New Tool addition: Haltools

tools/haltools/.shed.yml

@@ -0,0 +1,17 @@
+name: haltools
+owner: iuc
+description: A set of tools to for manipulating HAL alignment files
+long_description: |
+  HAL is a graph based, phylogenetically structured format for multiple genome alignments. Unlike block based formats such as MAF, it stores genomes in a hierarchy, which allows efficient handling of rearrangements, indels, ancestral states, and flexible queries across any genome or subclade.
+homepage_url: https://github.com/ComparativeGenomicsToolkit/hal
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/main/tools/haltools
+categories: 
+- Sequence Analysis
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "Wrapper for haltool suite: {{ tool_name }}"
+suite:
+  name: "suite_haltools"
+  description: "A set of tools to for manipulating HAL alignment files"
+  long_description: |
+    HAL is a graph based, phylogenetically structured format for multiple genome alignments. Unlike block based formats such as MAF, it stores genomes in a hierarchy, which allows efficient handling of rearrangements, indels, ancestral states, and flexible queries across any genome or subclade.

tools/haltools/macros.xml

@@ -0,0 +1,46 @@
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">cactus</requirement>
+        </requirements>
+    </xml>
+    <token name="@TOOL_VERSION@">2.9.9</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@PROFILE@">25.0</token>
+    <xml name="input_hal">
+        <param name="input_hal" type="data" format="hal" label="Input hal file to analyze" optional="false"/>
+    </xml>
+    <xml name="params_inputFormat">
+        <param name="inputFormat" type="select" label="Back-end storage format" help="Choose the back-end storage format of the input hal file">
+            <option value="hdf5" selected="true">HDF5</option>
+            <option value="mmap">mmap</option>
+        </param>
+    </xml>
+    <xml name="sanitizer_default">
+        <sanitizer invalid_char="">                
+            <valid initial="string.ascii_letters,string.digits,string.punctuation">
+                <add value=" " />
+            </valid>
+        </sanitizer>
+    </xml>
+    <xml name="validator_trim">
+        <validator type="regex" message="Enter without leading or trailing spaces">^\S(?:.*\S)?$</validator>   
+    </xml>
+    <xml name="creator">
+        <creator>
+            <person givenName="Niklas" familyName="Mayle" url="https://github.com/Maed0x"/>
+            <organization name="Galaxy Europe" url="https://galaxyproject.org/eu/"/>
+        </creator>
+    </xml>
+    <xml name="citation">
+        <citations>
+            <citation type="doi">10.1093/bioinformatics/btt128</citation>
+            <citation type="bibtex">
+                @misc{githubhal,
+                title = {HAL GitHub page},
+                url = {https://github.com/ComparativeGenomicsToolkit/hal},
+                }
+            </citation>
+        </citations>
+    </xml>
+</macros>

tools/haltools/test-data/halStats_allCoverage_output.csv

@@ -0,0 +1,10 @@
+FromGenome, ToGenome, sitesCovered1Times, sitesCovered2Times, sitesCovered3Times, sitesCovered4Times, sitesCovered5Times
+Genome_1, Genome_1, 5472, 4688, 3516, 2637, 1465
+Genome_2, Genome_1, 4688, 2637, 2637, 1172, 0
+Genome_3, Genome_1, 4688, 4688, 3516, 2960, 880
+Genome_1, Genome_2, 3516, 3516, 2344, 1465, 293
+Genome_2, Genome_2, 4270, 2930, 2930, 1172, 0
+Genome_3, Genome_2, 3516, 3516, 2344, 1788, 176
+Genome_1, Genome_3, 4725, 4725, 3553, 2381, 1348
+Genome_2, Genome_3, 4725, 2791, 2791, 1033, 0
+Genome_3, Genome_3, 6139, 4725, 3553, 3136, 880

tools/haltools/test-data/halStats_baseComp_output.tsv

@@ -0,0 +1,2 @@
+fraction_of_As	fraction_of_Gs	fraction_of_Cs	fraction_of_Ts
+0.5	0	0.5	0

tools/haltools/test-data/halStats_bedSequences_output.bed

@@ -0,0 +1 @@
+Genome_0_seq	0	1758

tools/haltools/test-data/halStats_bottomSegments_output.bed

@@ -0,0 +1,8 @@
+Genome_0_seq	0	293
+Genome_0_seq	293	586
+Genome_0_seq	586	879
+Genome_0_seq	879	1033
+Genome_0_seq	1033	1172
+Genome_0_seq	1172	1348
+Genome_0_seq	1348	1465
+Genome_0_seq	1465	1758

tools/haltools/test-data/halStats_chromSizes_output.tsv

@@ -0,0 +1 @@
+Genome_1_seq	5472

tools/haltools/test-data/halStats_output.txt

@@ -0,0 +1,10 @@
+
+hal v2.2
+(Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;
+
+GenomeName, NumChildren, Length, NumSequences, NumTopSegments, NumBottomSegments
+Genome_0, 3, 1758, 1, 0, 8
+Genome_1, 0, 5472, 1, 28, 0
+Genome_2, 0, 4270, 1, 20, 0
+Genome_3, 0, 6139, 1, 28, 0
+

tools/haltools/test-data/halStats_percentID_output.csv

@@ -0,0 +1,5 @@
+Genome, % ID, numID, numSites
+Genome_0, 1, 1758, 1758
+Genome_1, nan, 0, 0
+Genome_2, 1, 586, 586
+Genome_3, nan, 0, 0

tools/haltools/test-data/halStats_sequenceStats_output.csv

@@ -0,0 +1,3 @@
+SequenceName, Length, NumTopSegments, NumBottomSegments
+Genome_0_seq, 1758, 0, 8
+

tools/haltools/test-data/halStats_topSegments_output.bed

@@ -0,0 +1,28 @@
+Genome_1_seq	0	293
+Genome_1_seq	293	586
+Genome_1_seq	586	879
+Genome_1_seq	879	1033
+Genome_1_seq	1033	1172
+Genome_1_seq	1172	1348
+Genome_1_seq	1348	1465
+Genome_1_seq	1465	1758
+Genome_1_seq	1758	2051
+Genome_1_seq	2051	2227
+Genome_1_seq	2227	2344
+Genome_1_seq	2344	2498
+Genome_1_seq	2498	2637
+Genome_1_seq	2637	2930
+Genome_1_seq	2930	3223
+Genome_1_seq	3223	3399
+Genome_1_seq	3399	3516
+Genome_1_seq	3516	3809
+Genome_1_seq	3809	4102
+Genome_1_seq	4102	4256
+Genome_1_seq	4256	4395
+Genome_1_seq	4395	4571
+Genome_1_seq	4571	4688
+Genome_1_seq	4688	4864
+Genome_1_seq	4864	4981
+Genome_1_seq	4981	5135
+Genome_1_seq	5135	5274
+Genome_1_seq	5274	5472