Repository 'meme_meme'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/meme_meme

Changeset 12:5585f04eb317 (2018-04-25)
Previous changeset 11:7a5164f99316 (2018-04-24) Next changeset 13:57e5d9382f36 (2018-05-17)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/meme commit 42fa6e319cf1a97330818dc8c869871a32f0e7aa
added:
test-data/dreme1.html
test-data/dreme1.txt
test-data/dreme1.xml
test-data/dreme2.html
test-data/dreme2.txt
test-data/dreme_test_sites.fa
b
diff -r 7a5164f99316 -r 5585f04eb317 test-data/dreme1.html
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dreme1.html Wed Apr 25 12:12:22 2018 -0400
[
b'@@ -0,0 +1,6199 @@\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": "4.11.2",\n+        "release": "Thu May 05 14:58:55 2016 -0700",\n+        "cmd": [\n+          "dreme", "-o", "./output", "-p",\n+          "/tmp/tmpijN1y0/files/000/dataset_1.dat", "-norc", "-rna", "-s",\n+          "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+          }\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+            }, {\n+              "symbol": "G",\n+              "name": "Guanine",\n+              "colour": "FFB300"\n+            }, {\n+              "symbol": "U",\n+              "aliases": "T",\n+              "name": "Uracil",\n+              "colour": "008000"\n+            }, {\n+              "symbol": "N",\n+              "aliases": "X.",\n+              "name": "Any base",\n+              "equals": "ACGU"\n+            }, {\n+              "symbol": "V",\n+              "name": "Not U",\n+              "equals": "ACG"\n+            }, {\n+              "symbol": "H",\n+              "name": "Not G",\n+              "equals": "ACU"\n+            }, {\n+              "symbol": "D",\n+              "name": "Not C",\n+              "equals": "AGU"\n+            }, {\n+              "symbol": "B",\n+              "name": "Not A",\n+              "equals": "CGU"\n+            }, {\n+              "symbol": "M",\n+              "name": "Amino",\n+              "equals": "AC"\n+            }, {\n+              "symbol": "R",\n+              "name": "Purine",\n+              "equals": "AG"\n+            }, {\n+              "symbol": "W",\n+              "name": "Weak",\n+              "equals": "AU"\n+            }, {\n+              "symbol": "S",\n+              "name": "Strong",\n+              "equals": "CG"\n+            }, {\n+              "symbol": "Y",\n+              "name": "Pyrimidine",\n+              "equals": "CU"\n+            }, {\n+              "symbol": "K",\n+              "name": "Keto",\n+              "equals": "GU"\n+            }\n+          ]\n+        },\n+        "background": {\n+          "freqs": [0.221, 0.245, 0.221, 0.312]\n+        },\n+        "sequence_db": {\n+          "name": "dataset 1",\n+          "file": "/tmp/tmpijN1y0/files/000/dataset_1.dat",\n+          "lmod": "Tue Apr 24 13:55:48 CEST 2018",\n+          "count": 1000\n+        },\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+        },\n+        "motifs": [\n+          {\n+            "db": 0,\n+            "id": "UUYUCY",\n+            "alt": "MEME",\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+            ],\n+            "matches": [\n+              {\n+                "seq": "UUUUCC",\n+                "p": 147,\n+                "n": 75,\n+                "pvalue": "1.8e-007",\n+                "evalue": "8.1e-003"\n+              }, {\n+              '..b'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 = dreme_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(dreme_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 = (dreme_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+        $("ins_release").innerHTML = data["release"];\n+      </script>\n+      <div class="subsection">\n+        <h5 id="reference">Reference</h5>\n+        <span class="citation">\n+          Timothy L. Bailey, "DREME: Motif discovery in transcription factor ChIP-seq data", <i>Bioinformatics</i>, <b>27</b>(12):1653-1659, 2011.\n+          <a href="http://bioinformatics.oxfordjournals.org/content/27/12/1653">[full text]</a>\n+        </span>\n+      </div>\n+      <div class="subsection">\n+        <h5 id="command">Command line</h5>\n+        <textarea id="cmd" rows="3" style="width:100%;" readonly="readonly">\n+        </textarea>\n+        <script>$("cmd").value = data["cmd"].join(" ");</script>\n+      </div>\n+    </div>\n+    \n+  </body>\n+</html>\n'
b
diff -r 7a5164f99316 -r 5585f04eb317 test-data/dreme1.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dreme1.txt Wed Apr 25 12:12:22 2018 -0400
b
@@ -0,0 +1,102 @@
+# DREME 4.12.0
+#     command: dreme -oc dreme_out -rna -norc -p dreme_test_sites.fa -e 0.05 -mink 3 -maxk 8
+#   positives: 1000 from dreme_test_sites.fa (Thu Apr 19 19:09:45 CEST 2018)
+#   negatives: 1000 from shuffled positives
+#        host: ThinkPad-T450s
+#        when: Thu Apr 19 19:11:17 CEST 2018
+
+MEME version 4.12.0
+
+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
+0.000000 0.294118 0.000000 0.705882
+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
+1.000000 0.000000 0.000000 0.000000
+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
+0.000000 0.000000 0.000000 1.000000
+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
+#    Running time: 13.45 seconds
b
diff -r 7a5164f99316 -r 5585f04eb317 test-data/dreme1.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dreme1.xml Wed Apr 25 12:12:22 2018 -0400
b
@@ -0,0 +1,32 @@
+<dreme version="4.12.0" release="Tue Jun 27 16:22:50 2017 -0700">
+  <model>
+    <command_line>dreme -oc dreme_out -rna -norc -p dreme_test_sites.fa -e 0</command_line>
+    <positives name="dreme test sites" count="1000" file="dreme_test_sites.fa" last_mod_date="Thu Apr 19 19:09:45 CEST 2018" />
+    <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"/>
+    <ngen>100</ngen>
+    <add_pv_thresh>0.01</add_pv_thresh>
+    <seed>1</seed>
+    <host>ThinkPad-T450s</host>
+    <when>Thu Apr 19 19:40:08 CEST 2018</when>
+  </model>
+  <motifs>
b
diff -r 7a5164f99316 -r 5585f04eb317 test-data/dreme2.html
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dreme2.html Wed Apr 25 12:12:22 2018 -0400
[
b'@@ -0,0 +1,6118 @@\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": "4.12.0",\n+        "release": "Tue Jun 27 16:22:50 2017 -0700",\n+        "cmd": [\n+          "dreme", "-oc", "dreme_out_adv", "-rna", "-norc", "-p",\n+          "dreme_test_sites.fa", "-e", "0.00001", "-mink", "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+            }, {\n+              "symbol": "G",\n+              "name": "Guanine",\n+              "colour": "FFB300"\n+            }, {\n+              "symbol": "U",\n+              "aliases": "T",\n+              "name": "Uracil",\n+              "colour": "008000"\n+            }, {\n+              "symbol": "N",\n+              "aliases": "X.",\n+              "name": "Any base",\n+              "equals": "ACGU"\n+            }, {\n+              "symbol": "V",\n+              "name": "Not U",\n+              "equals": "ACG"\n+            }, {\n+              "symbol": "H",\n+              "name": "Not G",\n+              "equals": "ACU"\n+            }, {\n+              "symbol": "D",\n+              "name": "Not C",\n+              "equals": "AGU"\n+            }, {\n+              "symbol": "B",\n+              "name": "Not A",\n+              "equals": "CGU"\n+            }, {\n+              "symbol": "M",\n+              "name": "Amino",\n+              "equals": "AC"\n+            }, {\n+              "symbol": "R",\n+              "name": "Purine",\n+              "equals": "AG"\n+            }, {\n+              "symbol": "W",\n+              "name": "Weak",\n+              "equals": "AU"\n+            }, {\n+              "symbol": "S",\n+              "name": "Strong",\n+              "equals": "CG"\n+            }, {\n+              "symbol": "Y",\n+              "name": "Pyrimidine",\n+              "equals": "CU"\n+            }, {\n+              "symbol": "K",\n+              "name": "Keto",\n+              "equals": "GU"\n+            }\n+          ]\n+        },\n+        "background": {\n+          "freqs": [0.221, 0.245, 0.221, 0.312]\n+        },\n+        "sequence_db": {\n+          "name": "dreme test sites",\n+          "file": "dreme_test_sites.fa",\n+          "lmod": "Thu Apr 19 19:09:45 CEST 2018",\n+          "count": 1000\n+        },\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+        },\n+        "motifs": [\n+          {\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+            ],\n+            "matches": [\n+              {\n+                "seq": "UUUUCC",\n+                "p": 147,\n+                "n": 75,\n+                "pvalue": "1.8e-007",\n+                "evalue": "2.2e-002"\n+              }, {\n+           '..b'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 = dreme_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(dreme_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 = (dreme_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+        $("ins_release").innerHTML = data["release"];\n+      </script>\n+      <div class="subsection">\n+        <h5 id="reference">Reference</h5>\n+        <span class="citation">\n+          Timothy L. Bailey, "DREME: Motif discovery in transcription factor ChIP-seq data", <i>Bioinformatics</i>, <b>27</b>(12):1653-1659, 2011.\n+          <a href="http://bioinformatics.oxfordjournals.org/content/27/12/1653">[full text]</a>\n+        </span>\n+      </div>\n+      <div class="subsection">\n+        <h5 id="command">Command line</h5>\n+        <textarea id="cmd" rows="3" style="width:100%;" readonly="readonly">\n+        </textarea>\n+        <script>$("cmd").value = data["cmd"].join(" ");</script>\n+      </div>\n+    </div>\n+    \n+  </body>\n+</html>\n'
b
diff -r 7a5164f99316 -r 5585f04eb317 test-data/dreme2.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dreme2.txt Wed Apr 25 12:12:22 2018 -0400
b
@@ -0,0 +1,68 @@
+# DREME 4.12.0
+#     command: dreme -oc dreme_out_adv -rna -norc -p dreme_test_sites.fa -e 0.00001 -mink 4 -maxk 10
+#   positives: 1000 from dreme_test_sites.fa (Thu Apr 19 19:09:45 CEST 2018)
+#   negatives: 1000 from shuffled positives
+#        host: ThinkPad-T450s
+#        when: Tue Apr 24 18:44:36 CEST 2018
+
+MEME version 4.12.0
+
+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   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
+0.000000 0.294118 0.000000 0.705882
+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
+#    Running time: 18.17 seconds
b
diff -r 7a5164f99316 -r 5585f04eb317 test-data/dreme_test_sites.fa
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dreme_test_sites.fa Wed Apr 25 12:12:22 2018 -0400
b
b'@@ -0,0 +1,2000 @@\n+>U2AF2_K562_rep02_1\n+UCUACACAUAGGGUGUUCCUGAAAAGCCCCAUAGUGAUUGAGUCUUCAAAACCACCGAUUC\n+>U2AF2_K562_rep02_2\n+UUGGAUAGCGGAAGCCCUGACCAGGCAUGGAGUAUCUCACAAAGUAGACGAUUCCUCUGGG\n+>U2AF2_K562_rep02_3\n+GGUUUCGGUCUAAGUACCACCCAGAUGAGGUGGGGAAGCGUCGGCAGGAGGCCCGGGGGGC\n+>U2AF2_K562_rep02_4\n+AAACAGGGUUUGUGGAUGCACUUAGAUGUUUGCAAUGAGCACUGUGGCUGGCAUGCCCCAG\n+>U2AF2_K562_rep02_5\n+UCCCAUUGUUUCUGCAGAGGCAGUUGGUGUCACCAGCCAGCGACCAGUGUUUUGUCCUUUU\n+>U2AF2_K562_rep02_6\n+UUCUACCCUCUCUAACUCCUCCCAGCAGCAAAAGGGAGACACUUCAGCUGGAACAAAAUAG\n+>U2AF2_K562_rep02_7\n+UUCUACCCUCUCUAACUCCUCCCAGCAGCAAAAGGGAGACACUUCAGCUGGAACAAAAUAG\n+>U2AF2_K562_rep02_8\n+UUUUCUCCCUUCCACCCACACCCUGCAGCGUCGAGGUCCUCAGCGAUCAGUUGAUGUAAUA\n+>U2AF2_K562_rep02_9\n+GGCAGGGGAAGUGGGGAUGGCAGGACAUGGAUGGCCCUUGAGGCAUUGGCUCUGGGUGUCA\n+>U2AF2_K562_rep02_10\n+GCAGGGGAAGUGGGGAUGGCAGGACAUGGAUGGCCCUUGAGGCAUUGGCUCUGGGUGUCAU\n+>U2AF2_K562_rep02_11\n+UUAGUCUUUCCAUCUACAGCCCACUGGCACUCCAGGCACCUACCUACUUCAAACAAGCUCA\n+>U2AF2_K562_rep02_12\n+UUUCUCUUUUCCUUCCACAGGGGACCGUGAUUAGGGUAUUUUCCAUUCCAGAAGGACAAAA\n+>U2AF2_K562_rep02_13\n+AUAACUGUUUUGUCUUUCCCUCCCCCGCUUCGUUCCCAGGUUUCGGUCUAAGUACCACCCA\n+>U2AF2_K562_rep02_14\n+UUUCAGAGAACGUUUGUCUGCCUGAUGAGAGCCACUUGGGUUAAGAAACUACCUGUGAAUA\n+>U2AF2_K562_rep02_15\n+AUGCUUUGCAAUUGCAGCUCCUUUAUGUCUCCAAAUGAUACAAGAAGACCCGAGAAAGUGG\n+>U2AF2_K562_rep02_16\n+UUUGCAAUUUUGCCUAGGGCCCUGGUGGUGGCAACCGCCUGUGUGCCACUGAAAAUCGUGC\n+>U2AF2_K562_rep02_17\n+UUGCAAUUUUGCCUAGGGCCCUGGUGGUGGCAACCGCCUGUGUGCCACUGAAAAUCGUGCC\n+>U2AF2_K562_rep02_18\n+CUAAUUUUUAAAAAGCAGCCUCUGGAGCCAGCCAUGUUUGGCACUGAAUCUUCAUGUAAGU\n+>U2AF2_K562_rep02_19\n+UCUAAUUUUUAAAAAGCAGCCUCUGGAGCCAGCCAUGUUUGGCACUGAAUCUUCAUGUAAG\n+>U2AF2_K562_rep02_20\n+UUUCUGUCUUCUCCUCUCUUCCUUUACACAAACUUAAACAGAAUGGAAAUGAAAACCAAGG\n+>U2AF2_K562_rep02_21\n+AAACAGUUUCAGCUCCUGGCAUCAGCUCUAUUCAAAUCUGGUUCAGAUUUUACAGCUCUGG\n+>U2AF2_K562_rep02_22\n+UUCUCUCUCUUCCCCUGGCUCCCUCAAGGUGAACAGCCAUAUACCAGGAAUAGGAUACCAG\n+>U2AF2_K562_rep02_23\n+UAUAUCCUUAGUGCAGGCUGUGGAAGAACAGGUGCCAUUUGUGCCAUAGAUUAUACGUGGA\n+>U2AF2_K562_rep02_24\n+UCCCUAAUUCUUCACCUCCCCCUCCUCUGCUGCCUCCUUGCUCUCCUCGCAGGUCAAGUUU\n+>U2AF2_K562_rep02_25\n+AUUGUUACUCCCAGGUGCCUUCGAAACAUCUGCAAGUUUUUAGUCUUGCUCAUCCCACUCU\n+>U2AF2_K562_rep02_26\n+CACAUUUUUUAAAAGGGCAAGUACAGGAGCAACUGCUGCUACCCAGAAAAAUGUGUGUAUU\n+>U2AF2_K562_rep02_27\n+CACAUUUUUUAAAAGGGCAAGUACAGGAGCAACUGCUGCUACCCAGAAAAAUGUGUGUAUU\n+>U2AF2_K562_rep02_28\n+AUUCCGUAGGUUCUAAUCUGUUCUCCCUCCUCCUCAACGUAAGUACACAGUGGAUACCCUC\n+>U2AF2_K562_rep02_29\n+UAUUCCGUAGGUUCUAAUCUGUUCUCCCUCCUCCUCAACGUAAGUACACAGUGGAUACCCU\n+>U2AF2_K562_rep02_30\n+ACUAAAGUUUUUUUUCCUAGUGGUUAUCAUGAGACUUAUAUAAAACAUGUUGUAUCUUAAC\n+>U2AF2_K562_rep02_31\n+CCUCCUCUUUCUCCCUCCCUCCUUCAUUCCCUCCAUCCCUCUCUUAACAGCUUGAAGAUAA\n+>U2AF2_K562_rep02_32\n+CCUCCUCUUUCUCCCUCCCUCCUUCAUUCCCUCCAUCCCUCUCUUAACAGCUUGAAGAUAA\n+>U2AF2_K562_rep02_35\n+AUUUAUCCUCUUGCUUUUGCAUCUCAAAAUUUUAUCGCCUUGAAGACACGUUUCUAUGAAU\n+>U2AF2_K562_rep02_36\n+GUCAGAAGGUAGCAGGGGCUGGGGGUUGCAGGGGGAUGUUGAGAAGAAGUGGUCCUUUGGU\n+>U2AF2_K562_rep02_37\n+AGUCAGAAGGUAGCAGGGGCUGGGGGUUGCAGGGGGAUGUUGAGAAGAAGUGGUCCUUUGG\n+>U2AF2_K562_rep02_38\n+UUGCUUCUCCUUUCUUCCUUCCUUCCUGCCCAGGGCCUCAUCUUUGUGGUGGACAGUAAUG\n+>U2AF2_K562_rep02_39\n+UAGAGACUGUUUAUUUGUUUGGUGGCUGGGAUGGAACACAAGAUCUUGCUGACUUCUGGGC\n+>U2AF2_K562_rep02_40\n+CUUAGGUAUGCCGAGCAGACAGCUGGAGGAUCCCGGGGCAGGGACACCUAGCCCGGUGCGU\n+>U2AF2_K562_rep02_41\n+AUUCUCCUGGGUUUUUGGCAGAUGGUUGCAGUGGCAGGACCAAGGCCUAGUGAGCUAUAGC\n+>U2AF2_K562_rep02_42\n+GCAGAUGGUUGCAGUGGCAGGACCAAGGCCUAGUGAGCUAUAGCUAAAUCUACAGUGGGAU\n+>U2AF2_K562_rep02_43\n+CCCCGUGCCUUGCCUCCCCAGGCGUGUGACCCCCUGCCGCACGAGGAGGAGCCCUCUGAAG\n+>U2AF2_K562_rep02_44\n+UUUACCCCACUACUAGGUAAGGGGCCUGGAUACCAAGAAGUGACUGCUCAUCUAAUCCAUA\n+>U2AF2_K562_rep02_45\n+GAUGGUCAUUGUCCUCCAGAGCAGUGAUGGAGGAAAUACCAGCCCAGGAAGCAGCAGGGUC\n+>U2AF2_K562_rep02_46\n+AUGGUCAUUGUCCUCCAGAGCAGUGAUGGAGGAAAUACCAGCCCAGGAAGCAGCAGGGUCA\n+>U2AF2_K562_rep02_47\n+UAGGCCUGUGAGGCUGCCACACCCUGUGCCCCCGUGCCUUGCCUCCCCAGGCGUGUGACCC\n+>U2AF2_K562_rep02_48\n+CAGGUCUCUCCUUACGGGGCCAGGGCAAUUUCUUUUCGUUCUUGCCCGUGUUGAACUGGGC\n+>U2AF2_K562_rep02_49\n+UACUUCUCUUUCCCUGUCCCCAAAGCAGAUCGCCAAACUGAGGCAGCAACUACAAC'..b'UUUUGGUAGGAAACUCAACAGUGUAAAUUUGAUGGCCA\n+>U2AF2_K562_rep02_12274\n+UGAUUUUGUCCCCUAGAGCAAGGUCCGUGGUCCUGUCAGUGGAAGCCCGGAUAGCAUGAAU\n+>U2AF2_K562_rep02_12275\n+GGUGGGGUGGGGGCGGGGAGGGCUCCCGGGAGGCAAGUGGUCACGGUGAGAGUCACUGGGC\n+>U2AF2_K562_rep02_12276\n+UACCCAUUGCUUUUACUGAUUAGGUAUGAAUUUCAGCCCUUUAUUUCCUUCUAAUUUUGGA\n+>U2AF2_K562_rep02_12279\n+CCUCAUUUCACCCAGGAGGAAGGUGCAGCUCAGAGCUGUUACGACUAGUCAGAGAGAGCGA\n+>U2AF2_K562_rep02_12281\n+AUAAUUCUUACCUGCCUCCUUUCUCUUCCCGGACCUUCCUAAUUUGAAGAGGUGAUUUGGA\n+>U2AF2_K562_rep02_12286\n+UUUCUCUCCCUAAUCUUUUCUCCAAUCAGGCUUCAAUGUUAGCUGCAGAAAAUGACCCUUA\n+>U2AF2_K562_rep02_12287\n+UUUUUGUUUUUCAGCCCUGGUACCUGACAGUGUAAAGAAGGAGCUCCUACAAAGAAUAAGA\n+>U2AF2_K562_rep02_12292\n+UUUACCUGGGUAACAAUUUUACUUUUUACCACAGUCACCAAGGAGCUAGUUAGCUGGAUGA\n+>U2AF2_K562_rep02_12293\n+UAGUUUGCAGGUCGAAGUAAGAAGGAAACCAAAUAUUCUCUUAAGGCUGUCGAAGACAUGU\n+>U2AF2_K562_rep02_12299\n+UUUGUUUUUCUUUUCAGGUAUGGAACCCUUCAGAUCAAAGCUUACCAAUAAAUUCAGUAUG\n+>U2AF2_K562_rep02_12300\n+UUUGUUUUUCUUUUCAGGUAUGGAACCCUUCAGAUCAAAGCUUACCAAUAAAUUCAGUAUG\n+>U2AF2_K562_rep02_12302\n+CUCAUUUUUCUCUUGCCGCCGCCAUGUAAGAGGUAACUUUCACCUCCCGUCAUGAUUCUGA\n+>U2AF2_K562_rep02_12303\n+UUAUUUUUCUUAUUUAGGGAAGGUUACCGCCACCUCUCUGUAGGAAAUCAAGUGUACAUGA\n+>U2AF2_K562_rep02_12305\n+ACUUGCUAUCCUUCCCUUGCAGGAAGACACGUUUCAGCAGUAUGUAAGACCAGAGAUUAAC\n+>U2AF2_K562_rep02_12306\n+CUUGUGCAAUUUCCAGGUGAUGAACAGCCUCCUUCUAAAUCAUUGACCACAUUUCUUAUUC\n+>U2AF2_K562_rep02_12307\n+UUCUCUUUUUGUGCCAGGUCAUACUUUAAGGAGCCCAAGAGCUUUAUAACAUAACAAAAGA\n+>U2AF2_K562_rep02_12308\n+UUCUCUUUUUGUGCCAGGUCAUACUUUAAGGAGCCCAAGAGCUUUAUAACAUAACAAAAGA\n+>U2AF2_K562_rep02_12311\n+UCCCUUAAACUUUAUACCACCAGAAUACCAACAGAAGCUAAAUGUAGCAAAUGUGACUGCC\n+>U2AF2_K562_rep02_12312\n+AAAAUUAAGUUCUUUUAUUAGCUGGCCGUUCUCUCAUUAUCUCAAAUUUAUUUAAGUAUUU\n+>U2AF2_K562_rep02_12316\n+UUUUCUUCUUUGUAGCAUGGAGCAGAUCCAACUAAAAAGAACAGAGAUGGAAAUACACCUU\n+>U2AF2_K562_rep02_12317\n+CUUUUCUCUAGGUUAGUAACACUGAAGAAAUCACUUUUGAAGCAUUGAAGAAAGCAAUUGG\n+>U2AF2_K562_rep02_12318\n+UCAUAGCUCCUUCUCCCCCUGCUUCUUUCCCAAAUGAAUGAGUAUUUCUUUUAGAUAAAUU\n+>U2AF2_K562_rep02_12321\n+AUUAUUUUUUUGUGUUGGCCAGGAAGUGAACCCAGGUCAACUGCUUGGAAGGUGGCUAUGC\n+>U2AF2_K562_rep02_12322\n+ACAGGCCCAGACCUUCUCUUUCCCUUUCCAGCAGCCGGAGAAGUGCGACAACAACCAGUAC\n+>U2AF2_K562_rep02_12323\n+CCCACCGCCUUGACACCCCCACCCCCGCAGGGAAGCAGCUGGUGCACUACACAGCGCAGCC\n+>U2AF2_K562_rep02_12324\n+UUUUUUCAUUACAUUACAGGAAGCAGAAUCUGGUAAUAUAAGUCAAAAGUCUGAUGAAGAA\n+>U2AF2_K562_rep02_12325\n+GUUUUCUUUUUUCCCUUUCCCAGUUUGACUUUUGCCAUCUAGAGUUUGUAAAUUAAGUGGU\n+>U2AF2_K562_rep02_12326\n+CUUUCCCUUCCACAGCCCAGGGUCCGUCUGCAUUUUGUGGAGCUGGGCUCCGGCCCUGCUG\n+>U2AF2_K562_rep02_12334\n+UUUGACUUUGCUUUGCUUUUCCCCUUUUGUGUUUGCAGUUGAAUGGAGAGGUUUUCAUAUU\n+>U2AF2_K562_rep02_12335\n+AUAUUAAACUCUUCAGAAGGAAGUCACUGUGCAUAGCCAUCCCCUAAGAAGAGGGCAUUCC\n+>U2AF2_K562_rep02_12336\n+ACACUUCUGUUCCUUUGUCUGCAGGAGAGCUGGAGGUGUUUCAGAAAGAUGGGGAACGAAA\n+>U2AF2_K562_rep02_12337\n+UAAAACUGUGGUUUGCAAGCAGAAGGCGCUGGAACUGUUGCCCAAGGUGGAAGAGGUGGUG\n+>U2AF2_K562_rep02_12338\n+CUAUCCUUCUACCUCCACGCACGUUUUUUAAGGCAGCGGCAAAAGUAGUAGAAAGCAAAAG\n+>U2AF2_K562_rep02_12339\n+UCAGCUUUUUAAUUAAAUGAAGCCAAGUGGGAUUUGCAUAAAGUGAAUGUUUACCAUGAAG\n+>U2AF2_K562_rep02_12340\n+UUUUCCUCCUCAAUCUUCCUUUGCCCUACCUAUGUGUUACUAGAGAACAUUUCUACAAAUU\n+>U2AF2_K562_rep02_12341\n+UCUUUUUCCUUCCUCCCUCCCUGUCUCCCUCCCUCUCUGCCUCCCUCCCUCCCUCCCUCUU\n+>U2AF2_K562_rep02_12342\n+UGUCUUUUUUUCUUUAGUGCUCCAGACAAUGAAACAUCCAAAUCUGCUAAUCAAGAUACCU\n+>U2AF2_K562_rep02_12343\n+CUUUGUACCAAUAGGUAAUUUGUCGUCCAGAUGCUCUGCUAUAUGUGAAGUAUCAUUUUUC\n+>U2AF2_K562_rep02_12344\n+CUUUGUACCAAUAGGUAAUUUGUCGUCCAGAUGCUCUGCUAUAUGUGAAGUAUCAUUUUUC\n+>U2AF2_K562_rep02_12352\n+UUUUUCCUCUGAAUUUACAUGGAAGGAGCGGUAGAUGAUGAGACAUAUAAGAUCCUCACAU\n+>U2AF2_K562_rep02_12353\n+AGAUGCCACUGCCUCCUUUCCAUUGUCAGCUGGCGGGUGACGCGACUGUUGUUGCACUGGG\n+>U2AF2_K562_rep02_12354\n+AGAUGCCACUGCCUCCUUUCCAUUGUCAGCUGGCGGGUGACGCGACUGUUGUUGCACUGGG\n+>U2AF2_K562_rep02_12355\n+CUAACUUCUCUAGCCAAAUACAGAUAGUCUUUCCCACUGAGUGUCUGUCAACAACUAGAUU\n+>U2AF2_K562_rep02_12356\n+UCCCUGAUUCUUUUUCAAGGGCCGCUUGAAGAUGCCAUUGAAGAUGAGGAAGAAGAAUGUC\n+>U2AF2_K562_rep02_12357\n+AUUUUAAUUCUAGUCUAGGUGAUGGCUGCUCCUUUCCAACUUGCCUUGUUAACCAGGAUCC\n'