# HG changeset patch # User rnateam # Date 1423924115 18000 # Node ID 70170338b4f7ba0a9bd978c38343b6cd3b843df2 # Parent 78b364f5d93e7e3a48f50deaf3a44b17ce6a55b9 Uploaded diff -r 78b364f5d93e -r 70170338b4f7 blockclust_workflow.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/blockclust_workflow.ga Sat Feb 14 09:28:35 2015 -0500 @@ -0,0 +1,461 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "format-version": "0.1", + "name": "BlockClustWorkflow", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Input BAM file" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 267, + "top": 257.5 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Input BAM file\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": { + "tool_mode|reads_bam": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "BlockClust", + "outputs": [ + { + "name": "tags_bed", + "type": "bed" + }, + { + "name": "hclust_plot", + "type": "pdf" + }, + { + "name": "clusters", + "type": "bed" + }, + { + "name": "model_based_pred_bed", + "type": "bed" + }, + { + "name": "nearest_neighbour_pred_bed", + "type": "bed" + }, + { + "name": "sim_tab_out", + "type": "tabular" + }, + { + "name": "cluster_dist", + "type": "pdf" + }, + { + "name": "cluster_hclust", + "type": "pdf" + } + ], + "position": { + "left": 524, + "top": 323 + }, + "post_job_actions": { + "HideDatasetActioncluster_dist": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "cluster_dist" + }, + "HideDatasetActioncluster_hclust": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "cluster_hclust" + }, + "HideDatasetActionclusters": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "clusters" + }, + "HideDatasetActionhclust_plot": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "hclust_plot" + }, + "HideDatasetActionmodel_based_pred_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "model_based_pred_bed" + }, + "HideDatasetActionnearest_neighbour_pred_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "nearest_neighbour_pred_bed" + }, + "HideDatasetActionsim_tab_out": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "sim_tab_out" + }, + "HideDatasetActiontags_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "tags_bed" + } + }, + "tool_errors": null, + "tool_id": "testtoolshed.g2.bx.psu.edu/repos/rnateam/blockclust/blockclust/1.0.0", + "tool_state": "{\"tool_mode\": \"{\\\"operation\\\": \\\"pre\\\", \\\"reads_bam\\\": null, \\\"__current_case__\\\": 0}\", \"__rerun_remap_job_id__\": null, \"mode\": \"{\\\"operation\\\": \\\"pre\\\", \\\"reads_bam\\\": null, \\\"__current_case__\\\": 0}\", \"__page__\": 0}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [] + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": { + "input": { + "id": 1, + "output_name": "tags_bed" + } + }, + "inputs": [], + "name": "Sort", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 797, + "top": 355 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_errors": null, + "tool_id": "sort1", + "tool_state": "{\"__page__\": 0, \"style\": \"\\\"alpha\\\"\", \"column\": \"{\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"1\\\"}\", \"__rerun_remap_job_id__\": null, \"order\": \"\\\"ASC\\\"\", \"input\": \"null\", \"column_set\": \"[{\\\"other_order\\\": \\\"ASC\\\", \\\"__index__\\\": 0, \\\"other_column\\\": {\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"6\\\"}, \\\"other_style\\\": \\\"alpha\\\"}, {\\\"other_order\\\": \\\"ASC\\\", \\\"__index__\\\": 1, \\\"other_column\\\": {\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"2\\\"}, \\\"other_style\\\": \\\"num\\\"}, {\\\"other_order\\\": \\\"ASC\\\", \\\"__index__\\\": 2, \\\"other_column\\\": {\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"3\\\"}, \\\"other_style\\\": \\\"num\\\"}]\"}", + "tool_version": "1.0.3", + "type": "tool", + "user_outputs": [] + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": { + "input": { + "id": 2, + "output_name": "out_file1" + } + }, + "inputs": [], + "name": "blockbuster", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 970, + "top": 225 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "testtoolshed.g2.bx.psu.edu/repos/rnateam/blockbuster/blockbuster/0.1", + "tool_state": "{\"distance\": \"\\\"40\\\"\", \"scale\": \"\\\"0.5\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"print\": \"\\\"2\\\"\", \"tagFilter\": \"\\\"0\\\"\", \"merge\": \"\\\"0\\\"\", \"minBlockHeight\": \"\\\"1.0\\\"\", \"input\": \"null\", \"minClusterHeight\": \"\\\"50.0\\\"\"}", + "tool_version": "0.1", + "type": "tool", + "user_outputs": [] + }, + "4": { + "annotation": "", + "id": 4, + "input_connections": { + "tool_mode|input_bbo": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool BlockClust", + "name": "tool_mode" + } + ], + "name": "BlockClust", + "outputs": [ + { + "name": "tags_bed", + "type": "bed" + }, + { + "name": "hclust_plot", + "type": "pdf" + }, + { + "name": "clusters", + "type": "bed" + }, + { + "name": "model_based_pred_bed", + "type": "bed" + }, + { + "name": "nearest_neighbour_pred_bed", + "type": "bed" + }, + { + "name": "sim_tab_out", + "type": "tabular" + }, + { + "name": "cluster_dist", + "type": "pdf" + }, + { + "name": "cluster_hclust", + "type": "pdf" + } + ], + "position": { + "left": 1232, + "top": 321 + }, + "post_job_actions": { + "HideDatasetActioncluster_dist": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "cluster_dist" + }, + "HideDatasetActioncluster_hclust": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "cluster_hclust" + }, + "HideDatasetActionclusters": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "clusters" + }, + "HideDatasetActionnearest_neighbour_pred_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "nearest_neighbour_pred_bed" + }, + "HideDatasetActionsim_tab_out": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "sim_tab_out" + }, + "HideDatasetActiontags_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "tags_bed" + } + }, + "tool_errors": null, + "tool_id": "testtoolshed.g2.bx.psu.edu/repos/rnateam/blockclust/blockclust/1.0.0", + "tool_state": "{\"tool_mode\": \"{\\\"pred\\\": {\\\"pred_mode\\\": \\\"model_based\\\", \\\"enable_pred\\\": \\\"yes\\\", \\\"__current_case__\\\": 0}, \\\"operation\\\": \\\"clust\\\", \\\"reference\\\": {\\\"__class__\\\": \\\"RuntimeValue\\\"}, \\\"__current_case__\\\": 1, \\\"input_bbo\\\": null}\", \"__rerun_remap_job_id__\": null, \"mode\": \"{\\\"operation\\\": \\\"clust\\\", \\\"reference\\\": {\\\"__class__\\\": \\\"RuntimeValue\\\"}, \\\"__current_case__\\\": 1, \\\"input_bbo\\\": null}\", \"__page__\": 0}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [] + }, + "5": { + "annotation": "", + "id": 5, + "input_connections": { + "input": { + "id": 4, + "output_name": "clusters" + } + }, + "inputs": [], + "name": "Extract Genomic DNA", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1495, + "top": 248 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_errors": null, + "tool_id": "Extract genomic DNA 1", + "tool_state": "{\"out_format\": \"\\\"fasta\\\"\", \"__page__\": 0, \"interpret_features\": \"\\\"yes\\\"\", \"__rerun_remap_job_id__\": null, \"seq_source\": \"{\\\"index_source\\\": \\\"cached\\\", \\\"__current_case__\\\": 0}\", \"input\": \"null\"}", + "tool_version": "2.2.3", + "type": "tool", + "user_outputs": [] + }, + "6": { + "annotation": "", + "id": 6, + "input_connections": { + "seqdb": { + "id": 5, + "output_name": "out_file1" + } + }, + "inputs": [], + "name": "Search covariance model(s)", + "outputs": [ + { + "name": "outfile", + "type": "tabular" + }, + { + "name": "multiple_alignment_output", + "type": "tabular" + } + ], + "position": { + "left": 1753, + "top": 247 + }, + "post_job_actions": { + "HideDatasetActionmultiple_alignment_output": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "multiple_alignment_output" + }, + "HideDatasetActionoutfile": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "outfile" + } + }, + "tool_errors": null, + "tool_id": "testtoolshed.g2.bx.psu.edu/repos/bgruening/infernal/infernal_cmsearch/1.1.0.2", + "tool_state": "{\"A\": \"\\\"False\\\"\", \"nohmm\": \"\\\"False\\\"\", \"--acyk\": \"\\\"False\\\"\", \"bottomonly\": \"\\\"False\\\"\", \"g\": \"\\\"False\\\"\", \"inclusion_thresholds_opts\": \"{\\\"inclusion_thresholds_selector\\\": \\\"\\\", \\\"__current_case__\\\": 3}\", \"__page__\": 0, \"max\": \"\\\"False\\\"\", \"notrunc\": \"\\\"False\\\"\", \"mid\": \"\\\"False\\\"\", \"seqdb\": \"null\", \"toponly\": \"\\\"False\\\"\", \"cm_opts\": \"{\\\"database\\\": null, \\\"__current_case__\\\": 0, \\\"cm_opts_selector\\\": \\\"db\\\"}\", \"reporting_thresholds_opts\": \"{\\\"reporting_thresholds_selector\\\": \\\"\\\", \\\"__current_case__\\\": 3}\", \"cyk\": \"\\\"False\\\"\", \"__rerun_remap_job_id__\": null}", + "tool_version": "1.1.0.2", + "type": "tool", + "user_outputs": [] + }, + "7": { + "annotation": "", + "id": 7, + "input_connections": { + "tool_mode|clusters_bed": { + "id": 4, + "output_name": "clusters" + }, + "tool_mode|cmsearch_out": { + "id": 6, + "output_name": "outfile" + }, + "tool_mode|sim_tab_in": { + "id": 4, + "output_name": "sim_tab_out" + } + }, + "inputs": [], + "name": "BlockClust", + "outputs": [ + { + "name": "tags_bed", + "type": "bed" + }, + { + "name": "hclust_plot", + "type": "pdf" + }, + { + "name": "clusters", + "type": "bed" + }, + { + "name": "model_based_pred_bed", + "type": "bed" + }, + { + "name": "nearest_neighbour_pred_bed", + "type": "bed" + }, + { + "name": "sim_tab_out", + "type": "tabular" + }, + { + "name": "cluster_dist", + "type": "pdf" + }, + { + "name": "cluster_hclust", + "type": "pdf" + } + ], + "position": { + "left": 2049, + "top": 433 + }, + "post_job_actions": { + "HideDatasetActionclusters": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "clusters" + }, + "HideDatasetActionhclust_plot": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "hclust_plot" + }, + "HideDatasetActionmodel_based_pred_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "model_based_pred_bed" + }, + "HideDatasetActionnearest_neighbour_pred_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "nearest_neighbour_pred_bed" + }, + "HideDatasetActionsim_tab_out": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "sim_tab_out" + }, + "HideDatasetActiontags_bed": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "tags_bed" + } + }, + "tool_errors": null, + "tool_id": "testtoolshed.g2.bx.psu.edu/repos/rnateam/blockclust/blockclust/1.0.0", + "tool_state": "{\"tool_mode\": \"{\\\"cmsearch_out\\\": null, \\\"operation\\\": \\\"post\\\", \\\"clusters_bed\\\": null, \\\"__current_case__\\\": 2, \\\"sim_tab_in\\\": null}\", \"__rerun_remap_job_id__\": null, \"mode\": \"{\\\"cmsearch_out\\\": null, \\\"operation\\\": \\\"post\\\", \\\"clusters_bed\\\": null, \\\"__current_case__\\\": 2, \\\"sim_tab_in\\\": null}\", \"__page__\": 0}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [] + } + } +} \ No newline at end of file diff -r 78b364f5d93e -r 70170338b4f7 readme.rst --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/readme.rst Sat Feb 14 09:28:35 2015 -0500 @@ -0,0 +1,243 @@ + + +This package is a Galaxy workflow for BlockClust pipeline. + + +====== +Galaxy +====== + +`Galaxy `_ is an open, web-based platform for data intensive research. +All tools can be combined in workflows without any need of programming skills. +Furthermore the platform can be extended with more tools at any time. +Each tool has its own information about what it does and how the input is supposed to look like. +You can make data available for Galaxy by uploading local files or downloading online content. +Inputfiles, workflowsteps and results are stored in a history where you can view them or reaccess them later. +It is possible to share workflows and histories with other users or make the public available. +Saved workflows can be used with new input files or just to rerun an analyses which ensures repeatability. + + + +Getting Started +=============== + +BlockClust can be installed on all common Unix systems. +However, it is developed on Linux and I don't have access to OS X. You are welcome to help improving this documentation, just contact_ me. + +For any additional information, especially cluster configuration or general Galaxy_ questions, +please have a look at the Galaxy Wiki. + +- http://wiki.galaxyproject.org/ + +- http://wiki.galaxyproject.org/Admin/ + +- http://galaxyproject.org/search/web/ + +.. _contact: https://github.com/bgruening +.. _Galaxy: http://galaxyproject.org/ + +Prerequisites:: + +* Python 2.6 or 2.7 +* standard C compiler, C++ and Fortran compiler +* Autotools +* CMake +* cairo development files (used for PNG depictions) +* python development files +* Java Runtime Environment (JRE, used by OPSIN and NPLS) + +To install all of the prerequisites you can run the following command, depending on your OS: + +- Debian based systems: apt-get install build-essential gfortran cmake mercurial libcairo2-dev python-dev +- Fedora: yum install make automake gcc gcc-c++ gcc-gfortran cmake mercurial libcairo2-devel python-devel +- OS X (MacPorts_): port install gcc cmake automake mercurial cairo-devel + +.. _MacPorts: http://www.macports.org/ + + +=================== +Galaxy installation +=================== + + +0. Create a sand-boxed Python using virtualenv_ (not necessary but recommended):: + + wget https://raw.github.com/pypa/virtualenv/master/virtualenv.py + python ./virtualenv.py --no-site-packages galaxy_env + . ./galaxy_env/bin/activate + +.. _virtualenv: http://www.virtualenv.org/ + + +1. Clone the latest `Galaxy platform`_:: + + hg clone https://bitbucket.org/galaxy/galaxy-central/ + +.. _Galaxy platform: http://wiki.galaxyproject.org/Admin/Get%20Galaxy + +2. Navigate to the galaxy-central folder and update it:: + + cd ~/galaxy-central + hg pull + hg update + + This step is not necessary if you have a fresh checkout. Anyway, it is good to know ;) + +3. Create folders for toolshed and dependencies:: + + mkdir ~/shed_tools + mkdir ~/galaxy-central/tool_deps + +4. Create configuration file:: + + cp ~/galaxy-central/universe_wsgi.ini.sample ~/galaxy-central/universe_wsgi.ini + +5. Open universe_wsgi.ini and change the dependencies directory:: + + LINUX: gedit ~/galaxy-central/universe_wsgi.ini + OS X: open -a TextEdit ~/galaxy-central/universe_wsgi.ini + +6. Search for ``tool_dependency_dir = None`` and change it to ``tool_dependency_dir = ./tool_deps``, remove the ``#`` if needed + +7. Remove the ``#`` in front of ``tool_config_file`` and ``tool_path`` + +8. (Re-)Start the galaxy daemon:: + + sh run.sh --reload + + In deamon mode all logs will be written to main.log in your Galaxy Home directory. You can also use:: + + run.sh + + During the first startup Galaxy will prepare your database. That can take some time. Have a look at the log file if you want to know what happens. + +After launching galaxy is accessible via the browser at ``http://localhost:8080/``. + + + +======================= +Tool Shed configuration +======================= + +- Register a new user account in your Galaxy instance: Top Panel → User → Register +- Become an admin + - open ``universe_wsgi.ini`` in your favourite text editor (gedit universe_wsgi.ini) + - search ``admin_users = None`` and change it to ``admin_users = EMAIL_ADDRESS`` (your Galaxy Username) + - remove the ``#`` if needed +- restart Galaxy + +:: + + sh run.sh --reload + + +======================= +BlockClust installation +======================= + +BlockClust will automatically download and compile all requirements, +like EDeN, samtools and so on. It can take up to 1-2 hours. + + +Installation via webbrowser +=========================== + +- go to the `admin page`_ +- select *Search and browse tool sheds* +- Galaxy test tool shed > Sequence Analysis > blockclust_workflow +- install + +.. _admin page: http://localhost:8080/admin + + +=============== +Troubleshooting +=============== +You can navigate to the blockclust_workflow repository in your browser and repair manually: +Top Panel → Admin → Manage installed tool shed repositories → blockclust_workflow → Repository Actions → Repair repository + +------ + + +On slow computers and during the compilation of large software libraries, like R, +the Tool Shed can run into a timeout and kills the installation. +That problem is known and should be fixed in the near future. + +If you encouter a timeout or 'hung' during the installation you can increase the ``threadpool_kill_thread_limit`` in your universe_wsgi.ini file. + + +------ + +**Database locking errors** + +Please note that Galaxy per default uses a SQLite database. Sqlite is not intended for production use. +With multiple users or complex components, like that workflow, you will see database locking errors. +We highly recommend to use PostgreSQL for any kind of production system. + + +.. _Galaxy wiki: http://wiki.galaxyproject.org/ + + +Workflows +========= + +The BlockClust workflow is located in the `Tool Shed`:: + + http://toolshed.g2.bx.psu.edu/view/rnateam/blockclust_workflow + +To import successfully installed the workflow to all your users you need to go to the admin panel, choose the worklow and import it. +For more information have a look at the Galaxy wiki:: + + http://wiki.galaxyproject.org/ToolShedWorkflowSharing#Finding_workflows_in_tool_shed_repositories + +Please **note** that Galaxy per default uses a SQLite database. Sqlite is not intended for production use. +With multiple users or complex components, like that workflow, you will see database locking errors. +We highly recommend to use PostgreSQL for any kind of production system. + + + +Sample Data +=========== + + + +Citation +======== + +If you use this workflow directly, or a derivative of it, or the associated +wrappers for Galaxy, in work leading to a scientific publication, +please cite: + +Pavankumar Videm, Dominic Rose, Fabrizio Costa, and Rolf Backofen. "BlockClust: efficient clustering and classification of non-coding RNAs from short read RNA-seq profiles." Bioinformatics 30, no. 12 (2014): i274-i282. + + + +Additional References +===================== + + + +Availability +============ + +This workflow is available on the main Galaxy Tool Shed: + + http://toolshed.g2.bx.psu.edu/view/rnateam/blockclust_workflow + +Development is being done on github: + +https://github.com/bgruening/galaxytools/tree/master/workflows/blockclust + + +Dependencies +============ + +These dependencies should be resolved automatically via the Galaxy Tool Shed: + +* http://testtoolshed.g2.bx.psu.edu/view/iuc/package_samtools_0_1_19 +* http://testtoolshed.g2.bx.psu.edu/view/iuc/package_r_3_0_1 +* http://testtoolshed.g2.bx.psu.edu/view/iuc/msa_datatypes +* http://testtoolshed.g2.bx.psu.edu/view/iuc/package_infernal_1_1rc4 +* http://testtoolshed.g2.bx.psu.edu/view/rnateam/blockbuster +* http://testtoolshed.g2.bx.psu.edu/view/bgruening/package_eden_1_1 +* http://testtoolshed.g2.bx.psu.edu/view/iuc/package_mcl_12_135 diff -r 78b364f5d93e -r 70170338b4f7 repository_dependencies.xml --- a/repository_dependencies.xml Thu Feb 12 12:19:22 2015 -0500 +++ b/repository_dependencies.xml Sat Feb 14 09:28:35 2015 -0500 @@ -3,6 +3,6 @@ - +