Mercurial > repos > greg > cwpair2
changeset 10:b52d6705aed0 draft
Uploaded
| author | greg |
|---|---|
| date | Wed, 02 Dec 2015 16:14:07 -0500 |
| parents | 6469dda597d6 |
| children | 6383cae47688 |
| files | cwpair2.xml |
| diffstat | 1 files changed, 59 insertions(+), 146 deletions(-) [+] |
line wrap: on
line diff
--- a/cwpair2.xml Wed Dec 02 16:13:59 2015 -0500 +++ b/cwpair2.xml Wed Dec 02 16:14:07 2015 -0500 @@ -11,9 +11,9 @@ #for $i in $input: --input "${i}" "${i.hid}" #end for - --method $method --up_distance $up_distance --down_distance $down_distance + --method $method --binsize $binsize --threshold_format $threshold_format_cond.threshold_format #if str($threshold_format_cond.threshold_format) == "absolute_threshold": @@ -22,20 +22,19 @@ --relative_threshold $threshold_format_cond.relative_threshold #end if --output_files $output_files - --sort_score $sort_score --statistics_output "$statistics_output" ]]> </command> <inputs> <param name="input" type="data" format="gff" multiple="True" label="Find matched pairs on" /> + <param name="up_distance" type="integer" value="50" min="0" label="Distance upstream from a peak to allow a pair" /> + <param name="down_distance" type="integer" value="100" min="0" label="Distance downstream from a peak to allow a pair" /> <param name="method" type="select" label="Method of finding a match"> <option value="mode" selected="True">Mode</option> <option value="closest">Closest</option> <option value="largest">Largest</option> <option value="all">All</option> </param> - <param name="up_distance" type="integer" value="50" min="0" label="Distance upstream from a peak to allow a pair" /> - <param name="down_distance" type="integer" value="100" min="0" label="Distance downstream from a peak to allow a pair" /> <param name="binsize" type="integer" value="1" min="0" label="Width of bins for frequency plots and mode calculation" help="Value 1 implies no bins" /> <conditional name="threshold_format_cond"> <param name="threshold_format" type="select" label="Filter using"> @@ -50,197 +49,111 @@ </when> </conditional> <param name="output_files" type="select" label="Restrict output to" help="Statistics will always be generated." > - <option value="simple" selected="True">matched pairs only (S)</option> - <option value="simple_orphan">matched pairs and orphans only (O,S)</option> - <option value="simple_orphan_detail">matched pairs, orphans and details only (D,O,S)</option> - <option value="all">no restrictions (output everything: C,D,F,O,P,S)</option> - </param> - <param name="sort_score" type="select" label="Sort output by score?"> - <option value="no" selected="True">No</option> - <option value="asc">Yes, in ascending order</option> - <option value="desc">Yes, in descending order</option> + <option value="all" selected="True">no restrictions (output everything: C,D,F,O,P,MP)</option> + <option value="matched_pair">matched pairs only (MP)</option> + <option value="matched_pair_orphan">matched pairs and orphans only (O,MP)</option> + <option value="matched_pair_orphan_detail">matched pairs, orphans and details only (D,O,MP)</option> </param> </inputs> <outputs> - <collection name="closest_C_pdf" type="list" label="closest C: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "closest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="closest_C" ext="pdf" visible="false" /> - </collection> - <collection name="largest_C_pdf" type="list" label="largest C: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "largest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="largest_C" ext="pdf" visible="false" /> - </collection> - <collection name="mode_C_pdf" type="list" label="mode C: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "mode"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="mode_C" ext="pdf" visible="false" /> - </collection> - <collection name="closest_D" type="list" label="closest D: ${tool.name} on ${on_string}"> - <filter>output_files in ["all", "simple_orphan_detail"] and method in ["all", "closest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="closest_D" ext="tabular" visible="false" /> - </collection> - <collection name="largest_D" type="list" label="largest D: ${tool.name} on ${on_string}"> - <filter>output_files in ["all", "simple_orphan_detail"] and method in ["all", "largest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="largest_D" ext="tabular" visible="false" /> - </collection> - <collection name="mode_D" type="list" label="mode D: ${tool.name} on ${on_string}"> - <filter>output_files in ["all", "simple_orphan_detail"] and method in ["all", "mode"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="mode_D" ext="tabular" visible="false" /> - </collection> - <collection name="closest_F_pdf" type="list" label="closest F: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "closest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="closest_F" ext="pdf" visible="false" /> - </collection> - <collection name="largest_F_pdf" type="list" label="largest F: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "largest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="largest_F" ext="pdf" visible="false" /> - </collection> - <collection name="mode_F_pdf" type="list" label="mode F: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "mode"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="mode_F" ext="pdf" visible="false" /> + <data name="statistics_output" format="tabular" label="Statistics Table: ${tool.name} on ${on_string}" /> + <collection name="H" type="list" label="Statistics Histogram: ${tool.name} on ${on_string}"> + <filter>output_files == "all"</filter> + <discover_datasets pattern="(?P<designation>.*)" directory="H" ext="pdf" visible="false" /> </collection> - <collection name="closest_O" type="list" label="closest O: ${tool.name} on ${on_string}"> - <filter>output_files in ["all", "simple_orphan", "simple_orphan_detail"] and method in ["all", "closest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="closest_O" ext="tabular" visible="false" /> - </collection> - <collection name="largest_O" type="list" label="largest O: ${tool.name} on ${on_string}"> - <filter>output_files in ["all", "simple_orphan", "simple_orphan_detail"] and method in ["all", "largest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="largest_O" ext="tabular" visible="false" /> - </collection> - <collection name="mode_O" type="list" label="mode O: ${tool.name} on ${on_string}"> - <filter>output_files in ["all", "simple_orphan", "simple_orphan_detail"] and method in ["all", "mode"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="mode_O" ext="tabular" visible="false" /> - </collection> - <collection name="closest_P_pdf" type="list" label="closest P: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "closest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="closest_P" ext="pdf" visible="false" /> + <collection name="D" type="list" label="Data D: ${tool.name} on ${on_string}"> + <filter>output_files in ["all", "matched_pair_orphan_detail"]</filter> + <discover_datasets pattern="(?P<designation>.*)" directory="data_D" ext="tabular" visible="false" /> </collection> - <collection name="largest_P_pdf" type="list" label="largest P: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "largest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="largest_P" ext="pdf" visible="false" /> - </collection> - <collection name="mode_P_pdf" type="list" label="mode P: ${tool.name} on ${on_string}"> - <filter>output_files == "all" and method in ["all", "mode"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="mode_P" ext="pdf" visible="false" /> + <collection name="O" type="list" label="Data O: ${tool.name} on ${on_string}"> + <filter>output_files in ["all", "matched_pair_orphan", "matched_pair_orphan_detail"]</filter> + <discover_datasets pattern="(?P<designation>.*)" directory="data_O" ext="tabular" visible="false" /> </collection> - <collection name="closest_S" type="list" label="closest S: ${tool.name} on ${on_string}"> - <filter>method in ["all", "closest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="closest_S" ext="gff" visible="false" /> + <collection name="MP" type="list" label="Data MP: ${tool.name} on ${on_string}"> + <discover_datasets pattern="(?P<designation>.*)" directory="data_MP" ext="gff" visible="false" /> </collection> - <collection name="largest_S" type="list" label="largest S: ${tool.name} on ${on_string}"> - <filter>method in ["all", "largest"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="largest_S" ext="gff" visible="false" /> - </collection> - <collection name="mode_S" type="list" label="mode S: ${tool.name} on ${on_string}"> - <filter>method in ["all", "mode"]</filter> - <discover_datasets pattern="(?P<designation>.*)" directory="mode_S" ext="gff" visible="false" /> - </collection> - <data name="statistics_output" format="tabular" label="Statistics: ${tool.name} on ${on_string}" /> </outputs> <tests> <test> <param name="input" value="cwpair2_input1.gff" /> - <param name="method" value="all" /> <param name="up_distance" value="25" /> <param name="down_distance" value="100" /> + <param name="method" value="all" /> <param name="binsize" value="1" /> <param name="threshold_format" value="relative_threshold" /> <param name="relative_threshold" value="0.0" /> - <param name="output_files" value="simple" /> - <param name="sort_score" value="asc" /> - <output_collection name="closest_S" type="list"> - <element name="closest_S_data_1_f0u25d100b1" file="closest_s_output1.gff" ftype="gff" /> + <param name="output_files" value="matched_pair" /> + <output name="statistics_output" file="statistics1.tabular" ftype="tabular" /> + <output_collection name="MP" type="list"> + <element name="f0u25d100_on_data_1" file="closest_mp_output1.gff" ftype="gff" /> + <element name="f0u25d100_on_data_1" file="largest_mp_output1.gff" ftype="gff" /> + <element name="f0u25d100_on_data_1" file="mode_mp_output1.gff" ftype="gff" /> </output_collection> - <output_collection name="largest_S" type="list"> - <element name="largest_S_data_1_f0u25d100b1" file="largest_s_output1.gff" ftype="gff" /> - </output_collection> - <output_collection name="mode_S" type="list"> - <element name="mode_S_data_1_f0u25d100b1" file="mode_s_output1.gff" ftype="gff" /> - </output_collection> - <output name="statistics_output" file="statistics1.tabular" ftype="tabular" /> </test> <test> <param name="input" value="cwpair2_input1.gff" /> - <param name="method" value="all" /> <param name="up_distance" value="50" /> <param name="down_distance" value="100" /> + <param name="method" value="all" /> <param name="binsize" value="1" /> <param name="threshold_format" value="relative_threshold" /> <param name="relative_threshold" value="0.0" /> <param name="output_files" value="all" /> - <param name="sort_score" value="no" /> - <output_collection name="closest_D" type="list"> - <element name="closest_D_data_1_f0u50d100b1" file="closest_d_output2.tabular" ftype="tabular" /> - </output_collection> - <output_collection name="closest_F" type="list"> - <element name="closest_F_data_1_f0u50d100b1" file="closest_f_output2.pdf" ftype="pdf" compare="sim_size" /> - </output_collection> - <output_collection name="closest_O" type="list"> - <element name="closest_O_data_1_f0u50d100b1" file="closest_o_output2.tabular" ftype="tabular" /> - </output_collection> - <output_collection name="closest_S" type="list"> - <element name="closest_S_data_1_f0u50d100b1" file="closest_s_output2.gff" ftype="gff" /> - </output_collection> - <output_collection name="largest_D" type="list"> - <element name="largest_D_data_1_f0u50d100b1" file="largest_d_output2.tabular" ftype="tabular" /> - </output_collection> - <output_collection name="largest_F" type="list"> - <element name="largest_F_data_1_f0u50d100b1" file="largest_f_output2.pdf" ftype="pdf" compare="sim_size" /> - </output_collection> - <output_collection name="largest_O" type="list"> - <element name="largest_O_data_1_f0u50d100b1" file="largest_o_output2.tabular" ftype="tabular" /> + <output name="statistics_output" file="statistics2.tabular" ftype="tabular" /> + <output_collection name="H" type="list"> + <element name="histogram_C_mode_f0u50d100_on_data_1" file="mode_c_output2.pdf" ftype="pdf" compare="sim_size" /> + <element name="histogram_F_closest_f0u50d100_on_data_1" file="closest_f_output2.pdf" ftype="pdf" compare="sim_size" /> + <element name="histogram_F_largest_f0u50d100_on_data_1" file="largest_f_output2.pdf" ftype="pdf" compare="sim_size" /> + <element name="histogram_F_mode_f0u50d100_on_data_1" file="mode_f_output2.pdf" ftype="pdf" compare="sim_size" /> + <element name="histogram_P_mode_f0u50d100_on_data_1" file="mode_p_output2.pdf" ftype="pdf" compare="sim_size" /> </output_collection> - <output_collection name="largest_S" type="list"> - <element name="largest_S_data_1_f0u50d100b1" file="largest_s_output2.gff" ftype="gff" /> - </output_collection> - <output_collection name="mode_C" type="list"> - <element name="mode_C_data_1_f0u50d100b1" file="mode_c_output2.pdf" ftype="pdf" compare="sim_size" /> - </output_collection> - <output_collection name="mode_D" type="list"> - <element name="mode_D_data_1_f0u50d100b1" file="mode_d_output2.tabular" ftype="tabular" /> + <output_collection name="D" type="list"> + <element name="data_D_closest_f0u50d100_on_data_1" file="closest_d_output2.tabular" ftype="tabular" /> + <element name="data_D_largest_f0u50d100_on_data_1" file="largest_d_output2.tabular" ftype="tabular" /> + <element name="data_D_mode_f0u50d100_on_data_1" file="mode_d_output2.tabular" ftype="tabular" /> </output_collection> - <output_collection name="mode_F" type="list"> - <element name="mode_F_data_1_f0u50d100b1" file="mode_f_output2.pdf" ftype="pdf" compare="sim_size" /> - </output_collection> - <output_collection name="mode_O" type="list"> - <element name="mode_O_data_1_f0u50d100b1" file="mode_o_output2.tabular" ftype="tabular" /> + <output_collection name="O" type="list"> + <element name="data_O_closest_f0u50d100_on_data_1" file="closest_o_output2.tabular" ftype="tabular" /> + <element name="data_O_largest_f0u50d100_on_data_1" file="largest_o_output2.tabular" ftype="tabular" /> + <element name="data_O_mode_f0u50d100_on_data_1" file="mode_o_output2.tabular" ftype="tabular" /> </output_collection> - <output_collection name="mode_P" type="list"> - <element name="mode_P_data_1_f0u50d100b1" file="mode_p_output2.pdf" ftype="pdf" compare="sim_size" /> + <output_collection name="MP" type="list"> + <element name="data_MP_closest_f0u50d100_on_data_1" file="closest_mp_output2.gff" ftype="gff" /> + <element name="data_MP_largest_f0u50d100_on_data_1" file="largest_mp_output2.gff" ftype="gff" /> + <element name="data_MP_mode_f0u50d100_on_data_1" file="mode_mp_output2.gff" ftype="gff" /> </output_collection> - <output_collection name="mode_S" type="list"> - <element name="mode_S_data_1_f0u50d100b1" file="mode_s_output2.gff" ftype="gff" /> - </output_collection> - <output name="statistics_output" file="statistics2.tabular" ftype="tabular" /> </test> </tests> <help> **What it does** -Takes a list of called peaks on both strands and produces a list of matched pairs and a list of unmatched orphans -using a specified method for finding matched pairs. Methods for finding matched pairs are mode, closest, largest -or all (where the analysis is run for each method). A statistics dataset is generated and a collection of datasets +Takes a list of called peaks on both strands and produces lists of matched pairs and unmatched peaks using a +specified method for finding matched pairs. Methods for finding matched pairs are mode, closest, largest or +all (where the analysis is run for each method). A statistics dataset is generated and a collection of datasets is produced for each method as follows. +**Data Files** + +* **closest/largest/mode MP** - the Matched Pairs in gff format +* **closest/largest/mode O** - the Orphans in tabular format +* **closest/largest/mode D** - the Details in tabular format + +**Statistics Files** + * **closest/largest/mode C** - the stastics graph in pdf format -* **closest/largest/mode D** - the details in tabular format +* **closest/largest/mode P** - the preview plots graph in pdf format * **closest/largest/mode F** - the final plots graph in pdf format -* **closest/largest/mode O** - the orphans in tabular format -* **closest/largest/mode P** - the preview plots graph in pdf format -* **closest/largest/mode S** - the matched pairs in gff format ----- **Options** -* **Output files** - Restrict output dataset collections to matched pairs only or one of several combinations of collection types. * **Method of finding match** - Method of finding matched pair, mode, closest, largest, or all (run with each method). * **Distance upstream from a peak to allow a pair** - Distance upstream from a Watson peak to allow a Crick pair. * **Distance downstream from a peak to allow a pair** - Distance downstream from a Watson peak to allow a Crick pair. * **Percentage of the 95 percentile value to filter below** - Percentage of the 95 percentile value below which to filter when using a relative threshold. * **Absolute value to filter below** - Absolute value below which to filter when using an absolute threshold. -* **Sort output by chromosomes in** - Output will be sorted by chromsome in the specified order. -* **Sort output by score?** - If yes, output will be sorted by score in the specified order. -* **Summary output format** - Format for summary output. +* **Output files** - Restrict output dataset collections to matched pairs only or one of several combinations of collection types. </help> <expand macro="citations" />