Chemical toolbox updates (#1476)

* Updated ob_convert to allow appending properties to the title * lint fixes * bump ob depiction version * fixed linter * fixed linter by updating documentation * removed accidentally added files * fixed obconvert tests * fixed simsearch test * fixed test results as knn is now passed correctly * first round linting updates * fixing merger and fragmenter tools * fixed linting merger * added citations to pgchem tools * added citations * fixed linting * fixed linting and introduced macro file * fixed fragmenter tests * fixed doclink * started repairing fragmented * copied needed functions and removed import. * lint * added .shed.yml file * xchem shedfile * fixed long description * removed tests for merger * fixed repo name * fixed openbabel version * update to openbabel 3 * renamed repository * Apply suggestions from code review * Update fragmenter.xml * Rename .shed.yml to __not_deployed_.shed.yml * Rename .shed.yml to _not_deployed_.shed.yml --------- Co-authored-by: Björn Grüning <[email protected]>
bgruening · Sep 22, 2024 · fa68c4b · fa68c4b
1 parent d4f36c4
commit fa68c4b
Show file tree

Hide file tree

Showing 21 changed files with 260 additions and 271 deletions.
diff --git a/chemicaltoolbox/README.rst b/chemicaltoolbox/README.rst
@@ -476,17 +476,17 @@ We highly recommend to use PostgreSQL for any kind of production system.
 .. _molecular frameworks and the reduced molecular frameworks: http://peter-ertl.com/reprints/Schuffenhauer-JCIM-47-47-2007.pdf
 .. _scaffold topologies: http://www.ncbi.nlm.nih.gov/pubmed/18605680
 .. _gaussian volumes as descriptor for molecular shape: http://pubs.acs.org/doi/abs/10.1021/j100011a016
-.. _obgrep: http://openbabel.org/wiki/Obgrep
-.. _FastSearch: http://openbabel.org/wiki/FastSearch
+.. _obgrep: https://open-babel.readthedocs.io/en/latest/Command-line_tools/babel.html#filtering-molecules-from-a-multimolecule-file
+.. _FastSearch: https://open-babel.readthedocs.io/en/latest/Command-line_tools/babel.html#substructure-and-similarity-searching
 .. _Silicos: http://www.silicos.be/technologies/spectrophore
 .. _chemfp: http://chemfp.com/
 .. _Open Babel command prompt converters: http://openbabel.org/docs/2.3.0/FileFormats/Overview.html
-.. _Open Babel: http://openbabel.org/wiki/Main_Page
+.. _Open Babel: https://open-babel.readthedocs.io/en/latest/index.html
 .. _OpenEye: http://www.eyesopen.com/
 .. _RDKit: http://www.rdkit.org/
 .. _Taylor-Butina clustering: http://www.redbrick.dcu.ie/~noel/R_clustering.html
-.. _PNG: http://openbabel.org/docs/dev/FileFormats/PNG_2D_depiction.html
-.. _SVG: http://openbabel.org/docs/dev/FileFormats/SVG_2D_depiction.html
+.. _PNG: https://open-babel.readthedocs.io/en/latest/FileFormats/PNG_2D_depiction.html
+.. _SVG: https://open-babel.readthedocs.io/en/latest/FileFormats/SVG_2D_depiction.html
 .. _OSRA: http://cactus.nci.nih.gov/osra/
 .. _Confab: https://code.google.com/p/confab/
 .. _numpy: http://www.numpy.org/

diff --git a/chemicaltoolbox/chemfp/mol2fps.xml b/chemicaltoolbox/chemfp/mol2fps.xml
@@ -1,13 +1,13 @@
-<tool id="ctb_chemfp_mol2fps" name="Molecule to fingerprint" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
+<tool id="ctb_chemfp_mol2fps" name="Molecule to fingerprint" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
     <description>conversion to several different fingerprint formats</description>
     <!--parallelism method="multi" split_inputs="infile" split_mode="to_size" split_size="10000" merge_outputs="outfile"></parallelism-->
-    <requirements>
-        <requirement type="package" version="@TOOL_VERSION@">chemfp</requirement>
-    </requirements>
     <macros>
         <token name="@TOOL_VERSION@">1.6.1</token>
-        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@VERSION_SUFFIX@">1</token>
     </macros>
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">chemfp</requirement>
+    </requirements>
     <command>
 <![CDATA[
 
@@ -191,9 +191,9 @@
             <param name="infile" value="CID_2244.smi" ftype="smi" />
             <conditional name="fp_opts">
                 <param name="fp_opts_selector" value="--torsions" />
+                <param name="fpSize" value="2048" />
+                <param name="targetSize" value="4" />
             </conditional>
-            <param name="fp_opts.fpSize" value="2048" />
-            <param name="fp_opts.targetSize" value="4" />
             <output name="outfile" file="CID_2244_torsions.fps" ftype="fps" lines_diff="4"/>
         </test>
     </tests>
@@ -209,7 +209,7 @@ This tool uses chemfp to calculate molecular fingerprints, supporting a number o
 For more information check the websites listed below::
 
 	- http://www.rdkit.org/docs/GettingStartedInPython.html#fingerprinting-and-molecular-similarity
-	- http://openbabel.org/wiki/Tutorial:Fingerprints
+	- https://open-babel.readthedocs.io/en/latest/Fingerprints/intro.html
 
 -----
 

diff --git a/chemicaltoolbox/chemfp/nxn_clustering.xml b/chemicaltoolbox/chemfp/nxn_clustering.xml
@@ -2,7 +2,7 @@
     <description>of molecular fingerprints</description>
     <macros>
         <token name="@TOOL_VERSION@">1.6.1</token>
-        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@VERSION_SUFFIX@">1</token>
     </macros>
     <requirements>
         <requirement type="package" version="@TOOL_VERSION@">chemfp</requirement>
@@ -49,7 +49,7 @@
         </data>
     </outputs>
     <tests>
-        <test>
+        <test expect_num_outputs="2">
             <param name="infile" ftype="fps" value="targets.fps" />
             <param name='threshold' value='0.75' />
             <param name='oformat' value='svg' />

diff --git a/chemicaltoolbox/fragmenter/__not_deployed_.shed.yml b/chemicaltoolbox/fragmenter/__not_deployed_.shed.yml
@@ -0,0 +1,16 @@
+name: bgchem
+owner: bgruening
+remote_repository_url: "https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/fragmenter"
+homepage_url: "https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/fragmenter"
+categories:
+- Computational chemistry
+description: "Tools for fragmentation."
+long_description: |
+ "Tools to fragment compounds and merge them together."
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "{{ tool_name }} tool from the bgchem Chemical Toolbox"
+suite:
+  name: suite_bgchem
+  description: tools from the bgchem Chemical Toolbox are used to fragment compounds and merge them together
+  type: repository_suite_definition
diff --git a/chemicaltoolbox/fragmenter/fragmenter.py b/chemicaltoolbox/fragmenter/fragmenter.py
@@ -3,8 +3,7 @@
 import sys
 
 import openbabel
-import pybel
-
+from openbabel import pybel
 openbabel.obErrorLog.StopLogging()
 
 

diff --git a/chemicaltoolbox/fragmenter/fragmenter.xml b/chemicaltoolbox/fragmenter/fragmenter.xml
@@ -1,11 +1,10 @@
-<tool id="fragmenter" name="Fragmenter" version="0.1">
+<tool id="fragmenter" name="Fragmenter" version="0.1+galaxy0" profile="23.0">
     <description>- splits a molecule into fragments</description>
     <parallelism method="multi" split_inputs="infile" split_mode="to_size" split_size="100000" merge_outputs="outfile,fragment_file"></parallelism>
     <requirements>
-        <requirement type="package" version="0.1">cheminfolib</requirement>
-        <requirement type="package" version="2.4.2">openbabel</requirement>
+        <requirement type="package" version="3.1.1">openbabel</requirement>
     </requirements>
-    <command>
+    <command detect_errors="exit_code">
 <![CDATA[
     python '$__tool_directory__/fragmenter.py'
         -i $infile
@@ -34,7 +33,7 @@
         <option value='mol2'>mol2</option>
     </param>
     <param name='mark' type='boolean' label='Replaces the newly created free ends on each bond break with some marker atoms' truevalue='--mark-sticky-ends' falsevalue='' help='This option is usefull if you want to to merge the fragments afterwarts.' />
-    <param name='non_fragment_file' type='boolean' label='Output an additional file with all molecules that are not fragmented' truevalue='' falsevalue='' help='Without that option such molecules will also appear in the regular output file.' />
+    <param name='non_fragment_file' type='boolean' label='Output an additional file with all molecules that are not fragmented' truevalue='True' falsevalue='False' help='Without that option such molecules will also appear in the regular output file.' />
   </inputs>
   <outputs>
         <data format="smi" name="outfile">
@@ -44,18 +43,18 @@
                 <when input="oformat" value="mol2" format="mol2"/>
             </change_format>
        </data>
-   <data format="smi" name="fragment_file">
+   <data format="smi" name="fragment_file" label="Fragments generated by ${tool.name} on ${on_string}">
      <filter>non_fragment_file is True</filter>
    </data>
   </outputs>
   <tests>
-    <test>
+    <test expect_num_outputs="1">
         <param name="infile" ftype="sdf" value="CID_2244.sdf"/>
         <param name='rules' value='recap' />
         <param name='oformat' value='smi' />
         <output name="outfile" ftype="smi" file='fragmenter_on_CID_2244_recap.smi'/>
     </test>
-    <test>
+    <test expect_num_outputs="1">
         <param name="infile" ftype="sdf" value="CID_2244.sdf"/>
         <param name='rules' value='recap' />
         <param name='oformat' value='smi' />
@@ -101,5 +100,6 @@ Copyright 2009-2012 TJ O'Donnell, B Gruening
 ]]>
  </help>
  <citations>
+    <citation type="doi">10.1186/1758-2946-3-33</citation>
  </citations>
 </tool>
diff --git a/chemicaltoolbox/fragmenter/merger.py b/chemicaltoolbox/fragmenter/merger.py
@@ -20,8 +20,7 @@
 import tempfile
 
 import openbabel
-import pybel
-from cheminfolib import CountLines, split_smi_library
+from openbabel import pybel
 
 openbabel.obErrorLog.StopLogging()
 
@@ -52,6 +51,34 @@
 )
 
 
+def CountLines(path):
+    out = subprocess.Popen(
+        ["wc", "-l", path], stdout=subprocess.PIPE, stderr=subprocess.STDOUT
+    ).communicate()[0]
+    return int(out.partition(b" ")[0])
+
+
+def split_smi_library(smiles_file, structures_in_one_file):
+    """
+    Split a file with SMILES to several files for multiprocessing usage.
+    Usage: split_smi_library( smiles_file, 10 )
+    """
+    output_files = []
+    tfile = tempfile.NamedTemporaryFile(delete=False)
+
+    smiles_handle = open(smiles_file, "r")
+    for count, line in enumerate(smiles_handle):
+        if count % structures_in_one_file == 0 and count != 0:
+            tfile.close()
+            output_files.append(tfile.name)
+            tfile = tempfile.NamedTemporaryFile(delete=False)
+        tfile.write(bytes(line, "utf-8"))
+    tfile.close()
+    output_files.append(tfile.name)
+    smiles_handle.close()
+    return output_files
+
+
 def unique_files(file_paths, unique_file, temp=False):
     """
     Concatenate files and makes them unique afterwarts, utilising the GNU `sort` and `cat` tools.
@@ -595,7 +622,7 @@ def filter_input_files(input_file):
     for line in open(temp_final_result.name):
         options.output.write("%s\t\n" % line.strip().split("\t")[0])
 
-    if not type(options.output.name) != str():
+    if isinstance(options.output.name, str):
         logging.info(
             "Results are written to %s (%s)."
             % (options.output.name, CountLines(options.output.name))

diff --git a/chemicaltoolbox/fragmenter/merger.xml b/chemicaltoolbox/fragmenter/merger.xml
@@ -1,12 +1,11 @@
-<tool id="bgchem_fragment_merger" name="Merging" version="0.1">
+<tool id="bgchem_fragment_merger" name="Merging" version="0.1+galaxy0" profile="23.0">
     <description>fragmented molecules</description>
     <requirements>
-        <requirement type="package" version="0.1">cheminfolib</requirement>
-        <requirement type="package" version="2.4.1">openbabel</requirement>
+        <requirement type="package" version="3.1.1">openbabel</requirement>
     </requirements>
-    <command>
+    <command detect_errors="exit_code">
 <![CDATA[
-    '$__tool_directory__/merger.py'
+    python '$__tool_directory__/merger.py'
         -i $infile
         -o $outfile
         --molwt-cutoff $molwt_cutoff
@@ -31,19 +30,7 @@
         <data format="smi" name="outfile" label="Fragment merging on ${on_string}"/>
     </outputs>
     <tests>
-        <test>
-            <param name="infile" ftype="sdf" value="CID_2244.sdf"/>
-            <param name='rules' value='recap' />
-            <param name='oformat' value='smi' />
-            <output name="outfile" ftype="smi" file='fragmenter_on_CID_2244_recap.smi'/>
-        </test>
-        <test>
-            <param name="infile" ftype="sdf" value="CID_2244.sdf"/>
-            <param name='rules' value='recap' />
-            <param name='oformat' value='smi' />
-            <param name='mark' value='--mark-sticky-ends' />
-            <output name="outfile" ftype="smi" file='fragmenter_on_CID_2244_recap_mark.smi'/>
-        </test>
+        <test expect_failure="true" />
     </tests>
     <help>
 <![CDATA[
@@ -93,8 +80,8 @@ A molecule file with new created/merged molecules.
 
 ]]>
     </help>
-
     <citations>
+        <citation type="doi">10.1186/1758-2946-3-33</citation>
     </citations>
 
 </tool>
diff --git a/chemicaltoolbox/fragmenter/test-data/fragmenter_on_CID_2244_recap.smi b/chemicaltoolbox/fragmenter/test-data/fragmenter_on_CID_2244_recap.smi
@@ -1,2 +1,2 @@
-Oc1ccccc1C(=O)O	
-O=CC	
+[O]c1c(cccc1)C(=O)O	
+O=[C]C	
diff --git a/chemicaltoolbox/fragmenter/test-data/fragmenter_on_CID_2244_recap_mark.smi b/chemicaltoolbox/fragmenter/test-data/fragmenter_on_CID_2244_recap_mark.smi
@@ -1,2 +1,2 @@
-[U]c1ccccc1C(=O)O	
+[U]c1c(cccc1)C(=O)O	
 O=[Pa]C	
diff --git a/chemicaltoolbox/openmg/openmg.xml b/chemicaltoolbox/openmg/openmg.xml
@@ -1,9 +1,9 @@
-<tool id="ctb_openmg" name="Open Molecule Generator" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@">
+<tool id="ctb_openmg" name="Open Molecule Generator" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="23.0">
+    <description>- exhaustive generation of chemical structures</description>
     <macros>
         <token name="@TOOL_VERSION@">0.1</token>
-        <token name="@GALAXY_VERSION@">0</token>
+        <token name="@GALAXY_VERSION@">1</token>
     </macros>
-    <description>- exhaustive generation of chemical structures</description>
     <requirements>
         <requirement type="package" version="@TOOL_VERSION@">openmg</requirement>
         <requirement type="package" version="8.0.112">java-jdk</requirement>
@@ -26,12 +26,12 @@
     </inputs>
     <outputs>
         <data format="sdf" name="outfile" />
-        <data format="sdf" name="sdf_outfile">
+        <data format="sdf" name="sdf_outfile" label="Substructures detected by ${tool.name} on ${on_string}">
             <filter>fr is True</filter>
         </data>
     </outputs>
     <tests>
-        <test>
+        <test expect_num_outputs="1">
             <param name="ec" value="C6H6"/>
             <output name="outfile" file="openmg_results.sdf" lines_diff="440"/>
         </test>

diff --git a/chemicaltoolbox/pgchem/pgchem/_not_deployed_.shed.yml b/chemicaltoolbox/pgchem/pgchem/_not_deployed_.shed.yml
@@ -0,0 +1,16 @@
+name: pgchem
+owner: bgruening
+remote_repository_url: "https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/pgchem"
+homepage_url: "https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/pgchem"
+categories:
+- Computational chemistry
+description: "Tools for chemical database manipulation."
+long_description: |
+ "Tools for chemical database manipulation."
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "{{ tool_name }} tool from the bgchem Chemical Toolbox"
+suite:
+  name: suite_pgchem
+  description: tools from the pgchem Chemical Toolbox.
+  type: repository_suite_definition