/tools/peak_calling/sicer_wrapper.xml

https://bitbucket.org/cistrome/cistrome-harvard/ · XML · 178 lines · 167 code · 11 blank · 0 comment · 0 complexity · 19d8b0aaab9b93f96de33e4d235bc5a5 MD5 · raw file 

    

  1. <tool id="peakcalling_sicer" name="SICER" version="0.0.1">
    2. 

  2.   <description>Statistical approach for the Identification of ChIP-Enriched Regions</description>
    3. 

  3.   <command interpreter="python">sicer_wrapper.py 
    4. 

  4.   --bed_file '${input_bed_file}' 
    5. 

  5.   #if str( $input_control_file ) != 'None':
    6. 

  6.       --control_file '${input_control_file}'
    7. 

  7.       --significant_islands_output_file "${significant_islands_output_file}"
    8. 

  8.       --islands_summary_output_file "${islands_summary_output_file}"
    9. 

  9.       --significant_islands_summary_output_file "${significant_islands_summary_output_file}"
    10. 

  10.   #end if
    11. 

  11.   ${fix_off_by_one_errors}
    12. 

  12.   --dbkey '${input_bed_file.dbkey}'
    13. 

  13.   --redundancy_threshold '${redundancy_threshold}'
    14. 

  14.   --window_size '${window_size}'
    15. 

  15.   --fragment_size '${fragment_size}'
    16. 

  16.   --effective_genome_fraction '${effective_genome_fraction}'
    17. 

  17.   --gap_size '${gap_size}'
    18. 

  18.   --error_cut_off '${error_cut_off}'
    19. 

  19.   ##output files
    20. 

  20.   --stdout "${output_log_file}"
    21. 

  21.   --redundancy_removed_test_bed_output_file "${redundancy_removed_test_bed_output_file}"
    22. 

  22.   --redundancy_removed_control_bed_output_file "${redundancy_removed_control_bed_output_file}"
    23. 

  23.   --score_island_output_file "${score_island_output_file}"
    24. 

  24.   --summary_graph_output_file "${summary_graph_output_file}"
    25. 

  25.   --test_normalized_wig_output_file "${test_normalized_wig_output_file}"
    26. 

  26.   --island_filtered_output_file "${island_filtered_output_file}"
    27. 

  27.   --island_filtered_normalized_wig_output_file "${island_filtered_normalized_wig_output_file}"
    28. 

  28.   </command>
    29. 

  29.   <requirements>
    30. 

  30.     <requirement type="package" version="1.1">SICER</requirement>
    31. 

  31.   </requirements>
    32. 

  32.   <inputs>
    33. 

  33.     <param name="input_bed_file" type="data" format="bed" label="ChIP-Seq Tag File" >
    34. 

  34.       <validator type="expression" message="SICER is not available for the genome.">value is not None and value.dbkey in [ 'mm8', 'mm9', 'hg18', 'hg19', 'dm2', 'dm3', 'sacCer1', 'pombe', 'rn4', 'tair8' ]</validator>
    35. 

  35.     </param>
    36. 

  36.     <param name="input_control_file" type="data" format="bed" label="ChIP-Seq Control File" optional="True"> <!-- fix me, add filter to match dbkeys -->
    37. 

  37.       <options>
    38. 

  38.         <filter type="data_meta" ref="input_bed_file" key="dbkey" />
    39. 

  39.       </options>
    40. 

  40.     </param>
    41. 

  41.     <param name="fix_off_by_one_errors" type="boolean" truevalue="--fix_off_by_one_errors" falsevalue="" checked="True" label="Fix off-by-one errors in output files" help="SICER creates non-standard output files, this option will fix these coordinates"/> 
    42. 

  42.     <param name="redundancy_threshold" type="integer" label="Redundancy Threshold" value="1" help="The number of copies of identical reads allowed in a library" />
    43. 

  43.     <param name="window_size" type="integer" label="Window size" value="200" help="Resolution of SICER algorithm. For histone modifications, one can use 200 bp" />
    44. 

  44.     <param name="fragment_size" type="integer" label="Fragment size" value="150" help="for determination of the amount of shift from the beginning of a read to the center of the DNA fragment represented by the read. FRAGMENT_SIZE=150 means the shift is 75." />
    45. 

  45.     <param name="effective_genome_fraction" type="float" label="Effective genome fraction" value="0.74" help="Effective Genome as fraction of the genome size. It depends on read length." />
    46. 

  46.     <param name="gap_size" type="integer" label="Gap size" value="600" help="Needs to be multiples of window size. Namely if the window size is 200, the gap size should be 0, 200, 400, 600, ..." />
    47. 

  47.     <param name="error_cut_off" type="float" label="Statistic threshold value" value="0.01" help="FDR (with control) or E-value (without control)" />
    48. 

  48.   </inputs>
    49. 

  49.   <outputs>
    50. 

  50.     <data name="redundancy_removed_test_bed_output_file" format="bed" label="${tool.name} on ${on_string} (test-${redundancy_threshold}-removed.bed)"/>
    51. 

  51.     <data name="redundancy_removed_control_bed_output_file" format="bed" label="${tool.name} on ${on_string} (control-${redundancy_threshold}-removed.bed)">
    52. 

  52.       <filter>input_control_file is not None</filter>
    53. 

  53.     </data>
    54. 

  54.     <data name="summary_graph_output_file" format="bedgraph" label="${tool.name} on ${on_string} (test-W${window_size}.graph)"/>
    55. 

  55.     <data name="test_normalized_wig_output_file" format="wig" label="${tool.name} on ${on_string} (test-W${window_size}-normalized.wig)"/>
    56. 

  56.     <data name="significant_islands_output_file" format="interval" label="${tool.name} on ${on_string} (test-W${window_size}-G${gap_size}-FDR${error_cut_off}-island.bed)">
    57. 

  57.       <filter>input_control_file is not None</filter>
    58. 

  58.     </data>
    59. 

  59.     <data name="island_filtered_output_file" format="bed" label="${tool.name} on ${on_string} (#if str( $input_control_file ) != 'None' then ''.join( map( str, [ 'test-W', $window_size, '-G',$gap_size, '-FDR', $error_cut_off, '-islandfiltered.bed' ] ) ) else ''.join( map( str, [ 'test-W', $window_size, '-G', $gap_size, '-E', $error_cut_off, '-islandfiltered.bed' ] ) ) #)"/>
    60. 

  60.     <data name="island_filtered_normalized_wig_output_file" format="wig" label="${tool.name} on ${on_string} (#if str( $input_control_file ) != 'None' then ''.join( map( str, [ 'test-W', $window_size, '-G',$gap_size, '-FDR', $error_cut_off, '-islandfiltered-normalized.wig' ] ) ) else ''.join( map( str, [ 'test-W', $window_size, '-G', $gap_size, '-E', $error_cut_off, '-islandfiltered-normalized.wig' ] ) ) #)"/>
    61. 

  61.     <data name="score_island_output_file" format="interval" label="${tool.name} on ${on_string} (#if str( $input_control_file ) != 'None' then ''.join( map( str, [ 'test-W', $window_size, '-G',$gap_size, '.scoreisland' ] ) ) else ''.join( map( str, [ 'test-W', $window_size, '-G', $gap_size, '-E', $error_cut_off, '.scoreisland' ] ) ) #)"/>
    62. 

  62.     <data name="islands_summary_output_file" format="interval" label="${tool.name} on ${on_string} (test-W${window_size}-G${gap_size}-islands-summary)">
    63. 

  63.       <filter>input_control_file is not None</filter>
    64. 

  64.     </data>
    65. 

  65.     <data name="significant_islands_summary_output_file" format="interval" label="${tool.name} on ${on_string} (test-W${window_size}-G${gap_size}-islands-summary-FDR${error_cut_off})">
    66. 

  66.       <filter>input_control_file is not None</filter>
    67. 

  67.     </data>
    68. 

  68.     <data name="output_log_file" format="txt" label="${tool.name} on ${on_string} (log)"/>
    69. 

  69.   </outputs>
    70. 

  70.   <tests>
    71. 

  71.     <test>
    72. 

  72.       <param name="input_bed_file" value="chipseq_enriched.bed.gz" ftype="bed" dbkey="mm8" />
    73. 

  73.       <param name="input_control_file" />
    74. 

  74.       <param name="fix_off_by_one_errors" />
    75. 

  75.       <param name="redundancy_threshold" value="1" />
    76. 

  76.       <param name="window_size" value="200" />
    77. 

  77.       <param name="fragment_size" value="150" />
    78. 

  78.       <param name="effective_genome_fraction" value="0.74" />
    79. 

  79.       <param name="gap_size" value="600" />
    80. 

  80.       <param name="error_cut_off" value="0.01" />
    81. 

  81.       <output name="redundancy_removed_test_bed_output_file" file="peakcalling_sicer/test_1/test-1-removed.bed" />
    82. 

  82.       <output name="summary_graph_output_file" file="peakcalling_sicer/test_1/test-W200.graph" />
    83. 

  83.       <output name="test_normalized_wig_output_file" file="peakcalling_sicer/test_1/test-W200-normalized.wig" />
    84. 

  84.       <output name="island_filtered_output_file" file="peakcalling_sicer/test_1/test-W200-G600-E0.01-islandfiltered.bed" />
    85. 

  85.       <output name="island_filtered_normalized_wig_output_file" file="peakcalling_sicer/test_1/test-W200-G600-E0.01-islandfiltered-normalized.wig" />
    86. 

  86.       <output name="score_island_output_file" file="peakcalling_sicer/test_1/test-W200-G600-E0.01.scoreisland" />
    87. 

  87.       <output name="output_log_file" file="peakcalling_sicer/test_1/output_log_file.contains" compare="contains"/>
    88. 

  88.     </test>
    89. 

  89.     <test>
    90. 

  90.       <param name="input_bed_file" value="chipseq_enriched.bed.gz" ftype="bed" dbkey="mm8" />
    91. 

  91.       <param name="input_control_file" value="chipseq_input.bed.gz" ftype="bed" dbkey="mm8" />
    92. 

  92.       <param name="fix_off_by_one_errors" />
    93. 

  93.       <param name="redundancy_threshold" value="1" />
    94. 

  94.       <param name="window_size" value="200" />
    95. 

  95.       <param name="fragment_size" value="150" />
    96. 

  96.       <param name="effective_genome_fraction" value="0.74" />
    97. 

  97.       <param name="gap_size" value="600" />
    98. 

  98.       <param name="error_cut_off" value="0.01" />
    99. 

  99.       <output name="redundancy_removed_test_bed_output_file" file="peakcalling_sicer/test_2/test-1-removed.bed" />
    100. 

  100.       <output name="redundancy_removed_control_bed_output_file" file="peakcalling_sicer/test_2/control-1-removed.bed" />
    101. 

  101.       <output name="summary_graph_output_file" file="peakcalling_sicer/test_2/test-W200.graph" />
    102. 

  102.       <output name="test_normalized_wig_output_file" file="peakcalling_sicer/test_2/test-W200-normalized.wig" />
    103. 

  103.       <output name="significant_islands_output_file" file="peakcalling_sicer/test_2/test-W200-G600-FDR0.01-island.bed" />
    104. 

  104.       <output name="island_filtered_output_file" file="peakcalling_sicer/test_2/test-W200-G600-FDR0.01-islandfiltered.bed" />
    105. 

  105.       <output name="island_filtered_normalized_wig_output_file" file="peakcalling_sicer/test_2/test-W200-G600-FDR0.01-islandfiltered-normalized.wig" />
    106. 

  106.       <output name="score_island_output_file" file="peakcalling_sicer/test_2/test-W200-G600.scoreisland" />
    107. 

  107.       <output name="islands_summary_output_file" file="peakcalling_sicer/test_2/test-W200-G600-islands-summary" />
    108. 

  108.       <output name="significant_islands_summary_output_file" file="peakcalling_sicer/test_2/test-W200-G600-islands-summary-FDR0.01" />
    109. 

  109.       <output name="output_log_file" file="peakcalling_sicer/test_2/output_log_file.contains" compare="contains"/>
    110. 

  110.     </test>
    111. 

  111.     <test>
    112. 

  112.       <param name="input_bed_file" value="chipseq_enriched.bed.gz" ftype="bed" dbkey="mm8" />
    113. 

  113.       <param name="input_control_file" value="chipseq_input.bed.gz" ftype="bed" dbkey="mm8" />
    114. 

  114.       <param name="fix_off_by_one_errors" value="True" />
    115. 

  115.       <param name="redundancy_threshold" value="1" />
    116. 

  116.       <param name="window_size" value="200" />
    117. 

  117.       <param name="fragment_size" value="150" />
    118. 

  118.       <param name="effective_genome_fraction" value="0.74" />
    119. 

  119.       <param name="gap_size" value="600" />
    120. 

  120.       <param name="error_cut_off" value="0.01" />
    121. 

  121.       <output name="redundancy_removed_test_bed_output_file" file="peakcalling_sicer/test_2/test-1-removed.bed" />
    122. 

  122.       <output name="redundancy_removed_control_bed_output_file" file="peakcalling_sicer/test_2/control-1-removed.bed" />
    123. 

  123.       <output name="summary_graph_output_file" file="peakcalling_sicer/test_3/test-W200.graph" />
    124. 

  124.       <output name="test_normalized_wig_output_file" file="peakcalling_sicer/test_2/test-W200-normalized.wig" />
    125. 

  125.       <output name="significant_islands_output_file" file="peakcalling_sicer/test_3/test-W200-G600-FDR0.01-island.bed" />
    126. 

  126.       <output name="island_filtered_output_file" file="peakcalling_sicer/test_2/test-W200-G600-FDR0.01-islandfiltered.bed" />
    127. 

  127.       <output name="island_filtered_normalized_wig_output_file" file="peakcalling_sicer/test_2/test-W200-G600-FDR0.01-islandfiltered-normalized.wig" />
    128. 

  128.       <output name="score_island_output_file" file="peakcalling_sicer/test_3/test-W200-G600.scoreisland" />
    129. 

  129.       <output name="islands_summary_output_file" file="peakcalling_sicer/test_3/test-W200-G600-islands-summary" />
    130. 

  130.       <output name="significant_islands_summary_output_file" file="peakcalling_sicer/test_3/test-W200-G600-islands-summary-FDR0.01" />
    131. 

  131.       <output name="output_log_file" file="peakcalling_sicer/test_2/output_log_file.contains" compare="contains"/>
    132. 

  132.     </test>
    133. 

  133.     <test>
    134. 

  134.       <param name="input_bed_file" value="chipseq_enriched.bed.gz" ftype="bed" dbkey="mm8" />
    135. 

  135.       <param name="input_control_file" />
    136. 

  136.       <param name="fix_off_by_one_errors" value="True" />
    137. 

  137.       <param name="redundancy_threshold" value="1" />
    138. 

  138.       <param name="window_size" value="200" />
    139. 

  139.       <param name="fragment_size" value="150" />
    140. 

  140.       <param name="effective_genome_fraction" value="0.74" />
    141. 

  141.       <param name="gap_size" value="600" />
    142. 

  142.       <param name="error_cut_off" value="0.01" />
    143. 

  143.       <output name="redundancy_removed_test_bed_output_file" file="peakcalling_sicer/test_1/test-1-removed.bed" />
    144. 

  144.       <output name="summary_graph_output_file" file="peakcalling_sicer/test_4/test-W200.graph" />
    145. 

  145.       <output name="test_normalized_wig_output_file" file="peakcalling_sicer/test_1/test-W200-normalized.wig" />
    146. 

  146.       <output name="island_filtered_output_file" file="peakcalling_sicer/test_1/test-W200-G600-E0.01-islandfiltered.bed" />
    147. 

  147.       <output name="island_filtered_normalized_wig_output_file" file="peakcalling_sicer/test_1/test-W200-G600-E0.01-islandfiltered-normalized.wig" />
    148. 

  148.       <output name="score_island_output_file" file="peakcalling_sicer/test_4/test-W200-G600-E0.01.scoreisland" />
    149. 

  149.       <output name="output_log_file" file="peakcalling_sicer/test_1/output_log_file.contains" compare="contains"/>
    150. 

  150.     </test>
    151. 

  151.   </tests>
    152. 

  152.   <help>
    153. 

  153. **What it does**
    154. 

  154. 

  155. SICER first and foremost is a filtering tool. Its main functions are::
    156. 

  156.   
    157. 

  157.   1. Delineation of the significantly ChIP-enriched regions, which can be used to associate with other genomic landmarks. 
    158. 

  158.   2. Identification of reads on the ChIP-enriched regions, which can be used for profiling and other quantitative analysis.
    159. 

  159. 

  160. View the original SICER documentation: http://home.gwu.edu/~wpeng/Software.htm.
    161. 

  161. 

  162. ------
    163. 

  163. 

  164. .. class:: warningmark
    165. 

  165. 

  166.   By default, SICER creates files that do not conform to standards (e.g. BED files are closed, not half-open). This could have implications for downstream analysis.
    167. 

  167.   To force the output of SICER to be formatted properly to standard file formats, check the **"Fix off-by-one errors in output files"** option.
    168. 

  168. 

  169. ------
    170. 

  170. 

  171. **Citation**
    172. 

  172. 

  173. For the underlying tool, please cite `Zang C, Schones DE, Zeng C, Cui K, Zhao K, Peng W. A clustering approach for identification of enriched domains from histone modification ChIP-Seq data. Bioinformatics. 2009 Aug 1;25(15):1952-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/19505939&gt;`_
    174. 

  174. 

  175. If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
    176. 

  176. 

  177.   </help>
    178. 

  178. </tool>
    179.