From ca829bee8283713ac1125ecb9bd10efdefa0b354 Mon Sep 17 00:00:00 2001
From: Troubardours <arthur.lebars@gmail.com>
Date: Mon, 26 Jul 2021 17:10:36 +0200
Subject: [PATCH] New blast+interproscan branch (merging issues with
refactor_blast_interproscan_workflow)
---
constants_phaeo.py | 80 +-
gga_run_workflow_phaeo_blast_interpro.py | 1607 ++++-------------
...load_blast_interproscan_results_1org_v1.ga | 611 +++++++
...load_blast_interproscan_results_2org_v1.ga | 1063 +++++++++++
4 files changed, 2032 insertions(+), 1329 deletions(-)
create mode 100644 workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_1org_v1.ga
create mode 100644 workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_2org_v1.ga
diff --git a/constants_phaeo.py b/constants_phaeo.py
index 57d2bd5..74afc10 100644
--- a/constants_phaeo.py
+++ b/constants_phaeo.py
@@ -8,7 +8,8 @@ import constants
WORKFLOWS_PATH = "workflows_phaeoexplorer/"
-WF_LOAD_GFF_JB_1_ORG_FILE = "Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_1org_v7.ga"
+# Workflow to load the genome and annotations into chado, create/update organisms in a jbrowse instance
+WF_LOAD_GFF_JB_1_ORG_FILE = "Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_1org_v6.ga"
WF_LOAD_GFF_JB_1_ORG_INPUT_GENOME = "0"
WF_LOAD_GFF_JB_1_ORG_INPUT_GFF = "1"
WF_LOAD_GFF_JB_1_ORG_INPUT_PROTEINS = "2"
@@ -16,37 +17,64 @@ WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_FASTA = "3"
WF_LOAD_GFF_JB_1_ORG_STEP_JBROWSE = "4"
WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_GFF = "5"
WF_LOAD_GFF_JB_1_ORG_STEP_JB_TO_CONTAINER = "6"
-WF_LOAD_GFF_JB_1_ORG_STEP_SYNC_FEATURE = "7"
-WF_LOAD_GFF_JB_1_ORG_STEP_SYNC_ORG = "8"
-WF_LOAD_GFF_JB_1_ORG_STEP_SYNC_GENOME_ANALYSIS = "9"
-WF_LOAD_GFF_JB_1_ORG_STEP_SYNC_OGS_ANALYSIS = "10"
-WF_LOAD_GFF_JB_1_ORG_STEP_POPULATE_VIEWS = "11"
-WF_LOAD_GFF_JB_1_ORG_STEP_INDEX = "12"
+WF_LOAD_GFF_JB_1_ORG_STEP_FEATURE_SYNC = "7"
+WF_LOAD_GFF_JB_1_ORG_STEP_POPULATE_VIEWS = "8"
+WF_LOAD_GFF_JB_1_ORG_STEP_INDEX = "9"
-WF_LOAD_GFF_JB_2_ORG_FILE = "Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v7.ga"
-WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG1 = "4"
-WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG1 = "2"
-WF_LOAD_GFF_JB_2_ORG_INPUT_PROTEINS_ORG1 = "0"
-WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG2 = "1"
-WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG2 = "3"
+WF_LOAD_GFF_JB_2_ORG_FILE = "Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v6.ga"
+WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG1 = "0"
+WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG1 = "1"
+WF_LOAD_GFF_JB_2_ORG_INPUT_PROTEINS_ORG1 = "2"
+WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG2 = "3"
+WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG2 = "4"
WF_LOAD_GFF_JB_2_ORG_INPUT_PROTEINS_ORG2 = "5"
-WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_FASTA_ORG1 = "7"
-WF_LOAD_GFF_JB_2_ORG_STEP_JBROWSE_ORG1 = "8"
-WF_LOAD_GFF_JB_2_ORG_STEP_JBROWSE_ORG2 = "6"
+WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_FASTA_ORG1 = "6"
+WF_LOAD_GFF_JB_2_ORG_STEP_JBROWSE_ORG1 = "7"
+WF_LOAD_GFF_JB_2_ORG_STEP_JRBOWSE_ORG2 = "8"
WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_GFF_ORG1 = "9"
WF_LOAD_GFF_JB_2_ORG_STEP_JB_TO_CONTAINER = "10"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_FEATURE_ORG1 = "11"
+WF_LOAD_GFF_JB_2_ORG_STEP_FEATURE_SYNC_ORG1 = "11"
WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_FASTA_ORG2 = "12"
WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_GFF_ORG2 = "13"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_FEATURE_ORG2 = "14"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_ORG1 = "15"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_ORG2 = "16"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_GENOME_ANALYSIS_ORG1 = "17"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_OGS_ANALYSIS_ORG1 = "18"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_GENOME_ANALYSIS_ORG2 = "19"
-WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_OGS_ANALYSIS_ORG2 = "20"
-WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS = "21"
-WF_LOAD_GFF_JB_2_ORG_STEP_INDEX = "22"
+WF_LOAD_GFF_JB_2_ORG_STEP_FEATURE_SYNC_ORG2 = "14"
+WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS = "15"
+WF_LOAD_GFF_JB_2_ORG_STEP_INDEX = "16"
+
+# Workflow to load blastp, blastx and interproscan into chado and tripal
+WF_BLAST_INTERPRO_1_ORG_FILE = "Galaxy-Workflow-load_blast_interproscan_results_1org_v1.ga"
+WF_BLAST_INTERPRO_1_ORG_INPUT_BLASTP = "0"
+WF_BLAST_INTERPRO_1_ORG_INPUT_BLASTX = "1"
+WF_BLAST_INTERPRO_1_ORG_INPUT_INTERPRO = "2"
+WF_BLAST_INTERPRO_1_ORG_LOAD_BLASTP = "3"
+WF_BLAST_INTERPRO_1_ORG_LOAD_BLASTX = "4"
+WF_BLAST_INTERPRO_1_ORG_LOAD_INTERPRO = "5"
+WF_BLAST_INTERPRO_1_ORG_POPULATE_MAT_VIEWS = "6"
+WF_BLAST_INTERPRO_1_ORG_INDEX_TRIPAL_DATA = "7"
+WF_BLAST_INTERPRO_1_ORG_SYNC_BLASTP_ANALYSIS = "8"
+WF_BLAST_INTERPRO_1_ORG_SYNC_BLASTX_ANALYSIS = "9"
+WF_BLAST_INTERPRO_1_ORG_SYNC_INTERPRO_ANALYSIS = "10"
+
+WF_BLAST_INTERPRO_2_ORG_FILE = "Galaxy-Workflow-load_blast_interproscan_results_2org_v1.ga"
+WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTP_ORG1 = "0"
+WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTP_ORG2 = "1"
+WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTX_ORG1 = "2"
+WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTX_ORG2 = "3"
+WF_BLAST_INTERPRO_2_ORG_INPUT_INTERPRO_ORG1 = "4"
+WF_BLAST_INTERPRO_2_ORG_INPUT_INTERPRO_ORG2 = "5"
+WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTP_ORG1 = "6"
+WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTP_ORG2 = "7"
+WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTX_ORG1 = "8"
+WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTX_ORG2 = "9"
+WF_BLAST_INTERPRO_2_ORG_LOAD_INTERPRO_ORG1 = "10"
+WF_BLAST_INTERPRO_2_ORG_LOAD_INTERPRO_ORG2 = "11"
+WF_BLAST_INTERPRO_2_ORG_POPULATE_MAT_VIEWS = "12"
+WF_BLAST_INTERPRO_2_ORG_INDEX_TRIPAL_DATA = "13"
+WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTP_ANALYSIS_ORG1 = "14"
+WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTX_ANALYSIS_ORG1 = "15"
+WF_BLAST_INTERPRO_2_ORG_SYNC_INTERPRO_ANALYSIS_ORG1 = "16"
+WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTP_ANALYSIS_ORG2 = "17"
+WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTX_ANALYSIS_ORG2 = "18"
+WF_BLAST_INTERPRO_2_ORG_SYNC_INTERPRO_ANALYSIS_ORG2 = "19"
### Galaxy tools
diff --git a/gga_run_workflow_phaeo_blast_interpro.py b/gga_run_workflow_phaeo_blast_interpro.py
index 85a565b..30579fc 100644
--- a/gga_run_workflow_phaeo_blast_interpro.py
+++ b/gga_run_workflow_phaeo_blast_interpro.py
@@ -7,74 +7,42 @@ import os
import logging
import sys
import json
-import time
-
-from bioblend import galaxy
+from bioblend.galaxy.objects import GalaxyInstance
import utilities
import utilities_bioblend
-import species_data
import constants
import constants_phaeo
import gga_run_workflow_phaeo
-class OrgWorkflowParamJbrowse(gga_run_workflow_phaeo.OrgWorkflowParam):
-
- def __init__(self, genus_species, strain_sex, genus_uppercase, chado_species_name, full_name, species_folder_name,
- org_id, history_id, instance, genome_analysis_id=None, ogs_analysis_id=None, blastp_analysis_id=None, interpro_analysis_id=None,
- genome_hda_id=None, gff_hda_id=None, transcripts_hda_id=None, proteins_hda_id=None, blastp_hda_id=None, blastx_hda_id=None, interproscan_hda_id=None):
- self.genus_species = genus_species
- self.strain_sex = strain_sex
- self.genus_uppercase = genus_uppercase
- self.chado_species_name = chado_species_name,
- self.full_name = full_name
- self.species_folder_name = species_folder_name
- self.org_id = org_id
- self.genome_analysis_id = genome_analysis_id
- self.ogs_analysis_id = ogs_analysis_id
+class OrgWorkflowParamBlastInterproscan(gga_run_workflow_phaeo.OrgWorkflowParam):
+
+ def __init__(self, genus_uppercase, chado_species_name, full_name, species_folder_name, org_id, history_id,
+ instance, blastp_analysis_id=None, blastx_analysis_id=None, interpro_analysis_id=None,
+ blastp_hda_id=None, blastx_hda_id=None, interproscan_hda_id=None):
self.blastp_analysis_id = blastp_analysis_id
+ self.blastx_analysis_id = blastx_analysis_id
self.interpro_analysis_id = interpro_analysis_id
- self.history_id = history_id
- self.instance = instance
- self.genome_hda_id = genome_hda_id
- self.gff_hda_id = gff_hda_id
- self.transcripts_hda_id = transcripts_hda_id
- self.proteins_hda_id = proteins_hda_id
self.blastp_hda_id = blastp_hda_id
self.blastx_hda_id = blastx_hda_id
self.interproscan_hda_id = interproscan_hda_id
- super().__init__(genus_species, strain_sex, genus_uppercase, chado_species_name, full_name, species_folder_name,
- org_id, history_id, instance)
-
- def check_param_for_workflow_load_fasta_gff_jbrowse(self):
- params = [self.genus_species, self.strain_sex, self.genus_uppercase,
- self.chado_species_name, self.full_name,
- self.species_folder_name, self.org_id,
- self.history_id, self.instance,
- self.genome_analysis_id, self.ogs_analysis_id,
- self.genome_hda_id, self.gff_hda_id, self.transcripts_hda_id, self.proteins_hda_id]
- utilities_bioblend.check_wf_param(self.full_name, params)
-
- def check_param_for_workflow_blastp(self):
- params = [self.genus_species, self.strain_sex, self.genus_uppercase,
- self.chado_species_name, self.full_name,
- self.species_folder_name, self.org_id,
- self.history_id, self.instance,
+ super().__init__(genus_uppercase, chado_species_name, full_name, species_folder_name,
+ org_id, history_id, instance)
+
+ def check_param(self):
+ params = [self.genus_uppercase,
+ self.chado_species_name,
+ self.full_name,
+ self.species_folder_name,
+ self.org_id,
+ self.history_id,
+ self.instance,
self.blastp_analysis_id,
self.blastp_hda_id]
utilities_bioblend.check_wf_param(self.full_name, params)
- def check_param_for_workflow_interpro(self):
- params = [self.genus_species, self.strain_sex, self.genus_uppercase,
- self.chado_species_name, self.full_name,
- self.species_folder_name, self.org_id,
- self.history_id, self.instance,
- self.interpro_analysis_id,
- self.interproscan_hda_id]
- utilities_bioblend.check_wf_param(self.full_name, params)
-
-class RunWorkflow(species_data.SpeciesData):
+class RunWorkflowBlastInterpro(gga_run_workflow_phaeo.RunWorkflow):
"""
Run a workflow into the galaxy instance's history of a given species
@@ -89,29 +57,30 @@ class RunWorkflow(species_data.SpeciesData):
super().__init__(parameters_dictionary)
- self.chado_species_name = " ".join(utilities.filter_empty_not_empty_items(
- [self.species, self.strain, self.sex])["not_empty"])
+ self.chado_species_name = " ".join(utilities.filter_empty_not_empty_items([self.species,
+ self.strain,
+ self.sex])["not_empty"])
self.abbreviation = self.genus_uppercase[0] + ". " + self.chado_species_name
self.common = self.name
- if not self.common_name is None and self.common_name != "":
+ if self.common_name is not None and self.common_name != "":
self.common = self.common_name
self.history_name = str(self.genus_species)
- self.genome_analysis_name = "genome v{0} of {1}".format(self.genome_version, self.full_name)
- self.genome_analysis_programversion = "genome v{0}".format(self.genome_version)
- self.genome_analysis_sourcename = self.full_name
+ self.blastp_analysis_name = "Diamond blastp on OGS{0} of {1}".format(self.ogs_version, self.full_name)
+ self.blastp_analysis_programversion = "Diamond blastp on OGS{0}".format(self.ogs_version)
+ self.blastp_analysis_sourcename = self.full_name
+
+ self.blastx_analysis_name = "Diamond blastx on OGS{0} of {1}".format(self.ogs_version, self.full_name)
+ self.blastx_analysis_programversion = "Diamond blastx on OGS{0}".format(self.ogs_version)
+ self.blastx_analysis_sourcename = self.full_name
- self.ogs_analysis_name = "OGS{0} of {1}".format(self.ogs_version, self.full_name)
- self.ogs_analysis_programversion = "OGS{0}".format(self.ogs_version)
- self.ogs_analysis_sourcename = self.full_name
+ self.interpro_analysis_name = "InterProScan on OGS{0} of {1}".format(self.ogs_version, self.full_name)
+ self.interpro_analysis_programversion = "InterProScan on OGS{0}".format(self.ogs_version)
+ self.interpro_analysis_sourcename = self.full_name
- self.genome_hda_id = None
- self.gff_hda_id = None
- self.transcripts_hda_id = None
- self.proteins_hda_id = None
self.blastp_hda_id = None
self.blastx_hda_id = None
self.interproscan_hda_id = None
@@ -128,8 +97,9 @@ class RunWorkflow(species_data.SpeciesData):
logging.info("Validating installed individual tools versions and changesets")
# Verify that the add_organism and add_analysis versions are correct in the instance
- # changeset for 2.3.4+galaxy0 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
+ # changeset for 2.3.4+galaxy0 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
utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.GET_ORGANISMS_TOOL_ID,
version=constants_phaeo.GET_ORGANISMS_TOOL_VERSION,
@@ -141,11 +111,6 @@ class RunWorkflow(species_data.SpeciesData):
changeset_revision=constants_phaeo.GET_ANALYSES_TOOL_CHANGESET_REVISION,
instance=self.instance)
- utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.ADD_ORGANISM_TOOL_ID,
- version=constants_phaeo.ADD_ORGANISM_TOOL_VERSION,
- changeset_revision=constants_phaeo.ADD_ORGANISM_TOOL_CHANGESET_REVISION,
- instance=self.instance)
-
utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.ADD_ANALYSIS_TOOL_ID,
version=constants_phaeo.ADD_ANALYSIS_TOOL_VERSION,
changeset_revision=constants_phaeo.ADD_ANALYSIS_TOOL_CHANGESET_REVISION,
@@ -179,16 +144,54 @@ class RunWorkflow(species_data.SpeciesData):
return analysis_id
- def sync_analysis(self, analysis_id):
+ def install_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
- time.sleep(60)
- utilities_bioblend.run_tool(
- instance=self.instance,
- tool_id=constants_phaeo.ANALYSIS_SYNC_TOOL_ID,
- history_id=self.history_id,
- tool_inputs={"analysis_id": analysis_id})
+ :return:
+ """
+
+ logging.info("Validating installed individual tools versions and changesets")
+
+ # Verify that the add_organism and add_analysis versions are correct in the instance
+ # changeset for 2.3.4+galaxy0 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
+
+ utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.GET_ORGANISMS_TOOL_ID,
+ version=constants_phaeo.GET_ORGANISMS_TOOL_VERSION,
+ changeset_revision=constants_phaeo.GET_ORGANISMS_TOOL_CHANGESET_REVISION,
+ instance=self.instance)
+
+ utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.GET_ANALYSES_TOOL_ID,
+ version=constants_phaeo.GET_ANALYSES_TOOL_VERSION,
+ changeset_revision=constants_phaeo.GET_ANALYSES_TOOL_CHANGESET_REVISION,
+ instance=self.instance)
+
+ utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.ADD_ORGANISM_TOOL_ID,
+ version=constants_phaeo.ADD_ORGANISM_TOOL_VERSION,
+ changeset_revision=constants_phaeo.ADD_ORGANISM_TOOL_CHANGESET_REVISION,
+ instance=self.instance)
+
+ utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.ADD_ANALYSIS_TOOL_ID,
+ version=constants_phaeo.ADD_ANALYSIS_TOOL_VERSION,
+ changeset_revision=constants_phaeo.ADD_ANALYSIS_TOOL_CHANGESET_REVISION,
+ instance=self.instance)
+
+ utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.ANALYSIS_SYNC_TOOL_ID,
+ version=constants_phaeo.ANALYSIS_SYNC_TOOL_VERSION,
+ changeset_revision=constants_phaeo.ANALYSIS_SYNC_TOOL_CHANGESET_REVISION,
+ instance=self.instance)
+
+ utilities_bioblend.install_repository_revision(tool_id=constants_phaeo.ORGANISM_SYNC_TOOL_ID,
+ version=constants_phaeo.ORGANISM_SYNC_TOOL_VERSION,
+ changeset_revision=constants_phaeo.ORGANISM_SYNC_TOOL_CHANGESET_REVISION,
+ instance=self.instance)
- def add_organism_and_sync(self):
+ logging.info("Success: individual tools versions and changesets validated")
+
+ def get_organism(self):
get_organisms_tool_dataset = utilities_bioblend.run_tool_and_download_single_output_dataset(
instance=self.instance,
@@ -207,25 +210,8 @@ class RunWorkflow(species_data.SpeciesData):
org_id = str(org_dict["organism_id"]) # id needs to be a str to be recognized by chado tools
if org_id is None:
- add_organism_tool_dataset = utilities_bioblend.run_tool_and_download_single_output_dataset(
- instance=self.instance,
- tool_id=constants_phaeo.ADD_ORGANISM_TOOL_ID,
- history_id=self.history_id,
- tool_inputs={"abbr": self.abbreviation,
- "genus": self.genus_uppercase,
- "species": self.chado_species_name,
- "common": self.common})
- organism_dict = json.loads(add_organism_tool_dataset)
- org_id = str(organism_dict["organism_id"]) # id needs to be a str to be recognized by chado tools
-
- # Synchronize newly added organism in Tripal
- logging.info("Synchronizing organism %s in Tripal" % self.full_name)
- time.sleep(60)
- utilities_bioblend.run_tool(
- instance=self.instance,
- tool_id=constants_phaeo.ORGANISM_SYNC_TOOL_ID,
- history_id=self.history_id,
- tool_inputs={"organism_id": org_id})
+ logging.critical("Cannot find required organism in Chado database for %s" % self.full_name)
+ sys.exit()
return org_id
@@ -262,283 +248,34 @@ class RunWorkflow(species_data.SpeciesData):
sourcename=analysis_sourcename
)
- # Synchronize analysis in Tripal
- logging.info("Synchronizing analysis %s in Tripal" % analysis_name)
- self.sync_analysis(analysis_id=analysis_id)
-
return analysis_id
- def add_organism_blastp_analysis(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.set_galaxy_instance()
- self.set_history()
-
- tool_version = "2.3.4+galaxy0"
-
- get_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.4+galaxy0")
-
- get_organisms = 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={})
-
- time.sleep(10) # Ensure the tool has had time to complete
- org_outputs = get_organisms["outputs"] # Outputs from the get_organism tool
- org_job_out_id = org_outputs[0]["id"] # ID of the get_organism output dataset (list of dicts)
- org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out_id) # Download the dataset
- org_output = json.loads(org_json_output) # Turn the dataset into a list for parsing
-
- org_id = None
-
- # Look up list of outputs (dictionaries)
- for organism_output_dict in org_output:
- if organism_output_dict["genus"] == self.genus and organism_output_dict["species"] == "{0} {1}".format(self.species, self.sex):
- correct_organism_id = str(organism_output_dict["organism_id"]) # id needs to be a str to be recognized by chado tools
- org_id = str(correct_organism_id)
-
-
- if org_id is None:
- add_org_job = 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})
- org_job_out_id = add_org_job["outputs"][0]["id"]
- org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out_id)
- org_output = json.loads(org_json_output)
- org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
-
- # Synchronize newly added organism in Tripal
- logging.info("Synchronizing organism %s in Tripal" % self.full_name)
- time.sleep(60)
- org_sync = self.instance.tools.run_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/tripal_organism_sync/organism_sync/3.2.1.0",
- history_id=self.history_id,
- tool_inputs={"organism_id": org_id})
-
-
- get_analyses = self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/%s" % tool_version,
- history_id=self.history_id,
- tool_inputs={})
-
- time.sleep(10)
- analysis_outputs = get_analyses["outputs"]
- analysis_job_out_id = analysis_outputs[0]["id"]
- analysis_json_output = self.instance.datasets.download_dataset(dataset_id=analysis_job_out_id)
- analysis_output = json.loads(analysis_json_output)
-
- blastp_analysis_id = None
-
- # Look up list of outputs (dictionaries)
- for analysis_output_dict in analysis_output:
- if analysis_output_dict["name"] == "Diamond on " + self.full_name_lowercase + " OGS" + self.ogs_version:
- blastp_analysis_id = str(analysis_output_dict["analysis_id"])
-
-
- if blastp_analysis_id is None:
- add_blast_analysis_job = 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": "Diamond on " + 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})
- analysis_outputs = add_blast_analysis_job["outputs"]
- analysis_job_out_id = analysis_outputs[0]["id"]
- analysis_json_output = self.instance.datasets.download_dataset(dataset_id=analysis_job_out_id)
- analysis_output = json.loads(analysis_json_output)
- blastp_analysis_id = str(analysis_output["analysis_id"])
-
- # Synchronize blastp analysis
- logging.info("Synchronizing Diamong blastp OGS%s analysis in Tripal" % self.ogs_version)
- time.sleep(60)
- blastp_analysis_sync = self.instance.tools.run_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
- history_id=self.history_id,
- tool_inputs={"analysis_id": blastp_analysis_id})
-
- # print({"org_id": org_id, "genome_analysis_id": genome_analysis_id, "ogs_analysis_id": ogs_analysis_id})
- return {"org_id": org_id, "blastp_analysis_id": blastp_analysis_id}
-
- def add_organism_interproscan_analysis(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.set_galaxy_instance()
- self.set_history()
-
- tool_version = "2.3.4+galaxy0"
-
- get_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.4+galaxy0")
-
- get_organisms = 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={})
-
- time.sleep(10) # Ensure the tool has had time to complete
- org_outputs = get_organisms["outputs"] # Outputs from the get_organism tool
- org_job_out_id = org_outputs[0]["id"] # ID of the get_organism output dataset (list of dicts)
- org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out_id) # Download the dataset
- org_output = json.loads(org_json_output) # Turn the dataset into a list for parsing
-
- org_id = None
-
- # Look up list of outputs (dictionaries)
- for organism_output_dict in org_output:
- if organism_output_dict["genus"] == self.genus and organism_output_dict["species"] == "{0} {1}".format(self.species, self.sex):
- correct_organism_id = str(organism_output_dict["organism_id"]) # id needs to be a str to be recognized by chado tools
- org_id = str(correct_organism_id)
-
-
- if org_id is None:
- add_org_job = 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})
- org_job_out_id = add_org_job["outputs"][0]["id"]
- org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out_id)
- org_output = json.loads(org_json_output)
- org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
-
- # Synchronize newly added organism in Tripal
- logging.info("Synchronizing organism %s in Tripal" % self.full_name)
- time.sleep(60)
- org_sync = self.instance.tools.run_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/tripal_organism_sync/organism_sync/3.2.1.0",
- history_id=self.history_id,
- tool_inputs={"organism_id": org_id})
-
-
- get_analyses = self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/%s" % tool_version,
- history_id=self.history_id,
- tool_inputs={})
-
- time.sleep(10)
- analysis_outputs = get_analyses["outputs"]
- analysis_job_out_id = analysis_outputs[0]["id"]
- analysis_json_output = self.instance.datasets.download_dataset(dataset_id=analysis_job_out_id)
- analysis_output = json.loads(analysis_json_output)
-
- interpro_analysis_id = None
-
- # Look up list of outputs (dictionaries)
- for analysis_output_dict in analysis_output:
- if analysis_output_dict["name"] == "Interproscan on " + self.full_name_lowercase + " OGS" + self.ogs_version:
- interpro_analysis_id = str(analysis_output_dict["analysis_id"])
-
-
- if interpro_analysis_id is None:
- add_interproscan_analysis_job = 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": "Interproscan on " + 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})
- analysis_outputs = add_interproscan_analysis_job["outputs"]
- analysis_job_out_id = analysis_outputs[0]["id"]
- analysis_json_output = self.instance.datasets.download_dataset(dataset_id=analysis_job_out_id)
- analysis_output = json.loads(analysis_json_output)
- interpro_analysis_id = str(analysis_output["analysis_id"])
-
- # Synchronize blastp analysis
- logging.info("Synchronizing Diamong blastp OGS%s analysis in Tripal" % self.ogs_version)
- time.sleep(60)
- interproscan_analysis_sync = self.instance.tools.run_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
- history_id=self.history_id,
- tool_inputs={"analysis_id": interpro_analysis_id})
-
- # print({"org_id": org_id, "genome_analysis_id": genome_analysis_id, "ogs_analysis_id": ogs_analysis_id})
- return({"org_id": org_id, "interpro_analysis_id": interpro_analysis_id})
-
-
- 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/2.3.4+galaxy0",
- 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 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):
+ def import_datasets_into_history(self, config):
"""
Find datasets in a library, get their ID and import them into the current history if they are not already
:return:
"""
- genome_ldda_id = None
- transcripts_ldda_id = None
- proteins_ldda_id = None
- gff_ldda_id = None
interpro_ldda_id = None
blastp_ldda_id = None
blastx_ldda_id = None
- genome_hda_id = None
- gff_hda_id = None
- transcripts_hda_id = None
- proteins_hda_id = None
blastp_hda_id = None
blastx_hda_id = None
interproscan_hda_id = None
- folder_dict_list = self.instance.libraries.get_folders(library_id=str(self.library_id))
+ gio = GalaxyInstance(url=self.instance_url,
+ email=config[constants.CONF_GALAXY_DEFAULT_ADMIN_EMAIL],
+ password=config[constants.CONF_GALAXY_DEFAULT_ADMIN_PASSWORD]
+ )
+ prj_lib = gio.libraries.get_previews(constants.GALAXY_LIBRARY_NAME)
+ if len(prj_lib) == 1:
+ library_id = prj_lib[0].id
+ else:
+ logging.critical("Multiple (or no one) libraries '%s' exist" % constants.GALAXY_LIBRARY_NAME)
+ sys.exit()
+ folder_dict_list = self.instance.libraries.get_folders(library_id=str(library_id))
folders_id_dict = {}
@@ -548,14 +285,6 @@ class RunWorkflow(species_data.SpeciesData):
# Iterating over the folders to find datasets and map datasets to their IDs
for folder_name, folder_id in folders_id_dict.items():
- if folder_name == "/genome/{0}/v{1}".format(self.species_folder_name, self.genome_version):
- sub_folder_content = self.instance.folders.show_folder(folder_id=folder_id, contents=True)
- for value in sub_folder_content.values():
- for e in value:
- if type(e) == dict:
- if e["name"].endswith(self.genome_filename):
- genome_ldda_id = e["ldda_id"]
-
if folder_name == "/annotation/{0}/OGS{1}".format(self.species_folder_name, self.ogs_version):
sub_folder_content = self.instance.folders.show_folder(folder_id=folder_id, contents=True)
for value in sub_folder_content.values():
@@ -563,13 +292,7 @@ class RunWorkflow(species_data.SpeciesData):
if type(e) == dict:
ldda_name = e["name"]
ldda_id = e["ldda_id"]
- if ldda_name.endswith(self.transcripts_filename):
- transcripts_ldda_id = ldda_id
- elif ldda_name.endswith(self.proteins_filename):
- proteins_ldda_id = ldda_id
- elif ldda_name.endswith(self.gff_filename):
- gff_ldda_id = ldda_id
- elif ldda_name.endswith(self.interpro_filename):
+ if ldda_name.endswith(self.interpro_filename):
interpro_ldda_id = ldda_id
elif ldda_name.endswith(self.blastp_filename):
blastp_ldda_id = ldda_id
@@ -583,7 +306,7 @@ class RunWorkflow(species_data.SpeciesData):
hda_id = hda["id"]
if hda_name == self.genome_filename:
genome_hda_id = hda_id
- if hda_name == self.gff_filename:
+ if hda_name == self.gff_filename:
gff_hda_id = hda_id
if hda_name == self.transcripts_filename:
transcripts_hda_id = hda_id
@@ -599,220 +322,117 @@ class RunWorkflow(species_data.SpeciesData):
# Import each dataset into history if it is not imported
logging.debug("Uploading datasets into history %s" % self.history_id)
- if genome_hda_id is None:
- genome_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=genome_ldda_id)
- genome_hda_id = genome_dataset_upload["id"]
- if gff_hda_id is None:
- gff_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=gff_ldda_id)
- gff_hda_id = gff_dataset_upload["id"]
- if proteins_hda_id is None:
- proteins_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=proteins_ldda_id)
- proteins_hda_id = proteins_dataset_upload["id"]
- if transcripts_hda_id is None:
- transcripts_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=transcripts_ldda_id)
- transcripts_hda_id = transcripts_dataset_upload["id"]
if interproscan_hda_id is None:
try:
- interproscan_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=interpro_ldda_id)
+ interproscan_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id,
+ lib_dataset_id=interpro_ldda_id)
interproscan_hda_id = interproscan_dataset_upload["id"]
- except Exception as exc:
- logging.debug("Interproscan file not found in library (history: {0})".format(self.history_id))
+ except bioblend.ConnectionError as exc:
+ logging.debug("Interproscan file not found in library (exit code: {0})".format(exc))
if blastp_hda_id is None:
try:
- blastp_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=blastp_ldda_id)
+ blastp_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id,
+ lib_dataset_id=blastp_ldda_id)
blastp_hda_id = blastp_dataset_upload["id"]
- except Exception as exc:
- logging.debug("blastp file not found in library (history: {0})".format(self.history_id))
+ except bioblend.ConnectionError as exc:
+ logging.debug("blastp file not found in library (exit code: {0})".format(exc))
if blastx_hda_id is None:
try:
- blastx_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=blastx_ldda_id)
+ blastx_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id,
+ lib_dataset_id=blastx_ldda_id)
blastx_hda_id = blastx_dataset_upload["id"]
- except Exception as exc:
- logging.debug("blastp file not found in library (history: {0})".format(self.history_id))
+ except bioblend.ConnectionError as exc:
+ logging.debug("blastp file not found in library (exit code: {0})".format(exc))
- self.genome_hda_id = genome_hda_id
- self.gff_hda_id = gff_hda_id
- self.transcripts_hda_id = transcripts_hda_id
- self.proteins_hda_id = proteins_hda_id
self.blastp_hda_id = blastp_hda_id
self.blastx_hda_id = blastx_hda_id
self.interproscan_hda_id = interproscan_hda_id
-def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
+
+def prepare_history_and_get_wf_param(sp_dict_list, main_dir, config):
"""
+
"""
- run_workflow_for_current_organism = RunWorkflow(parameters_dictionary=sp_dict)
+ all_org_wf_param_dict = {}
+ for sp_dict in sp_dict_list:
- # Verifying the galaxy container is running
- if not utilities_bioblend.check_galaxy_state(network_name=run_workflow_for_current_organism.genus_species,
- script_dir=run_workflow_for_current_organism.script_dir):
- logging.critical("The galaxy container for %s is not ready yet!" % run_workflow_for_current_organism.genus_species)
- sys.exit()
+ run_workflow_for_current_organism = RunWorkflowBlastInterpro(parameters_dictionary=sp_dict)
- else:
+ # Verifying the galaxy container is running
+ if not utilities_bioblend.check_galaxy_state(network_name=run_workflow_for_current_organism.genus_species,
+ script_dir=run_workflow_for_current_organism.script_dir):
+ logging.critical(
+ "The galaxy container for %s is not ready yet!" % run_workflow_for_current_organism.genus_species)
+ sys.exit()
- # Setting some of the instance attributes
- run_workflow_for_current_organism.main_dir = main_dir
- 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 = config
- # Set the instance url attribute --> TODO: the localhost rule in the docker-compose still doesn't work on scratchgmodv1
- run_workflow_for_current_organism.instance_url = "http://localhost:{0}/sp/{1}/galaxy/".format(
- run_workflow_for_current_organism.config[constants.CONF_ALL_HTTP_PORT],
- run_workflow_for_current_organism.genus_species)
-
- run_workflow_for_current_organism.instance = utilities_bioblend.get_galaxy_instance(
- instance_url=run_workflow_for_current_organism.instance_url,
- email=run_workflow_for_current_organism.config[constants.CONF_GALAXY_DEFAULT_ADMIN_EMAIL],
- password=run_workflow_for_current_organism.config[constants.CONF_GALAXY_DEFAULT_ADMIN_PASSWORD],
- )
- history_id = utilities_bioblend.get_history(
- instance=run_workflow_for_current_organism.instance,
- history_name=run_workflow_for_current_organism.history_name)
- run_workflow_for_current_organism.install_changesets_revisions_for_individual_tools()
+ else:
+
+ # Setting some of the instance attributes
+ run_workflow_for_current_organism.main_dir = main_dir
- if workflow_type == constants_phaeo.WF_LOAD_GFF_JB:
+ run_workflow_for_current_organism.set_galaxy_instance(config)
+ run_workflow_for_current_organism.set_history()
+ run_workflow_for_current_organism.install_individual_tools()
+ run_workflow_for_current_organism.import_datasets_into_history(config)
analyses_dict_list = run_workflow_for_current_organism.get_analyses()
- org_id = run_workflow_for_current_organism.add_organism_and_sync()
- genome_analysis_id = run_workflow_for_current_organism.add_analysis_and_sync(
+ org_id = run_workflow_for_current_organism.get_organism()
+ blastp_analysis_id = run_workflow_for_current_organism.add_analysis_if_needed(
analyses_dict_list=analyses_dict_list,
- analysis_name=run_workflow_for_current_organism.genome_analysis_name,
- analysis_programversion=run_workflow_for_current_organism.genome_analysis_programversion,
- analysis_sourcename=run_workflow_for_current_organism.genome_analysis_sourcename
+ analysis_name=run_workflow_for_current_organism.blastp_analysis_name,
+ analysis_programversion=run_workflow_for_current_organism.blastp_analysis_programversion,
+ analysis_sourcename=run_workflow_for_current_organism.blastp_analysis_sourcename
)
- ogs_analysis_id = run_workflow_for_current_organism.add_analysis_and_sync(
+ blastx_analysis_id = run_workflow_for_current_organism.add_analysis_if_needed(
analyses_dict_list=analyses_dict_list,
- analysis_name=run_workflow_for_current_organism.ogs_analysis_name,
- analysis_programversion=run_workflow_for_current_organism.ogs_analysis_programversion,
- analysis_sourcename=run_workflow_for_current_organism.ogs_analysis_sourcename
+ analysis_name=run_workflow_for_current_organism.blastx_analysis_name,
+ analysis_programversion=run_workflow_for_current_organism.blastx_analysis_programversion,
+ analysis_sourcename=run_workflow_for_current_organism.blastx_analysis_sourcename
)
-
- run_workflow_for_current_organism.import_datasets_into_history()
-
- # Create the StrainWorkflowParam object holding all attributes needed for the workflow
- sp_wf_param = OrgWorkflowParamJbrowse(
- genus_species=run_workflow_for_current_organism.genus_species,
- strain_sex=run_workflow_for_current_organism.strain_sex,
- genus_uppercase = run_workflow_for_current_organism.genus_uppercase,
- full_name=run_workflow_for_current_organism.full_name,
- species_folder_name=run_workflow_for_current_organism.species_folder_name,
- chado_species_name=run_workflow_for_current_organism.chado_species_name,
- org_id=org_id,
- genome_analysis_id=genome_analysis_id,
- ogs_analysis_id=ogs_analysis_id,
- genome_hda_id=run_workflow_for_current_organism.genome_hda_id,
- gff_hda_id=run_workflow_for_current_organism.gff_hda_id,
- transcripts_hda_id=run_workflow_for_current_organism.transcripts_hda_id,
- proteins_hda_id=run_workflow_for_current_organism.proteins_hda_id,
- blastp_hda_id=run_workflow_for_current_organism.blastp_hda_id,
- blastx_hda_id=run_workflow_for_current_organism.blastx_hda_id,
- interproscan_hda_id=run_workflow_for_current_organism.interproscan_hda_id,
- history_id=history_id,
- instance=run_workflow_for_current_organism.instance
+ interpro_analysis_id = run_workflow_for_current_organism.add_analysis_if_needed(
+ analyses_dict_list=analyses_dict_list,
+ analysis_name=run_workflow_for_current_organism.interpro_analysis_name,
+ analysis_programversion=run_workflow_for_current_organism.interpro_analysis_programversion,
+ analysis_sourcename=run_workflow_for_current_organism.interpro_analysis_sourcename
)
- sp_wf_param.check_param_for_workflow_load_fasta_gff_jbrowse()
-
- if workflow_type == "blast":
-
- ids = run_workflow_for_current_organism.add_organism_blastp_analysis()
-
- org_id = ids["org_id"]
- blastp_analysis_id = ids["blastp_analysis_id"]
- run_workflow_for_current_organism.import_datasets_into_history()
# Create the StrainWorkflowParam object holding all attributes needed for the workflow
- sp_wf_param = OrgWorkflowParamJbrowse(
- genus_species=run_workflow_for_current_organism.genus_species,
- strain_sex=run_workflow_for_current_organism.strain_sex,
- genus_uppercase = run_workflow_for_current_organism.genus_uppercase,
+ org_wf_param = OrgWorkflowParamBlastInterproscan(
+ genus_uppercase=run_workflow_for_current_organism.genus_uppercase,
full_name=run_workflow_for_current_organism.full_name,
species_folder_name=run_workflow_for_current_organism.species_folder_name,
chado_species_name=run_workflow_for_current_organism.chado_species_name,
org_id=org_id,
blastp_analysis_id=blastp_analysis_id,
- genome_hda_id=run_workflow_for_current_organism.genome_hda_id,
- gff_hda_id=run_workflow_for_current_organism.gff_hda_id,
- transcripts_hda_id=run_workflow_for_current_organism.transcripts_hda_id,
- proteins_hda_id=run_workflow_for_current_organism.proteins_hda_id,
- blastp_hda_id=run_workflow_for_current_organism.blastp_hda_id,
- blastx_hda_id=run_workflow_for_current_organism.blastx_hda_id,
- interproscan_hda_id=run_workflow_for_current_organism.interproscan_hda_id,
- history_id=history_id,
- instance=run_workflow_for_current_organism.instance
- )
- sp_wf_param.check_param_for_workflow_blastp()
-
- if workflow_type == "interpro":
-
- ids = run_workflow_for_current_organism.add_organism_interproscan_analysis()
-
- org_id = ids["org_id"]
- interpro_analysis_id = ids["interpro_analysis_id"]
- run_workflow_for_current_organism.import_datasets_into_history()
-
- # Create the StrainWorkflowParam object holding all attributes needed for the workflow
- sp_wf_param = OrgWorkflowParamJbrowse(
- genus_species=run_workflow_for_current_organism.genus_species,
- strain_sex=run_workflow_for_current_organism.strain_sex,
- genus_uppercase = run_workflow_for_current_organism.genus_uppercase,
- full_name=run_workflow_for_current_organism.full_name,
- species_folder_name=run_workflow_for_current_organism.species_folder_name,
- chado_species_name=run_workflow_for_current_organism.chado_species_name,
- org_id=org_id,
+ blastx_analysis_id=blastx_analysis_id,
interpro_analysis_id=interpro_analysis_id,
- genome_hda_id=run_workflow_for_current_organism.genome_hda_id,
- gff_hda_id=run_workflow_for_current_organism.gff_hda_id,
- transcripts_hda_id=run_workflow_for_current_organism.transcripts_hda_id,
- proteins_hda_id=run_workflow_for_current_organism.proteins_hda_id,
- blastp_hda_id=run_workflow_for_current_organism.blastp_hda_id,
- blastx_hda_id=run_workflow_for_current_organism.blastx_hda_id,
- interproscan_hda_id=run_workflow_for_current_organism.interproscan_hda_id,
- history_id=history_id,
+ history_id=run_workflow_for_current_organism.history_id,
instance=run_workflow_for_current_organism.instance
)
- sp_wf_param.check_param_for_workflow_interpro()
-
- return sp_wf_param
-
-
-def install_changesets_revisions_from_workflow(instance, 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:
+ org_wf_param.check_param()
- # Then store the decoded json dictionary
- workflow_dict = json.load(ga_in_file)
+ # Add the species dictionary to the complete dictionary
+ # This dictionary contains every organism present in the input file
+ # Its structure is the following:
+ # {genus species: {strain1_sex1: {variables_key: variables_values}, strain1_sex2: {variables_key: variables_values}}}
+ if run_workflow_for_current_organism.genus_species not in all_org_wf_param_dict.keys():
+ all_org_wf_param_dict[run_workflow_for_current_organism.genus_species] = {
+ run_workflow_for_current_organism.strain_sex: org_wf_param}
+ else:
+ if run_workflow_for_current_organism.strain_sex not in all_org_wf_param_dict[run_workflow_for_current_organism.genus_species].keys():
+ all_org_wf_param_dict[run_workflow_for_current_organism.genus_species][
+ run_workflow_for_current_organism.strain_sex] = org_wf_param
+ else:
+ logging.error("Duplicate organism with 'genus_species' = '{0}' and 'strain_sex' = '{1}'".format(
+ run_workflow_for_current_organism.genus_species, run_workflow_for_current_organism.strain_sex))
- # Look up every "step_id" looking for tools
- for step in workflow_dict["steps"].values():
- if step["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")
- utilities_bioblend.install_repository_revision(tool_id=step["tool_id"],
- version=step["tool_version"],
- changeset_revision=step["tool_shed_repository"]["changeset_revision"],
- instance=instance)
+ return all_org_wf_param_dict
- logging.info("Tools versions and changeset_revisions from workflow validated")
if __name__ == "__main__":
- parser = argparse.ArgumentParser(description="Run Galaxy workflows, specific to Phaeoexplorer data")
+ parser = argparse.ArgumentParser(description="Run Galaxy workflow to load Blast and Interproscan data in GGA, specific to Phaeoexplorer data")
parser.add_argument("input",
type=str,
@@ -822,6 +442,10 @@ if __name__ == "__main__":
help="Increase output verbosity",
action="store_true")
+ parser.add_argument("-vv", "--very_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")
@@ -830,26 +454,22 @@ if __name__ == "__main__":
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. Available options: load_fasta_gff_jbrowse, blast, interpro")
-
args = parser.parse_args()
- bioblend_logger = logging.getLogger("bioblend")
- if args.verbose:
+ if args.verbose or args.very_verbose:
logging.basicConfig(level=logging.DEBUG)
- bioblend_logger.setLevel(logging.DEBUG)
else:
logging.basicConfig(level=logging.INFO)
- bioblend_logger.setLevel(logging.INFO)
+
+ if not args.very_verbose:
+ logging.getLogger("urllib3").setLevel(logging.INFO)
+ logging.getLogger("bioblend").setLevel(logging.INFO)
# Parsing the config file if provided, using the default config otherwise
if args.config:
config_file = os.path.abspath(args.config)
else:
config_file = os.path.join(os.path.dirname(os.path.realpath(sys.argv[0])), constants.DEFAULT_CONFIG)
- config = utilities.parse_config(config_file)
main_dir = None
if not args.main_directory:
@@ -857,811 +477,192 @@ if __name__ == "__main__":
else:
main_dir = os.path.abspath(args.main_directory)
+ config = utilities.parse_config(config_file)
sp_dict_list = utilities.parse_input(args.input)
-
- workflow_type = None
- # Checking if user specified a workflow to run
- if not args.workflow:
- logging.critical("No workflow type specified, exiting")
- sys.exit()
- elif args.workflow in constants_phaeo.WORKFLOW_VALID_TYPES:
- workflow_type = args.workflow
- logging.info("Workflow type set to '%s'" % workflow_type)
-
script_dir = os.path.dirname(os.path.realpath(sys.argv[0]))
- all_sp_workflow_dict = {}
-
- if workflow_type == constants_phaeo.WF_LOAD_GFF_JB:
- for sp_dict in sp_dict_list:
-
- # Add and retrieve all analyses/organisms for the current input species and add their IDs to the input dictionary
- sp_wf_param = get_sp_workflow_param(
- sp_dict,
- main_dir=main_dir,
- config=config,
- workflow_type=constants_phaeo.WF_LOAD_GFF_JB)
- current_sp_genus_species = sp_wf_param.genus_species
- current_sp_strain_sex = sp_wf_param.strain_sex
-
- # Add the species dictionary to the complete dictionary
- # This dictionary contains every organism present in the input file
- # Its structure is the following:
- # {genus species: {strain1_sex1: {variables_key: variables_values}, strain1_sex2: {variables_key: variables_values}}}
- if not current_sp_genus_species in all_sp_workflow_dict.keys():
- all_sp_workflow_dict[current_sp_genus_species] = {current_sp_strain_sex: sp_wf_param}
- else:
- if not current_sp_strain_sex in all_sp_workflow_dict[current_sp_genus_species].keys():
- all_sp_workflow_dict[current_sp_genus_species][current_sp_strain_sex] = sp_wf_param
- else:
- logging.error("Duplicate organism with 'genus_species' = '{0}' and 'strain_sex' = '{1}'".format(current_sp_genus_species, current_sp_strain_sex))
-
- for species, strains in all_sp_workflow_dict.items():
- strains_list = list(strains.keys())
- strains_count = len(strains_list)
-
- if strains_count == 1:
- logging.info("Input species %s: 1 strain detected in input dictionary" % species)
- strain_sex = list(strains.keys())[0]
- sp_wf_param = strains[strain_sex]
-
- # Set workflow path (1 organism)
- workflow_path = os.path.join(os.path.abspath(script_dir), constants_phaeo.WORKFLOWS_PATH, constants_phaeo.WF_LOAD_GFF_JB_1_ORG_FILE)
-
- # Check if the versions of tools specified in the workflow are installed in galaxy
- install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=sp_wf_param.instance)
-
- # Set the workflow parameters (individual tools runtime parameters in the workflow)
- workflow_parameters = {}
- # Input files have no parameters (they are set via assigning the hda IDs in the datamap parameter of the bioblend method)
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_INPUT_GENOME] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_INPUT_GFF] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_INPUT_PROTEINS] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_FASTA] = {
- "organism": sp_wf_param.org_id,
- "analysis_id": sp_wf_param.genome_analysis_id,
- "do_update": "true"}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_JBROWSE] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_GFF] = {
- "organism": sp_wf_param.org_id,
- "analysis_id": sp_wf_param.ogs_analysis_id}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_SYNC_FEATURE] = {
- "organism_id": sp_wf_param.org_id}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_POPULATE_VIEWS] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_INDEX] = {}
-
- # Set datamap (mapping of input files in the workflow)
- datamap = {}
- datamap[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_INPUT_GENOME] = {"src": "hda", "id": sp_wf_param.genome_hda_id}
- datamap[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_INPUT_GFF] = {"src": "hda", "id": sp_wf_param.gff_hda_id}
- datamap[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_INPUT_PROTEINS] = {"src": "hda", "id": sp_wf_param.proteins_hda_id}
-
- with open(workflow_path, 'r') as ga_in_file:
-
- # Store the decoded json dictionary
- workflow_dict = json.load(ga_in_file)
- workflow_name = workflow_dict["name"]
-
- # For the Jbrowse tool, 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)
- # Scratchgmod test: need "http" (or "https"), the hostname (+ port)
- if constants.CONF_JBROWSE_MENU_URL not in config.keys():
- # default
- root_url = "https://{0}".format(config[constants.CONF_ALL_HOSTNAME])
- else:
- root_url = config[constants.CONF_JBROWSE_MENU_URL]
- species_strain_sex = sp_wf_param.chado_species_name.replace(" ", "-")
- jbrowse_menu_url = "{root_url}/sp/{genus_sp}/feature/{Genus}/{species_strain_sex}/mRNA/{id}".format(
- root_url=root_url,
- genus_sp=sp_wf_param.genus_species,
- Genus=sp_wf_param.genus_uppercase,
- species_strain_sex=species_strain_sex,
- id="{id}")
-
- # Replace values in the workflow dictionary
- jbrowse_tool_state = workflow_dict["steps"][constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_JBROWSE]["tool_state"]
- jbrowse_tool_state = jbrowse_tool_state.replace("__MENU_URL_ORG__", jbrowse_menu_url)
- jb_to_container_tool_state = workflow_dict["steps"][constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_JB_TO_CONTAINER]["tool_state"]
- jb_to_container_tool_state = jb_to_container_tool_state\
- .replace("__DISPLAY_NAME_ORG__", sp_wf_param.full_name)\
- .replace("__UNIQUE_ID_ORG__", sp_wf_param.species_folder_name)
-
- # Import the workflow in galaxy as a dict
- sp_wf_param.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
-
- # Get its attributes
- workflow_attributes = sp_wf_param.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)
- logging.debug("Workflow ID: %s" % workflow_id)
- # Check if the workflow is found
- try:
- show_workflow = sp_wf_param.instance.workflows.show_workflow(workflow_id=workflow_id)
- except bioblend.ConnectionError:
- logging.warning("Error finding workflow %s" % workflow_name)
-
- # Finally, invoke the workflow along with its datamap, parameters and the history in which to invoke it
- sp_wf_param.instance.workflows.invoke_workflow(
- workflow_id=workflow_id,
- history_id=sp_wf_param.history_id,
- params=workflow_parameters,
- inputs=datamap,
- allow_tool_state_corrections=True)
-
- logging.info("Successfully imported and invoked workflow {0}, check the galaxy instance for the jobs state".format(workflow_name))
-
- if strains_count == 2:
-
- logging.info("Input organism %s: 2 species detected in input dictionary" % species)
- strain_sex_org1 = strains_list[0]
- strain_sex_org2 = strains_list[1]
- sp_wf_param_org1 = strains[strain_sex_org1]
- sp_wf_param_org2 = strains[strain_sex_org2]
-
- # Set workflow path (2 organisms)
- workflow_path = os.path.join(os.path.abspath(script_dir), constants_phaeo.WORKFLOWS_PATH, constants_phaeo.WF_LOAD_GFF_JB_2_ORG_FILE)
-
- # Check if the versions of tools specified in the workflow are installed in galaxy
- install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=sp_wf_param_org1.instance)
-
- # Set the workflow parameters (individual tools runtime parameters in the workflow)
- workflow_parameters = {}
-
- # Input files have no parameters (they are set via assigning the hda IDs in the datamap parameter of the bioblend method)
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG1] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG1] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_PROTEINS_ORG1] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG2] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG2] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_PROTEINS_ORG2] = {}
-
- # Organism 1
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_FASTA_ORG1] = {
- "organism": sp_wf_param_org1.org_id,
- "analysis_id": sp_wf_param_org1.genome_analysis_id,
- "do_update": "true"}
- # workflow_parameters[JBROWSE_ORG1] = {"jbrowse_menu_url": jbrowse_menu_url_org1}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_JBROWSE_ORG1] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_GFF_ORG1] = {
- "organism": sp_wf_param_org1.org_id,
- "analysis_id": sp_wf_param_org1.ogs_analysis_id}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_FEATURE_ORG1] = {
- "organism_id": sp_wf_param_org1.org_id}
- # workflow_parameters[JBROWSE_CONTAINER] = {"organisms": [{"name": org1_full_name, "unique_id": org1_species_folder_name, }, {"name": org2_full_name, "unique_id": org2_species_folder_name}]}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_JB_TO_CONTAINER] = {}
-
- # Organism 2
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_FASTA_ORG2] = {
- "organism": sp_wf_param_org2.org_id,
- "analysis_id": sp_wf_param_org2.genome_analysis_id,
- "do_update": "true"}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_LOAD_GFF_ORG2] = {
- "organism": sp_wf_param_org2.org_id,
- "analysis_id": sp_wf_param_org2.ogs_analysis_id}
- # workflow_parameters[JRBOWSE_ORG2] = {"jbrowse_menu_url": jbrowse_menu_url_org2}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_JRBOWSE_ORG2] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_SYNC_FEATURE_ORG2] = {
- "organism_id": sp_wf_param_org2.org_id}
-
- # POPULATE + INDEX DATA
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS] = {}
- workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_INDEX] = {}
-
- # Set datamap (mapping of input files in the workflow)
- datamap = {}
-
- # Organism 1
- datamap[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG1] = {"src": "hda", "id": sp_wf_param_org1.genome_hda_id}
- datamap[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG1] = {"src": "hda", "id": sp_wf_param_org1.gff_hda_id}
- datamap[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_PROTEINS_ORG1] = {"src": "hda", "id": sp_wf_param_org1.proteins_hda_id}
-
- # Organism 2
- datamap[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GENOME_ORG2] = {"src": "hda", "id": sp_wf_param_org2.genome_hda_id}
- datamap[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_GFF_ORG2] = {"src": "hda", "id": sp_wf_param_org2.gff_hda_id}
- datamap[constants_phaeo.WF_LOAD_GFF_JB_2_ORG_INPUT_PROTEINS_ORG2] = {"src": "hda", "id": sp_wf_param_org2.proteins_hda_id}
-
- with open(workflow_path, 'r') as ga_in_file:
-
- # Store the decoded json dictionary
- workflow_dict = json.load(ga_in_file)
- workflow_name = workflow_dict["name"]
-
- # For the Jbrowse tool, 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)
- # Scratchgmod test: need "http" (or "https"), the hostname (+ port)
- if constants.CONF_JBROWSE_MENU_URL not in config.keys():
- # default
- root_url = "https://{0}".format(config[constants.CONF_ALL_HOSTNAME])
- else:
- root_url = config[constants.CONF_JBROWSE_MENU_URL]
- species_strain_sex_org1 = sp_wf_param_org1.chado_species_name.replace(" ", "-")
- species_strain_sex_org2 = sp_wf_param_org2.chado_species_name.replace(" ", "-")
- jbrowse_menu_url_org1 = "{root_url}/sp/{genus_sp}/feature/{Genus}/{species_strain_sex}/mRNA/{id}".format(
- root_url=root_url,
- genus_sp=sp_wf_param_org1.genus_species,
- Genus=sp_wf_param_org1.genus_uppercase,
- species_strain_sex=species_strain_sex_org1,
- id="{id}")
- jbrowse_menu_url_org2 = "{root_url}/sp/{genus_sp}/feature/{Genus}/{species_strain_sex}/mRNA/{id}".format(
- root_url=root_url,
- genus_sp=sp_wf_param_org2.genus_species,
- Genus=sp_wf_param_org2.genus_uppercase,
- species_strain_sex=species_strain_sex_org2,
- id="{id}")
-
- # Replace values in the workflow dictionary
- jbrowse_tool_state_org1 = workflow_dict["steps"][constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_JBROWSE_ORG1]["tool_state"]
- jbrowse_tool_state_org1 = jbrowse_tool_state_org1.replace("__MENU_URL_ORG1__", jbrowse_menu_url_org1)
- jbrowse_tool_state_org2 = workflow_dict["steps"][constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_JRBOWSE_ORG2]["tool_state"]
- jbrowse_tool_state_org2 = jbrowse_tool_state_org2.replace("__MENU_URL_ORG2__", jbrowse_menu_url_org2)
- # The UNIQUE_ID is specific to a combination genus_species_strain_sex so every combination should have its unique workflow
- # in galaxy --> define a naming method for these workflows
- jb_to_container_tool_state = workflow_dict["steps"][constants_phaeo.WF_LOAD_GFF_JB_2_ORG_STEP_JB_TO_CONTAINER]["tool_state"]
- jb_to_container_tool_state = jb_to_container_tool_state\
- .replace("__DISPLAY_NAME_ORG1__", sp_wf_param_org1.full_name)\
- .replace("__UNIQUE_ID_ORG1__", sp_wf_param_org1.species_folder_name)\
- .replace("__DISPLAY_NAME_ORG2__", sp_wf_param_org2.full_name)\
- .replace("__UNIQUE_ID_ORG2__", sp_wf_param_org2.species_folder_name)
-
- # Import the workflow in galaxy as a dict
- sp_wf_param_org1.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
-
- # Get its attributes
- workflow_attributes = sp_wf_param_org1.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)
- logging.debug("Workflow ID: %s" % workflow_id)
- # Check if the workflow is found
- try:
- show_workflow = sp_wf_param_org1.instance.workflows.show_workflow(workflow_id=workflow_id)
- except bioblend.ConnectionError:
- logging.warning("Error finding workflow %s" % workflow_name)
-
- # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
- sp_wf_param_org1.instance.workflows.invoke_workflow(
- workflow_id=workflow_id,
- history_id=sp_wf_param_org1.history_id,
- params=workflow_parameters,
- inputs=datamap,
- allow_tool_state_corrections=True)
-
- logging.info("Successfully imported and invoked workflow {0}, check the galaxy instance for the jobs state".format(workflow_name))
-
- if workflow_type == constants_phaeo.WORKFLOW_BLAST:
- for sp_dict in sp_dict_list:
-
- # Add and retrieve all analyses/organisms for the current input species and add their IDs to the input dictionary
- sp_wf_param = get_sp_workflow_param(sp_dict, main_dir=args.main_directory, config=config, workflow_type=constants_phaeo.WORKFLOW_BLAST)
-
- current_sp_genus_species = list(sp_wf_param.keys())[0]
- current_sp_genus_species_dict = list(sp_wf_param.values())[0]
- current_sp_strain_sex = list(current_sp_genus_species_dict.keys())[0]
- current_sp_strain_sex_attributes_dict = list(current_sp_genus_species_dict.values())[0]
+ all_org_wf_param_dict = prepare_history_and_get_wf_param(
+ sp_dict_list=sp_dict_list,
+ main_dir=main_dir,
+ config=config)
- # Add the species dictionary to the complete dictionary
- # This dictionary contains every organism present in the input file
- # Its structure is the following:
- # {genus species: {strain1_sex1: {variables_key: variables_values}, strain1_sex2: {variables_key: variables_values}}}
- if not current_sp_genus_species in all_sp_workflow_dict.keys():
- all_sp_workflow_dict[current_sp_genus_species] = current_sp_genus_species_dict
- else:
- all_sp_workflow_dict[current_sp_genus_species][current_sp_strain_sex] = current_sp_strain_sex_attributes_dict
+ for genus_species, strains in all_org_wf_param_dict.items():
+ strains_list = list(strains.keys())
+ strains_count = len(strains_list)
- if len(list(strains.keys())) == 1:
- logging.info("Input organism %s: 1 species detected in input dictionary" % species)
+ if strains_count == 1:
+ logging.info("Input species %s: 1 strain detected in input dictionary" % genus_species)
+ strain_sex = list(strains.keys())[0]
+ org_wf_param = strains[strain_sex]
# Set workflow path (1 organism)
- workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_1org_v1.ga")
-
- # Instance object required variables
- instance_url, email, password = None, None, None
-
- # Set the galaxy instance variables
- for k2, v2 in strains.items():
- instance_url = v2["instance_url"]
- email = v2["email"]
- password = v2["password"]
-
- instance = galaxy.GalaxyInstance(url=instance_url, email=email, password=password)
+ workflow_path = os.path.join(os.path.abspath(script_dir), constants_phaeo.WORKFLOWS_PATH,
+ constants_phaeo.WF_LOAD_GFF_JB_1_ORG_FILE)
# Check if the versions of tools specified in the workflow are installed in galaxy
- install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=instance)
-
- organisms_key_name = list(strains.keys())
- org_dict = strains[organisms_key_name[0]]
-
- history_id = org_dict["history_id"]
-
- # Organism attributes
- org_genus = org_dict["genus"]
- org_species = org_dict["species"]
- org_genus_species = org_dict["genus_species"]
- org_species_folder_name = org_dict["species_folder_name"]
- org_full_name = org_dict["full_name"]
- org_strain = org_dict["sex"]
- org_sex = org_dict["strain"]
- org_org_id = org_dict["org_id"]
- org_blastp_analysis_id = org_dict["blastp_analysis_id"]
- org_blastp_hda_id = org_dict["hda_ids"]["blastp_hda_id"]
-
- # Store these values into a dict for parameters logging/validation
- org_parameters_dict = {
- "org_genus": org_genus,
- "org_species": org_species,
- "org_genus_species": org_genus_species,
- "org_species_folder_name": org_species_folder_name,
- "org_full_name": org_full_name,
- "org_strain": org_strain,
- "org_sex": org_sex,
- "org_org_id": org_org_id,
- "org_blast_analysis_id": org_blastp_analysis_id,
- "org_blastp_hda_id": org_blastp_hda_id,
- }
-
- # Look for empty parameters values, throw a critical error if a parameter value is invalid
- for param_name, param_value in org_parameters_dict.items():
- if param_value is None or param_value == "":
- logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org_full_name, param_name, param_value))
- sys.exit()
-
- BLASTP_FILE = "0"
- LOAD_BLASTP_FILE = "1"
- WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS = "2"
- WF_LOAD_GFF_JB_2_ORG_STEP_INDEX = "3"
+ utilities_bioblend.install_workflow_tools(workflow_path=workflow_path, instance=org_wf_param.instance)
# Set the workflow parameters (individual tools runtime parameters in the workflow)
- workflow_parameters = {}
- workflow_parameters[BLASTP_FILE] = {}
- workflow_parameters[LOAD_BLASTP_FILE] = {"analysis_id": org_blastp_analysis_id, "organism_id": org_org_id}
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS] = {}
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_INDEX] = {}
-
- datamap = {}
- datamap[BLASTP_FILE] = {"src": "hda", "id": org_blastp_hda_id}
-
- with open(workflow_path, 'r') as ga_in_file:
- # Store the decoded json dictionary
- workflow_dict = json.load(ga_in_file)
- workflow_name = workflow_dict["name"]
+ workflow_parameters = dict()
- # Import the workflow in galaxy as a dict
- instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
- # Get its attributes
- workflow_attributes = 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 = 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 finding workflow %s" % workflow_name)
-
- # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
- instance.workflows.invoke_workflow(workflow_id=workflow_id, history_id=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, instance_url))
-
-
-
- if len(list(strains.keys())) == 2:
-
- logging.info("Input organism %s: 2 species detected in input dictionary" % species)
-
- # Set workflow path (2 organisms)
- workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_2org_v1.ga")
-
- # Instance object required variables
- instance_url, email, password = None, None, None
-
- # Set the galaxy instance variables
- for k2, v2 in strains.items():
- instance_url = v2["instance_url"]
- email = v2["email"]
- password = v2["password"]
-
- instance = galaxy.GalaxyInstance(url=instance_url, email=email, password=password)
-
- # Check if the versions of tools specified in the workflow are installed in galaxy
- install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=instance)
-
- organisms_key_names = list(strains.keys())
- org1_dict = strains[organisms_key_names[0]]
- org2_dict = strains[organisms_key_names[1]]
-
- history_id = org1_dict["history_id"]
-
- # Organism 1 attributes
- org1_genus = org1_dict["genus"]
- org1_species = org1_dict["species"]
- org1_genus_species = org1_dict["genus_species"]
- org1_species_folder_name = org1_dict["species_folder_name"]
- org1_full_name = org1_dict["full_name"]
- org1_strain = org1_dict["sex"]
- org1_sex = org1_dict["strain"]
- org1_org_id = org1_dict["org_id"]
- org1_blastp_analysis_id = org1_dict["blastp_analysis_id"]
- org1_blastp_hda_id = org1_dict["hda_ids"]["blastp_hda_id"]
-
- # Store these values into a dict for parameters logging/validation
- org1_parameters_dict = {
- "org1_genus": org1_genus,
- "org1_species": org1_species,
- "org1_genus_species": org1_genus_species,
- "org1_species_folder_name": org1_species_folder_name,
- "org1_full_name": org1_full_name,
- "org1_strain": org1_strain,
- "org1_sex": org1_sex,
- "org1_org_id": org1_org_id,
- "org1_blast_analysis_id": org1_blastp_analysis_id,
- "org1_blastp_hda_id": org1_blastp_hda_id,
+ # Input files have no parameters (they are set via assigning the hda IDs in the datamap parameter of the bioblend method)
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_INPUT_BLASTP] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_INPUT_BLASTX] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_INPUT_INTERPRO] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_LOAD_BLASTP] = {
+ "organism_id": org_wf_param.org_id,
+ "analysis_id": org_wf_param.blastp_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_LOAD_BLASTX] = {
+ "organism_id": org_wf_param.org_id,
+ "analysis_id": org_wf_param.blastx_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_LOAD_INTERPRO] = {
+ "organism_id": org_wf_param.org_id,
+ "analysis_id": org_wf_param.interpro_analysis_id}
+ workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_POPULATE_VIEWS] = {}
+ workflow_parameters[constants_phaeo.WF_LOAD_GFF_JB_1_ORG_STEP_INDEX] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_SYNC_BLASTP_ANALYSIS] = {
+ "analysis_id": org_wf_param.blastp_analysis_id
}
-
-
- # Look for empty parameters values, throw a critical error if a parameter value is invalid
- for param_name, param_value in org1_parameters_dict.items():
- if param_value is None or param_value == "":
- logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org1_full_name, param_name, param_value))
- sys.exit()
-
- # Organism 2 attributes
- org2_genus = org2_dict["genus"]
- org2_species = org2_dict["species"]
- org2_genus_species = org2_dict["genus_species"]
- org2_species_folder_name = org2_dict["species_folder_name"]
- org2_full_name = org2_dict["full_name"]
- org2_strain = org2_dict["sex"]
- org2_sex = org2_dict["strain"]
- org2_org_id = org2_dict["org_id"]
- org2_blastp_analysis_id = org2_dict["blastp_analysis_id"]
- org2_blastp_hda_id = org2_dict["hda_ids"]["blastp_hda_id"]
-
- # Store these values into a dict for parameters logging/validation
- org2_parameters_dict = {
- "org2_genus": org2_genus,
- "org2_species": org2_species,
- "org2_genus_species": org2_genus_species,
- "org2_species_folder_name": org_species_folder_name,
- "org2_full_name": org2_full_name,
- "org2_strain": org2_strain,
- "org2_sex": org2_sex,
- "org2_org_id": org2_org_id,
- "org2_blast_analysis_id": org2_blastp_analysis_id,
- "org2_blastp_hda_id": org2_blastp_hda_id,
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_SYNC_BLASTX_ANALYSIS] = {
+ "analysis_id": org_wf_param.blastx_analysis_id
+ }
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_SYNC_INTERPRO_ANALYSIS] = {
+ "analysis_id": org_wf_param.interpro_analysis_id
}
-
-
- # Look for empty parameters values, throw a critical error if a parameter value is invalid
- for param_name, param_value in org2_parameters_dict.items():
- if param_value is None or param_value == "":
- logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org2_full_name, param_name, param_value))
- sys.exit()
-
- # Source files association (ordered by their IDs in the workflow)
- # WARNING: Be very careful about how the workflow is "organized" (i.e the order of the steps/datasets, check the .ga if there is any error)
- BLASTP_FILE_ORG1 = "0"
- BLASTP_FILE_ORG2 = "1"
- LOAD_BLASTP_FILE_ORG1 = "2"
- LOAD_BLASTP_FILE_ORG2 = "3"
- WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS = "4"
- WF_LOAD_GFF_JB_2_ORG_STEP_INDEX = "5"
-
- # Set the workflow parameters (individual tools runtime parameters in the workflow)
- workflow_parameters = {}
-
- # Input files have no parameters (they are set via assigning the hda IDs in the datamap parameter of the bioblend method)
- workflow_parameters[BLASTP_FILE_ORG1] = {}
- workflow_parameters[BLASTP_FILE_ORG2] = {}
-
- # Organism 1
- workflow_parameters[LOAD_BLASTP_FILE_ORG1] = {"organism_id": org1_org_id,
- "analysis_id": org1_blastp_analysis_id}
-
- # Organism 2
- workflow_parameters[LOAD_BLASTP_FILE_ORG2] = {"organism_id": org2_org_id,
- "analysis_id": org2_blastp_analysis_id}
-
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS] = {}
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_INDEX] = {}
# Set datamap (mapping of input files in the workflow)
- datamap = {}
-
- # Organism 1
- datamap[BLASTP_FILE_ORG1] = {"src": "hda", "id": org1_blastp_hda_id}
-
- # Organism 2
- datamap[BLASTP_FILE_ORG2] = {"src": "hda", "id": org2_blastp_hda_id}
+ datamap = dict()
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_INPUT_BLASTP] = {"src": "hda",
+ "id": org_wf_param.blastp_hda_id}
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_INPUT_BLASTX] = {"src": "hda",
+ "id": org_wf_param.blastx_hda_id}
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_1_ORG_INPUT_INTERPRO] = {"src": "hda",
+ "id": org_wf_param.interproscan_hda_id}
with open(workflow_path, 'r') as ga_in_file:
- # Store the decoded json dictionary
- workflow_dict = json.load(ga_in_file)
- workflow_name = workflow_dict["name"]
- # Import the workflow in galaxy as a dict
- instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
- # Get its attributes
- workflow_attributes = 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 = 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 finding workflow %s" % workflow_name)
-
- # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
- instance.workflows.invoke_workflow(workflow_id=workflow_id, history_id=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, instance_url))
-
-
- if workflow_type == "interpro":
- for sp_dict in sp_dict_list:
-
- # Add and retrieve all analyses/organisms for the current input species and add their IDs to the input dictionary
- sp_wf_param = get_sp_workflow_param(sp_dict, main_dir=args.main_directory, config=config, workfow_type="blast")
-
- current_sp_genus_species = list(sp_wf_param.keys())[0]
- current_sp_genus_species_dict = list(sp_wf_param.values())[0]
- current_sp_strain_sex = list(current_sp_genus_species_dict.keys())[0]
- current_sp_strain_sex_attributes_dict = list(current_sp_genus_species_dict.values())[0]
-
- # Add the species dictionary to the complete dictionary
- # This dictionary contains every organism present in the input file
- # Its structure is the following:
- # {genus species: {strain1_sex1: {variables_key: variables_values}, strain1_sex2: {variables_key: variables_values}}}
- if not current_sp_genus_species in all_sp_workflow_dict.keys():
- all_sp_workflow_dict[current_sp_genus_species] = current_sp_genus_species_dict
- else:
- all_sp_workflow_dict[current_sp_genus_species][current_sp_strain_sex] = current_sp_strain_sex_attributes_dict
-
- if len(list(strains.keys())) == 1:
- logging.info("Input organism %s: 1 species detected in input dictionary" % species)
-
- # Set workflow path (1 organism)
- workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_1org_v1.ga")
-
- # Instance object required variables
- instance_url, email, password = None, None, None
-
- # Set the galaxy instance variables
- for k2, v2 in strains.items():
- instance_url = v2["instance_url"]
- email = v2["email"]
- password = v2["password"]
-
- instance = galaxy.GalaxyInstance(url=instance_url, email=email, password=password)
-
- # Check if the versions of tools specified in the workflow are installed in galaxy
- install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=instance)
-
- organism_key_name = list(strains.keys())
- org_dict = strains[organisms_key_name[0]]
-
- history_id = org_dict["history_id"]
-
- # Organism attributes
- org_genus = org_dict["genus"]
- org_species = org_dict["species"]
- org_genus_species = org_dict["genus_species"]
- org_species_folder_name = org_dict["species_folder_name"]
- org_full_name = org_dict["full_name"]
- org_strain = org_dict["sex"]
- org_sex = org_dict["strain"]
- org_org_id = org_dict["org_id"]
- org_inteproscan_analysis_id = org_dict["inteproscan_analysis_id"]
- org_interproscan_hda_id = org_dict["hda_ids"]["interproscan_hda_id"]
-
- # Store these values into a dict for parameters logging/validation
- org_parameters_dict = {
- "org_genus": org_genus,
- "org_species": org_species,
- "org_genus_species": org_genus_species,
- "org_species_folder_name": org_species_folder_name,
- "org_full_name": org_full_name,
- "org_strain": org_strain,
- "org_sex": org_sex,
- "org_org_id": org_org_id,
- "org_inteproscan_analysis_id": org_inteproscan_analysis_id,
- "org_interproscan_hda_id": org_interproscan_hda_id,
- }
-
- # Look for empty parameters values, throw a critical error if a parameter value is invalid
- for param_name, param_value in org_parameters_dict.items():
- if param_value is None or param_value == "":
- logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org_full_name, param_name, param_value))
- sys.exit()
-
- INTEPRO_FILE = "0"
- LOAD_INTERPRO_FILE = "1"
- WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS = "2"
- WF_LOAD_GFF_JB_2_ORG_STEP_INDEX = "3"
-
- # Set the workflow parameters (individual tools runtime parameters in the workflow)
- workflow_parameters = {}
- workflow_parameters[INTEPRO_FILE] = {}
- workflow_parameters[LOAD_INTERPRO_FILE] = {"analysis_id": org_inteproscan_analysis_id, "organism_id": org_org_id}
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS] = {}
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_INDEX] = {}
-
- datamap = {}
- datamap[INTEPRO_FILE] = {"src": "hda", "id": org_interproscan_hda_id}
-
- with open(workflow_path, 'r') as ga_in_file:
# Store the decoded json dictionary
workflow_dict = json.load(ga_in_file)
workflow_name = workflow_dict["name"]
# Import the workflow in galaxy as a dict
- instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
+ org_wf_param.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
+
# Get its attributes
- workflow_attributes = instance.workflows.get_workflows(name=workflow_name)
+ workflow_dict_list = org_wf_param.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 = instance.workflows.show_workflow(workflow_id=workflow_id)
+ workflow_id = workflow_dict_list[0]["id"] # Index 0 is the most recently imported workflow (the one we want)
+ logging.debug("Workflow ID: %s" % workflow_id)
# Check if the workflow is found
try:
- logging.debug("Workflow ID: %s" % workflow_id)
+ show_workflow = org_wf_param.instance.workflows.show_workflow(workflow_id=workflow_id)
except bioblend.ConnectionError:
logging.warning("Error finding workflow %s" % workflow_name)
- # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
- instance.workflows.invoke_workflow(workflow_id=workflow_id, history_id=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, instance_url))
+ # Finally, invoke the workflow along with its datamap, parameters and the history in which to invoke it
+ org_wf_param.instance.workflows.invoke_workflow(
+ workflow_id=workflow_id,
+ history_id=org_wf_param.history_id,
+ params=workflow_parameters,
+ inputs=datamap,
+ allow_tool_state_corrections=True)
+ logging.info("Successfully imported and invoked workflow {0}, check the galaxy instance for the jobs state".format(workflow_name))
+ if strains_count == 2:
- if len(list(strains.keys())) == 2:
-
- logging.info("Input organism %s: 2 species detected in input dictionary" % species)
+ logging.info("Input organism %s: 2 species detected in input dictionary" % genus_species)
+ strain_sex_org1 = strains_list[0]
+ strain_sex_org2 = strains_list[1]
+ sp_wf_param_org1 = strains[strain_sex_org1]
+ sp_wf_param_org2 = strains[strain_sex_org2]
# Set workflow path (2 organisms)
- workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_2org_v1.ga")
-
- # Instance object required variables
- instance_url, email, password = None, None, None
-
- # Set the galaxy instance variables
- for k2, v2 in strains.items():
- instance_url = v2["instance_url"]
- email = v2["email"]
- password = v2["password"]
-
- instance = galaxy.GalaxyInstance(url=instance_url, email=email, password=password)
+ workflow_path = os.path.join(os.path.abspath(script_dir), constants_phaeo.WORKFLOWS_PATH, constants_phaeo.WF_BLAST_INTERPRO_2_ORG_FILE)
# Check if the versions of tools specified in the workflow are installed in galaxy
- install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=instance)
-
- organisms_key_names = list(strains.keys())
- org1_dict = strains[organisms_key_names[0]]
- org2_dict = strains[organisms_key_names[1]]
-
- history_id = org1_dict["history_id"]
-
- # Organism 1 attributes
- org1_genus = org1_dict["genus"]
- org1_species = org1_dict["species"]
- org1_genus_species = org1_dict["genus_species"]
- org1_species_folder_name = org1_dict["species_folder_name"]
- org1_full_name = org1_dict["full_name"]
- org1_strain = org1_dict["sex"]
- org1_sex = org1_dict["strain"]
- org1_org_id = org1_dict["org_id"]
- org1_interproscan_analysis_id = org1_dict["interproscan_analysis_id"]
- org1_interproscan_hda_id = org1_dict["hda_ids"]["interproscan_hda_id"]
-
- # Store these values into a dict for parameters logging/validation
- org1_parameters_dict = {
- "org1_genus": org1_genus,
- "org1_species": org1_species,
- "org1_genus_species": org1_genus_species,
- "org1_species_folder_name": org1_species_folder_name,
- "org1_full_name": org1_full_name,
- "org1_strain": org1_strain,
- "org1_sex": org1_sex,
- "org1_org_id": org1_org_id,
- "org1_interproscan_analysis_id": org1_interproscan_analysis_id,
- "org1_interproscan_hda_id": org1_interproscan_hda_id,
- }
-
-
- # Look for empty parameters values, throw a critical error if a parameter value is invalid
- for param_name, param_value in org1_parameters_dict.items():
- if param_value is None or param_value == "":
- logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org1_full_name, param_name, param_value))
- sys.exit()
-
- # Organism 2 attributes
- org2_genus = org2_dict["genus"]
- org2_species = org2_dict["species"]
- org2_genus_species = org2_dict["genus_species"]
- org2_species_folder_name = org2_dict["species_folder_name"]
- org2_full_name = org2_dict["full_name"]
- org2_strain = org2_dict["sex"]
- org2_sex = org2_dict["strain"]
- org2_org_id = org2_dict["org_id"]
- org2_interproscan_analysis_id = org2_dict["interproscan_analysis_id"]
- org2_interproscan_hda_id = org2_dict["hda_ids"]["interproscan_hda_id"]
-
- # Store these values into a dict for parameters logging/validation
- org2_parameters_dict = {
- "org2_genus": org2_genus,
- "org2_species": org2_species,
- "org2_genus_species": org2_genus_species,
- "org2_species_folder_name": org_species_folder_name,
- "org2_full_name": org2_full_name,
- "org2_strain": org2_strain,
- "org2_sex": org2_sex,
- "org2_org_id": org2_org_id,
- "org2_interproscan_analysis_id": org2_interproscan_analysis_id,
- "org2_interproscan_hda_id": org2_interproscan_hda_id,
- }
-
-
- # Look for empty parameters values, throw a critical error if a parameter value is invalid
- for param_name, param_value in org2_parameters_dict.items():
- if param_value is None or param_value == "":
- logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org2_full_name, param_name, param_value))
- sys.exit()
-
- # Source files association (ordered by their IDs in the workflow)
- # WARNING: Be very careful about how the workflow is "organized" (i.e the order of the steps/datasets, check the .ga if there is any error)
- INTERPRO_FILE_ORG1 = "0"
- INTERPRO_FILE_ORG2 = "1"
- LOAD_INTERPRO_FILE_ORG1 = "2"
- LOAD_INTERPRO_FILE_ORG2 = "3"
- WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS = "4"
- WF_LOAD_GFF_JB_2_ORG_STEP_INDEX = "5"
+ utilities_bioblend.install_workflow_tools(workflow_path=workflow_path, instance=sp_wf_param_org1.instance)
# Set the workflow parameters (individual tools runtime parameters in the workflow)
- workflow_parameters = {}
+ workflow_parameters = dict()
# Input files have no parameters (they are set via assigning the hda IDs in the datamap parameter of the bioblend method)
- workflow_parameters[INTERPRO_FILE_ORG1] = {}
- workflow_parameters[INTERPRO_FILE_ORG2] = {}
-
- # Organism 1
- workflow_parameters[LOAD_INTERPRO_FILE_ORG1] = {"organism_id": org1_org_id,
- "analysis_id": org1_interproscan_analysis_id}
-
- # Organism 2
- workflow_parameters[LOAD_INTERPRO_FILE_ORG2] = {"organism_id": org2_org_id,
- "analysis_id": org2_interproscan_analysis_id}
-
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_POPULATE_VIEWS] = {}
- workflow_parameters[WF_LOAD_GFF_JB_2_ORG_STEP_INDEX] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTP_ORG1] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTP_ORG2] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTX_ORG1] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTX_ORG2] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_INTERPRO_ORG1] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_INTERPRO_ORG2] = {}
+
+ # Load xml results
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTP_ORG1] = {"organism_id": sp_wf_param_org1.org_id,
+ "analysis_id": sp_wf_param_org1.blastp_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTP_ORG2] = {"organism_id": sp_wf_param_org2.org_id,
+ "analysis_id": sp_wf_param_org2.blastp_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTX_ORG1] = {"organism_id": sp_wf_param_org1.org_id,
+ "analysis_id": sp_wf_param_org1.blastx_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_LOAD_BLASTX_ORG2] = {"organism_id": sp_wf_param_org2.org_id,
+ "analysis_id": sp_wf_param_org2.blastx_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_LOAD_INTERPRO_ORG1] = {"organism_id": sp_wf_param_org1.org_id,
+ "analysis_id": sp_wf_param_org1.interpro_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_LOAD_INTERPRO_ORG2] = {"organism_id": sp_wf_param_org2.org_id,
+ "analysis_id": sp_wf_param_org2.interpro_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_POPULATE_MAT_VIEWS] = {}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INDEX_TRIPAL_DATA] = {}
+
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTP_ANALYSIS_ORG1] = {"analysis_id": sp_wf_param_org1.blastp_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTX_ANALYSIS_ORG1] = {"analysis_id": sp_wf_param_org1.blastx_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_SYNC_INTERPRO_ANALYSIS_ORG1] = {"analysis_id": sp_wf_param_org1.interpro_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTP_ANALYSIS_ORG2] = {"analysis_id": sp_wf_param_org2.blastp_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_SYNC_BLASTX_ANALYSIS_ORG2] = {"analysis_id": sp_wf_param_org2.blastx_analysis_id}
+ workflow_parameters[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_SYNC_INTERPRO_ANALYSIS_ORG2] = {"analysis_id": sp_wf_param_org2.interpro_analysis_id}
# Set datamap (mapping of input files in the workflow)
- datamap = {}
-
- # Organism 1
- datamap[BLASTP_FILE_ORG1] = {"src": "hda", "id": org1_interproscan_hda_id}
-
- # Organism 2
- datamap[BLASTP_FILE_ORG2] = {"src": "hda", "id": org2_interproscan_hda_id}
+ datamap = dict()
+
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_INTERPRO_ORG1] = {"src": "hda",
+ "id": sp_wf_param_org1.interproscan_hda_id}
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTP_ORG1] = {"src": "hda",
+ "id": sp_wf_param_org1.blastp_hda_id}
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTX_ORG1] = {"src": "hda",
+ "id": sp_wf_param_org1.blastx_hda_id}
+
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_INTERPRO_ORG2] = {"src": "hda",
+ "id": sp_wf_param_org2.interproscan_hda_id}
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTP_ORG2] = {"src": "hda",
+ "id": sp_wf_param_org2.blastp_hda_id}
+ datamap[constants_phaeo.WF_BLAST_INTERPRO_2_ORG_INPUT_BLASTX_ORG2] = {"src": "hda",
+ "id": sp_wf_param_org2.blastx_hda_id}
with open(workflow_path, 'r') as ga_in_file:
+
# Store the decoded json dictionary
workflow_dict = json.load(ga_in_file)
workflow_name = workflow_dict["name"]
# Import the workflow in galaxy as a dict
- instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
+ sp_wf_param_org1.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
+
# Get its attributes
- workflow_attributes = instance.workflows.get_workflows(name=workflow_name)
+ workflow_dict_list = sp_wf_param_org1.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 = instance.workflows.show_workflow(workflow_id=workflow_id)
+ workflow_id = workflow_dict_list[0][
+ "id"] # Index 0 is the most recently imported workflow (the one we want)
+ logging.debug("Workflow ID: %s" % workflow_id)
# Check if the workflow is found
try:
- logging.debug("Workflow ID: %s" % workflow_id)
+ show_workflow = sp_wf_param_org1.instance.workflows.show_workflow(workflow_id=workflow_id)
except bioblend.ConnectionError:
logging.warning("Error finding workflow %s" % workflow_name)
# Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
- instance.workflows.invoke_workflow(workflow_id=workflow_id, history_id=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, instance_url))
+ sp_wf_param_org1.instance.workflows.invoke_workflow(
+ workflow_id=workflow_id,
+ history_id=sp_wf_param_org1.history_id,
+ params=workflow_parameters,
+ inputs=datamap,
+ allow_tool_state_corrections=True)
+
+ logging.info(
+ "Successfully imported and invoked workflow {0}, check the galaxy instance for the jobs state".format(
+ workflow_name))
diff --git a/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_1org_v1.ga b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_1org_v1.ga
new file mode 100644
index 0000000..be675e5
--- /dev/null
+++ b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_1org_v1.ga
@@ -0,0 +1,611 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "load_blast_interproscan_results_1org_v1",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blastp file org"
+ }
+ ],
+ "label": "blastp file org",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 343.8000030517578,
+ "height": 61.80000305175781,
+ "left": 381,
+ "right": 581,
+ "top": 282,
+ "width": 200,
+ "x": 381,
+ "y": 282
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "8327075f-dcdf-429b-9d35-6c899e5096b5",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "6c6461d5-7752-4169-86aa-a1fdc6a59490"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 1,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blastx file org"
+ }
+ ],
+ "label": "blastx file org",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 524.8000030517578,
+ "height": 61.80000305175781,
+ "left": 659,
+ "right": 859,
+ "top": 463,
+ "width": 200,
+ "x": 659,
+ "y": 463
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "435d2bbe-746f-4e68-991e-8822834ba8c0",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "4634cf97-8960-4ebb-9f55-79244c042e22"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 2,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "interproscan file org"
+ }
+ ],
+ "label": "interproscan file org",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 575.1999969482422,
+ "height": 82.19999694824219,
+ "left": 937,
+ "right": 1137,
+ "top": 493,
+ "width": 200,
+ "x": 937,
+ "y": 493
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "1b9e1874-f200-49a9-8bda-9d4d14ff046d",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "cd5eccc5-f364-4476-b5ea-afc4534a3e11"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 3,
+ "input_connections": {
+ "input": {
+ "id": 0,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blastp results org",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 425.3999938964844,
+ "height": 164.39999389648438,
+ "left": 659,
+ "right": 859,
+ "top": 261,
+ "width": 200,
+ "x": 659,
+ "y": 261
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"176\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "9a4b7425-f3dd-4a37-a259-d2dd37b6d9c3",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "b532b247-339e-4c21-ac4b-bf15226981f7"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 4,
+ "input_connections": {
+ "input": {
+ "id": 1,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 3,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blastx results org",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 456.3999938964844,
+ "height": 164.39999389648438,
+ "left": 939,
+ "right": 1139,
+ "top": 292,
+ "width": 200,
+ "x": 939,
+ "y": 292
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"176\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "bc71b4f2-3b55-41ab-b4cd-d171c880978c",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "7d106bd3-779b-473c-b487-b1e6b4080e02"
+ }
+ ]
+ },
+ "5": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_interpro/load_interpro/2.3.4+galaxy0",
+ "errors": null,
+ "id": 5,
+ "input_connections": {
+ "input": {
+ "id": 2,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 4,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load interproscan results org",
+ "name": "Chado load InterProScan results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 486.3999938964844,
+ "height": 164.39999389648438,
+ "left": 1216,
+ "right": 1416,
+ "top": 322,
+ "width": 200,
+ "x": 1216,
+ "y": 322
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_interpro/load_interpro/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "3284a0c7570e",
+ "name": "chado_load_interpro",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"parse_go\": \"false\", \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "4cd2a7bd-aaa7-4cb4-bedf-fb5d2c161901",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "2f2cab43-a0e0-43b0-9b7c-3513354dbb98"
+ }
+ ]
+ },
+ "6": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 6,
+ "input_connections": {
+ "wait_for": {
+ "id": 5,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "wait_for"
+ }
+ ],
+ "label": "sync blastp analysis org",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 480.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1493,
+ "right": 1693,
+ "top": 326,
+ "width": 200,
+ "x": 1493,
+ "y": 326
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "096dc1ba-28fa-4ac7-8077-5b0d7dfd50a9",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "c79f9855-071c-4b69-ba7e-517722a2bbee"
+ }
+ ]
+ },
+ "7": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 7,
+ "input_connections": {
+ "wait_for": {
+ "id": 6,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "wait_for"
+ }
+ ],
+ "label": "sync blastx analysis org",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 480.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1771,
+ "right": 1971,
+ "top": 326,
+ "width": 200,
+ "x": 1771,
+ "y": 326
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "beb6de1d-e0ef-477d-a2d3-1156ee80e299",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "b8e8a0cc-1966-4263-9f45-97e08734dccb"
+ }
+ ]
+ },
+ "8": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 8,
+ "input_connections": {
+ "wait_for": {
+ "id": 7,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "wait_for"
+ }
+ ],
+ "label": "sync interproscan analysis org",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 480.3999938964844,
+ "height": 154.39999389648438,
+ "left": 2049,
+ "right": 2249,
+ "top": 326,
+ "width": 200,
+ "x": 2049,
+ "y": 326
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "48eaf070-3d21-486c-a098-7bb459598a8b",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "e42bc9c9-7fa4-4934-bf64-9928e019ef51"
+ }
+ ]
+ },
+ "9": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 9,
+ "input_connections": {
+ "wait_for": {
+ "id": 8,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "populate mat views",
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 480.3999938964844,
+ "height": 154.39999389648438,
+ "left": 2327,
+ "right": 2527,
+ "top": 326,
+ "width": 200,
+ "x": 2327,
+ "y": 326
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "3c08f32a3dc1",
+ "name": "tripal_db_populate_mviews",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"mview\": \"\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "18f15132-1161-49b0-809f-eab40e945db4",
+ "workflow_outputs": [
+ {
+ "label": "Populate Tripal materialized view(s)",
+ "output_name": "results",
+ "uuid": "36a6b38e-7def-4092-a3d6-8d4df216a45b"
+ }
+ ]
+ },
+ "10": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 10,
+ "input_connections": {
+ "wait_for": {
+ "id": 9,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "index tripal data",
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 481.6000061035156,
+ "height": 113.60000610351562,
+ "left": 2605,
+ "right": 2805,
+ "top": 368,
+ "width": 200,
+ "x": 2605,
+ "y": 368
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "tool_shed_repository": {
+ "changeset_revision": "d55a39f12dda",
+ "name": "tripal_db_index",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"expose\": {\"do_expose\": \"no\", \"__current_case__\": 0}, \"queues\": \"10\", \"table\": {\"mode\": \"website\", \"__current_case__\": 0}, \"tokenizer\": \"standard\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "1c8c2f38-7c44-44fd-bc37-b4ff151440e8",
+ "workflow_outputs": [
+ {
+ "label": "Index Tripal data",
+ "output_name": "results",
+ "uuid": "c5e7ffe8-f322-4957-a7c1-9b92a3cf2fa1"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "0a48b57a-2c27-4d25-a942-31bf4497d2f6",
+ "version": 3
+}
\ No newline at end of file
diff --git a/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_2org_v1.ga b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_2org_v1.ga
new file mode 100644
index 0000000..9cf37bf
--- /dev/null
+++ b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_interproscan_results_2org_v1.ga
@@ -0,0 +1,1063 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "load_blast_interproscan_results_2org_v1",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blastp file org1"
+ }
+ ],
+ "label": "blastp file org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 198.3000030517578,
+ "height": 61.80000305175781,
+ "left": -280,
+ "right": -80,
+ "top": 136.5,
+ "width": 200,
+ "x": -280,
+ "y": 136.5
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "c7230bbe-4603-4f3a-b841-157daf9e4b86",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "77e22768-c8ed-488a-ac74-5bd1f0fdad26"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 1,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blastp file org2"
+ }
+ ],
+ "label": "blastp file org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 379.3000030517578,
+ "height": 61.80000305175781,
+ "left": -2,
+ "right": 198,
+ "top": 317.5,
+ "width": 200,
+ "x": -2,
+ "y": 317.5
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "99dc8355-cd87-4eab-9170-cded45dc962a",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "f6dac312-112c-4a28-a999-acfea4522e40"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 2,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blastx file org1"
+ }
+ ],
+ "label": "blastx file org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 409.3000030517578,
+ "height": 61.80000305175781,
+ "left": 276,
+ "right": 476,
+ "top": 347.5,
+ "width": 200,
+ "x": 276,
+ "y": 347.5
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "3f7f7682-46cb-4a61-a649-7a2a43174ae2",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "b623f9b8-6258-4a02-a6d7-f38cc6b51467"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 3,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blastx file org2"
+ }
+ ],
+ "label": "blastx file org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 439.3000030517578,
+ "height": 61.80000305175781,
+ "left": 554,
+ "right": 754,
+ "top": 377.5,
+ "width": 200,
+ "x": 554,
+ "y": 377.5
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "07615e25-392b-4533-8efd-6a400de9a2b6",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "216b7b96-8fa0-4c03-82d7-496a398e04ef"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 4,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "interproscan file org1"
+ }
+ ],
+ "label": "interproscan file org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 489.6999969482422,
+ "height": 82.19999694824219,
+ "left": 832,
+ "right": 1032,
+ "top": 407.5,
+ "width": 200,
+ "x": 832,
+ "y": 407.5
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "fe4a1d12-ac12-435b-acd3-10a66d6eee89",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "17e2b6a0-8cd5-4cf9-974b-d843ee35d237"
+ }
+ ]
+ },
+ "5": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 5,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "interproscan file org2"
+ }
+ ],
+ "label": "interproscan file org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 519.6999969482422,
+ "height": 82.19999694824219,
+ "left": 1110,
+ "right": 1310,
+ "top": 437.5,
+ "width": 200,
+ "x": 1110,
+ "y": 437.5
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "7dc39a56-6afa-46b1-a49c-3103ca847405",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "030a9365-6810-484b-ac90-8d236262a931"
+ }
+ ]
+ },
+ "6": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 6,
+ "input_connections": {
+ "input": {
+ "id": 0,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blastp results org1",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 279.8999938964844,
+ "height": 164.39999389648438,
+ "left": -2,
+ "right": 198,
+ "top": 115.5,
+ "width": 200,
+ "x": -2,
+ "y": 115.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"176\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "da2ce96c-d7e7-40ba-b5e3-da001c7e8ea7",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "f9fe5c14-42c7-4d13-a6d0-796e6534c466"
+ }
+ ]
+ },
+ "7": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 7,
+ "input_connections": {
+ "input": {
+ "id": 1,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 6,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ }
+ ],
+ "label": "load blastp results org2",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 309.8999938964844,
+ "height": 164.39999389648438,
+ "left": 276,
+ "right": 476,
+ "top": 145.5,
+ "width": 200,
+ "x": 276,
+ "y": 145.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"176\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "e570180a-d503-4ab1-bb5f-7916e32b974a",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "37193d90-4908-4dc4-87e1-12320c9012f2"
+ }
+ ]
+ },
+ "8": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 8,
+ "input_connections": {
+ "input": {
+ "id": 2,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 7,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blastx results org1",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 339.8999938964844,
+ "height": 164.39999389648438,
+ "left": 554,
+ "right": 754,
+ "top": 175.5,
+ "width": 200,
+ "x": 554,
+ "y": 175.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"176\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "3fd25463-269d-454f-8467-72deb1788fdc",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "c3f95842-f8e6-4088-9255-175aebb90ce1"
+ }
+ ]
+ },
+ "9": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 9,
+ "input_connections": {
+ "input": {
+ "id": 3,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 8,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blastx results org2",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 369.8999938964844,
+ "height": 164.39999389648438,
+ "left": 832,
+ "right": 1032,
+ "top": 205.5,
+ "width": 200,
+ "x": 832,
+ "y": 205.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"176\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "e5d9b775-8d0c-468f-b32a-067228bc1e05",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "e2461d5a-918e-42e4-9be8-9d64d0624de7"
+ }
+ ]
+ },
+ "10": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_interpro/load_interpro/2.3.4+galaxy0",
+ "errors": null,
+ "id": 10,
+ "input_connections": {
+ "input": {
+ "id": 4,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 9,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "organism_id"
+ }
+ ],
+ "label": "load interproscan results org1",
+ "name": "Chado load InterProScan results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 399.8999938964844,
+ "height": 164.39999389648438,
+ "left": 1110,
+ "right": 1310,
+ "top": 235.5,
+ "width": 200,
+ "x": 1110,
+ "y": 235.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_interpro/load_interpro/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "3284a0c7570e",
+ "name": "chado_load_interpro",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"parse_go\": \"false\", \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "93acf95c-2f49-4424-8d6a-3aaa50dff8c0",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "d9d0fde7-38f3-43ff-9f3d-6c26dcde83aa"
+ }
+ ]
+ },
+ "11": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_interpro/load_interpro/2.3.4+galaxy0",
+ "errors": null,
+ "id": 11,
+ "input_connections": {
+ "input": {
+ "id": 5,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 10,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load InterProScan results",
+ "name": "organism_id"
+ }
+ ],
+ "label": "load interproscan results org2",
+ "name": "Chado load InterProScan results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 429.8999938964844,
+ "height": 164.39999389648438,
+ "left": 1388,
+ "right": 1588,
+ "top": 265.5,
+ "width": 200,
+ "x": 1388,
+ "y": 265.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_interpro/load_interpro/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "3284a0c7570e",
+ "name": "chado_load_interpro",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"parse_go\": \"false\", \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "a6f4ea32-821c-4d8f-92b8-133dedad1cf3",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "1116bc6e-ffde-404d-8f94-f90310babad4"
+ }
+ ]
+ },
+ "12": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 12,
+ "input_connections": {
+ "wait_for": {
+ "id": 11,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync blastp analysis org1",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 424.8999938964844,
+ "height": 154.39999389648438,
+ "left": 1666,
+ "right": 1866,
+ "top": 270.5,
+ "width": 200,
+ "x": 1666,
+ "y": 270.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "ded3538e-88bb-4958-bab2-59236702a55a",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "872ba62f-d5b2-4be6-8e04-312fc323b66e"
+ }
+ ]
+ },
+ "13": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 13,
+ "input_connections": {
+ "wait_for": {
+ "id": 12,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync blastp analysis org2",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 424.8999938964844,
+ "height": 154.39999389648438,
+ "left": 1944,
+ "right": 2144,
+ "top": 270.5,
+ "width": 200,
+ "x": 1944,
+ "y": 270.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "856b071e-d134-401a-8083-c937ef1e9a82",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "dbb5ca07-fc4b-4792-8b0a-225799e35ed9"
+ }
+ ]
+ },
+ "14": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 14,
+ "input_connections": {
+ "wait_for": {
+ "id": 13,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync blastx analysis org1",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 424.8999938964844,
+ "height": 154.39999389648438,
+ "left": 2222,
+ "right": 2422,
+ "top": 270.5,
+ "width": 200,
+ "x": 2222,
+ "y": 270.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "9f737334-00a3-40e4-8d1d-2c82e43ea41c",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "fce3de08-8796-43e0-922d-7f6fbf35c20c"
+ }
+ ]
+ },
+ "15": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 15,
+ "input_connections": {
+ "wait_for": {
+ "id": 14,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync blastx analysis org2",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 424.8999938964844,
+ "height": 154.39999389648438,
+ "left": 2500,
+ "right": 2700,
+ "top": 270.5,
+ "width": 200,
+ "x": 2500,
+ "y": 270.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "c9579d14-f8e8-4d98-8c15-55242f6ab970",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "163dfb0c-e4fc-406e-aff3-0377deb0808b"
+ }
+ ]
+ },
+ "16": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 16,
+ "input_connections": {
+ "wait_for": {
+ "id": 15,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync interproscan analysis org1",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 424.8999938964844,
+ "height": 154.39999389648438,
+ "left": 2778,
+ "right": 2978,
+ "top": 270.5,
+ "width": 200,
+ "x": 2778,
+ "y": 270.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "78622cfb-78f2-468d-8427-cf3763b28630",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "ca3e8b73-686d-4975-88b6-388decfb63da"
+ }
+ ]
+ },
+ "17": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 17,
+ "input_connections": {
+ "wait_for": {
+ "id": 16,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync interproscan analysis org2",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 424.8999938964844,
+ "height": 154.39999389648438,
+ "left": 3056,
+ "right": 3256,
+ "top": 270.5,
+ "width": 200,
+ "x": 3056,
+ "y": 270.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "191af79d-80cb-4da3-b6b8-47a3f651ba4b",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "cfc30f51-85f5-4bda-9ae0-9550805a306e"
+ }
+ ]
+ },
+ "18": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 18,
+ "input_connections": {
+ "wait_for": {
+ "id": 17,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "populate mat views",
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 424.8999938964844,
+ "height": 154.39999389648438,
+ "left": 3334,
+ "right": 3534,
+ "top": 270.5,
+ "width": 200,
+ "x": 3334,
+ "y": 270.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "3c08f32a3dc1",
+ "name": "tripal_db_populate_mviews",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"mview\": \"\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "b2c9b425-3df6-40a8-b83f-d4719c2c925f",
+ "workflow_outputs": [
+ {
+ "label": "Populate Tripal materialized view(s)",
+ "output_name": "results",
+ "uuid": "7942bda1-54d6-4ae7-9694-e8946d089d9b"
+ }
+ ]
+ },
+ "19": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 19,
+ "input_connections": {
+ "wait_for": {
+ "id": 18,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "index tripal data",
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 426.1000061035156,
+ "height": 113.60000610351562,
+ "left": 3612,
+ "right": 3812,
+ "top": 312.5,
+ "width": 200,
+ "x": 3612,
+ "y": 312.5
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "tool_shed_repository": {
+ "changeset_revision": "d55a39f12dda",
+ "name": "tripal_db_index",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"expose\": {\"do_expose\": \"no\", \"__current_case__\": 0}, \"queues\": \"10\", \"table\": {\"mode\": \"website\", \"__current_case__\": 0}, \"tokenizer\": \"standard\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": null,
+ "type": "tool",
+ "uuid": "7bce942d-6087-43a9-aa07-fd64d1a7079c",
+ "workflow_outputs": [
+ {
+ "label": "Index Tripal data",
+ "output_name": "results",
+ "uuid": "87687ee1-8319-47b1-a94c-2ea95ac88511"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "419ce581-8a2f-4376-a0ce-df72321bf11d",
+ "version": 10
+}
\ No newline at end of file
--
GitLab