# HG changeset patch # User iuc # Date 1649493178 0 # Node ID f33d77dcacce36cb66561a961bbf572415a9dbc6 # Parent e383d4bc8682a54a02af5fd386149c5020da259e "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/meme commit 03235f29be6368f58bc730a20d87a13cf215310f" diff -r e383d4bc8682 -r f33d77dcacce dreme.xml --- a/dreme.xml Sat Nov 27 14:39:01 2021 +0000 +++ b/dreme.xml Sat Apr 09 08:32:58 2022 +0000 @@ -1,4 +1,4 @@ - + - Discriminative Regular Expression Motif Elicitation macros.xml diff -r e383d4bc8682 -r f33d77dcacce macros.xml --- a/macros.xml Sat Nov 27 14:39:01 2021 +0000 +++ b/macros.xml Sat Apr 09 08:32:58 2022 +0000 @@ -1,9 +1,10 @@ - 5.0.5 + 0 + 5.4.1 - meme + meme diff -r e383d4bc8682 -r f33d77dcacce test-data/dreme_output_test1.html --- a/test-data/dreme_output_test1.html Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/dreme_output_test1.html Sat Apr 09 08:32:58 2022 +0000 @@ -1,113 +1,100 @@ - - - - - DREME - -/* dreme output specific css */ -/* program settings */ - - - - The name of the motif uses the IUPAC codes for nucleotides which has - a different letter to represent each of the 15 possible combinations. - The name is itself a representation of the motif though the position - weight matrix is not directly equivalent as it is generated from the - sites found that matched the letters given in the name. -

The E-value is the enrichment p-value times the number of candidate - motifs tested.

-

The enrichment p-value is calculated using Fisher's Exact Test for - enrichment of the motif in the positive sequences.

-

Note that the counts used in Fisher's Exact Test are made after - erasing sites that match previously found motifs.

-

The E-value of the motif calculated without erasing the sites of - previously found motifs.

-

Show more information on the motif.

-

Submit your motif to another MEME Suite program or download your motif.

-
Supported Programs
-
Tomtom
-
Tomtom is a tool for searching for similar known motifs. -
MAST
-
MAST is a tool for searching biological sequence databases for - sequences that contain one or more of a group of known motifs. -
FIMO
-
FIMO is a tool for searching biological sequence databases for - sequences that contain one or more known motifs. -
GOMo
-
GOMo is a tool for identifying possible roles (Gene Ontology - terms) for DNA binding motifs. -
SpaMo
-
SpaMo is a tool for inferring possible transcription factor - complexes by finding motifs with enriched spacings. + +
+

Sequences

+ + + + + + + + + + +
Source
Alphabet
Sequence Count
+ +

Control Sequences

+ + + + + + + + +
Source
Sequence Count
+ +

Background

+ + +

Other Settings

+ + + + + + + + + + +
Strand Handling + This alphabet only has one strand + Only the given strand is processed + Both the given and reverse complement strands are processed +
# REs to Generalize
Shuffle Seed
E-value Threshold
Max Motif Count
Max Run Time
+ +
+ +
+ +
+
DREME version
+ + (Release date: )
+
+ +
+
+
Command line
+ + +
+
+ diff -r e383d4bc8682 -r f33d77dcacce test-data/dreme_output_test1.txt --- a/test-data/dreme_output_test1.txt Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/dreme_output_test1.txt Sat Apr 09 08:32:58 2022 +0000 @@ -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 diff -r e383d4bc8682 -r f33d77dcacce test-data/dreme_output_test1.xml --- a/test-data/dreme_output_test1.xml Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/dreme_output_test1.xml Sat Apr 09 08:32:58 2022 +0000 @@ -1,30 +1,3 @@ - - - - - - - - - - - - - - - - - - - - - none - - - 100 - 0.01 - 1 - @@ -68,5 +41,4 @@ - - + \ No newline at end of file diff -r e383d4bc8682 -r f33d77dcacce test-data/dreme_output_test2.html --- a/test-data/dreme_output_test2.html Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/dreme_output_test2.html Sat Apr 09 08:32:58 2022 +0000 @@ -1,167 +1,50 @@ - - - - - DREME - -var site_url = "http://meme-suite.org"; -//====================================================================== -// end RasterizedAlphabet -//====================================================================== -//====================================================================== -// start LogoMetrics object -//====================================================================== - * Initialise and display the download popup. - - - - -
Tomtom
-
Tomtom is a tool for searching for similar known motifs. -
MAST
-
MAST is a tool for searching biological sequence databases for - sequences that contain one or more of a group of known motifs. -
FIMO
-
FIMO is a tool for searching biological sequence databases for - sequences that contain one or more known motifs. -
GOMo
-
GOMo is a tool for identifying possible roles (Gene Ontology - terms) for DNA binding motifs. -
SpaMo
-
SpaMo is a tool for inferring possible transcription factor - complexes by finding motifs with enriched spacings. - -

DREME

-

Discriminative Regular Expression Motif Elicitation

- For further information on how to interpret these results please access - To get a copy of the MEME software please access - If you use DREME in your research please cite the following paper:
- Timothy L. Bailey, "DREME: Motif discovery in transcription factor ChIP-seq data", Bioinformatics, 27(12):1653-1659, 2011. +

Other Settings

+ + + + + + + + + + +
Strand Handling + This alphabet only has one strand + Only the given strand is processed + Both the given and reverse complement strands are processed +
# REs to Generalize
Shuffle Seed
E-value Threshold
Max Motif Count
Max Run Time
+ + + +
+ +
+
DREME version
+ + (Release date: )
+
+ +
+
+
Command line
+ + +
+
+ diff -r e383d4bc8682 -r f33d77dcacce test-data/dreme_output_test2.txt --- a/test-data/dreme_output_test2.txt Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/dreme_output_test2.txt Sat Apr 09 08:32:58 2022 +0000 @@ -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 diff -r e383d4bc8682 -r f33d77dcacce test-data/dreme_output_test2.xml --- a/test-data/dreme_output_test2.xml Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/dreme_output_test2.xml Sat Apr 09 08:32:58 2022 +0000 @@ -1,30 +1,3 @@ - - - - - - - - - - - - - - - - - - - - - none - - - 100 - 0.01 - 1 - @@ -46,5 +19,4 @@ - - + \ No newline at end of file diff -r e383d4bc8682 -r f33d77dcacce test-data/fimo_output_test1.gff --- a/test-data/fimo_output_test1.gff Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/fimo_output_test1.gff Sat Apr 09 08:32:58 2022 +0000 @@ -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; diff -r e383d4bc8682 -r f33d77dcacce test-data/fimo_output_test1.html --- a/test-data/fimo_output_test1.html Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/fimo_output_test1.html Sat Apr 09 08:32:58 2022 +0000 @@ -1,73 +1,34 @@ - - - - - -FIMO Results - - - - -
- - - - - - - - + + + + + + + + + + + + + + + + + + + + + + +
Database and MotifsHigh-scoring Motif OccurencesDebugging InformationResults in TSV FormatResults in GFF3 Format
alphabet = DNAmax stored scores = 100000
allow clobber = falsecompute q-values = trueparse genomic coord. = false
text only = falsescan both strands = truemax strand = false
threshold type = p-valueoutput theshold = 0.0001pseudocount = 0.1
alpha = 1verbosity = 2
-
FIMO - Motif search tool
-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 http://meme-suite.org/doc/fimo-output-format.html.
-To get a copy of the FIMO software please access http://meme-suite.org -

If you use FIMO in your research, please cite the following paper:
-Charles E. Grant, Timothy L. Bailey, and William Stafford Noble, -"FIMO: Scanning for occurrences of a given motif", -Bioinformatics, 27(7):1017-1018, 2011. -

DATABASE AND MOTIFS
- Database contains 1 sequences, 16569 residues - - - - - -
-A 0.278 C 0.222 G 0.222 T 0.278

-
SECTION I: HIGH-SCORING MOTIF OCCURENCES
-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 p-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. -
  • The table is sorted by increasing p-value.
  • -Motif ID -Alt ID -Sequence Name -Strand -Start -End -p-value -q-value -Matched Sequence - - CCAGCAY - DREME-5 - chrM - + - 510 - 516 - 4.15e-05 - 0.683 - CCAGCAC - 2093 - 2099 - 8.2e-05 - 0.332 - ACTAACA - -
    -
    DEBUGGING INFORMATION
    -Command line: -Settings: + +

    This information can be useful in the event you wish to report a problem with the FIMO software. +

    +
    +Go to top diff -r e383d4bc8682 -r f33d77dcacce test-data/fimo_output_test2.txt --- a/test-data/fimo_output_test2.txt Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/fimo_output_test2.txt Sat Apr 09 08:32:58 2022 +0000 @@ -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 diff -r e383d4bc8682 -r f33d77dcacce test-data/fimo_output_test2.xml --- a/test-data/fimo_output_test2.xml Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/fimo_output_test2.xml Sat Apr 09 08:32:58 2022 +0000 @@ -1,11 +1,3 @@ - - - - xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" - xsi:schemaLocation= xmlns:fimo="http://noble.gs.washington.edu/schema/fimo" -> - -false true false false @@ -39,11 +31,4 @@ - -0.278 -0.222 -0.222 -0.278 - -cisml.xml - + \ No newline at end of file diff -r e383d4bc8682 -r f33d77dcacce test-data/fimo_output_test3.html --- a/test-data/fimo_output_test3.html Sat Nov 27 14:39:01 2021 +0000 +++ b/test-data/fimo_output_test3.html Sat Apr 09 08:32:58 2022 +0000 @@ -1,92 +1,23 @@ - - - - - -FIMO Results -