From b33c4b5e9f172b3d515615e37ff8b440405a8aa6 Mon Sep 17 00:00:00 2001
From: Arthur Le Bars <arthur.le-bars@sb-roscoff.fr>
Date: Fri, 5 Feb 2021 15:31:15 +0100
Subject: [PATCH] Added interpro and blast workflows and methods
---
gga_init.py | 13 +-
run_workflow_phaeoexplorer.py | 126 +++++++++-
templates/orthology_compose_template.yml.j2 | 149 ++++++++++++
workflows/Blast_Diamond.ga | 244 ++++++++++++++++++++
workflows/Interproscan.ga | 236 +++++++++++++++++++
5 files changed, 759 insertions(+), 9 deletions(-)
create mode 100644 templates/orthology_compose_template.yml.j2
create mode 100644 workflows/Blast_Diamond.ga
create mode 100644 workflows/Interproscan.ga
diff --git a/gga_init.py b/gga_init.py
index b0b7436..95ee781 100644
--- a/gga_init.py
+++ b/gga_init.py
@@ -181,7 +181,6 @@ class DeploySpeciesStack(speciesData.SpeciesData):
:return:
"""
- # Proceed to the traefik and authelia directories
os.chdir(self.main_dir)
# Create directory tree
@@ -229,6 +228,18 @@ class DeploySpeciesStack(speciesData.SpeciesData):
os.chdir(self.main_dir)
+ def make_orthology_compose_files(self):
+ """
+
+ :return:
+ """
+
+ os.chdir(self.main_dir)
+
+ self.make_dirs["./orthology", "./orthology/src_data", "./orthology/src_data/genomes",
+ "./orthology/src_data/gff", "./orthology/src_data/newicks", "./orthology/src_data/proteomes"]
+
+
def create_mounts(self, working_dir):
"""
Create the folders (volumes) required by a container (to see required volumes, check their compose file)
diff --git a/run_workflow_phaeoexplorer.py b/run_workflow_phaeoexplorer.py
index a67b7e7..27ec597 100644
--- a/run_workflow_phaeoexplorer.py
+++ b/run_workflow_phaeoexplorer.py
@@ -337,12 +337,20 @@ class RunWorkflow(speciesData.SpeciesData):
elif "gff" in e["name"]:
self.datasets["gff_file"] = e["ldda_id"]
logging.debug("\t" + e["name"] + ": " + e["ldda_id"])
+ elif e["name"].endswith(".xml") and e["name"].startswith("Interpro"):
+ self.datasets["interproscan_file"] = e["ldda_id"]
+ logging.debug("\t" + e["name"] + ": " + e["ldda_id"])
+ elif e["name"].endswith(".xml") and "diamond" in e["name"]:
+ self.datasets["blast_diamond_file"] = e["ldda_id"]
+ logging.debug("\t" + e["name"] + ": " + e["ldda_id"])
logging.info("Uploading datasets into history %s" % self.history_id)
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["genome_file"])
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["gff_file"])
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["transcripts_file"])
self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["proteins_file"])
+ self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["interproscan_file"])
+ self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["blast_diamond_file"])
_datasets = self.instance.datasets.get_datasets()
with open(os.path.join(self.main_dir, "datasets_ids.json"), "w") as datasets_ids_outfile:
@@ -370,13 +378,14 @@ class RunWorkflow(speciesData.SpeciesData):
history_datasets_li = self.instance.datasets.get_datasets()
genome_dataset_hda_id, gff_dataset_hda_id, transcripts_dataset_hda_id, proteins_datasets_hda_id = None, None, None, None
+ interproscan_dataset_hda_id, blast_diamond_dataset_hda_id = None, None
genome_dataset_hda_id = history_datasets_li[3]["id"]
gff_dataset_hda_id = history_datasets_li[2]["id"]
transcripts_dataset_hda_id = history_datasets_li[1]["id"]
proteins_datasets_hda_id = history_datasets_li[0]["id"]
- for dataset_dict in history_datasets_li[0:3]:
+ for dataset_dict in history_datasets_li[0:5]:
# Datasets imports should be the last jobs in history if the function calls are in correct order
# If not, add the function call "get_datasets_hda_ids()" just after "import_datasets_into_history()"
if dataset_dict["name"].endswith("proteins.fa"):
@@ -388,13 +397,20 @@ class RunWorkflow(speciesData.SpeciesData):
elif dataset_dict["name"].endswith(".gff"):
gff_dataset_hda_id = dataset_dict["id"]
logging.debug("gff dataset hda ID: %s" % gff_dataset_hda_id)
+ elif dataset_dict["name"].endwsith(".xml") and dataset["name"].startswith("Interpro"):
+ interproscan_dataset_hda_id = dataset_dict["id"]
+ logging.debug("InterproScan dataset hda ID: %s" % gff_dataset_hda_id)
+ elif dataset_dict["name"].endswith(".xml") and "diamond" in dataset_dict["name"]:
+ blast_diamond_dataset_hda_id = dataset_dict["id"]
+ logging.debug("Blast Diamond dataset hda ID: %s" % gff_dataset_hda_id)
else:
genome_dataset_hda_id = dataset_dict["id"]
logging.debug("Genome dataset hda id: %s" % genome_dataset_hda_id)
# Return a dict made of the hda ids
return{"genome_hda_id": genome_dataset_hda_id, "transcripts_hda_id": transcripts_dataset_hda_id,
- "proteins_hda_id": proteins_datasets_hda_id, "gff_hda_id": gff_dataset_hda_id}
+ "proteins_hda_id": proteins_datasets_hda_id, "gff_hda_id": gff_dataset_hda_id,
+ "interproscan_hda_id": interproscan_dataset_hda_id, "blast_diamond_hda_id": blast_diamond_dataset_hda_id}
def get_organism_and_analyses_ids(self):
"""
@@ -442,7 +458,7 @@ class RunWorkflow(speciesData.SpeciesData):
ogs_analysis_output = json.loads(ogs_analysis_json_output)[0]
self.ogs_analysis_id = str(ogs_analysis_output["analysis_id"])
except IndexError:
- logging.debug("no matching OGS analysis exists in the instance's chado database")
+ logging.debug("No matching OGS analysis exists in the instance's chado database")
# Get the ID for the genome analysis in chado
genome_analysis = self.instance.tools.run_tool(
@@ -457,7 +473,32 @@ class RunWorkflow(speciesData.SpeciesData):
except IndexError:
logging.debug("no matching genome analysis exists in the instance's chado database")
- return {"org_id": self.org_id, "genome_analysis_id": self.genome_analysis_id, "ogs_analysis_id": self.ogs_analysis_id}
+ interpro_analysis = self.instance.tools.run_tool(
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3",
+ history_id=self.history_id,
+ tool_inputs={"name": "InterproScan on OGS%s" % self.ogs_version})
+ interpro_analysis_job_out = interpro_analysis["outputs"][0]["id"]
+ interpro_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=interpro_analysis_job_out)
+ try:
+ interpro_analysis_output = json.loads(interpro_analysis_json_output)[0]
+ self.interpro_analysis_id = str(interpro_analysis_output["analysis_id"])
+ except IndexError:
+ logging.debug("No matching InterproScan analysis exists in the instance's chado database")
+
+ blast_diamond_analysis = self.instance.tools.run_tool(
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3",
+ history_id=self.history_id,
+ tool_inputs={"name": "Diamond on OGS%s" % self.ogs_version})
+ blast_diamond_analysis_job_out = blast_diamond_analysis["outputs"][0]["id"]
+ blast_diamond_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=blast_diamond_analysis_job_out)
+ try:
+ blast_diamond_analysis_output = json.loads(blast_diamond_analysis_json_output)[0]
+ self.blast_diamond_analysis_id = str(blast_diamond_analysis_output["analysis_id"])
+ except IndexError:
+ logging.debug("No matching InterproScan analysis exists in the instance's chado database")
+
+ return {"org_id": self.org_id, "genome_analysis_id": self.genome_analysis_id, "ogs_analysis_id": self.ogs_analysis_id,
+ "interpro_analysis_id": self.interpro_analysis_id, "blast_diamond_analysis_id": self.blast_diamond_analysis_id}
if __name__ == "__main__":
@@ -572,7 +613,7 @@ if __name__ == "__main__":
# Import datasets into history and retrieve their hda IDs
run_workflow_for_current_organism.import_datasets_into_history()
- run_workflow_for_current_organism.get_datasets_hda_ids()
+ hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
# Explicit workflow parameter names
GENOME_FASTA_FILE = "0"
@@ -656,8 +697,6 @@ if __name__ == "__main__":
run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE] = {"src": "hda", "id": hda_ids["genome_hda_id"]}
run_workflow_for_current_organism.datamap[GFF_FILE] = {"src": "hda", "id": hda_ids["gff_hda_id"]}
- # run_workflow_for_current_organism.replace_placeholders_workflow(workflow_str=json.dumps(workflow))
-
# Run the jbrowse creation workflow
run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
workflow_parameters=workflow_parameters,
@@ -672,13 +711,84 @@ if __name__ == "__main__":
run_workflow_for_current_organism.set_get_history()
# run_workflow_for_current_organism.get_species_history_id()
+ # Prepare the instance+history for the current organism (add organism and analyses in Chado)
+ # (although it should pose no problem as the "Chado add" refuses to duplicate an analysis/organism anyway)
+ if args.setup:
+ run_workflow_for_current_organism.prepare_history()
+
# Get the attributes of the instance and project data files
run_workflow_for_current_organism.get_instance_attributes()
run_workflow_for_current_organism.get_organism_and_analyses_ids()
# Import datasets into history and retrieve their hda IDs
run_workflow_for_current_organism.import_datasets_into_history()
- run_workflow_for_current_organism.get_datasets_hda_ids()
+ hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
+
+ INTERPRO_FILE = "0"
+ LOAD_INTERPRO_IN_CHADO = "1"
+ SYNC_INTERPRO_ANALYSIS_INTO_TRIPAL = "2"
+ SYNC_FEATURES_INTO_TRIPAL = "3"
+ POPULATE_MAT_VIEWS = "4"
+ INDEX_TRIPAL_DATA = "5"
+
+ workflow_parameters = {}
+ workflow_parameters[INTERPRO_FILE] = {}
+ workflow_parameters[LOAD_INTERPRO_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
+ "analysis_id": run_workflow_for_current_organism.interpro_analysis_id}
+ workflow_parameters[SYNC_INTERPRO_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.interpro_analysis_id}
+
+
+ run_workflow_for_current_organism.datamap = {}
+ run_workflow_for_current_organism.datamap[INTERPRO_FILE] = {"src": "hda", "id": hda_ids["interproscan_hda_id"]}
+
+ # Run Interproscan workflow
+ run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
+ workflow_parameters=workflow_parameters,
+ datamap=run_workflow_for_current_organism.datamap,
+ workflow_name="Interproscan")
+
+ elif "Blast" in str(workflow):
+
+ logging.info("Executing workflow 'Blast_Diamond")
+
+ run_workflow_for_current_organism.connect_to_instance()
+ run_workflow_for_current_organism.set_get_history()
+ # run_workflow_for_current_organism.get_species_history_id()
+
+ # Prepare the instance+history for the current organism (add organism and analyses in Chado)
+ # (although it should pose no problem as the "Chado add" refuses to duplicate an analysis/organism anyway)
+ if args.setup:
+ run_workflow_for_current_organism.prepare_history()
+
+ # Get the attributes of the instance and project data files
+ run_workflow_for_current_organism.get_instance_attributes()
+ run_workflow_for_current_organism.get_organism_and_analyses_ids()
+
+ # Import datasets into history and retrieve their hda IDs
+ run_workflow_for_current_organism.import_datasets_into_history()
+ hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
+
+ BLAST_FILE = "0"
+ LOAD_BLAST_IN_CHADO = "1"
+ SYNC_BLAST_ANALYSIS_INTO_TRIPAL = "2"
+ SYNC_FEATURES_INTO_TRIPAL = "3"
+ POPULATE_MAT_VIEWS = "4"
+ INDEX_TRIPAL_DATA = "5"
+
+ workflow_parameters = {}
+ workflow_parameters[INTERPRO_FILE] = {}
+ workflow_parameters[LOAD_BLAST_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
+ "analysis_id": run_workflow_for_current_organism.blast_diamond_analysis_id}
+ workflow_parameters[SYNC_BLAST_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.blast_diamond_analysis_id}
+
+ run_workflow_for_current_organism.datamap = {}
+ run_workflow_for_current_organism.datamap[INTERPRO_FILE] = {"src": "hda", "id": hda_ids["interproscan_hda_id"]}
+
+ # Run Interproscan workflow
+ run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
+ workflow_parameters=workflow_parameters,
+ datamap=run_workflow_for_current_organism.datamap,
+ workflow_name="Interproscan")
else:
diff --git a/templates/orthology_compose_template.yml.j2 b/templates/orthology_compose_template.yml.j2
new file mode 100644
index 0000000..58af1ea
--- /dev/null
+++ b/templates/orthology_compose_template.yml.j2
@@ -0,0 +1,149 @@
+# ./docker_data is created and filled with persistent data that should be backuped
+
+version: '3.7'
+services:
+ tripal:
+ image: quay.io/galaxy-genome-annotation/tripal:v2.x
+ depends_on:
+ - tripal-db
+ volumes:
+ - ./docker_data/galaxy/:/export/:ro
+ - ./src_data/:/data/:ro
+ environment:
+ DB_HOST: tripal-db.orthology
+ BASE_URL_PATH: /sp/orthology
+ UPLOAD_LIMIT: 20M
+ MEMORY_LIMIT: 512M
+ TRIPAL_GIT_CLONE_MODULES: "https://github.com/abretaud/tripal_rest_api.git[@c6f9021ea5d4c6d7c67c5bd363a7dd9359228bbc] https://github.com/abretaud/tripal_linkout.git[@91e08a11b788f005631cc0fafa4d68b1d2ce3ceb] https://github.com/abretaud/tripal_phylotree.git[@4cad769c9deaa5cd2933e1ae29be6aea8c8c0cc2]"
+ TRIPAL_DOWNLOAD_MODULES: ""
+ TRIPAL_ENABLE_MODULES: "tripal_rest_api tripal_phylotree tripal_linkout"
+ SITE_NAME: "Orthology"
+ ENABLE_JBROWSE: 0
+ ENABLE_APOLLO: 0
+ ENABLE_BLAST: 0
+ ENABLE_DOWNLOAD: 0
+ ENABLE_WIKI: 0
+ ENABLE_GO: 0
+ ENABLE_ORTHOLOGY: 1
+ # Must match the SITE_NAME in the gcv part
+ GCV_SITE_NAME: "example"
+ # Use this to point to the external adress of your main tripal host
+ MAIN_TRIPAL_URL: "http://{{ hostname }}"
+ #THEME: "{{ tripal_theme_name }}" # Use this to use another theme
+ #THEME_GIT_CLONE: "{{ tripal_theme_git_clone }}" # Use this to install another theme
+ ADMIN_PASSWORD: {{ tripal_password }} # You need to define it and update it in galaxy config below
+ networks:
+ - traefikbig
+ - orthology
+ deploy:
+ labels:
+ - "traefik.http.routers.orthology-tripal.rule=(Host(`{{ hostname }}`) && PathPrefix(`/sp/orthology`))"
+ - "traefik.http.routers.orthology-tripal.tls=true"
+ - "traefik.http.routers.orthology-tripal.entryPoints=webs"
+ - "traefik.http.routers.orthology-tripal.middlewares=sp-auth,sp-trailslash,sp-prefix,tripal-addprefix"
+ - "traefik.http.services.orthology-tripal.loadbalancer.server.port=80"
+ restart_policy:
+ condition: on-failure
+ delay: 5s
+ max_attempts: 3
+ window: 120s
+
+ tripal-db:
+ image: quay.io/galaxy-genome-annotation/chado:1.31-jenkins21-pg9.5
+ environment:
+ - POSTGRES_PASSWORD=postgres
+ # The default chado image would try to install the schema on first run,
+ # we just want the tools to be available.
+ - INSTALL_CHADO_SCHEMA=0
+ - INSTALL_YEAST_DATA=0
+ volumes:
+ - ./docker_data/tripal_db/:/var/lib/postgresql/data/
+ networks:
+ - orthology
+
+ gcv:
+ image: quay.io/abretaud/lis-gcv
+ depends_on:
+ - tripal-db
+ environment:
+ DB_HOST: tripal-db.orthology
+ HOST: {{ hostname }}
+ SITE_NAME: example
+ SITE_FULL_NAME: example
+ DEBUG: "false"
+ GCV_URL: http://{{ hostname }}/sp/orthology/gcv
+ SERVICES_URL: http://{{ hostname }}/sp/orthology/gcv_api/services
+ TRIPAL_URL: http://{{ hostname }}/sp/orthology/
+ USE_GENE_UNAME: "true"
+ networks:
+ - traefikbig
+ - orthology
+ deploy:
+ labels:
+ - "traefik.http.routers.orthology-gcv.rule=(Host(`{{ hostname }}`) && PathPrefix(`/sp/orthology/gcv`))"
+ - "traefik.http.routers.orthology-gcv.tls=true"
+ - "traefik.http.routers.orthology-gcv.entryPoints=webs"
+ - "traefik.http.routers.orthology-gcv.service=orthology-gcv"
+ - "traefik.http.routers.orthology-gcv.middlewares=sp-auth,sp-app-trailslash,sp-app-prefix"
+ - "traefik.http.services.orthology-gcv.loadbalancer.server.port=80"
+
+ - "traefik.http.routers.orthology-gcv-api.rule=(Host(`{{ hostname }}`) && PathPrefix(`/sp/orthology/gcv_api`))"
+ - "traefik.http.routers.orthology-gcv-api.tls=true"
+ - "traefik.http.routers.orthology-gcv-api.entryPoints=webs"
+ - "traefik.http.routers.orthology-gcv-api.service=orthology-gcv-api"
+ - "traefik.http.routers.orthology-gcv-api.middlewares=sp-auth,sp-app-trailslash,sp-app-prefix"
+ - "traefik.http.services.orthology-gcv-api.loadbalancer.server.port=8000"
+ restart_policy:
+ condition: on-failure
+ delay: 5s
+ max_attempts: 3
+ window: 120s
+
+ galaxy:
+ image: quay.io/galaxy-genome-annotation/docker-galaxy-annotation:gmod
+ volumes:
+ - ../galaxy_data_libs_SI.py:/opt/setup_data_libraries.py
+ - ./docker_data/galaxy/:/export/
+ - ./src_data/:/project_data/:ro
+ #- /groups/XXX/:/groups/XXX/:ro # We do this when we have symlinks in src_data pointing to /groups/XXX/...
+ environment:
+ NONUSE: nodejs,proftp,reports,condor
+ GALAXY_LOGGING: full
+ GALAXY_CONFIG_BRAND: "Orthology"
+ GALAXY_CONFIG_ALLOW_LIBRARY_PATH_PASTE: "True"
+ GALAXY_CONFIG_USE_REMOTE_USER: "True"
+ GALAXY_CONFIG_REMOTE_USER_MAILDOMAIN: "bipaa"
+ GALAXY_CONFIG_ADMIN_USERS: "admin@galaxy.org,gogepp@bipaa" # admin@galaxy.org is the default (leave it), gogepp@bipaa is a shared ldap user we use to connect
+ ENABLE_FIX_PERMS: 0
+ PROXY_PREFIX: /sp/orthology/galaxy
+ GALAXY_TRIPAL_URL: http://tripal.orthology/tripal/
+ GALAXY_TRIPAL_PASSWORD: {{ tripal_password }} # See tripal config above
+ GALAXY_CHADO_DBHOST: tripal-db.orthology
+ GALAXY_CHADO_DBSCHEMA: chado
+ GALAXY_AUTO_UPDATE_DB: 1
+ GALAXY_AUTO_UPDATE_CONDA: 1
+ GALAXY_AUTO_UPDATE_TOOLS: "/galaxy-central/tools_1.yaml"
+ GALAXY_SHARED_DIR: ""
+ BLAT_ENABLED: 1
+ networks:
+ - traefikbig
+ - orthology
+ deploy:
+ labels:
+ - "traefik.http.routers.orthology-galaxy.rule=(Host(`{{ hostname }}`) && PathPrefix(`/sp/orthology/galaxy`))"
+ - "traefik.http.routers.orthology-galaxy.tls=true"
+ - "traefik.http.routers.orthology-galaxy.entryPoints=webs"
+ - "traefik.http.routers.orthology-galaxy.middlewares=sp-auth,sp-app-trailslash,sp-app-prefix"
+ - "traefik.http.services.orthology-galaxy.loadbalancer.server.port=80"
+ restart_policy:
+ condition: on-failure
+ delay: 5s
+ max_attempts: 3
+ window: 120s
+
+networks:
+ traefikbig:
+ external: true
+ orthology:
+ driver: overlay
+ name: orthology
diff --git a/workflows/Blast_Diamond.ga b/workflows/Blast_Diamond.ga
new file mode 100644
index 0000000..479b7d9
--- /dev/null
+++ b/workflows/Blast_Diamond.ga
@@ -0,0 +1,244 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "Blast_Diamond",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [],
+ "label": null,
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "left": 200,
+ "top": 200
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "89e7487e-004d-4db1-b5eb-1676b98aebde",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "c1602850-3c2c-44b9-87fa-af3509c6e751"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 1,
+ "input_connections": {
+ "input": {
+ "id": 0,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "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": null,
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "left": 487.66668701171875,
+ "top": 200
+ },
+ "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\": \"59\", \"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": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "a9d3b3a9-b377-44cd-bc10-87b37edb52b5",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "e686e177-04ac-41e9-ab42-a40cd6d5a0a7"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 2,
+ "input_connections": {
+ "wait_for": {
+ "id": 1,
+ "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": null,
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "left": 775.3333740234375,
+ "top": 200
+ },
+ "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": "3.2.1.0",
+ "type": "tool",
+ "uuid": "8ed9fc57-f900-456f-9c77-b75a20d90b76",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "7c31aa69-2993-4d1f-a6ef-6a014cf68964"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 3,
+ "input_connections": {
+ "wait_for": {
+ "id": 2,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "left": 1063,
+ "top": 200
+ },
+ "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": "3.2.1.0",
+ "type": "tool",
+ "uuid": "7da6acf6-87a1-4c26-a750-3bf410d2642d",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "b747c370-0b27-4a8a-b1dd-71c0f9635cc6"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 4,
+ "input_connections": {
+ "wait_for": {
+ "id": 3,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "left": 1350.6666259765625,
+ "top": 200
+ },
+ "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": "3.2.1.1",
+ "type": "tool",
+ "uuid": "5808d837-a507-4fe5-8a90-ad1934645b56",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "2db45aa2-e09e-493b-b095-47dac7dff6fc"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "3119f6f5-5500-4d9f-b939-123c54d31968",
+ "version": 1
+}
\ No newline at end of file
diff --git a/workflows/Interproscan.ga b/workflows/Interproscan.ga
new file mode 100644
index 0000000..41f4a2b
--- /dev/null
+++ b/workflows/Interproscan.ga
@@ -0,0 +1,236 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "Interproscan",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [],
+ "label": null,
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "left": 200,
+ "top": 200
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "89e7487e-004d-4db1-b5eb-1676b98aebde",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "032bfe93-96b6-4628-a7e2-209f92a94b4f"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_interpro/load_interpro/2.3.4+galaxy0",
+ "errors": null,
+ "id": 1,
+ "input_connections": {
+ "input": {
+ "id": 0,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 0,
+ "output_name": "output"
+ }
+ },
+ "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": null,
+ "name": "Chado load InterProScan results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "left": 487.66668701171875,
+ "top": 200
+ },
+ "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": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "81eab133-ed2e-4302-9c3c-75c035a12840",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "e53f0344-9fde-4489-a951-636507c6bef8"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 2,
+ "input_connections": {
+ "wait_for": {
+ "id": 1,
+ "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": null,
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "left": 775.3333740234375,
+ "top": 200
+ },
+ "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": "3.2.1.0",
+ "type": "tool",
+ "uuid": "8ed9fc57-f900-456f-9c77-b75a20d90b76",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "7c31aa69-2993-4d1f-a6ef-6a014cf68964"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 3,
+ "input_connections": {
+ "wait_for": {
+ "id": 2,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "left": 1063,
+ "top": 200
+ },
+ "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": "3.2.1.0",
+ "type": "tool",
+ "uuid": "7da6acf6-87a1-4c26-a750-3bf410d2642d",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "b747c370-0b27-4a8a-b1dd-71c0f9635cc6"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 4,
+ "input_connections": {
+ "wait_for": {
+ "id": 3,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "left": 1350.6666259765625,
+ "top": 200
+ },
+ "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": "3.2.1.1",
+ "type": "tool",
+ "uuid": "5808d837-a507-4fe5-8a90-ad1934645b56",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "2db45aa2-e09e-493b-b095-47dac7dff6fc"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "3446613c-b251-4a11-98fe-4965948773c3",
+ "version": 4
+}
\ No newline at end of file
--
GitLab