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

Changeset 0:6847a625db4d (2020-04-30)
Next changeset 1:ad011fc670d6 (2020-05-12)
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ commit e96954b0926211a1da3292c00aada6d366a2b25d"
added:
eventaligncollapse.xml
macros.xml
test-data/sample.tsv
b
diff -r 000000000000 -r 6847a625db4d eventaligncollapse.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/eventaligncollapse.xml Thu Apr 30 05:56:29 2020 -0400
[
b'@@ -0,0 +1,166 @@\n+<?xml version="1.0"?>\n+<tool id="nanopolishcomp_eventaligncollapse" name="Eventalign Collapse" version="@TOOL_VERSION@+@WRAPPER_VERSION@">\n+    <description>by kmers rather than by event</description>\n+    <macros>\n+        <import>macros.xml</import>\n+    </macros>\n+    <expand macro="requirements"/>\n+    <stdio></stdio>\n+    <version_command>NanopolishComp --version</version_command>\n+    <command detect_errors="exit_code"><![CDATA[\n+        ## initialize\n+        ## requires a minimum of 3 threads\n+        threads=\\$((3 > \\${GALAXY_SLOTS:-3} ? 3 : \\${GALAXY_SLOTS:-3})) &&\n+\n+        ## run\n+        NanopolishComp\n+            Eventalign_collapse\n+            -i \'$i\'\n+            -s\n+            -r $r\n+            -f \n+            #for $current in $f\n+                $current \n+            #end for\n+            -o \'results\'\n+            -p \'out\'\n+            -t \\$threads\n+            -v\n+        ]]></command>\n+    <inputs>\n+        <param argument="-i" type="data" format="tabular" label="Select nanopolish eventalign file"/>\n+        <param argument="-s" type="boolean" truevalue="-s" falsevalue="" label="Should raw samples be written?" help="You need to run nanopolish eventalign with --sample option to make use of this feature."/>\n+        <param argument="-r" type="integer" value="0" min="0" label="Set maximum number of reads to parse" help="Use 0 to deactivate this option."/>\n+        <param argument="-f" type="select" multiple="true" label="Select statistical fields to compute" help="You need to run nanopolish eventalign with --sample option to make use of this feature.">\n+            <option value="mean" selected="true">Mean</option>\n+            <option value="std">Std</option>\n+            <option value="median" selected="true">Median</option>\n+            <option value="mad">Mad</option>\n+            <option value="num_signals" selected="true">Number of signals</option>\n+        </param>\n+        <param name="out" type="select" multiple="true" label="Select output file(s)" help="">\n+            <option value="eventalign_collapse" selected="true">Eventalign Collapse</option>\n+            <option value="index" selected="true">Index</option>\n+            <option value="log">Log</option>\n+        </param>\n+    </inputs>\n+    <outputs>\n+        <data name="out_eventalign_collapse" format="tabular" from_work_dir="results/out_eventalign_collapse.tsv" label="${tool.name} on ${on_string}: Eventalign Collapse">\n+            <filter>\'eventalign_collapse\' in out</filter>\n+        </data>\n+        <data name="out_index" format="tabular" from_work_dir="results/out_eventalign_collapse.tsv.idx" label="${tool.name} on ${on_string}: Index">\n+            <filter>\'index\' in out</filter>\n+        </data>\n+        <data name="out_log" format="txt" from_work_dir="results/out_eventalign_collapse.log" label="${tool.name} on ${on_string}: log">\n+            <filter>\'log\' in out</filter>\n+        </data>\n+    </outputs>\n+    <tests>\n+        <!-- #1 default -->\n+        <test expect_num_outputs="3">\n+            <param name="i" value="sample.tsv"/>\n+            <param name="out" value="eventalign_collapse,index,log"/>\n+            <output name="out_eventalign_collapse">\n+                <assert_contents>\n+                    <has_n_lines n="236"/>\n+                    <has_text_matching expression="ref_pos&#009;ref_kmer"/>\n+                    <has_text_matching expression="22102&#009;GGAAA"/>\n+                </assert_contents>\n+            </output>\n+            <output name="out_index">\n+                <assert_contents>\n+                    <has_n_lines n="60"/>\n+                    <has_text_matching expression="ref_id&#009;ref_start"/>\n+                    <has_text_matching expression="chr&#009;22102"/>\n+                </assert_contents>\n+            </output>\n+            <output name="out_log">\n+                <assert_contents>\n+                    <has_n_lines n="13"/>\n+                    <has_line line="General '..b'assert_contents>\n+            </output>\n+            <output name="out_index">\n+                <assert_contents>\n+                    <has_n_lines n="60"/>\n+                    <has_text_matching expression="ref_id&#009;ref_start"/>\n+                    <has_text_matching expression="chr&#009;22102"/>\n+                </assert_contents>\n+            </output>\n+        </test>\n+    </tests>\n+    <help><![CDATA[\n+.. class:: infomark\n+\n+**What it does**\n+\n+@WID@\n+\n+Eventalign_collapse collapses the raw file generated by nanopolish eventalign by kmers rather than by event.\n+\n+**Input**\n+\n+A nanopolish eventalign tabular output file. \n+\n+**Output**\n+\n+Contrary to nanopolish eventalign output text file, in Eventalign_collapse the reads are separated by a hashtag headers containing the read_id and ref_id. This reduces the redundancy and makes it easier to find the start and end of a read.\n+\n+::\n+\n+    Example : #7ef1d7b9-5824-4382-b23b-78d82c07ebbd YHR055C.\n+\n+The main data file contains the following fields:\n+\n+- ref_pos: Reference sequence ID (contig).\n+- ref_kmer: Sequence of the reference kmers.\n+- -num_events: Number of events for this kmer before collapsing.\n+- dwell_time: dwell time for this kmer in seconds\n+- NNNNN_dwell_time: dwell time of events for this kmers with a model sequence "NNNNN" (events ignored by nanopolish HMM).\n+- mismatch_dwell_time: dwell time of events for this kmers with a model sequence different from the reference kmer\n+- start_idx: Only if nanopolish eventalign called with --signal_idx. Start coordinate on original raw signal in fast5 file\n+- end_idx: Only if nanopolish eventalign called with --signal_idx. End coordinate on original raw signal in fast5 file\n+- mean: Only if nanopolish eventalign called with --samples. Mean of the normalised signal values provided by Nanopolish eventalign\n+- median: Only if nanopolish eventalign called with --samples. Median of the normalised signal values provided by Nanopolish eventalign\n+- std: Only if nanopolish eventalign called with --samples. Standard deviation of the normalised signal values provided by Nanopolish eventalign\n+- mad: Only if nanopolish eventalign called with --samples. Median absolute deviation of the normalised signal values provided by Nanopolish eventalign\n+- num_signals: Only if nanopolish eventalign called with --samples. Number of raw signal points.\n+- samples: Only if nanopolish eventalign called with --samples and Eventalign_collapse called with --write_samples. List of normalised signal intensity values for this kmer\n+\n+In addition Eventalign_collapse also generates an useful index file containing reads level information. It contains the following fields:\n+\n+- read_id: Name or index of the read\n+- ref_id: Name of the reference sequence the read was aligned on (contig)\n+- ref_start: Start coordinate of the alignment on the reference sequence\n+- ref_end: End coordinate of the alignment on the reference sequence\n+- dwell_time: Cumulative dwell time in seconds for the entire resquiggled sequence\n+- kmers: Overall number of resquiggled kmers\n+- NNNNN_kmers: Number of resquiggled kmers containing at least 1 event for which the model sequence was "NNNNN"\n+- mismatching_kmers: Number of resquiggled kmers containing at least 1 event for which the model sequence diverged from the reference sequence\n+- missing_kmers: Number of skipped/missing reference positions in nanopolish output\n+- byte_offset: Number of characters before the start of the sequence in the main output file. This can be used in conjunction with file.seek() to directly access the start of a read. An example is provided in the Usage notebook.\n+- byte_len: Length of characters after byte_offset to the end of the read, excluding the last newline. This can be used in conjunction with read() to read all the text chunk corresponding to the read.\n+\n+.. class:: infomark\n+\n+**References**\n+\n+@REFERENCES@\n+    ]]></help>\n+    <expand macro="citations"/>\n+</tool>\n\\ No newline at end of file\n'
b
diff -r 000000000000 -r 6847a625db4d macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Thu Apr 30 05:56:29 2020 -0400
[
@@ -0,0 +1,28 @@
+<?xml version="1.0"?>
+<macros>
+    <token name="@TOOL_VERSION@">0.6.11</token>
+    <token name="@WRAPPER_VERSION@">galaxy0</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">nanopolishcomp</requirement>
+        </requirements>
+    </xml>
+ <xml name="citations">
+        <citations>
+            <citation type="doi">111</citation> <!-- todo -->
+            <citation type="bibtex">@online{NanopolishComp,
+              author = {Adrien Leger },
+              title = {NanopolishComp},
+              year = 2019,
+              url = {https://a-slide.github.io/NanopolishComp/},
+              urldate = {2020-04-29}
+            }</citation>
+        </citations>
+    </xml>
+    <token name="@WID@"><![CDATA[
+NanopolishComp is a companion package for downstream analyses of Nanopolish output files.
+    ]]></token>
+    <token name="@REFERENCES@"><![CDATA[
+More information are available on the `project website <https://a-slide.github.io/NanopolishComp/>`_ and `github <https://github.com/a-slide/NanopolishComp>`_.
+    ]]></token>
+</macros>
\ No newline at end of file
b
diff -r 000000000000 -r 6847a625db4d test-data/sample.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/sample.tsv Thu Apr 30 05:56:29 2020 -0400
b
b'@@ -0,0 +1,271 @@\n+contig\tposition\treference_kmer\tread_name\tstrand\tevent_index\tevent_level_mean\tevent_stdv\tevent_length\tmodel_kmer\tmodel_mean\tmodel_stdv\tstandardized_level\tsamples\n+chr\t22101\tAGGAA\tf30a0489-ec1e-4f6e-829e-fa6d16dbee2e\tt\t8291\t124.19\t3.490\t0.00664\tAGGAA\t117.46\t3.17\t1.88\t122.692,122.834,120.843,120.558,119.705,122.834,129.235,120.132,126.248,122.977,123.83,127.813,124.541,122.55,122.265,129.947,119.42,133.076,127.528,124.684\n+chr\t22102\tGGAAA\tf30a0489-ec1e-4f6e-829e-fa6d16dbee2e\tt\t8292\t130.37\t3.206\t0.00365\tGGAAA\t121.47\t5.56\t1.42\t131.369,132.08,134.641,127.955,125.822,133.076,132.08,124.257,126.96,132.08,133.787\n+chr\t22102\tGGAAA\tf30a0489-ec1e-4f6e-829e-fa6d16dbee2e\tt\t8293\t121.86\t9.392\t0.00199\tGGAAA\t121.47\t5.56\t0.06\t124.684,132.223,130.8,107.33,126.391,109.748\n+chr\t22101\tAGGAA\te924b30f-22dc-4156-8e5c-ba664abbe7a7\tt\t2723\t118.83\t5.213\t0.00730\tAGGAA\t117.46\t3.17\t0.37\t108.391,113.503,114.639,119.893,121.881,106.687,119.325,116.627,128.555,120.035,120.177,114.781,127.561,122.733,115.349,118.899,118.189,119.609,126.141,116.059,119.609,125.715\n+chr\t22102\tGGAAA\te924b30f-22dc-4156-8e5c-ba664abbe7a7\tt\t2724\t122.61\t5.634\t0.00863\tGGAAA\t121.47\t5.56\t0.17\t122.165,117.337,122.449,111.657,118.331,112.935,119.609,122.307,121.313,142.329,123.869,121.313,120.603,121.455,120.461,134.377,118.473,123.869,122.591,121.739,120.035,124.153,124.863,126.141,127.277,126.141\n+chr\t22102\tGGAAA\te924b30f-22dc-4156-8e5c-ba664abbe7a7\tt\t2725\t124.78\t6.096\t0.01627\tGGAAA\t121.47\t5.56\t0.50\t121.171,121.029,114.781,130.259,129.265,116.485,126.283,110.095,130.827,132.815,128.839,115.065,127.703,131.963,133.667,105.835,132.247,121.881,120.461,126.283,131.395,121.029,110.095,124.721,133.809,131.537,127.987,125.715,120.035,130.685,124.579,123.869,127.419,130.827,131.111,124.721,130.543,120.887,124.863,128.555,126.425,120.461,128.129,127.703,121.455,120.603,125.005,122.165,120.887\n+chr\t22101\tAGGAA\td4988330-6f34-498a-b1e3-6574d8b3dae2\tt\t9924\t115.24\t5.197\t0.01228\tAGGAA\t117.46\t3.17\t-0.59\t104.751,123.941,105.044,118.961,113.248,109.293,114.42,120.865,117.935,108.707,115.005,119.84,118.521,107.974,112.515,109.732,108.853,122.183,106.949,117.349,114.566,108.56,117.789,115.445,119.4,123.209,119.547,114.859,110.318,113.541,123.209,122.037,122.916,108.853,113.834,121.597,118.228\n+chr\t22101\tAGGAA\td4988330-6f34-498a-b1e3-6574d8b3dae2\tt\t9925\t122.43\t2.734\t0.00797\tAGGAA\t117.46\t3.17\t1.32\t119.547,125.406,119.693,121.451,126.871,121.304,124.527,123.502,125.553,117.642,122.916,124.967,124.527,118.228,120.718,120.718,120.865,127.017,127.017,126.138,118.375,120.426,121.011,119.986\n+chr\t22102\tGGAAA\td4988330-6f34-498a-b1e3-6574d8b3dae2\tt\t9926\t125.96\t8.542\t0.00531\tGGAAA\t121.47\t5.56\t0.68\t118.082,116.031,119.693,130.387,119.547,135.66,136.393,111.636,107.242,123.648,133.463,131.705,134.488,134.928,134.342,128.189\n+chr\t22101\tAGGAA\t43000cf1-c697-4e0b-8414-5aed3db85976\tt\t3971\t115.45\t5.142\t0.00863\tAGGAA\t117.46\t3.17\t-0.58\t112.784,113.078,117.2,113.52,118.82,112.342,123.826,104.097,120.439,113.078,122.353,104.981,115.139,115.286,116.611,112.195,106.011,114.109,113.814,117.348,125.592,115.875,112.784,115.728,117.053,127.653\n+chr\t22102\tGGAAA\t43000cf1-c697-4e0b-8414-5aed3db85976\tt\t3972\t129.34\t5.262\t0.00232\tGGAAA\t121.47\t5.56\t1.30\t124.856,124.12,125.151,130.892,141.787,128.095,130.451\n+chr\t22102\tGGAAA\t43000cf1-c697-4e0b-8414-5aed3db85976\tt\t3973\t122.81\t3.290\t0.01527\tGGAAA\t121.47\t5.56\t0.22\t117.642,131.923,125.739,119.998,117.495,116.906,118.084,118.673,122.353,124.709,123.826,119.114,123.678,124.856,119.114,123.973,120.439,121.323,116.464,128.39,117.936,118.673,122.942,123.531,127.065,125.298,118.673,124.414,125.592,125.887,126.917,124.414,121.617,119.703,130.009,124.709,125.592,125.003,121.47,120.881,126.034,124.709,120.881,123.531,124.856,124.414\n+chr\t22102\tGGAAA\t43000cf1-c697-4e0b-8414-5aed3db85976\tt\t3974\t133.48\t2.700\t0.00232\tGGAAA\t121.47\t5.56\t1.98\t136.045,133.542,130.156,136.487,135.604,134.279,128.242\n+chr\t22102\tGGAAA\t43000cf1-c697-4e0b-8414-5aed3db85976\tt\t3975\t117.60\t8.898\t0.00730\tGGAAA\t121.47\t5.56'..b'8.144,121.167,111.26,105.679,103.586,112.097,117.26,125.632,116.004,116.423,124.655,113.213,123.26,116.283,116.144,116.283,114.609,116.562,118.376,127.865,115.027,122.283,100.655,121.027,116.702,117.26,111.539,100.516,107.911,110.702,116.423,109.446,102.888,105.539,107.353,110.981,113.911,105.26,110.702,116.283,110.702,110.144,105.26,113.493,113.632,111.818,115.307,113.213,108.748,110.283,123.4,110.981,112.237,121.307,121.725,113.911,113.911,113.632,105.539,115.586,113.632,104.981,113.353,122.562,120.469,119.493,108.33,113.074,118.097,110.004,110.702,106.655,111.818,122.702,106.097,110.841,109.586,116.283,114.748,106.237,108.19,104.144,106.237\n+chr\t22102\tGGAAA\t6057e4db-745d-407d-98bb-83a8e9a5f0ce\tt\t62\t122.77\t4.401\t0.01726\tGGAAA\t121.47\t5.56\t0.22\t116.562,119.772,117.4,114.609,118.237,121.865,123.26,118.655,124.934,116.702,119.353,127.865,124.795,122.562,121.307,127.027,118.655,124.655,141.121,127.307,120.469,120.609,124.655,121.167,133.446,122.702,121.865,124.934,119.353,126.19,125.493,128.144,125.772,122.841,123.539,118.934,121.586,122.841,123.4,127.446,123.958,123.539,123.26,122.841,117.818,115.027,124.237,124.934,122.004,122.562,116.283,125.632\n+chr\t22102\tGGAAA\t6057e4db-745d-407d-98bb-83a8e9a5f0ce\tt\t63\t123.47\t5.883\t0.02424\tGGAAA\t121.47\t5.56\t0.34\t133.446,128.841,129.121,129.4,131.214,133.307,135.539,133.446,132.33,112.376,129.818,128.841,105.958,133.028,129.958,125.911,118.516,131.214,117.818,126.19,129.121,129.26,115.167,122.981,124.376,118.934,119.353,123.539,118.516,120.748,129.679,124.237,122.841,114.469,115.307,121.586,121.027,131.632,126.19,125.353,114.609,120.888,125.353,134.702,123.12,117.539,119.214,118.655,120.19,124.655,121.446,123.12,128.144,118.516,123.12,116.144,120.888,119.911,120.609,123.12,124.516,114.051,120.19,121.167,115.307,120.33,124.516,125.353,121.586,128.004,115.586,122.144,126.19\n+chr\t22102\tGGAAA\t6057e4db-745d-407d-98bb-83a8e9a5f0ce\tt\t64\t119.90\t8.320\t0.00332\tGGAAA\t121.47\t5.56\t-0.27\t122.981,119.632,105.958,116.144,127.027,128.562,117.818,131.632,105.12,124.097\n+chr\t22102\tGGAAA\t6057e4db-745d-407d-98bb-83a8e9a5f0ce\tt\t65\t108.37\t1.812\t0.01029\tGGAAA\t121.47\t5.56\t-2.25\t104.702,109.167,110.841,109.027,110.004,110.562,109.586,105.818,107.911,109.027,106.655,106.516,109.725,108.748,112.237,106.934,110.562,108.33,111.26,109.167,106.655,106.795,110.144,108.748,105.818,109.865,108.051,107.074,107.213,106.097,106.237\n+chr\t22102\tGGAAA\t6057e4db-745d-407d-98bb-83a8e9a5f0ce\tt\t66\t120.71\t6.942\t0.00232\tGGAAA\t121.47\t5.56\t-0.13\t106.655,121.725,128.144,115.586,119.632,127.307,125.911\n+chr\t22101\tAGGAA\t6b779e7d-26fb-4863-9082-04068823a29d\tt\t11\t125.01\t4.330\t0.00863\tAGGAA\t117.46\t3.17\t1.96\t118.947,115.47,134.526,132.44,123.398,123.815,125.067,121.868,124.65,124.372,125.624,126.737,121.59,126.876,131.466,119.921,121.173,129.797,127.71,122.285,127.015,129.936,124.928,118.252,127.154,125.346\n+chr\t22102\tGGAAA\t6b779e7d-26fb-4863-9082-04068823a29d\tt\t12\t133.43\t2.914\t0.00232\tGGAAA\t121.47\t5.56\t1.77\t132.718,132.579,126.876,135.778,135.639,134.665,135.778\n+chr\t22101\tAGGAA\t484f63e8-a501-4edd-8c0e-fba261ed96e1\tt\t32\t118.35\t4.651\t0.00764\tAGGAA\t117.46\t3.17\t0.25\t115.392,107.698,115.064,123.74,123.249,106.88,115.555,113.264,122.103,120.957,121.776,108.844,122.267,118.502,116.538,120.302,115.392,114.41,126.686,127.505,121.939,122.267,121.776\n+chr\t22102\tGGAAA\t484f63e8-a501-4edd-8c0e-fba261ed96e1\tt\t33\t126.47\t5.067\t0.00697\tGGAAA\t121.47\t5.56\t0.80\t127.505,122.267,128.65,142.891,136.671,128.323,126.359,121.776,123.576,123.085,125.049,128.814,129.305,113.919,126.195,134.543,126.85,125.213,118.502,124.886,121.448\n+chr\t22102\tGGAAA\t484f63e8-a501-4edd-8c0e-fba261ed96e1\tt\t34\t127.41\t5.048\t0.00398\tGGAAA\t121.47\t5.56\t0.95\t135.689,124.886,135.853,133.888,135.525,117.52,123.249,121.121,123.249,127.341,126.686,123.903\n+chr\t22102\tGGAAA\t55fb9fbe-c25a-486b-9fed-b50328c70e5a\tt\t31\t127.10\t7.175\t0.00631\tGGAAA\t121.47\t5.56\t0.89\t127.165,133.781,119.847,105.491,129.277,125.477,131.247,117.736,131.81,133.781,137.299,118.721,131.388,136.173,127.447,126.884,128.01,129.699,123.647\n'