Mercurial > repos > bgruening > autodock_vina
diff docking.xml @ 7:7b2f205b3f68 draft
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/autodock_vina commit ef86cfa5f7ab5043de420511211579d03df58645"
| author | bgruening |
|---|---|
| date | Wed, 02 Oct 2019 12:49:30 -0400 |
| parents | 0ae768a0e5c0 |
| children | 7a871df65202 |
line wrap: on
line diff
--- a/docking.xml Wed Jun 19 06:43:41 2019 -0400 +++ b/docking.xml Wed Oct 02 12:49:30 2019 -0400 @@ -1,56 +1,50 @@ -<tool id="docking" name="Docking" version="0.2.1"> +<tool id="docking" name="VINA Docking" version="0.3.0"> <description>tool to perform protein-ligand docking with Autodock Vina</description> <requirements> <requirement type="package" version="1.1.2">autodock-vina</requirement> <requirement type="package" version="2.4.1">openbabel</requirement> + <requirement type="package" version="20190722">parallel</requirement> </requirements> - <stdio> - <exit_code range="1" /> - </stdio> - <command><![CDATA[ + <command detect_errors="exit_code"><![CDATA[ + #if $ligands.is_of_type("sdf") + obabel -isdf '$ligands' -O ligand.pdbqt -m -p $ph_value && + #else + ln -s '$ligands' ligand1.pdbqt && + #end if + mkdir output && + ls ligand*.pdbqt | parallel --will-cite -j \${GALAXY_SLOTS:-1} $'OUTNAME={.}_docked && vina + --receptor \'$receptor\' + --ligand {} + --out ./\${OUTNAME}.pdbqt + --log ./\${OUTNAME}.log + --cpu 1 #if $config_params.config_params == 'vals': - vina - --center_x '$config_params.center_x' - --center_y '$config_params.center_y' - --center_z '$config_params.center_z' - --size_x '$config_params.size_x' - --size_y '$config_params.size_y' - --size_z '$config_params.size_z' - --exhaustiveness '$config_params.exh' - --num_modes 9999 - --energy_range 9999 - --receptor '$receptor' - --ligand '$ligand' - --out './output1.dat' - --log './output2.dat' - --cpu \${GALAXY_SLOTS:-1} - #if $config_params.seed.seed == 'true': - --seed '$config_params.seed.seed_value' - #end if - #end if - #if $config_params.config_params == 'file': - vina - --config '$config_params.box' - --receptor '$receptor' - --ligand '$ligand' - --out './output1.dat' - --log './output2.dat' - --cpu \${GALAXY_SLOTS:-1} + --center_x $config_params.center_x + --center_y $config_params.center_y + --center_z $config_params.center_z + --size_x $config_params.size_x + --size_y $config_params.size_y + --size_z $config_params.size_z #if $config_params.exh != "": --exhaustiveness $config_params.exh #end if + #if $config_params.seed.seed == 'true': + --seed $config_params.seed.seed_value + #end if + #else if $config_params.config_params == 'file': + --config $config_params.box + #if $config_params.exh != "": + --exhaustiveness $config_params.exh + #end if #end if - #if $output_format == 'sdf': - && python '$__tool_directory__/convert_pdbqt_to_sdf.py' './output1.dat' '$sdf_output' - #else - && mv ./output1.dat '$file_output1' - && mv ./output2.dat '$file_output2' - #end if + && python \'$__tool_directory__/convert_pdbqt_to_sdf.py\' ./\${OUTNAME}.pdbqt output/\${OUTNAME}.sdf' ]]></command> <inputs> <param type="data" name="receptor" format="pdbqt" label="Receptor" help="Select a receptor (PDBQT format). This can be prepared using the receptor preparation tool." /> - <param type="data" name="ligand" format="pdbqt" label="Ligand" help="Select a ligand (PDBQT format). This can be prepared using the ligand preparation tool." /> + <param type="data" name="ligands" format="sdf,pdbqt" label="Ligands" help="Select ligands (SDF format with multiple ligands or PDBQT format with single ligand)." /> + <param name="ph_value" type="float" value="7.4" min="0" max="14" label="Specify pH value for ligand protonation" + help="Only used in case the input is a SD file."/> <conditional name="config_params"> <param name="config_params" type="select" label="Specify parameters"> <option value="file">Upload a config file to specify parameters</option> @@ -63,7 +57,8 @@ <param type="float" name="size_x" label="x size" help="Length of the binding site (Å) in the x direction." value="0"/> <param type="float" name="size_y" label="y size" help="Length of the binding site (Å) in the y direction." value="0"/> <param type="float" name="size_z" label="z size" help="Length of the binding site (Å) in the z direction." value="0"/> - <param type="integer" name="exh" label="Exhaustiveness" help="The number of poses to return from the docking job" value="10"/> + <param type="integer" name="exh" label="Exhaustiveness" optional="true" + help="Exhaustiveness of global search (optional - if not specified a default of 8 is used)"/> <conditional name="seed"> <param name="seed" type="boolean" label="Specify random seed for simulation reproducibility?"/> <when value="true"> @@ -74,60 +69,58 @@ </when> <when value="file"> <param type="data" name="box" format="txt" label="Box configuration" help="Text file with the box configurations" /> - <param type="integer" name="exh" label="Exhaustiveness" help="The number of poses to return from the docking job (optional, will override any value specified in the config file)" optional="true"/> + <param type="integer" name="exh" label="Exhaustiveness" optional="true" + help="Exhaustiveness of global search (optional - if not specified a default of 8 is used, if specified will override any value specified in the config file)"/> </when> </conditional> - <param type="select" name="output_format" label="Output format" help="Select a format for the output files"> - <option value="pdbqt" selected="true">PDBQT (and separate log file with binding scores)</option> - <option value="sdf">SDF</option> - </param> </inputs> <outputs> - <data name="file_output1" format="pdbqt"> - <filter>output_format == 'pdbqt'</filter> - </data> - <data name="file_output2" format="txt"> - <filter>output_format == 'pdbqt'</filter> - </data> - <data name="sdf_output" format="sdf"> - <filter>output_format == 'sdf'</filter> - </data> + <collection name="sdf_outputs" type="list" label="Docked ligands for ${on_string}" > + <discover_datasets pattern="__name_and_ext__" directory="output" visible="false" /> + </collection> </outputs> <tests> - <test expect_num_outputs="2"> - <param name="receptor" value="3u1i_for_DM.pdbqt"/> - <param name="ligand" value="NuBBE_1_obabel_3D.pdbqt"/> + + <test> + <param name="receptor" value="protein.pdbqt"/> + <param name="ligands" value="input_ligands.sdf"/> + <param name="box" value="box.txt"/> + <output_collection name="sdf_outputs" type="list" count="5"> + <element name="ligand1_docked" file="ligand1_docked.sdf" lines_diff="20"/> + <element name="ligand2_docked" file="ligand2_docked.sdf" lines_diff="20"/> + <!-- we check only the first 2 --> + </output_collection> + </test> + + <test> + <param name="receptor" value="protein.pdbqt"/> + <param name="ligands" value="input_ligand.pdbqt"/> + <param name="box" value="box.txt"/> + <output_collection name="sdf_outputs" type="list" count="1"> + <element name="ligand1_docked" file="ligand1_docked.sdf" lines_diff="20"/> + </output_collection> + </test> + + <!-- TODO - this should be able to use the same output as the previous test but there is inconsistency in + how the parameters are handled that needs to be resolved so we use a different output file to compare to. --> + <test> + <param name="receptor" value="protein.pdbqt"/> + <param name="ligands" value="input_ligand.pdbqt"/> <param name="config_params" value="vals"/> - <param name="center_x" value="70.92" /> - <param name="center_y" value="70.57" /> - <param name="center_z" value="36.86" /> - <param name="size_x" value="20.00" /> - <param name="size_y" value="18.40" /> - <param name="size_z" value="23.60" /> + <param name="center_x" value="36.454" /> + <param name="center_y" value="-43.608000000000004" /> + <param name="center_z" value="75.176" /> + <param name="size_x" value="18.768" /> + <param name="size_y" value="10.205999999999996" /> + <param name="size_z" value="15.521999999999991" /> <param name="seed" value="true" /> <param name="seed_value" value="1" /> - <param name="exhaustiveness" value="10" /> - <param name="output_format" value="pdbqt" /> - <output name="file_output1" file="NuBBE_1_obabel_3D_-_3u1i_for_DM.pdbqt"/> - <output name="file_output2" file="NuBBE_1_obabel_3D_-_3u1i_for_DM.log"/> + <param name="exh" value="10" /> + <output_collection name="sdf_outputs" type="list" count="1"> + <element name="ligand1_docked" file="ligand_params.sdf" lines_diff="20"/> + </output_collection> </test> - <test expect_num_outputs="2"> - <param name="receptor" value="3u1i_for_DM.pdbqt"/> - <param name="ligand" value="NuBBE_1_obabel_3D.pdbqt"/> - <param name="config_params" value="file"/> - <param name="box" value="config_complexo_dm.txt"/> - <param name="output_format" value="pdbqt" /> - <output name="file_output1" file="NuBBE_1_obabel_3D_-_3u1i_for_DM.pdbqt"/> - <output name="file_output2" file="NuBBE_1_obabel_3D_-_3u1i_for_DM.log"/> - </test> - <test expect_num_outputs="1"> - <param name="receptor" value="3u1i_for_DM.pdbqt"/> - <param name="ligand" value="NuBBE_1_obabel_3D.pdbqt"/> - <param name="config_params" value="file"/> - <param name="box" value="config_complexo_dm.txt"/> - <param name="output_format" value="sdf" /> - <output name="sdf_output" file="NuBBE_1_obabel_3D_-_3u1i_for_DM.sdf" lines_diff="40"/> - </test> + </tests> <help><![CDATA[ @@ -139,11 +132,22 @@ **Inputs** -The first two inputs required are files (in the pdbqt format) describing the receptor and ligand respectively. These files are produced by the receptor and ligand preparation tools. +The first two inputs required are files describing the receptor (in the pdbqt format) and ligands (in SDF of PDBQT format) respectively. +These files are produced by the receptor and ligand preparation tools. +If using PDBQT format for the ligands only a single ligand can be specified. If using SDF you can include multiple ligands +and those ligands are converted to individual PDBQT format files using openbabel as the first step of tool execution. +You can specify the pH for protonation by openbabel -In addition, parameters for docking must be defined. The Cartesian coordinates of the center of the binding site should be provided, along with the size of the binding site along each dimension. Effectively, this defines a cuboidal volume in which docking is performed. Alternatively, a config file can be uploaded containing this information - such a file can be generated from the box parameter calculation file. +VINA will dock each of the ligands in the SDF file sequentially. If there are a large number of ligands then first split +them into a collection of smaller files e.g. using the splitter tool. This allows each split chunk of molecules to be docked +as a separate task. The optimal size of the chunk will depend on the number of ligands and the capacity of the execution +environment. -A format for the output should also be selected: the available options are PDBQT or SDF. +In addition, parameters for docking must be defined. The Cartesian coordinates of the center of the binding site should +be provided, along with the size of the binding site along each dimension. Effectively, this defines a cuboidal volume in +which docking is performed. Alternatively, a config file can be uploaded containing this information - such a file can be +generated from the box parameter calculation file. + ----- @@ -151,11 +155,9 @@ **Outputs** -Either PDBQT or SDF may be selected as output. - -**Option 1: SDF** - -An SDF file is produced as output. The binding affinity scores are also contained within the SDF file.:: +SDF files are produced as output. +There is one file for each ligand in the input. Each entry in the file is a docked pose for that ligand. +The binding affinity scores are contained within the SDF file.:: OpenBabel06171915303D @@ -236,117 +238,6 @@ > <RMSD_UB> 0.000 - -**Option 2: PDBQT** - -Two outputs are generated if PDBQT output is selected. The first is another pdbqt file containing the molecular structure resulting from docking, such as the following example:: - - MODEL 1 - REMARK VINA RESULT: -0.0 0.000 0.000 - REMARK 9 active torsions: - REMARK status: ('A' for Active; 'I' for Inactive) - REMARK 1 A between atoms: C_2 and O_3 - REMARK 2 A between atoms: C_2 and C_14 - REMARK 3 A between atoms: O_3 and C_4 - REMARK 4 A between atoms: C_4 and C_5 - REMARK 5 A between atoms: C_6 and C_8 - REMARK 6 A between atoms: C_8 and C_9 - REMARK 7 A between atoms: C_9 and C_10 - REMARK 8 A between atoms: C_16 and O_17 - REMARK 9 A between atoms: C_19 and O_20 - ROOT - ATOM 1 O LIG d 1 72.801 71.157 37.352 0.00 0.00 -0.259 OA - ATOM 2 C LIG d 1 73.413 72.112 37.794 0.00 0.00 0.293 C - ENDROOT - BRANCH 2 3 - ATOM 3 O LIG d 1 72.912 73.321 38.144 0.00 0.00 -0.314 OA - BRANCH 3 4 - ATOM 4 C LIG d 1 71.868 73.332 39.120 0.00 0.00 0.206 C - BRANCH 4 5 - ATOM 5 C LIG d 1 72.522 73.555 40.453 0.00 0.00 0.002 C - ATOM 6 C LIG d 1 72.762 72.629 41.405 0.00 0.00 -0.085 C - ATOM 7 C LIG d 1 72.390 71.176 41.274 0.00 0.00 0.043 C - BRANCH 6 8 - ATOM 8 C LIG d 1 73.435 73.012 42.714 0.00 0.00 0.037 C - BRANCH 8 9 - ATOM 9 C LIG d 1 74.184 74.348 42.631 0.00 0.00 0.031 C - BRANCH 9 10 - ATOM 10 C LIG d 1 75.668 74.175 42.431 0.00 0.00 -0.024 C - ATOM 11 C LIG d 1 76.399 74.547 41.360 0.00 0.00 -0.091 C - ATOM 12 C LIG d 1 75.833 75.151 40.104 0.00 0.00 0.042 C - ATOM 13 C LIG d 1 77.897 74.373 41.339 0.00 0.00 0.042 C - ENDBRANCH 9 10 - ENDBRANCH 8 9 - ENDBRANCH 6 8 - ENDBRANCH 4 5 - ENDBRANCH 3 4 - ENDBRANCH 2 3 - BRANCH 2 14 - ATOM 14 C LIG d 1 74.882 72.132 38.012 0.00 0.00 0.042 A - ATOM 15 C LIG d 1 75.732 72.845 37.153 0.00 0.00 0.057 A - ATOM 16 C LIG d 1 77.101 72.826 37.385 0.00 0.00 0.099 A - ATOM 17 C LIG d 1 77.623 72.116 38.462 0.00 0.00 0.098 A - ATOM 18 C LIG d 1 76.791 71.422 39.330 0.00 0.00 0.040 A - ATOM 19 C LIG d 1 75.412 71.432 39.110 0.00 0.00 0.020 A - BRANCH 16 20 - ATOM 20 O LIG d 1 77.978 73.498 36.578 0.00 0.00 -0.358 OA - ATOM 21 HO LIG d 1 77.680 74.093 35.900 1.00 0.00 0.217 HD - ENDBRANCH 16 20 - BRANCH 17 22 - ATOM 22 O LIG d 1 78.971 72.100 38.675 0.00 0.00 -0.358 OA - ATOM 23 HO LIG d 1 79.541 71.651 38.060 1.00 0.00 0.217 HD - ENDBRANCH 17 22 - ENDBRANCH 2 14 - TORSDOF 9 - ENDMDL - -The second output is a log file containing the binding affinity scores, like the following:: - - ----------------------------------------------------------------- - If you used AutoDock Vina in your work, please cite: - - O. Trott, A. J. Olson, - AutoDock Vina: improving the speed and accuracy of docking - with a new scoring function, efficient optimization and - multithreading, Journal of Computational Chemistry 31 (2010) - 455-461 - - DOI 10.1002/jcc.21334 - - Please see http://vina.scripps.edu for more information. - ------------------------------------------------------------------ - - Reading input ... done. - Setting up the scoring function ... done. - Analyzing the binding site ... done. - Using random seed: 1899908181 - Performing search ... done. - Refining results ... done. - - mode | affinity | dist from best mode - | (kcal/mol) | rmsd l.b.| rmsd u.b. - -----+------------+----------+---------- - 1 -0.0 0.000 0.000 - 2 -0.0 2.046 2.443 - 3 -0.0 5.896 7.949 - 4 -0.0 2.518 3.100 - 5 -0.0 2.417 4.527 - 6 -0.0 5.686 7.689 - 7 -0.0 2.828 4.792 - 8 -0.0 5.547 7.086 - 9 -0.0 7.388 9.966 - 10 -0.0 7.877 11.352 - 11 -0.0 8.203 10.157 - 12 -0.0 5.163 7.653 - 13 -0.0 3.093 6.011 - 14 -0.0 7.998 11.146 - 15 -0.0 7.015 10.108 - 16 -0.0 8.795 11.682 - 17 -0.0 7.317 10.367 - 18 0.0 3.274 4.160 - 19 0.0 10.286 12.001 - 20 0.0 3.566 5.349 - Writing output ... done. ]]></help> <citations> <citation type="doi">10.1002/jcc.21334</citation>