#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import bioblend
import bioblend.galaxy.objects
import argparse
import os
import logging
import sys
import json
import time
from bioblend.galaxy.objects import GalaxyInstance
from bioblend import galaxy
import utilities
import speciesData
"""
gga_init.py
Usage: $ python3 gga_init.py -i input_example.yml --config [config file] [OPTIONS]
"""
class RunWorkflow(speciesData.SpeciesData):
"""
Run a workflow into the galaxy instance's history of a given species
This script is made to work for a Phaeoexplorer-specific workflow, but can be adapted to run any workflow,
provided the user creates their own workflow in a .ga format, and change the set_parameters function
to have the correct parameters for their workflow
"""
def set_get_history(self):
"""
Create or set the working history to the current species one
:return:
"""
try:
histories = self.instance.histories.get_histories(name=str(self.full_name))
self.history_id = histories[0]["id"]
except IndexError:
logging.info("Creating history for %s" % self.full_name)
self.instance.histories.create_history(name=str(self.full_name))
histories = self.instance.histories.get_histories(name=str(self.full_name))
self.history_id = histories[0]["id"]
return self.history_id
def get_instance_attributes(self):
"""
retrieves instance attributes:
- working history ID
- libraries ID (there should only be one library!)
- datasets IDs
:return:
"""
self.set_get_history()
logging.debug("History ID: %s" % self.history_id)
libraries = self.instance.libraries.get_libraries() # normally only one library
library_id = self.instance.libraries.get_libraries()[0]["id"] # project data folder/library
logging.debug("Library ID: %s" % self.library_id)
instance_source_data_folders = self.instance.libraries.get_folders(library_id=library_id)
# Access folders via their absolute path
genome_folder = self.instance.libraries.get_folders(library_id=library_id, name="/genome/" + str(self.species_folder_name) + "/v" + str(self.genome_version))
annotation_folder = self.instance.libraries.get_folders(library_id=library_id, name="/annotation/" + str(self.species_folder_name) + "/OGS" + str(self.ogs_version))
# Get their IDs
genome_folder_id = genome_folder[0]["id"]
annotation_folder_id = annotation_folder[0]["id"]
# Get the content of the folders
genome_folder_content = self.instance.folders.show_folder(folder_id=genome_folder_id, contents=True)
annotation_folder_content = self.instance.folders.show_folder(folder_id=annotation_folder_id, contents=True)
# Find genome folder datasets
genome_fasta_ldda_id = genome_folder_content["folder_contents"][0]["ldda_id"]
annotation_gff_ldda_id, annotation_proteins_ldda_id, annotation_transcripts_ldda_id = None, None, None
# Several dicts in the annotation folder content (one dict = one file)
for k, v in annotation_folder_content.items():
if k == "folder_contents":
for d in v:
if "proteins" in d["name"]:
annotation_proteins_ldda_id = d["ldda_id"]
if "transcripts" in d["name"]:
annotation_transcripts_ldda_id = d["ldda_id"]
if ".gff" in d["name"]:
annotation_gff_ldda_id = d["ldda_id"]
# Minimum datasets to populate tripal views --> will not work if these files are not assigned in the input file
self.datasets["genome_file"] = genome_fasta_ldda_id
self.datasets["gff_file"] = annotation_gff_ldda_id
self.datasets["proteins_file"] = annotation_proteins_ldda_id
self.datasets["transcripts_file"] = annotation_transcripts_ldda_id
return {"history_id": self.history_id, "library_id": library_id, "datasets": self.datasets}
def connect_to_instance(self):
"""
Test the connection to the galaxy instance for the current organism
Exit if we cannot connect to the instance
"""
self.instance = galaxy.GalaxyInstance(url=self.instance_url,
email=self.config["galaxy_default_admin_email"],
password=self.config["galaxy_default_admin_password"]
)
logging.info("Connecting to the galaxy instance %s" % self.instance_url)
try:
self.instance.histories.get_histories()
except bioblend.ConnectionError:
logging.critical("Cannot connect to galaxy instance %s" % self.instance_url)
sys.exit()
else:
logging.info("Successfully connected to galaxy instance %s" % self.instance_url)
return 1
def install_changesets_revisions_from_workflow(self, workflow_path):
"""
Read a .ga file to extract the information about the different tools called.
Check if every tool is installed via a "show_tool".
If a tool is not installed (versions don't match), send a warning to the logger and install the required changeset (matching the tool version)
Doesn't do anything if versions match
:return:
"""
logging.info("Validating that installed tools versions and changesets match workflow versions")
# Load the workflow file (.ga) in a buffer
with open(workflow_path, 'r') as ga_in_file:
# Then store the decoded json dictionary
workflow_dict = json.load(ga_in_file)
# Look up every "step_id" looking for tools
for k, v in workflow_dict["steps"].items():
if v["tool_id"]:
# Get the descriptive dictionary of the installed tool (using the tool id in the workflow)
show_tool = self.instance.tools.show_tool(v["tool_id"])
# Check if an installed version matches the workflow tool version
# (If it's not installed, the show_tool version returned will be a default version with the suffix "XXXX+0")
if show_tool["version"] != v["tool_version"]:
# If it doesn't match, proceed to install of the correct changeset revision
logging.warning("Tool versions don't match for {0} (changeset installed: {1} | changeset required: {2}). Installing changeset revision {3}...".format(v["tool_shed_repository"]["name"], show_tool["changeset_revision"], v["tool_shed_repository"]["changeset_revision"], v["tool_shed_repository"]["changeset_revision"]))
toolshed = "https://" + v["tool_shed_repository"]["tool_shed"]
name = v["tool_shed_repository"]["name"]
owner = v["tool_shed_repository"]["owner"]
changeset_revision = v["tool_shed_repository"]["changeset_revision"]
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
install_tool_dependencies=True,
install_repository_dependencies=False,
install_resolver_dependencies=True)
logging.info("Tools versions and changesets from workflow validated")
def install_changesets_revisions_for_individual_tools(self):
"""
This function is used to verify that installed tools called outside workflows have the correct versions and changesets
If it finds versions don't match, will install the correct version + changeset in the instance
Doesn't do anything if versions match
:return:
"""
self.connect_to_instance()
logging.info("Validating installed individual tools versions and changesets")
# Verify that the add_organism and add_analysis versions are correct in the toolshed
add_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/2.3.3")
add_analysis_tool= self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/2.3.3")
# print(add_organism_tool)
# print(add_analysis_tool)
get_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3")
get_analysis_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3")
# print(get_organism_tool)
# print(get_analysis_tool)
# changeset for 2.3.3 has to be manually found because there is no way to get the wanted changeset of a non installed tool via bioblend
# except for workflows (.ga) that already contain the changeset revisions inside the steps ids
if get_organism_tool["version"] != "2.3.3":
logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
changeset_revision = "b07279b5f3bf"
toolshed_dict = get_organism_tool["tool_shed_repository"]
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
install_tool_dependencies=True,
install_repository_dependencies=False,
install_resolver_dependencies=True)
if get_analysis_tool["version"] != "2.3.3":
logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
changeset_revision = "c7be2feafd73"
toolshed_dict = changeset_revision["tool_shed_repository"]
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
install_tool_dependencies=True,
install_repository_dependencies=False,
install_resolver_dependencies=True)
if add_organism_tool["version"] != "2.3.3":
logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
changeset_revision = "680a1fe3c266"
toolshed_dict = add_organism_tool["tool_shed_repository"]
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
install_tool_dependencies=True,
install_repository_dependencies=False,
install_resolver_dependencies=True)
if add_analysis_tool["version"] != "2.3.3":
logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
changeset_revision = "43c36801669f"
toolshed_dict = add_analysis_tool["tool_shed_repository"]
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
logging.warning("Installing changeset revision %s for add_analysis" % changeset_revision)
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
install_tool_dependencies=True,
install_repository_dependencies=False,
install_resolver_dependencies=True)
logging.info("Individual tools versions and changesets validated")
def add_organism_ogs_genome_analyses(self):
"""
Add OGS and genome vX analyses to Chado database
Required for Chado Load Tripal Synchronize workflow (which should be ran as the first workflow)
Called outside workflow for practical reasons (Chado add doesn't have an input link for analysis or organism)
:return:
"""
self.connect_to_instance()
self.set_get_history()
# We want the tools version default to be 2.3.3 at the moment
tool_version = "2.3.3"
# Add organism (species) to chado
logging.info("Adding organism to the instance's chado database")
if self.common == "" or self.common is None:
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.abbreviation})
else:
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.common})
# Add OGS analysis to chado
logging.info("Adding OGS analysis to the instance's chado database")
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"name": self.full_name_lowercase + " OGS" + self.ogs_version,
"program": "Performed by Genoscope",
"programversion": str(self.sex + " OGS" + self.ogs_version),
"sourcename": "Genoscope",
"date_executed": self.date})
# Add genome analysis to chado
logging.info("Adding genome analysis to the instance's chado database")
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"name": self.full_name_lowercase + " genome v" + self.genome_version,
"program": "Performed by Genoscope",
"programversion": str(self.sex + "genome v" + self.genome_version),
"sourcename": "Genoscope",
"date_executed": self.date})
# Get organism and analyses IDs (runtime inputs for workflow)
time.sleep(3)
# Get the ID for the current organism in chado
org = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.common})
time.sleep(3)
# Run tool again (sometimes the tool doesn't return anything despite the organism already being in the db)
org = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.common})
org_job_out = org["outputs"][0]["id"]
org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out)
try:
org_output = json.loads(org_json_output)[0]
self.org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
except IndexError:
logging.critical("No organism matching " + self.full_name + " exists in the instance's chado database")
sys.exit()
def get_genome_analysis_id(self):
"""
"""
# Get the ID for the genome analysis in chado
genome_analysis = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3",
history_id=self.history_id,
tool_inputs={"name": self.full_name_lowercase + " genome v" + self.genome_version})
genome_analysis_job_out = genome_analysis["outputs"][0]["id"]
genome_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=genome_analysis_job_out)
try:
genome_analysis_output = json.loads(genome_analysis_json_output)[0]
self.genome_analysis_id = str(genome_analysis_output["analysis_id"])
except IndexError as exc:
logging.critical("no matching genome analysis exists in the instance's chado database")
sys.exit(exc)
return self.genome_analysis_id
def get_ogs_analysis_id(self):
"""
"""
# Get the ID for the OGS analysis in chado
ogs_analysis = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3",
history_id=self.history_id,
tool_inputs={"name": self.full_name_lowercase + " OGS" + self.ogs_version})
ogs_analysis_job_out = ogs_analysis["outputs"][0]["id"]
ogs_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=ogs_analysis_job_out)
try:
ogs_analysis_output = json.loads(ogs_analysis_json_output)[0]
self.ogs_analysis_id = str(ogs_analysis_output["analysis_id"])
except IndexError as exc:
logging.critical("No matching OGS analysis exists in the instance's chado database")
sys.exit(exc)
return self.ogs_analysis_id
def add_interproscan_analysis(self):
"""
"""
# Add Interpro analysis to chado
logging.info("Adding Interproscan analysis to the instance's chado database")
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/2.3.3",
history_id=self.history_id,
tool_inputs={"name": "InterproScan on OGS%s" % self.ogs_version,
"program": "InterproScan",
"programversion": "OGS%s" % self.ogs_version,
"sourcename": "Genoscope",
"date_executed": self.date})
def get_interpro_analysis_id(self):
"""
"""
# Get interpro ID
interpro_analysis = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3",
history_id=self.history_id,
tool_inputs={"name": "InterproScan on OGS%s" % self.ogs_version})
interpro_analysis_job_out = interpro_analysis["outputs"][0]["id"]
interpro_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=interpro_analysis_job_out)
try:
interpro_analysis_output = json.loads(interpro_analysis_json_output)[0]
self.interpro_analysis_id = str(interpro_analysis_output["analysis_id"])
except IndexError as exc:
logging.critical("No matching InterproScan analysis exists in the instance's chado database")
sys.exit(exc)
return self.interpro_analysis_id
def add_blastp_diamond_analysis(self):
"""
"""
# Add Blastp (diamond) analysis to chado
logging.info("Adding Blastp Diamond analysis to the instance's chado database")
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/2.3.3",
history_id=self.history_id,
tool_inputs={"name": "Diamond on OGS%s" % self.ogs_version,
"program": "Diamond",
"programversion": "OGS%s" % self.ogs_version,
"sourcename": "Genoscope",
"date_executed": self.date})
def get_blastp_diamond_analysis_id(self):
"""
"""
# Get blasp ID
blast_diamond_analysis = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3",
history_id=self.history_id,
tool_inputs={"name": "Diamond on OGS%s" % self.ogs_version})
blast_diamond_analysis_job_out = blast_diamond_analysis["outputs"][0]["id"]
blast_diamond_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=blast_diamond_analysis_job_out)
try:
blast_diamond_analysis_output = json.loads(blast_diamond_analysis_json_output)[0]
self.blast_diamond_analysis_id = str(blast_diamond_analysis_output["analysis_id"])
except IndexErro as exc:
logging.critical("No matching InterproScan analysis exists in the instance's chado database")
sys.exit(exc)
return self.blast_diamond_analysis_id
def run_workflow(self, workflow_path, workflow_parameters, workflow_name, datamap):
"""
Run a workflow in galaxy
Requires the .ga file to be loaded as a dictionary (optionally could be uploaded as a raw file)
:param workflow_name:
:param workflow_parameters:
:param datamap:
:return:
"""
logging.info("Importing workflow %s" % str(workflow_path))
# Load the workflow file (.ga) in a buffer
with open(workflow_path, 'r') as ga_in_file:
# Then store the decoded json dictionary
workflow_dict = json.load(ga_in_file)
# In case of the Jbrowse workflow, we unfortunately have to manually edit the parameters instead of setting them
# as runtime values, using runtime parameters makes the tool throw an internal critical error ("replace not found" error)
if workflow_name == "Jbrowse":
workflow_dict["steps"]["2"]["tool_state"] = workflow_dict["steps"]["2"]["tool_state"].replace("__MENU_URL__", "https://{host}:{port}/sp/{genus_sp}/feature/{Genus}/{species}/{id}".format(host=self.config["host"], port=self.config["https_port"], genus_sp=self.genus_species, Genus=self.genus_uppercase, species=self.species, id="{id}"))
workflow_dict["steps"]["3"]["tool_state"] = workflow_dict["steps"]["3"]["tool_state"].replace("__FULL_NAME__", self.full_name).replace("__UNIQUE_ID__", self.abbreviation)
# Import the workflow in galaxy as a dict
self.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
# Get its attributes
workflow_attributes = self.instance.workflows.get_workflows(name=workflow_name)
# Then get its ID (required to invoke the workflow)
workflow_id = workflow_attributes[0]["id"] # Index 0 is the most recently imported workflow (the one we want)
show_workflow = self.instance.workflows.show_workflow(workflow_id=workflow_id)
# Check if the workflow is found
try:
logging.debug("Workflow ID: %s" % workflow_id)
except bioblend.ConnectionError:
logging.warning("Error retrieving workflow attributes for workflow %s" % workflow_name)
# Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
self.instance.workflows.invoke_workflow(workflow_id=workflow_id,
history_id=self.history_id,
params=workflow_parameters,
inputs=datamap,
allow_tool_state_corrections=True)
logging.info("Successfully imported and invoked workflow {0}, check the galaxy instance ({1}) for the jobs state".format(workflow_name, self.instance_url))
def get_invocation_report(self, workflow_name):
"""
Debugging method for workflows
Simply logs and returns a report of the previous workflow invocation (execution of a workflow in
the instance via the API)
:param workflow_name:
:return:
"""
workflow_attributes = self.instance.workflows.get_workflows(name=workflow_name)
workflow_id = workflow_attributes[1]["id"] # Most recently imported workflow (index 1 in the list)
invocations = self.instance.workflows.get_invocations(workflow_id=workflow_id)
invocation_id = invocations[1]["id"] # Most recent invocation
invocation_report = self.instance.invocations.get_invocation_report(invocation_id=invocation_id)
logging.debug(invocation_report)
return invocation_report
def import_datasets_into_history(self):
"""
Find datasets in a library, get their ID and import them into the current history if they are not already
:return:
"""
# Instanciate the instance
gio = GalaxyInstance(url=self.instance_url,
email=self.config["galaxy_default_admin_email"],
password=self.config["galaxy_default_admin_password"])
prj_lib = gio.libraries.get_previews(name="Project Data")
library_id = prj_lib[0].id
instance_source_data_folders = self.instance.libraries.get_folders(library_id=str(library_id))
folders_ids = {}
current_folder_name = ""
# Loop over the folders in the library and map folders names to their IDs
for i in instance_source_data_folders:
for k, v in i.items():
if k == "name":
folders_ids[v] = 0
current_folder_name = v
if k == "id":
folders_ids[current_folder_name] = v
history_datasets_li = self.instance.datasets.get_datasets()
genome_dataset_hda_id, gff_dataset_hda_id, transcripts_dataset_hda_id, proteins_datasets_hda_id = None, None, None, None
interproscan_dataset_hda_id, blast_diamond_dataset_hda_id = None, None
# Check for existing datasets for current organism (should have been run separately for mutliple organisms instances)
for dataset_dict in history_datasets_li[0:5]: # Limit of datasets is 6 atm
# Datasets imports should be ordered correctly
if dataset_dict["name"].endswith("proteins.fa"):
proteins_datasets_hda_id = dataset_dict["id"]
logging.debug("Proteins dataset hda ID: %s" % proteins_datasets_hda_id)
elif dataset_dict["name"].endswith("transcripts-gff.fa"):
transcripts_dataset_hda_id = dataset_dict["id"]
logging.debug("Transcripts dataset hda ID: %s" % transcripts_dataset_hda_id)
elif dataset_dict["name"].endswith(".gff"):
gff_dataset_hda_id = dataset_dict["id"]
logging.debug("gff dataset hda ID: %s" % gff_dataset_hda_id)
elif "Interpro" in dataset_dict["name"]:
interproscan_dataset_hda_id = dataset_dict["id"]
logging.debug("InterproScan dataset hda ID: %s" % gff_dataset_hda_id)
elif "diamond-blastp" in dataset_dict["name"]:
blast_diamond_dataset_hda_id = dataset_dict["id"]
logging.debug("Blast Diamond dataset hda ID: %s" % gff_dataset_hda_id)
else:
genome_dataset_hda_id = dataset_dict["id"]
logging.debug("Genome dataset hda id: %s" % genome_dataset_hda_id)
# Iterating over the folders to find datasets and map datasets to their IDs
logging.debug("Datasets IDs: ")
for k, v in folders_ids.items():
if k == "/genome":
sub_folder_content = self.instance.folders.show_folder(folder_id=v, contents=True)
final_sub_folder_content = self.instance.folders.show_folder(folder_id=sub_folder_content["folder_contents"][0]["id"], contents=True)
for k2, v2 in final_sub_folder_content.items():
for e in v2:
if type(e) == dict:
if e["name"].endswith(".fa"):
self.datasets["genome_file"] = e["ldda_id"]
logging.debug("Genome file:\t" + e["name"] + ": " + e["ldda_id"])
if k == "/annotation":
sub_folder_content = self.instance.folders.show_folder(folder_id=v, contents=True)
final_sub_folder_content = self.instance.folders.show_folder(folder_id=sub_folder_content["folder_contents"][0]["id"], contents=True)
for k2, v2 in final_sub_folder_content.items():
for e in v2:
if type(e) == dict:
if "transcripts" in e["name"]:
self.datasets["transcripts_file"] = e["ldda_id"]
logging.debug("Transcripts file:\t" + e["name"] + ": " + e["ldda_id"])
elif "proteins.fa" in e["name"]:
self.datasets["proteins_file"] = e["ldda_id"]
logging.debug("Proteins file:\t" + e["name"] + ": " + e["ldda_id"])
elif "gff" in e["name"]:
self.datasets["gff_file"] = e["ldda_id"]
logging.debug("GFF file:\t" + e["name"] + ": " + e["ldda_id"])
elif "Interpro" in e["name"]:
self.datasets["interproscan_file"] = e["ldda_id"]
logging.debug("Interproscan file:\t" + e["name"] + ": " + e["ldda_id"])
elif "diamond-blastp" in e["name"]:
self.datasets["blast_diamond_file"] = e["ldda_id"]
logging.debug("Blastp diamond file:\t" + e["name"] + ": " + e["ldda_id"])
logging.info("Uploading datasets into history %s" % self.history_id)
if genome_dataset_hda_id is None:
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["genome_file"])
if gff_dataset_hda_id is None:
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["gff_file"])
if transcripts_dataset_hda_id is None:
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["transcripts_file"])
if proteins_datasets_hda_id is None:
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["proteins_file"])
if interproscan_dataset_hda_id is None:
try:
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["interproscan_file"])
except Exception as exc:
logging.debug("Interproscan file not found in library (history: {0})\n{1}".format(self.history_id, exc))
if blast_diamond_dataset_hda_id is None:
try:
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["blast_diamond_file"])
except Exception as exc:
logging.debug("Blastp file not found in library (history: {0})\n{1}".format(self.history_id, exc))
_datasets = self.instance.datasets.get_datasets()
with open(os.path.join(self.main_dir, "datasets_ids.json"), "w") as datasets_ids_outfile:
datasets_ids_outfile.write(str(_datasets))
return {"history_id": self.history_id, "library_id": library_id, "datasets": self.datasets}
def get_datasets_hda_ids(self):
"""
Get the hda IDs of the datasets imported into an history
The most "recent" imports will be prioritized
As some tools will not work using the input datasets ldda IDs we need to retrieve the datasets IDs imported
into an history
:return:
"""
# List of all datasets in the instance (including outputs from jobs)
# "limit" and "offset" options *may* be used to restrict search to specific datasets but since
# there is no way to know which imported datasets are the correct ones depending on history content
# it's not currently used
history_datasets_li = self.instance.datasets.get_datasets()
genome_dataset_hda_id, gff_dataset_hda_id, transcripts_dataset_hda_id, proteins_datasets_hda_id = None, None, None, None
interproscan_dataset_hda_id, blast_diamond_dataset_hda_id = None, None
genome_dataset_hda_id = history_datasets_li[3]["id"]
gff_dataset_hda_id = history_datasets_li[2]["id"]
transcripts_dataset_hda_id = history_datasets_li[1]["id"]
proteins_datasets_hda_id = history_datasets_li[0]["id"]
for dataset_dict in history_datasets_li[0:5]:
# Datasets imports should be the last jobs in history if the function calls are in correct order
# If not, add the function call "get_datasets_hda_ids()" just after "import_datasets_into_history()"
if dataset_dict["name"].endswith("proteins.fa"):
proteins_datasets_hda_id = dataset_dict["id"]
logging.debug("Proteins dataset hda ID: %s" % proteins_datasets_hda_id)
elif dataset_dict["name"].endswith("transcripts-gff.fa"):
transcripts_dataset_hda_id = dataset_dict["id"]
logging.debug("Transcripts dataset hda ID: %s" % transcripts_dataset_hda_id)
elif dataset_dict["name"].endswith(".gff"):
gff_dataset_hda_id = dataset_dict["id"]
logging.debug("gff dataset hda ID: %s" % gff_dataset_hda_id)
elif "Interpro" in dataset_dict["name"]:
interproscan_dataset_hda_id = dataset_dict["id"]
logging.debug("InterproScan dataset hda ID: %s" % gff_dataset_hda_id)
elif "diamond-blastp" in dataset_dict["name"]:
blast_diamond_dataset_hda_id = dataset_dict["id"]
logging.debug("Blast Diamond dataset hda ID: %s" % gff_dataset_hda_id)
else:
genome_dataset_hda_id = dataset_dict["id"]
logging.debug("Genome dataset hda id: %s" % genome_dataset_hda_id)
# Return a dict made of the hda ids
return{"genome_hda_id": genome_dataset_hda_id, "transcripts_hda_id": transcripts_dataset_hda_id,
"proteins_hda_id": proteins_datasets_hda_id, "gff_hda_id": gff_dataset_hda_id,
"interproscan_hda_id": interproscan_dataset_hda_id, "blast_diamond_hda_id": blast_diamond_dataset_hda_id}
def get_organism_id(self):
"""
Retrieve current organism ID
Will try to add it to Chado if the organism ID can't be found
:return:
"""
time.sleep(3)
# Get the ID for the current organism in chado
org = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3",
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.common})
time.sleep(3)
# Run tool again (sometimes the tool doesn't return anything despite the organism already being in the db)
org = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3",
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.common})
org_job_out = org["outputs"][0]["id"]
org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out)
try:
org_output = json.loads(org_json_output)[0]
self.org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
except IndexError:
logging.warning("No organism matching " + self.full_name + " exists in the instance's chado database, adding it")
if self.common == "" or self.common is None:
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.abbreviation})
else:
self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/%s" % tool_version,
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.common})
# Run tool again (sometimes the tool doesn't return anything despite the organism already being in the db)
org = self.instance.tools.run_tool(
tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3",
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
"species": self.chado_species_name,
"common": self.common})
org_job_out = org["outputs"][0]["id"]
org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out)
try:
org_output = json.loads(org_json_output)[0]
self.org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
except IndexError:
logging.critical("Cannot add {0} as an organism in Chado, please check the galaxy instance {1}".format(self.full_name, self.instance_url))
sys.exit()
return self.org_id
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Automatic data loading in containers and interaction "
"with galaxy instances for GGA"
", following the protocol @ "
"http://gitlab.sb-roscoff.fr/abims/e-infra/gga")
parser.add_argument("input",
type=str,
help="Input file (yml)")
parser.add_argument("-v", "--verbose",
help="Increase output verbosity",
action="store_true")
parser.add_argument("--config",
type=str,
help="Config path, default to the 'config' file inside the script repository")
parser.add_argument("--main-directory",
type=str,
help="Where the stack containers will be located, defaults to working directory")
parser.add_argument("--workflow", "-w",
type=str,
help="Worfklow to run")
args = parser.parse_args()
if args.verbose:
logging.basicConfig(level=logging.DEBUG)
else:
logging.basicConfig(level=logging.INFO)
logging.getLogger("urllib3").setLevel(logging.INFO)
logging.getLogger("bioblend").setLevel(logging.INFO)
# Parsing the config file if provided, using the default config otherwise
if not args.config:
args.config = os.path.join(os.path.dirname(os.path.realpath(sys.argv[0])), "config")
else:
args.config = os.path.abspath(args.config)
if not args.main_directory:
args.main_directory = os.getcwd()
else:
args.main_directory = os.path.abspath(args.main_directory)
sp_dict_list = utilities.parse_input(args.input)
for sp_dict in sp_dict_list:
# Creating an instance of the RunWorkflow object for the current organism
run_workflow_for_current_organism = RunWorkflow(parameters_dictionary=sp_dict)
# Checking if user specified a workflow to run
if not args.workflow:
logging.critical("No workflow specified, exiting")
sys.exit()
else:
workflow = os.path.abspath(args.workflow)
# Verifying the galaxy container is running
if utilities.check_galaxy_state(genus_lowercase=run_workflow_for_current_organism.genus_lowercase,
species=run_workflow_for_current_organism.species,
script_dir=run_workflow_for_current_organism.script_dir):
# Starting
logging.info("run_workflow.py called for %s" % run_workflow_for_current_organism.full_name)
# Setting some of the instance attributes
run_workflow_for_current_organism.main_dir = args.main_directory
run_workflow_for_current_organism.species_dir = os.path.join(run_workflow_for_current_organism.main_dir,
run_workflow_for_current_organism.genus_species +
"/")
# Parse the config yaml file
run_workflow_for_current_organism.config = utilities.parse_config(args.config)
# Set the instance url attribute
run_workflow_for_current_organism.instance_url = "http://localhost:{0}/sp/{1}_{2}/galaxy/".format(
run_workflow_for_current_organism.config["http_port"]
run_workflow_for_current_organism.genus_lowercase,
run_workflow_for_current_organism.species)
# If input workflow is Chado_load_Tripal_synchronize.ga
if "Chado_load_Tripal_synchronize" in str(workflow):
logging.info("Executing workflow 'Chado_load_Tripal_synchronize'")
run_workflow_for_current_organism.connect_to_instance()
run_workflow_for_current_organism.set_get_history()
# run_workflow_for_current_organism.get_species_history_id()
run_workflow_for_current_organism.install_changesets_revisions_for_individual_tools()
run_workflow_for_current_organism.install_changesets_revisions_from_workflow(workflow_path=workflow)
run_workflow_for_current_organism.add_organism_ogs_genome_analyses()
run_workflow_for_current_organism.get_organism_id()
run_workflow_for_current_organism.get_genome_analysis_id()
run_workflow_for_current_organism.get_ogs_analysis_id()
# Get the attributes of the instance and project data files
run_workflow_for_current_organism.get_instance_attributes()
# Import datasets into history and retrieve their hda IDs
run_workflow_for_current_organism.import_datasets_into_history()
hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
# DEBUG
# run_workflow_for_current_organism.get_invocation_report(workflow_name="Chado load Tripal synchronize")
# Explicit workflow parameter names
GENOME_FASTA_FILE = "0"
GFF_FILE = "1"
PROTEINS_FASTA_FILE = "2"
TRANSCRIPTS_FASTA_FILE = "3"
LOAD_FASTA_IN_CHADO = "4"
LOAD_GFF_IN_CHADO = "5"
SYNC_ORGANISM_INTO_TRIPAL = "6"
SYNC_GENOME_ANALYSIS_INTO_TRIPAL = "7"
SYNC_OGS_ANALYSIS_INTO_TRIPAL = "8"
SYNC_FEATURES_INTO_TRIPAL = "9"
workflow_parameters = {}
workflow_parameters[GENOME_FASTA_FILE] = {}
workflow_parameters[GFF_FILE] = {}
workflow_parameters[PROTEINS_FASTA_FILE] = {}
workflow_parameters[TRANSCRIPTS_FASTA_FILE] = {}
workflow_parameters[LOAD_FASTA_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
"analysis_id": run_workflow_for_current_organism.genome_analysis_id,
"do_update": "true"}
# Change "do_update": "true" to "do_update": "false" in above parameters to prevent appending/updates to the fasta file in chado
# WARNING: It is safer to never update it and just change the genome/ogs versions in the config
workflow_parameters[LOAD_GFF_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
"analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
workflow_parameters[SYNC_ORGANISM_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
workflow_parameters[SYNC_GENOME_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
workflow_parameters[SYNC_OGS_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.genome_analysis_id}
workflow_parameters[SYNC_FEATURES_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
# Datamap for input datasets - dataset source (type): ldda (LibraryDatasetDatasetAssociation)
run_workflow_for_current_organism.datamap = {}
run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE] = {"src": "hda", "id": hda_ids["genome_hda_id"]}
run_workflow_for_current_organism.datamap[GFF_FILE] = {"src": "hda", "id": hda_ids["gff_hda_id"]}
run_workflow_for_current_organism.datamap[PROTEINS_FASTA_FILE] = {"src": "hda", "id": hda_ids["proteins_hda_id"]}
run_workflow_for_current_organism.datamap[TRANSCRIPTS_FASTA_FILE] = {"src": "hda", "id": hda_ids["transcripts_hda_id"]}
# run_workflow_for_current_organism.datamap = {}
# run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE] = {"src": "hda", "id":
# run_workflow_for_current_organism.datasets["genome_file"]}
# run_workflow_for_current_organism.datamap[GFF_FILE] = {"src": "hda",
# "id": hda_ids["gff_hda_id"]}
# Run the Chado load Tripal sync workflow with the parameters set above
run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
workflow_parameters=workflow_parameters,
datamap=run_workflow_for_current_organism.datamap,
workflow_name="Chado load Tripal synchronize")
# Jbrowse creation workflow
elif "Jbrowse" in str(workflow):
logging.info("Executing workflow 'Jbrowse'")
run_workflow_for_current_organism.connect_to_instance()
run_workflow_for_current_organism.set_get_history()
run_workflow_for_current_organism.install_changesets_revisions_from_workflow(workflow_path=workflow)
run_workflow_for_current_organism.get_organism_id()
# Import datasets into history and get their hda IDs
run_workflow_for_current_organism.import_datasets_into_history()
hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids() # Note: only call this function AFTER calling "import_datasets_into_history()"
# Debugging
# run_workflow_for_current_organism.get_invocation_report(workflow_name="Jbrowse")
GENOME_FASTA_FILE = "0"
GFF_FILE = "1"
ADD_JBROWSE = "2"
ADD_ORGANISM_TO_JBROWSE = "3"
workflow_parameters = {}
workflow_parameters[GENOME_FASTA_FILE] = {}
workflow_parameters[GFF_FILE] = {}
workflow_parameters[ADD_JBROWSE] = {}
workflow_parameters[ADD_ORGANISM_TO_JBROWSE] = {}
run_workflow_for_current_organism.datamap = {}
run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE] = {"src": "hda", "id": hda_ids["genome_hda_id"]}
run_workflow_for_current_organism.datamap[GFF_FILE] = {"src": "hda", "id": hda_ids["gff_hda_id"]}
# Run the jbrowse creation workflow
run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
workflow_parameters=workflow_parameters,
datamap=run_workflow_for_current_organism.datamap,
workflow_name="Jbrowse")
elif "Interpro" in str(workflow):
logging.info("Executing workflow 'Interproscan")
run_workflow_for_current_organism.connect_to_instance()
run_workflow_for_current_organism.set_get_history()
# run_workflow_for_current_organism.get_species_history_id()
# Get the attributes of the instance and project data files
run_workflow_for_current_organism.get_instance_attributes()
run_workflow.add_interproscan_analysis()
run_workflow_for_current_organism.get_interpro_analysis_id()
# Import datasets into history and retrieve their hda IDs
run_workflow_for_current_organism.import_datasets_into_history()
hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
INTERPRO_FILE = "0"
LOAD_INTERPRO_IN_CHADO = "1"
SYNC_INTERPRO_ANALYSIS_INTO_TRIPAL = "2"
SYNC_FEATURES_INTO_TRIPAL = "3"
POPULATE_MAT_VIEWS = "4"
INDEX_TRIPAL_DATA = "5"
workflow_parameters = {}
workflow_parameters[INTERPRO_FILE] = {}
workflow_parameters[LOAD_INTERPRO_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
"analysis_id": run_workflow_for_current_organism.interpro_analysis_id}
workflow_parameters[SYNC_INTERPRO_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.interpro_analysis_id}
run_workflow_for_current_organism.datamap = {}
run_workflow_for_current_organism.datamap[INTERPRO_FILE] = {"src": "hda", "id": run_workflow_for_current_organism.hda_ids["interproscan_hda_id"]}
# Run Interproscan workflow
run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
workflow_parameters=workflow_parameters,
datamap=run_workflow_for_current_organism.datamap,
workflow_name="Interproscan")
elif "Blast" in str(workflow):
logging.info("Executing workflow 'Blast_Diamond")
run_workflow_for_current_organism.connect_to_instance()
run_workflow_for_current_organism.set_get_history()
# run_workflow_for_current_organism.get_species_history_id()
# Get the attributes of the instance and project data files
run_workflow_for_current_organism.get_instance_attributes()
run_workflow_for_current_organism.add_blastp_diamond_analysis()
run_workflow_for_current_organism.get_blastp_diamond_analysis_id()
# Import datasets into history and retrieve their hda IDs
run_workflow_for_current_organism.import_datasets_into_history()
hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
BLAST_FILE = "0"
LOAD_BLAST_IN_CHADO = "1"
SYNC_BLAST_ANALYSIS_INTO_TRIPAL = "2"
SYNC_FEATURES_INTO_TRIPAL = "3"
POPULATE_MAT_VIEWS = "4"
INDEX_TRIPAL_DATA = "5"
workflow_parameters = {}
workflow_parameters[INTERPRO_FILE] = {}
workflow_parameters[LOAD_BLAST_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
"analysis_id": run_workflow_for_current_organism.blast_diamond_analysis_id}
workflow_parameters[SYNC_BLAST_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.blast_diamond_analysis_id}
run_workflow_for_current_organism.datamap = {}
run_workflow_for_current_organism.datamap[INTERPRO_FILE] = {"src": "hda", "id": hda_ids["interproscan_hda_id"]}
# Run Interproscan workflow
run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
workflow_parameters=workflow_parameters,
datamap=run_workflow_for_current_organism.datamap,
workflow_name="Interproscan")
else:
logging.critical("The galaxy container for %s is not ready yet!" % run_workflow_for_current_organism.full_name)
sys.exit()