=TACTAAYM-MEME-1-5-chrM;pvalue=2.18e-05;qvalue= 0.142;sequence=TACTAACA; -chrM fimo nucleotide_motif 861 868 44 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-6-chrM;pvalue=3.96e-05;qvalue= 0.185;sequence=TACTAACC; -chrM fimo nucleotide_motif 9346 9353 44 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-7-chrM;pvalue=3.96e-05;qvalue= 0.185;sequence=TACTAACC; -chrM fimo nucleotide_motif 3767 3774 41.8 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-8-chrM;pvalue=6.62e-05;qvalue= 0.216;sequence=TACTAATA; -chrM fimo nucleotide_motif 5497 5504 41.8 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-9-chrM;pvalue=6.62e-05;qvalue= 0.216;sequence=TACTAATA; -chrM fimo nucleotide_motif 10105 10112 41.8 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-10-chrM;pvalue=6.62e-05;qvalue= 0.216;sequence=TACTAATA; -chrM fimo nucleotide_motif 10959 10966 40.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-11-chrM;pvalue=8.79e-05;qvalue= 0.261;sequence=TACTAACT; +chrM fimo nucleotide_motif 6529 6536 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-1-chrM;pvalue=2.18e-05;qvalue=0.142;sequence=TACTAACA; +chrM fimo nucleotide_motif 7741 7748 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-2-chrM;pvalue=2.18e-05;qvalue=0.142;sequence=TACTAACA; +chrM fimo nucleotide_motif 13656 13663 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-3-chrM;pvalue=2.18e-05;qvalue=0.142;sequence=TACTAACA; +chrM fimo nucleotide_motif 13740 13747 46.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-4-chrM;pvalue=2.18e-05;qvalue=0.142;sequence=TACTAACA; +chrM fimo nucleotide_motif 2299 2306 46.6 - . Name=TACTAAYM_chrM-;Alias=MEME-1;ID=TACTAAYM-MEME-1-5-chrM;pvalue=2.18e-05;qvalue=0.142;sequence=TACTAACA; +chrM fimo nucleotide_motif 861 868 44 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-6-chrM;pvalue=3.96e-05;qvalue=0.185;sequence=TACTAACC; +chrM fimo nucleotide_motif 9346 9353 44 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-7-chrM;pvalue=3.96e-05;qvalue=0.185;sequence=TACTAACC; +chrM fimo nucleotide_motif 3767 3774 41.8 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-8-chrM;pvalue=6.62e-05;qvalue=0.216;sequence=TACTAATA; +chrM fimo nucleotide_motif 5497 5504 41.8 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-9-chrM;pvalue=6.62e-05;qvalue=0.216;sequence=TACTAATA; +chrM fimo nucleotide_motif 10105 10112 41.8 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-10-chrM;pvalue=6.62e-05;qvalue=0.216;sequence=TACTAATA; +chrM fimo nucleotide_motif 10959 10966 40.6 + . Name=TACTAAYM_chrM+;Alias=MEME-1;ID=TACTAAYM-MEME-1-11-chrM;pvalue=8.79e-05;qvalue=0.261;sequence=TACTAACT; |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test1.html --- a/test-data/fimo_output_test1.html Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test1.html Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,73 +1,34 @@ -<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> -<html xmlns:cis="http://zlab.bu.edu/schema/cisml" xmlns:fimo="http://noble.gs.washington.edu/schema/cisml" xmlns:mem="http://noble.gs.washington.edu/meme"> -<head> -<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> -<meta charset="UTF-8"> -<title>FIMO Results</title> -<style type="text/css"> -td.left {text-align: left;} -td.right {text-align: right; padding-right: 1cm;} -</head> -<body color="#000000"> -<a name="top_buttons"></a> -<hr> -<table summary="buttons" align="left" cellspacing="0"> -<tr> -<td bgcolor="#00FFFF"><a href="#database_and_motifs"><b>Database and Motifs</b></a></td> -<td bgcolor="#DDFFDD"><a href="#sec_i"><b>High-scoring Motif Occurences</b></a></td> -<td bgcolor="#DDDDFF"><a href="#debugging_information"><b>Debugging Information</b></a></td> -<td bgcolor="#FFDD00"><a href="fimo.tsv""><b>Results in TSV Format</b></a></td> -<td bgcolor="#FFDDFF"><a href="fimo.gff""><b>Results in GFF3 Format</b></a></td> -</tr> + <td style="padding-right: 2em">background file name = --nrdb--</td> + <td style="padding-left: 5em; padding-right: 2em">alphabet = DNA</td> + <td style="padding-left: 5em; padding-right: 2em">max stored scores = 100000</td> + </tr> <tr> + <td style="padding-right: 2em">allow clobber = false</td> + <td style="padding-left: 5em; padding-right: 2em">compute q-values = true</td> + <td style="padding-left: 5em; padding-right: 2em">parse genomic coord. = false</td> + </tr> + <tr> + <td style="padding-right: 2em">text only = false</td> + <td style="padding-left: 5em; padding-right: 2em">scan both strands = true</td> + <td style="padding-left: 5em; padding-right: 2em">max strand = false</td> + </tr> + <tr> + <td style="padding-right: 2em">threshold type = p-value</td> + <td style="padding-left: 5em; padding-right: 2em">output theshold = 0.0001</td> + <td style="padding-left: 5em; padding-right: 2em">pseudocount = 0.1</td> + </tr> + <tr> + <td style="padding-right: 2em">alpha = 1</td> + <td style="padding-left: 5em; padding-right: 2em">verbosity = 2</td> + <td style="padding-left: 5em; padding-right: 2em"></td> + </tr> + </table> -<center><big><b>FIMO - Motif search tool</b></big></center> -FIMO version 5.0.5, (Release date: Mon Mar 18 20:12:19 2019 -0700) -For further information on how to interpret these results please access <a href="http://meme-suite.org/doc/fimo-output-format.html">http://meme-suite.org/doc/fimo-output-format.html</a>.<br> -To get a copy of the FIMO software please access <a href="http://meme-suite.org">http://meme-suite.org</a> -<p>If you use FIMO in your research, please cite the following paper:<br> -Charles E. Grant, Timothy L. Bailey, and William Stafford Noble, -"FIMO: Scanning for occurrences of a given motif", -<i>Bioinformatics</i>, <b>27</b>(7):1017-1018, 2011. -<center><big><b><a name="database_and_motifs">DATABASE AND MOTIFS</a></b></big></center> - Database contains 1 sequences, 16569 residues - BEST POSSIBLE MATCH -Random model letter frequencies (--nrdb--): -A 0.275 C 0.225 G 0.225 T 0.275 </p> -<center><big><b><a name="sec_i">SECTION I: HIGH-SCORING MOTIF OCCURENCES</a></b></big></center> -There were 11 motif occurences with a p-value less than 0.0001. -The full set of motif occurences can be seen in the -TSV (tab-delimited values) output file -The <i>p</i>-value of a motif occurrence is defined as the -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. -The score for the match of a position in a sequence to a motif -is computed by summing the appropriate entries from each column of -the position-dependent scoring matrix that represents the motif. -The q-value of a motif occurrence is defined as the -false discovery rate if the occurrence is accepted as significant. -<li>The table is sorted by increasing <i>p</i>-value.</li> -<th>Motif ID</th> -<th>Alt ID</th> -<th>Sequence Name</th> -<th>Strand</th> -<th>Start</th> -<th>End</th> -<th>p-value</th> -<th>q-value</th> -<th>Matched Sequence</th> - <td style="text-align:left;">TACTAAYM</td> - <td style="text-align:left;">MEME-1</td> - <td style="text-align:left;">chrM</td> - <td style="text-align:center;">+</td> - <td style="text-align:left;">6529</td> - <td style="text-align:left;">6536</td> - <td style="text-align:left;">2.18e-05</td> - <td style="text-align:left;">0.142</td> - <td style="text-align:left;font-size:x-large;font-family:monospace;">TACTAACA</td> -</table> -<hr> -<center><big><b><a name="debugging_information">DEBUGGING INFORMATION</a></b></big></center> +</pre> +<p> This information can be useful in the event you wish to report a problem with the FIMO software. +</p> +<hr> +<span style="background-color: #DDDDFF"><a href="#top_buttons"><b>Go to top</b></a></span> </body> </html> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test1.xml --- a/test-data/fimo_output_test1.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test1.xml Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,10 +1,3 @@ -<?xml version="1.0" encoding="UTF-8" standalone="no"?> -<!-- Begin document body --> -<fimo version="5.0.5" release="Mon Mar 18 20:12:19 2019 -0700"> - xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" - xsi:schemaLocation= xmlns:fimo="http://noble.gs.washington.edu/schema/fimo" -> -<settings> <setting name="background file name">--nrdb--</setting> <setting name="allow clobber">false</setting> <setting name="compute q-values">true</setting> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test2.gff --- a/test-data/fimo_output_test2.gff Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test2.gff Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,12 +1,12 @@ ##gff-version 3 -chrM fimo nucleotide_motif 440 446 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-1-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 2093 2099 40.9 - . Name=ACTAAYH_chrM-;Alias=DREME-1;ID=ACTAAYH-DREME-1-2-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 2299 2305 40.9 - . Name=ACTAAYH_chrM-;Alias=DREME-1;ID=ACTAAYH-DREME-1-3-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 5186 5192 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-4-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 6530 6536 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-5-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 7742 7748 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-6-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 13657 13663 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-7-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 13741 13747 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-8-chrM;pvalue=8.2e-05;qvalue= 0.332;sequence=ACTAACA; -chrM fimo nucleotide_motif 510 516 43.8 + . Name=CCAGCAY_chrM+;Alias=DREME-5;ID=CCAGCAY-DREME-5-1-chrM;pvalue=4.15e-05;qvalue= 0.683;sequence=CCAGCAC; -chrM fimo nucleotide_motif 5137 5143 43.8 + . Name=CCAGCAY_chrM+;Alias=DREME-5;ID=CCAGCAY-DREME-5-2-chrM;pvalue=4.15e-05;qvalue= 0.683;sequence=CCAGCAC; -chrM fimo nucleotide_motif 4241 4247 40.3 + . Name=CCAGCAY_chrM+;Alias=DREME-5;ID=CCAGCAY-DREME-5-3-chrM;pvalue=9.37e-05;qvalue= 1;sequence=CCAGCAT; +chrM fimo nucleotide_motif 440 446 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-1-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 2093 2099 40.9 - . Name=ACTAAYH_chrM-;Alias=DREME-1;ID=ACTAAYH-DREME-1-2-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 2299 2305 40.9 - . Name=ACTAAYH_chrM-;Alias=DREME-1;ID=ACTAAYH-DREME-1-3-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 5186 5192 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-4-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 6530 6536 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-5-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 7742 7748 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-6-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 13657 13663 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-7-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 13741 13747 40.9 + . Name=ACTAAYH_chrM+;Alias=DREME-1;ID=ACTAAYH-DREME-1-8-chrM;pvalue=8.2e-05;qvalue=0.332;sequence=ACTAACA; +chrM fimo nucleotide_motif 510 516 43.8 + . Name=CCAGCAY_chrM+;Alias=DREME-5;ID=CCAGCAY-DREME-5-1-chrM;pvalue=4.15e-05;qvalue=0.683;sequence=CCAGCAC; +chrM fimo nucleotide_motif 5137 5143 43.8 + . Name=CCAGCAY_chrM+;Alias=DREME-5;ID=CCAGCAY-DREME-5-2-chrM;pvalue=4.15e-05;qvalue=0.683;sequence=CCAGCAC; +chrM fimo nucleotide_motif 4241 4247 40.3 + . Name=CCAGCAY_chrM+;Alias=DREME-5;ID=CCAGCAY-DREME-5-3-chrM;pvalue=9.37e-05;qvalue=1;sequence=CCAGCAT; |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test2.html --- a/test-data/fimo_output_test2.html Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test2.html Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,90 +1,33 @@ -<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> -<html xmlns:cis="http://zlab.bu.edu/schema/cisml" xmlns:fimo="http://noble.gs.washington.edu/schema/cisml" xmlns:mem="http://noble.gs.washington.edu/meme"> -<head> -<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> -<meta charset="UTF-8"> -<title>FIMO Results</title> -<style type="text/css"> -td.left {text-align: left;} -td.right {text-align: right; padding-right: 1cm;} -</style> -</head> -<body color="#000000"> -<a name="top_buttons"></a> -<hr> -<table summary="buttons" align="left" cellspacing="0"> -<tr> -<td bgcolor="#00FFFF"><a href="#database_and_motifs"><b>Database and Motifs</b></a></td> -<td bgcolor="#DDFFDD"><a href="#sec_i"><b>High-scoring Motif Occurences</b></a></td> -<td bgcolor="#DDDDFF"><a href="#debugging_information"><b>Debugging Information</b></a></td> -<td bgcolor="#FFDD00"><a href="fimo.tsv""><b>Results in TSV Format</b></a></td> -<td bgcolor="#FFDDFF"><a href="fimo.gff""><b>Results in GFF3 Format</b></a></td> -</tr> + <td style="padding-left: 5em; padding-right: 2em">alphabet = DNA</td> + <td style="padding-left: 5em; padding-right: 2em">max stored scores = 100000</td> + </tr> <tr> + <td style="padding-right: 2em">allow clobber = false</td> + <td style="padding-left: 5em; padding-right: 2em">compute q-values = true</td> + <td style="padding-left: 5em; padding-right: 2em">parse genomic coord. = false</td> + </tr> + <tr> + <td style="padding-right: 2em">text only = false</td> + <td style="padding-left: 5em; padding-right: 2em">scan both strands = true</td> + <td style="padding-left: 5em; padding-right: 2em">max strand = false</td> + </tr> + <tr> + <td style="padding-right: 2em">threshold type = p-value</td> + <td style="padding-left: 5em; padding-right: 2em">output theshold = 0.0001</td> + <td style="padding-left: 5em; padding-right: 2em">pseudocount = 0.1</td> + </tr> + <tr> + <td style="padding-right: 2em">alpha = 1</td> + <td style="padding-left: 5em; padding-right: 2em">verbosity = 2</td> + <td style="padding-left: 5em; padding-right: 2em"></td> + </tr> + </table> -<center><big><b>FIMO - Motif search tool</b></big></center> -FIMO version 5.0.5, (Release date: Mon Mar 18 20:12:19 2019 -0700) -For further information on how to interpret these results please access <a href="http://meme-suite.org/doc/fimo-output-format.html">http://meme-suite.org/doc/fimo-output-format.html</a>.<br> -To get a copy of the FIMO software please access <a href="http://meme-suite.org">http://meme-suite.org</a> -<p>If you use FIMO in your research, please cite the following paper:<br> -Charles E. Grant, Timothy L. Bailey, and William Stafford Noble, -"FIMO: Scanning for occurrences of a given motif", -<i>Bioinformatics</i>, <b>27</b>(7):1017-1018, 2011. -<center><big><b><a name="database_and_motifs">DATABASE AND MOTIFS</a></b></big></center> - Database contains 1 sequences, 16569 residues - <table> - <thead> - </thead> - <tbody> - </tbody> - </table> -A 0.278 C 0.222 G 0.222 T 0.278 </p> -<center><big><b><a name="sec_i">SECTION I: HIGH-SCORING MOTIF OCCURENCES</a></b></big></center> -There were 11 motif occurences with a p-value less than 0.0001. -The full set of motif occurences can be seen in the -TSV (tab-delimited values) output file -the GFF3 file -which may be suitable for uploading to the -(assuming the FASTA input sequences included genomic coordinates in UCSC or Galaxy format), -or the XML file -The <i>p</i>-value of a motif occurrence is defined as the -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. -The score for the match of a position in a sequence to a motif -is computed by summing the appropriate entries from each column of -the position-dependent scoring matrix that represents the motif. -The q-value of a motif occurrence is defined as the -false discovery rate if the occurrence is accepted as significant. -<li>The table is sorted by increasing <i>p</i>-value.</li> -<th>Motif ID</th> -<th>Alt ID</th> -<th>Sequence Name</th> -<th>Strand</th> -<th>Start</th> -<th>End</th> -<th>p-value</th> -<th>q-value</th> -<th>Matched Sequence</th> - <tr> - <td style="text-align:left;">CCAGCAY</td> - <td style="text-align:left;">DREME-5</td> - <td style="text-align:left;">chrM</td> - <td style="text-align:center;">+</td> - <td style="text-align:left;">510</td> - <td style="text-align:left;">516</td> - <td style="text-align:left;">4.15e-05</td> - <td style="text-align:left;">0.683</td> - <td style="text-align:left;font-size:x-large;font-family:monospace;">CCAGCAC</td> - <td style="text-align:left;">2093</td> - <td style="text-align:left;">2099</td> - <td style="text-align:left;">8.2e-05</td> - <td style="text-align:left;">0.332</td> - <td style="text-align:left;font-size:x-large;font-family:monospace;">ACTAACA</td> - </tr> -<hr> -<center><big><b><a name="debugging_information">DEBUGGING INFORMATION</a></b></big></center> -Command line: -Settings: +</pre> +<p> This information can be useful in the event you wish to report a problem with the FIMO software. +</p> +<hr> +<span style="background-color: #DDDDFF"><a href="#top_buttons"><b>Go to top</b></a></span> </body> </html> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test2.txt --- a/test-data/fimo_output_test2.txt Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test2.txt Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -9,4 +9,4 @@ ACTAAYH DREME-1 chrM 7742 7748 + 11.7286 8.2e-05 0.332 ACTAACA ACTAAYH DREME-1 chrM 13657 13663 + 11.7286 8.2e-05 0.332 ACTAACA ACTAAYH DREME-1 chrM 13741 13747 + 11.7286 8.2e-05 0.332 ACTAACA -CCAGCAY DREME-5 chrM 4241 4247 + 13.1461 9.37e-05 1 CCAGCAT +CCAGCAY DREME-5 chrM 4241 4247 + 13.1461 9.37e-05 1 CCAGCAT \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test2.xml --- a/test-data/fimo_output_test2.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test2.xml Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,11 +1,3 @@ -<?xml version="1.0" encoding="UTF-8" standalone="no"?> -<!-- Begin document body --> -<fimo version="5.0.5" release="Mon Mar 18 20:12:19 2019 -0700"> - xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" - xsi:schemaLocation= xmlns:fimo="http://noble.gs.washington.edu/schema/fimo" -> -<settings> -<setting name="allow clobber">false</setting> <setting name="compute q-values">true</setting> <setting name="parse genomic coord.">false</setting> <setting name="text only">false</setting> @@ -39,11 +31,4 @@ <motif name="TCTGT" alt="DREME-3" width="5" best-possible-match="TCTGT"/> <motif name="SCCAGG" alt="DREME-4" width="6" best-possible-match="CCCAGG"/> <motif name="CCAGCAY" alt="DREME-5" width="7" best-possible-match="CCAGCAC"/> -<motif name="GMATGT" alt="DREME-6" width="6" best-possible-match="GAATGT"/> -<value letter="A">0.278</value> -<value letter="C">0.222</value> -<value letter="G">0.222</value> -<value letter="T">0.278</value> -</background> -<cisml-file>cisml.xml</cisml-file> -</fimo> +<motif name="GMATGT" alt="DREME-6" width="6" best-possible-match="GAATGT"/> \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test3.html --- a/test-data/fimo_output_test3.html Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test3.html Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,92 +1,23 @@ -<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> -<html xmlns:cis="http://zlab.bu.edu/schema/cisml" xmlns:fimo="http://noble.gs.washington.edu/schema/cisml" xmlns:mem="http://noble.gs.washington.edu/meme"> -<head> -<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> -<meta charset="UTF-8"> -<title>FIMO Results</title> -<style type="text/css"> -</head> -<body color="#000000"> -<td bgcolor="#00FFFF"><a href="#database_and_motifs"><b>Database and Motifs</b></a></td> -<td bgcolor="#DDFFDD"><a href="#sec_i"><b>High-scoring Motif Occurences</b></a></td> -<td bgcolor="#DDDDFF"><a href="#debugging_information"><b>Debugging Information</b></a></td> -<td bgcolor="#FFDD00"><a href="fimo.tsv""><b>Results in TSV Format</b></a></td> -<td bgcolor="#FFDDFF"><a href="fimo.gff""><b>Results in GFF3 Format</b></a></td> -<center><big><b>FIMO - Motif search tool</b></big></center> -FIMO version 5.0.5, (Release date: Mon Mar 18 20:12:19 2019 -0700) -For further information on how to interpret these results please access <a href="http://meme-suite.org/doc/fimo-output-format.html">http://meme-suite.org/doc/fimo-output-format.html</a>.<br> -To get a copy of the FIMO software please access <a href="http://meme-suite.org">http://meme-suite.org</a> -<p>If you use FIMO in your research, please cite the following paper:<br> -Charles E. Grant, Timothy L. Bailey, and William Stafford Noble, -"FIMO: Scanning for occurrences of a given motif", -<i>Bioinformatics</i>, <b>27</b>(7):1017-1018, 2011. -<center><big><b><a name="database_and_motifs">DATABASE AND MOTIFS</a></b></big></center> - Database contains 1 sequences, 16569 residues - <table> - <thead> - <tr> - <th style="border-bottom: 1px dashed;">MOTIF</th> - <th style="border-bottom: 1px dashed; padding-left: 1em;">WIDTH</th> - <th style="border-bottom: 1px dashed; padding-left: 1em;text-align:left;" > - BEST POSSIBLE MATCH - </th> - </tr> - </thead> - <tbody> - <tr> - <td style="text-align:right;">ACTAAYH</td> - <td style="text-align:right;padding-left: 1em;">7</td> - <td style="text-align:left;padding-left: 1em;">ACTAACA</td> - </tr> - </tbody> - </table> -</p> -<p> -Random model letter frequencies (--uniform--): -A 0.250 C 0.250 G 0.250 T 0.250 </p> -<center><big><b><a name="sec_i">SECTION I: HIGH-SCORING MOTIF OCCURENCES</a></b></big></center> -There were 517 motif occurences with a p-value less than 0.01. -The full set of motif occurences can be seen in the -TSV (tab-delimited values) output file -the GFF3 file -which may be suitable for uploading to the -(assuming the FASTA input sequences included genomic coordinates in UCSC or Galaxy format), -or the XML file -The <i>p</i>-value of a motif occurrence is defined as the -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. -The score for the match of a position in a sequence to a motif -is computed by summing the appropriate entries from each column of -the position-dependent scoring matrix that represents the motif. -The q-value of a motif occurrence is defined as the -false discovery rate if the occurrence is accepted as significant. -<li>The table is sorted by increasing <i>p</i>-value.</li> -<table border="1"> -<thead> -<tr> -<th>Motif ID</th> -<th>Alt ID</th> -<th>Sequence Name</th> -<th>Strand</th> -<th>Start</th> -<th>End</th> -<th>p-value</th> -<th>q-value</th> -<th>Matched Sequence</th> -</tr> -</thead> -<tbody> - <tr> - <td style="text-align:left;">ACTAAYH</td> - <td style="text-align:left;">DREME-1</td> - <td style="text-align:left;">chrM</td> - <td style="text-align:center;">+</td> - <td style="text-align:left;">440</td> - <td style="text-align:left;">446</td> - <td style="text-align:left;">6.1e-05</td> - <td style="text-align:left;">0.239</td> - <td style="text-align:left;font-size:x-large;font-family:monospace;">ACTAACA</td> -This information can be useful in the event you wish to report a -problem with the FIMO software. -</body> -</html> + <td style="padding-right: 2em">background file name = --uniform--</td> + <td style="padding-left: 5em; padding-right: 2em">alphabet = DNA</td> + <td style="padding-left: 5em; padding-right: 2em">max stored scores = 100000</td> + </tr> <tr> + <td style="padding-right: 2em">allow clobber = false</td> + <td style="padding-left: 5em; padding-right: 2em">compute q-values = true</td> + <td style="padding-left: 5em; padding-right: 2em">parse genomic coord. = false</td> + </tr> + <tr> + <td style="padding-right: 2em">text only = false</td> + <td style="padding-left: 5em; padding-right: 2em">scan both strands = true</td> + <td style="padding-left: 5em; padding-right: 2em">max strand = false</td> + </tr> + <tr> + <td style="padding-right: 2em">threshold type = p-value</td> + <td style="padding-left: 5em; padding-right: 2em">output theshold = 0.01</td> + <td style="padding-left: 5em; padding-right: 2em">pseudocount = 0.1</td> + </tr> + <tr> + <td style="padding-right: 2em">alpha = 1</td> + <td style="padding-left: 5em; padding-right: 2em">verbosity = 2</td> + <td style="padding-left: 5em; padding-right: 2em"></td> + </tr> \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test3.txt --- a/test-data/fimo_output_test3.txt Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test3.txt Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -20,3 +20,21 @@ ACTAAYH DREME-1 chrM 862 868 + 11.2394 0.000244 0.294 ACTAACC ACTAAYH DREME-1 chrM 1832 1838 + 11.2394 0.000244 0.294 ACTAACC ACTAAYH DREME-1 chrM 8679 8685 + 11.2394 0.000244 0.294 ACTAACC +ACTAAYH DREME-1 chrM 8770 8776 + 11.2394 0.000244 0.294 ACTAACC +ACTAAYH DREME-1 chrM 9347 9353 + 11.2394 0.000244 0.294 ACTAACC +ACTAAYH DREME-1 chrM 9359 9365 + 11.2394 0.000244 0.294 ACTAACC +ACTAAYH DREME-1 chrM 10302 10308 + 11.2394 0.000244 0.294 ACTAACC +ACTAAYH DREME-1 chrM 14765 14771 + 11.2394 0.000244 0.294 ACTAACC +ACTAAYH DREME-1 chrM 4466 4472 + 10.8592 0.000305 0.302 ACTAATT +ACTAAYH DREME-1 chrM 11248 11254 + 10.8592 0.000305 0.302 ACTAATT +ACTAAYH DREME-1 chrM 475 481 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 7930 7936 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 8649 8655 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 8670 8676 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 10768 10774 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 11053 11059 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 11101 11107 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 12720 12726 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 13149 13155 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 14216 14222 + 10.6479 0.000366 0.302 ACTAATC +ACTAAYH DREME-1 chrM 678 684 - -1.07042 0.000549 0.366 ACTAAGA \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/fimo_output_test3.xml --- a/test-data/fimo_output_test3.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/fimo_output_test3.xml Sat Apr 09 08:32:23 2022 +0000 |
| b |
| @@ -1,23 +1,3 @@ -<?xml version="1.0" encoding="UTF-8" standalone="no"?> -<!-- Begin document body --> -<fimo version="5.0.5" release="Mon Mar 18 20:12:19 2019 -0700"> - xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" - xsi:schemaLocation= xmlns:fimo="http://noble.gs.washington.edu/schema/fimo" -> -<settings> -<setting name="background file name">--uniform--</setting> -<setting name="allow clobber">false</setting> -<setting name="compute q-values">true</setting> -<setting name="parse genomic coord.">false</setting> -<setting name="text only">false</setting> -<setting name="scan both strands">true</setting> -<setting name="output threshold">0.01</setting> -<setting name="threshold type">p-value</setting> -<setting name="max stored scores">100000</setting> -<setting name="pseudocount">0.1</setting> -<setting name="verbosity">2</setting> -<setting name="selected motif">ACTAAYH</setting> -</settings> <sequence-data num-sequences="1" num-residues="16569" /> <alphabet name="DNA" like="dna"> <letter id="A" symbol="A" complement="T" name="Adenine" colour="CC0000"/> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/meme_output_test1.html --- a/test-data/meme_output_test1.html Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/meme_output_test1.html Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| @@ -1,24 +1,73 @@ -<!DOCTYPE HTML> -<html> - <head> - <meta charset="UTF-8"> - <title>MEME</title> - <script> - // @JSON_VAR data - var data = { - "program": "MEME", - "version": "5.0.5", - "release": "Mon Mar 18 20:12:19 2019 -0700", - "stop_reason": "Stopped because requested number of motifs (1) found.", - "cmd": [ - "meme", - "-o", - "-nostatus", "-maxsize", "1000000" - ], - "options": { - }, - "motifs": [ - "scan": [ - </script> -var site_url = "http://meme-suite.org"; - + <script> + { + $("opt_mod").className = data.options.mod; + $("opt_objfun").textContent = data.options.objfun; + $("opt_spfun").textContent = data.options.spfun; + $("opt_strand").className = (current_alphabet.has_complement() ? (data.options.revcomp ? "both" : "given") : "none"); + $("opt_nmotifs").textContent = data.options.nmotifs; + $("opt_evt").textContent = (typeof data.options.evt === "number" ? data.options.evt : "no limit"); + $("opt_minw").textContent = data.options.minw; + $("opt_maxw").textContent = data.options.maxw; + $("opt_minsites").textContent = data.options.minsites; + $("opt_maxsites").textContent = data.options.maxsites; + $("opt_wnsites").textContent = data.options.wnsites; + $("opt_spmap").className = data.options.spmap; + $("opt_spfuzz").textContent = data.options.spfuzz; + $("opt_prior").className = data.options.prior; + if (data.options.prior == "dirichlet") { + $("opt_prior_source").textContent = make_background_source("Source", data.background.source, true); + } else { + $("opt_prior_source").textContent = (data.options.prior == "addone") ? "motif observed frequencies" : data.options.priors_source; + } + $("opt_b").textContent = (data.options.b < 0) ? "not applicable" : (data.options.b == 0) ? "intrinsic strength" : data.options.b; + $("opt_maxiter").textContent = data.options.maxiter; + $("opt_distance").textContent = data.options.distance; + $("opt_searchsize").textContent = data.options.searchsize; + if (typeof data.options.csites != "undefined") { + $("opt_csites").textContent = data.options.csites; + } else { + $("opt_csites").parentElement.style.display = "none" + } + if (typeof data.options.wg != "undefined") { + $("opt_wg").textContent = data.options.wg; + } else { + $("opt_wg").parentElement.style.display = "none" + } + if (typeof data.options.ws != "undefined") { + $("opt_ws").textContent = data.options.ws; + } + else { + $("opt_ws").parentElement.style.display = "none" + } + if (typeof data.options.noendgaps != "undefined") { + $("opt_noendgaps").className = (data.options.noendgaps ? "on" : "off"); + } + else { + $("opt_noendgaps").parentElement.style.display = "none" + } + $("opt_substring").className = (data.options.substring ? "on" : "off"); + } + </script> + </div> + <!-- list information on this program --> + <div id="info_sec" class="bar"> + <div class="subsection"> + <h5 id="version">MEME version</h5> + <span id="ins_version"></span> + (Release date: <span id="ins_release"></span>)<br> + </div> + <script> + $("ins_version").innerHTML = data["version"]; + $("ins_release").innerHTML = data["release"]; + </script> + <div class="subsection" id="reference"> <script>print_citation("reference", "MEME");</script></div> + <div class="subsection"> + <h5 id="command">Command line</h5> + <textarea id="cmd" rows="5" style="width:100%;" readonly="readonly"> + </textarea> + <script>$("cmd").value = data["cmd"].join(" ");</script> + </div> + </div> + + </body> +</html> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/meme_output_test1.txt --- a/test-data/meme_output_test1.txt Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/meme_output_test1.txt Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| @@ -1,61 +1,39 @@ ******************************************************************************** -MEME - Motif discovery tool -MEME version 5.0.5 (Release date: Mon Mar 18 20:12:19 2019 -0700) -REFERENCE -TRAINING SET -CONTROL SEQUENCES= --none-- -ALPHABET= ACDEFGHIKLMNPQRSTVWY -Sequence name Weight Length Sequence name Weight Length -------------- ------ ------ ------------- ------ ------ -chr21_19617074_19617124_ 1.0000 50 chr21_26934381_26934431_ 1.0000 50 -COMMAND LINE SUMMARY -model: mod= zoops nmotifs= 1 evt= inf -objective function: em= E-value of product of p-values - starts= E-value of product of p-values -width: minw= 8 maxw= 50 -nsites: minsites= 2 maxsites= 30 wnsites= 0.8 -theta: spmap= pam spfuzz= 120 -em: prior= megap b= 7500 maxiter= 50 - distance= 1e-05 -trim: wg= 11 ws= 1 endgaps= yes -data: n= 1500 N= 30 -sample: seed= 0 hsfrac= 0 - searchsize= 1500 norand= no csites= 1000 -Dirichlet mixture priors file: prior30.plib -Letter frequencies in dataset: -A 0.294 C 0.231 D 0 E 0 F 0 G 0.257 H 0 I 0 K 0 -L 0 M 0 N 0 P 0 Q 0 R 0 S 0 T 0.217 V 0 -W 0 Y 0 -Background letter frequencies (from file dataset with add-one prior applied): -A 0.291 C 0.229 D 0.000658 E 0.000658 F 0.000658 G 0.255 H 0.000658 I 0.000658 K 0.000658 -L 0.000658 M 0.000658 N 0.000658 P 0.000658 Q 0.000658 R 0.000658 S 0.000658 T 0.215 V 0.000658 -W 0.000658 Y 0.000658 -Background model order: 0 -MOTIF GGGGTATAAAA MEME-1 width = 11 sites = 25 llr = 239 E-value = 2.4e-011 +SUMMARY OF MOTIFS +******************************************************************************** + -------------------------------------------------------------------------------- - Motif GGGGTATAAAA MEME-1 Description - Motif GGGGTATAAAA MEME-1 sites sorted by position p-value -Sequence name Start P-value Site -------------- ----- --------- ----------- -chr21_46046964_46047014_ 13 1.06e-06 AAGGCCAGGA GGGGTATAAAA GCCTGAGAGC - Motif GGGGTATAAAA MEME-1 block diagrams -SEQUENCE NAME POSITION P-VALUE MOTIF DIAGRAM -------------- ---------------- ------------- -chr21_46046964_46047014_ 1.1e-06 12_[1]_27 - Motif GGGGTATAAAA MEME-1 in BLOCKS format -BL MOTIF GGGGTATAAAA width=11 seqs=25 -chr21_46046964_46047014_ ( 13) GGGGTATAAAA 1 - Motif GGGGTATAAAA MEME-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 - Motif GGGGTATAAAA MEME-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 - Motif GGGGTATAAAA MEME-1 regular expression -[GA][GA][GC][GA]TATA[AT]AA -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)] -Stopped because requested number of motifs (1) found. +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 |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/meme_output_test1.xml --- a/test-data/meme_output_test1.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/meme_output_test1.xml Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| b'@@ -1,118 +1,58 @@\n-<?xml version=\'1.0\' encoding=\'UTF-8\' standalone=\'yes\'?>\n-<!-- Document definition -->\n-<!DOCTYPE MEME[\n-<!ELEMENT MEME (\n- training_set,\n- model, \n- motifs, \n- scanned_sites_summary?\n-)>\n-<!ATTLIST MEME \n- version CDATA #REQUIRED\n- release CDATA #REQUIRED\n-<!-- Training-set elements -->\n-<!ELEMENT training_set (alphabet, ambigs, sequence*, letter_frequencies)>\n- name CDATA #REQUIRED\n- length CDATA #REQUIRED\n- weight CDATA #REQUIRED\n-<!ELEMENT letter_frequencies (alphabet_array)>\n-<!-- Model elements -->\n-<!ELEMENT model (\n- command_line,\n- host,\n- type,\n- nmotifs,\n-)>\n-<!ELEMENT command_line (#PCDATA)*>\n-<!ELEMENT host (#PCDATA)*>\n-<!ELEMENT type (#PCDATA)*>\n-<!ELEMENT nmotifs (#PCDATA)*>\n-<!-- The left_flank contains the sequence for 10 bases to the left of the motif start -->\n-<!ELEMENT left_flank (#PCDATA)>\n-<!-- The site contains the sequence for the motif instance -->\n-<!ELEMENT site (letter_ref*)>\n-<!-- The right_flank contains the sequence for 10 bases to the right of the motif end -->\n-<!ELEMENT right_flank (#PCDATA)>\n-<!-- Scanned site elements -->\n-<!-- Scanned sites are motif occurences found during the sequence scan phase -->\n-<!ELEMENT scanned_sites_summary (scanned_sites*)>\n-<!ATTLIST scanned_sites_summary p_thresh CDATA #REQUIRED>\n-<!ELEMENT scanned_sites (scanned_site*)>\n-<!ATTLIST scanned_sites sequence_id IDREF #REQUIRED\n- pvalue CDATA #REQUIRED\n- num_sites CDATA #REQUIRED>\n-<!ELEMENT scanned_site EMPTY>\n-<!ATTLIST scanned_site motif_id IDREF #REQUIRED\n- strand (plus|minus|none) \'none\'\n- position CDATA #REQUIRED\n- pvalue CDATA #REQUIRED>\n-<!-- Utility elements -->\n-<!-- A reference to a letter in the alphabet -->\n-<!ELEMENT letter_ref EMPTY>\n-<!ATTLIST letter_ref letter_id IDREF #REQUIRED>\n-<!-- A alphabet-array contains one floating point value for each letter in an alphabet -->\n-<!ELEMENT alphabet_array (value*)>\n-<!ELEMENT value (#PCDATA)>\n-<!ATTLIST value letter_id IDREF #REQUIRED>\n-<!-- A alphabet_matrix contains one alphabet_array for each position in a motif -->\n-<!ELEMENT alphabet_matrix (alphabet_array*)>\n-]>\n-<!-- Begin document body -->\n-<MEME version="5.0.5" release="Mon Mar 18 20:12:19 2019 -0700">\n-<alphabet name="Protein" like="protein">\n-<letter id="A" symbol="A" name="Alanine" colour="0000CC"/>\n-</alphabet>\n-<sequence id="sequence_0" name="chr21_19617074_19617124_+" length="50" weight="1.000000" />\n-<letter_frequencies>\n-<alphabet_array>\n-<value letter_id="A">0.294</value>\n-</letter_frequencies>\n-</training_set>\n-<model>\n-<scores>\n-<alphabet_matrix>\n-<value letter_id="A">-32</value>\n-<value letter_id="A">-79</value>\n-<value letter_id="A">11</value>\n-<value letter_id="A">-596</value>\n-<value letter_id="A">165</value>\n-<value letter_id="A">-838</value>\n-<value letter_id="A">176</value>\n-<value letter_id="A">134</value>\n-<value letter_id="A">165</value>\n-<value letter_id="A">147</value>\n-<value letter_id="A">0.240000</value>\n-<value letter_id="A">0.280000</value>\n-<value letter_id="A">0.160000</value>\n-<value letter_id="A">0.320000</value>\n-<value letter_id="A">0.000000</value>\n-<value letter_id="A">0.960000</value>\n-<value letter_id="A">0.000000</value>\n-<value letter_id="A">1.000000</value>\n-<value letter_id="A">0.760000</value>\n-<value letter_id="A">0.960000</value>\n-<value letter_id="A">0.840000</value>\n-</alphabet_matrix>\n-</probabilities>\n-<regular_expression>\n-[GA][GA][GC][GA]TATA[AT]AA\n-</regular_expression>\n-<contributing_sites>\n-<contributing_site sequence_id="sequence_24" position="12" strand="none" pvalue="1.06e-06" >\n-<left_flank>AAGGCCAGGA</left_flank>\n-<site>\n-<letter_ref letter_id="G"/>\n-</site>\n-<right_flank>GCCTGAGAGC</right_flank>\n-</contributing_site>\n-<contributing_site sequence_id="sequence_25" position="36" strand="none" pvalue="3.41e-06" >\n-<left_flank>ACAGGCCCTG</left_flank'..b'="none" position="12" pvalue="3.06e-05"/>\n+</scanned_sites>\n <scanned_sites sequence_id="sequence_5" pvalue="1.53e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="0" pvalue="3.82e-05"/>\n+</scanned_sites>\n <scanned_sites sequence_id="sequence_6" pvalue="6.70e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="15" pvalue="1.68e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_7" pvalue="1.81e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="4" pvalue="4.54e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_8" pvalue="1.61e-02" num_sites="0"></scanned_sites>\n+<scanned_sites sequence_id="sequence_9" pvalue="1.36e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="13" pvalue="3.41e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_10" pvalue="1.99e-01" num_sites="0"></scanned_sites>\n+<scanned_sites sequence_id="sequence_11" pvalue="3.47e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="16" pvalue="8.67e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_12" pvalue="3.47e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="18" pvalue="8.67e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_13" pvalue="2.01e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="13" pvalue="5.01e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_14" pvalue="8.11e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="19" pvalue="2.03e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_15" pvalue="3.47e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="21" pvalue="8.67e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_16" pvalue="2.71e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="22" pvalue="6.78e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_17" pvalue="8.23e-02" num_sites="0"></scanned_sites>\n+<scanned_sites sequence_id="sequence_18" pvalue="1.53e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="37" pvalue="3.82e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_19" pvalue="1.36e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="9" pvalue="3.41e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_20" pvalue="6.37e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="4" pvalue="1.59e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_21" pvalue="1.60e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="7" pvalue="4.00e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_22" pvalue="4.83e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="2" pvalue="1.21e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_23" pvalue="2.43e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="15" pvalue="6.06e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_24" pvalue="4.26e-05" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="12" pvalue="1.06e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_25" pvalue="1.36e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="36" pvalue="3.41e-06"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_26" pvalue="4.30e-02" num_sites="0"></scanned_sites>\n+<scanned_sites sequence_id="sequence_27" pvalue="4.30e-02" num_sites="0"></scanned_sites>\n+<scanned_sites sequence_id="sequence_28" pvalue="6.37e-04" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="32" pvalue="1.59e-05"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_29" pvalue="1.61e-03" num_sites="1"><scanned_site motif_id="motif_1" strand="none" position="30" pvalue="4.02e-05"/>\n+</scanned_sites>\n+</scanned_sites_summary>\n </MEME>\n' |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/meme_output_test2.html --- a/test-data/meme_output_test2.html Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/meme_output_test2.html Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| @@ -1,27 +1,73 @@ -<!DOCTYPE HTML> -<html> - <head> - <meta charset="UTF-8"> - <title>MEME</title> - <script> - // @JSON_VAR data - var data = { - "program": "MEME", - "version": "5.0.5", - "release": "Mon Mar 18 20:12:19 2019 -0700", - "stop_reason": "Stopped because requested number of motifs (1) found.", - "cmd": [ - "meme", - "-o", - "-nostatus", "-maxsize", "1000000", "-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", - "-spmap", "uni", "-spfuzz", "0.5" - ], - "motifs": [ - ] - }; - </script> -var site_url = "http://meme-suite.org"; + <script> + { + $("opt_mod").className = data.options.mod; + $("opt_objfun").textContent = data.options.objfun; + $("opt_spfun").textContent = data.options.spfun; + $("opt_strand").className = (current_alphabet.has_complement() ? (data.options.revcomp ? "both" : "given") : "none"); + $("opt_nmotifs").textContent = data.options.nmotifs; + $("opt_evt").textContent = (typeof data.options.evt === "number" ? data.options.evt : "no limit"); + $("opt_minw").textContent = data.options.minw; + $("opt_maxw").textContent = data.options.maxw; + $("opt_minsites").textContent = data.options.minsites; + $("opt_maxsites").textContent = data.options.maxsites; + $("opt_wnsites").textContent = data.options.wnsites; + $("opt_spmap").className = data.options.spmap; + $("opt_spfuzz").textContent = data.options.spfuzz; + $("opt_prior").className = data.options.prior; + if (data.options.prior == "dirichlet") { + $("opt_prior_source").textContent = make_background_source("Source", data.background.source, true); + } else { + $("opt_prior_source").textContent = (data.options.prior == "addone") ? "motif observed frequencies" : data.options.priors_source; + } + $("opt_b").textContent = (data.options.b < 0) ? "not applicable" : (data.options.b == 0) ? "intrinsic strength" : data.options.b; + $("opt_maxiter").textContent = data.options.maxiter; + $("opt_distance").textContent = data.options.distance; + $("opt_searchsize").textContent = data.options.searchsize; + if (typeof data.options.csites != "undefined") { + $("opt_csites").textContent = data.options.csites; + } else { + $("opt_csites").parentElement.style.display = "none" + } + if (typeof data.options.wg != "undefined") { + $("opt_wg").textContent = data.options.wg; + } else { + $("opt_wg").parentElement.style.display = "none" + } + if (typeof data.options.ws != "undefined") { + $("opt_ws").textContent = data.options.ws; + } + else { + $("opt_ws").parentElement.style.display = "none" + } + if (typeof data.options.noendgaps != "undefined") { + $("opt_noendgaps").className = (data.options.noendgaps ? "on" : "off"); + } + else { + $("opt_noendgaps").parentElement.style.display = "none" + } + $("opt_substring").className = (data.options.substring ? "on" : "off"); + } + </script> + </div> + <!-- list information on this program --> + <div id="info_sec" class="bar"> + <div class="subsection"> + <h5 id="version">MEME version</h5> + <span id="ins_version"></span> + (Release date: <span id="ins_release"></span>)<br> + </div> + <script> + $("ins_version").innerHTML = data["version"]; + $("ins_release").innerHTML = data["release"]; + </script> + <div class="subsection" id="reference"> <script>print_citation("reference", "MEME");</script></div> + <div class="subsection"> + <h5 id="command">Command line</h5> + <textarea id="cmd" rows="5" style="width:100%;" readonly="readonly"> + </textarea> + <script>$("cmd").value = data["cmd"].join(" ");</script> + </div> + </div> + + </body> +</html> |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/meme_output_test2.txt --- a/test-data/meme_output_test2.txt Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/meme_output_test2.txt Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| @@ -1,86 +1,40 @@ ******************************************************************************** -MEME - Motif discovery tool -MEME version 5.0.5 (Release date: Mon Mar 18 20:12:19 2019 -0700) -REFERENCE -TRAINING SET -PRIMARY SEQUENCES= Galaxy_FASTA_Input -CONTROL SEQUENCES= --none-- -ALPHABET= ACGT -Sequence name Weight Length Sequence name Weight Length -------------- ------ ------ ------------- ------ ------ -chr21_19617074_19617124_ 1.0000 50 chr21_26934381_26934431_ 1.0000 50 -COMMAND LINE SUMMARY -model: mod= zoops nmotifs= 1 evt= inf -objective function: em= E-value of product of p-values - starts= E-value of product of p-values -strands: + -width: minw= 8 maxw= 50 -nsites: minsites= 2 maxsites= 30 wnsites= 0.8 -theta: spmap= uni spfuzz= 0.5 -em: prior= dirichlet b= 0.01 maxiter= 50 - distance= 0.001 -trim: wg= 11 ws= 1 endgaps= yes -data: n= 1500 N= 30 -sample: seed= 0 hsfrac= 0 - searchsize= 1500 norand= no csites= 1000 -Dirichlet mixture priors file: -Letter frequencies in dataset: -A 0.294 C 0.231 G 0.257 T 0.217 -Background letter frequencies (from file dataset with add-one prior applied): -A 0.294 C 0.231 G 0.257 T 0.217 -Background model order: 0 -MOTIF GGSRTATAAAA MEME-1 width = 11 sites = 30 llr = 254 E-value = 5.1e-040 - Motif GGSRTATAAAA MEME-1 Description -Simplified A 3313:9:a798 -pos.-specific C 1:3::1:::1: -probability G 6756::::::2 -matrix T 1:11a1a:3:: +SUMMARY OF MOTIFS +******************************************************************************** - 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 GGSRTATAAAA MEME-1 sites sorted by position p-value -Sequence name Start P-value Site -chr21_46046964_46047014_ 13 4.51e-07 AAGGCCAGGA GGGGTATAAAA GCCTGAGAGC - Motif GGSRTATAAAA MEME-1 block diagrams -SEQUENCE NAME POSITION P-VALUE MOTIF DIAGRAM +-------------------------------------------------------------------------------- + Combined block diagrams: non-overlapping sites with p-value < 0.0001 +-------------------------------------------------------------------------------- +SEQUENCE NAME COMBINED P-VALUE MOTIF DIAGRAM ------------- ---------------- ------------- -chr21_46046964_46047014_ 4.5e-07 12_[+1]_27 - Motif GGSRTATAAAA MEME-1 in BLOCKS format -BL MOTIF GGSRTATAAAA width=11 seqs=30 -chr21_46046964_46047014_ ( 13) GGGGTATAAAA 1 - Motif GGSRTATAAAA MEME-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 GGSRTATAAAA MEME-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 - Motif GGSRTATAAAA MEME-1 regular expression -[GA][GA][GC][GA]TATA[AT]AA -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)] -Stopped because requested number of motifs (1) found. +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 +-------------------------------------------------------------------------------- \ No newline at end of file |
| b |
| diff -r d7a6ea1e3b9d -r c5209f38700d test-data/meme_output_test2.xml --- a/test-data/meme_output_test2.xml Sat Nov 27 14:37:42 2021 +0000 +++ b/test-data/meme_output_test2.xml Sat Apr 09 08:32:23 2022 +0000 |
| [ |
| b'@@ -1,82 +1,58 @@\n-<?xml version=\'1.0\' encoding=\'UTF-8\' standalone=\'yes\'?>\n-<!-- Document definition -->\n-<!DOCTYPE MEME[\n-<!ELEMENT MEME (\n- training_set,\n- model, \n- motifs, \n- scanned_sites_summary?\n-)>\n-<!ATTLIST MEME \n- version CDATA #REQUIRED\n- release CDATA #REQUIRED\n-<!-- Training-set elements -->\n-<!ELEMENT training_set (alphabet, ambigs, sequence*, letter_frequencies)>\n-<!ATTLIST training_set primary_sequences CDATA #REQUIRED primary_count CDATA #REQUIRED primary_positions CDATA #REQUIRED\n- control_sequences CDATA "" control_count CDATA "" control_positions CDATA "">\n-<!ELEMENT alphabet (letter*)>\n-<!ATTLIST alphabet name CDATA #REQUIRED>\n-<!ELEMENT letter_frequencies (alphabet_array)>\n-<!-- Model elements -->\n-<!ELEMENT model (\n- command_line,\n- host,\n- type,\n- nmotifs,\n-)>\n-<!ELEMENT command_line (#PCDATA)*>\n-<!ELEMENT motifs (motif*)>\n-<!ELEMENT motif (scores, probabilities, regular_expression?, contributing_sites)>\n-<!-- The left_flank contains the sequence for 10 bases to the left of the motif start -->\n-<!ELEMENT left_flank (#PCDATA)>\n-<!-- The site contains the sequence for the motif instance -->\n-<!ELEMENT site (letter_ref*)>\n-<!-- The right_flank contains the sequence for 10 bases to the right of the motif end -->\n-<!ELEMENT right_flank (#PCDATA)>\n-<!-- Scanned site elements -->\n-<!-- Scanned sites are motif occurences found during the sequence scan phase -->\n-<!ELEMENT scanned_sites_summary (scanned_sites*)>\n-<training_set primary_sequences="Galaxy_FASTA_Input" primary_count="30" primary_positions="1500" control_sequences="--none--" control_count="0" control_positions="0">\n-<alphabet name="DNA" like="dna">\n-<letter id="A" symbol="A" complement="T" name="Adenine" colour="CC0000"/>\n-<sequence id="sequence_0" name="chr21_19617074_19617124_+" length="50" weight="1.000000" />\n-<value letter_id="G">0.257</value>\n-<value letter_id="T">0.217</value>\n-</alphabet_array>\n-<model>\n-<type>zoops</type>\n-<scores>\n-<alphabet_matrix>\n-<alphabet_array>\n-<value letter_id="A">-14</value>\n-<value letter_id="A">3</value>\n-<value letter_id="A">-1155</value>\n-<value letter_id="A">156</value>\n-<value letter_id="A">-1155</value>\n-<value letter_id="A">172</value>\n-<value letter_id="A">125</value>\n-<value letter_id="A">167</value>\n-<value letter_id="A">144</value>\n-<value letter_id="A">0.266667</value>\n-<value letter_id="A">0.300000</value>\n-<value letter_id="A">0.800000</value>\n-<contributing_site sequence_id="sequence_24" position="12" strand="plus" pvalue="4.51e-07" >\n-<left_flank>AAGGCCAGGA</left_flank>\n-<letter_ref letter_id="G"/>\n-<right_flank>GCCTGAGAGC</right_flank>\n-<contributing_site sequence_id="sequence_23" position="15" strand="plus" pvalue="2.22e-06" >\n-<letter_ref letter_id="A"/>\n-<contributing_site sequence_id="sequence_13" position="13" strand="plus" pvalue="2.74e-06" >\n-<right_flank>AGCCCTGTAC</right_flank>\n-<contributing_site sequence_id="sequence_25" position="36" strand="plus" pvalue="4.86e-06" >\n-<left_flank>CGTGGTCGCG</left_flank>\n-<right_flank>GC</right_flank>\n-<contributing_site sequence_id="sequence_29" position="30" strand="plus" pvalue="3.04e-05" >\n-<left_flank>GCTGCCGGTG</left_flank>\n-<right_flank>GCCCTGGCG</right_flank>\n-<contributing_site sequence_id="sequence_4" position="12" strand="plus" pvalue="3.04e-05" >\n+</motifs>\n <scanned_sites_summary p_thresh="0.0001">\n <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"/>\n+</scanned_sites>\n <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"/>\n+</scanned_sites>\n <scanned_sites sequence_id="sequence_2" pvalue="1.00e-01" num_sites="0"></scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequen'..b'="plus" position="12" pvalue="3.04e-05"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_8" pvalue="3.37e-02" num_sites="0"></scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_10" pvalue="5.73e-02" num_sites="0"></scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_17" pvalue="1.90e-02" num_sites="0"></scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<scanned_sites sequence_id="sequence_26" pvalue="5.54e-03" num_sites="0"></scanned_sites>\n+<scanned_sites sequence_id="sequence_27" pvalue="5.54e-03" num_sites="0"></scanned_sites>\n+<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"/>\n+</scanned_sites>\n+<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"/>\n+</scanned_sites>\n+</scanned_sites_summary>\n </MEME>\n' |