From 62bdd2e1311c90036492c2d4917436a6b4bb2612 Mon Sep 17 00:00:00 2001 From: John Chilton Date: Thu, 6 Jul 2017 23:41:52 -0400 Subject: [PATCH] Enhance cwltoil to support SoftwareRequirements & BioContainers. This commit enables all the same options in cwltoil as added to cwltool recently in https://github.com/common-workflow-language/cwltool/pull/214 including `` --beta-conda-dependencies``, ``--beta-dependency-resolvers-configuration``, and ``--beta-use-biocontainers``. The first two of these are documented in depth in cwltool's README now (https://github.com/common-workflow-language/cwltool/#leveraging-softwarerequirements-beta). Here I will quickly review a couple of the available options against test examples available in cwltool's ``tests`` directory. I will assume cwltoil has been setup as configure in this branch and galaxy-lib installed in the same environment - for instance with ``pip install galaxy-lib``. Now lets grab the examples from cwltool... ``` git clone https://github.com/common-workflow-language/cwltool.git cd cwltool ``` From here we can quickly demonstrate installation and resolution of SoftwareRequirements using Conda using the tests/seqtk_seq.cwl tool. This tool doesn't define a DockerRequirement but does define the following SoftwareRequirements as ``hints`` as follows: ``` hints: SoftwareRequirement: packages: - package: seqtk version: - r93 ``` We can try this tool out with cwltoil and see that by default we probably don't have the binary seqtk on our ``PATH`` and so the tool fails using the following command: ``` cwltoil tests/seqtk_seq.cwl tests/seqtk_seq_job.json ``` This should result in a tool execution failure. We can then instruct cwltoil to install the required package from Bioconda into an isolated environment and use it as needed by passing it the ``--beta-conda-dependencies`` flag as follows: ``` cwltoil --beta-conda-dependencies tests/seqtk_seq.cwl tests/seqtk_seq_job.json ``` The tool should now be successful. The Conda support can be endless tweaked but the defaults are defaults that target the best practice Conda channels that work well for the Galaxy project. Additional SoftwareRequirement resolution options are available including targetting Software Modules, Homebrew, simple scripts called "Galaxy packages". All of these options can be specified and configured with a YAML file passed to cwltoil using the ``--beta-dependency-resolvers-configuration`` option instead of the simple shortcut ``--beta-conda-dependencies``. The cwltool documentation walks through a few examples of adapting infrastructure to tools and tools to package managers. In addition to options that allow configuring tool execution environments, containers themselves can be discovered and/or built from these software requirements. The [Biocontainers](https://github.com/BioContainers) project (previously Biodocker) contains a registry we use for this purpose. Every version of every Bioconda package has a corresponding best-practice (very lightweight, very small) Docker container on quay.io. There are over 2300 such containers currently. Continuing with the example above, the new `--beta-use-biocontainers` flag instructs cwltoil to fetch the corresponding Biocontainers container from quay.io automatically or build one to use locally (required for instance for tools with multiple software requirements - fat tools). ``` cwltoil --beta-use-biocontainers tests/seqtk_seq.cwl tests/seqtk_seq_job.json ``` These containers contain the same binaries that the package would use locally (outside of Docker). Therefore this technique allows cross platform reproducibility/remixability across cwltool, cwltoil, Galaxy, and CLI - both inside and outside of containers. --- setup.py | 5 +++-- src/toil/cwl/cwltoil.py | 37 +++++++++++++++++++++++++++++++++++-- 2 files changed, 38 insertions(+), 4 deletions(-) diff --git a/setup.py b/setup.py index 68363b797f..4a84238e46 100644 --- a/setup.py +++ b/setup.py @@ -50,8 +50,9 @@ def runSetup(): 'gcs_oauth2_boto_plugin==1.9', botoRequirement], 'cwl': [ - 'cwltool==1.0.20170413194156', - 'schema-salad==2.5.20170328195758', + 'cwltool==1.0.20170713144155', + 'schema-salad==2.6.20170630075932', + 'galaxy-lib==17.9.3', 'cwltest>=1.0.20170214185319']}, package_dir={'': 'src'}, packages=find_packages(where='src', diff --git a/src/toil/cwl/cwltoil.py b/src/toil/cwl/cwltoil.py index 2b13c1363d..712459acb1 100755 --- a/src/toil/cwl/cwltoil.py +++ b/src/toil/cwl/cwltoil.py @@ -31,6 +31,7 @@ import cwltool.stdfsaccess from cwltool.pathmapper import adjustFiles from cwltool.process import shortname, adjustFilesWithSecondary, fillInDefaults, compute_checksums +from cwltool.software_requirements import DependenciesConfiguration, get_container_from_software_requirements from cwltool.utils import aslist import schema_salad.validate as validate import schema_salad.ref_resolver @@ -657,6 +658,14 @@ def main(args=None, stdout=sys.stdout): metavar=("VAR1 VAR2"), default=("PATH",), dest="preserve_environment") + # help="Dependency resolver configuration file describing how to adapt 'SoftwareRequirement' packages to current system." + parser.add_argument("--beta-dependency-resolvers-configuration", default=None) + # help="Defaut root directory used by dependency resolvers configuration." + parser.add_argument("--beta-dependencies-directory", default=None) + # help="Use biocontainers for tools without an explicitly annotated Docker container." + parser.add_argument("--beta-use-biocontainers", default=None, action="store_true") + # help="Short cut to use Conda to resolve 'SoftwareRequirement' packages." + parser.add_argument("--beta-conda-dependencies", default=None, action="store_true") # mkdtemp actually creates the directory, but # toil requires that the directory not exist, @@ -677,9 +686,22 @@ def main(args=None, stdout=sys.stdout): cwllogger.setLevel(options.logLevel) useStrict = not options.not_strict + + conf_file = getattr(options, "beta_dependency_resolvers_configuration", None) # Text + use_conda_dependencies = getattr(options, "beta_conda_dependencies", None) # Text + + make_tool_kwds = {} + + if conf_file or use_conda_dependencies: + dependencies_configuration = DependenciesConfiguration(options) # type: DependenciesConfiguration + make_tool_kwds["job_script_provider"] = dependencies_configuration + + options.default_container = None + make_tool_kwds["find_default_container"] = functools.partial(find_default_container, options) + try: t = cwltool.load_tool.load_tool(options.cwltool, cwltool.workflow.defaultMakeTool, - resolver=cwltool.resolver.tool_resolver, strict=useStrict) + resolver=cwltool.resolver.tool_resolver, strict=useStrict, kwargs=make_tool_kwds) unsupportedRequirementsCheck(t.requirements) except cwltool.process.UnsupportedRequirement as e: logging.error(e) @@ -740,7 +762,8 @@ def importDefault(tool): outobj = toil.restart() else: basedir = os.path.dirname(os.path.abspath(options.cwljob or options.cwltool)) - builder = t._init_job(job, basedir=basedir, use_container=use_container) + builder = t._init_job(job, basedir=basedir, use_container=use_container, + job_script_provider=make_tool_kwds.get("job_script_provider", None)) (wf1, wf2) = makeJob(t, {}, use_container=use_container, preserve_environment=options.preserve_environment, tmpdir=os.path.realpath(outdir), builder=builder) @@ -775,3 +798,13 @@ def importDefault(tool): stdout.write(json.dumps(outobj, indent=4)) return 0 + + +def find_default_container(args, builder): + default_container = None + if args.default_container: + default_container = args.default_container + elif args.beta_use_biocontainers: + default_container = get_container_from_software_requirements(args, builder) + + return default_container