From 67ce6973feffc7a9548f3407aaa9672a094a2c49 Mon Sep 17 00:00:00 2001
From: Mada2 <arthur.lebars22@gmail.com>
Date: Wed, 25 Mar 2020 19:30:39 +0100
Subject: [PATCH] added use of new scripts before data loading
(headers+blastdb)
---
autoload.py | 155 ++++++++++++++++++++++++++++------------------------
1 file changed, 83 insertions(+), 72 deletions(-)
diff --git a/autoload.py b/autoload.py
index 82779cd..089a4d5 100644
--- a/autoload.py
+++ b/autoload.py
@@ -11,6 +11,7 @@ import numpy
import pandas
import logging
import re
+from . import table_parser
class Autoload:
@@ -82,7 +83,6 @@ class Autoload:
- change headers for pep file
- load data into the galaxy container with the galaxy_data_libs_SI.py script
- :param method:
:return:
"""
os.chdir(self.main_dir)
@@ -101,10 +101,8 @@ class Autoload:
species_folder_name = "_".join([self.genus_lowercase, self.species, self.strain, self.sex])
try:
os.mkdir("./src_data")
- os.mkdir("./src_data/annotation")
- os.mkdir("./src_data/genome")
- os.mkdir("./src_data/annotation/" + species_folder_name)
- os.mkdir("./src_data/genome/" + species_folder_name)
+ os.mkdir("./src_data/annotation /src_data/genome")
+ os.mkdir("./src_data/annotation/" + species_folder_name + " ./src_data/genome/" + species_folder_name)
except FileExistsError:
logging.debug("src_data directory tree already exists")
except PermissionError:
@@ -141,7 +139,14 @@ class Autoload:
self.source_files["proteins_file"]]
logging.info("changing fasta headers in " + self.source_files["proteins_file"])
subprocess.run(modify_pep_headers, stdout=subprocess.PIPE, cwd=annotation_dir)
-
+ # production version
+ modify_pep_headers = ["/usr/local/genome2/mmo/scripts/phaeoexplorer/phaeoexplorer-change_transcript_fasta_header.sh",
+ self.source_files["proteins_file"]]
+ # test version
+ modify_pep_headers = ["/home/alebars/gga/phaeoexplorer-change_transcript_fasta_header.sh",
+ self.source_files["proteins_file"]]
+ logging.info("changing fasta headers in " + self.source_files["transcripts_file"])
+ subprocess.run(modify_pep_headers, stdout=subprocess.PIPE, cwd=annotation_dir)
# src_data cleaning
if os.path.exists(annotation_dir + "outfile"):
subprocess.run(["mv", annotation_dir + "/outfile", self.source_files["proteins_file"]],
@@ -413,69 +418,75 @@ class Autoload:
return None
-parser = argparse.ArgumentParser(description="Input genus, species, strain, version")
-parser.add_argument("json", type=str, help="Input JSON file")
-parser.add_argument("-v", "--verbose",
- help="Increase output verbosity",
- action="store_true")
-parser.add_argument("--init-instance",
- help="Initialization of galaxy instance. Run first in an empty instance",
- action="store_true")
-parser.add_argument("--load-data",
- help="Create src_data directory tree and load its data into the instance",
- action="store_true")
-parser.add_argument("--run-main",
- help="Run main workflow (load data into chado, sync all with tripal, "
- "index tripal data, populate materialized view, "
- "create a jbrowse for the current genus_species_strain_sex and add organism to jbrowse",
- action="store_true")
-args = parser.parse_args()
-
-if args.verbose:
- logging.basicConfig(level=logging.DEBUG)
-else:
- logging.basicConfig(level=logging.INFO)
-
-sp_dict_list = list()
-with open(args.json, 'r') as infile:
- json_sp_dict = json.load(infile)
- json_sp_dump = json.dumps(json_sp_dict, indent=4, sort_keys=True)
- for json_sp in json_sp_dict:
- sp_dict_list.append(json_sp)
-
-for sp_dict in sp_dict_list:
- al = Autoload(species_parameters_dictionary=sp_dict, args=args)
- if args.init_instance:
- logging.info("initializing the galaxy instance")
- al.init_instance()
- al.get_instance_attributes()
- if args.load_data:
- logging.info("loading data into galaxy")
- al.load_data_in_galaxy()
- if args.run_main:
- logging.info("running main workflow")
- al.get_organism_and_analyses_ids()
- workflow_parameters = dict()
- workflow_parameters["0"] = {}
- workflow_parameters["1"] = {}
- workflow_parameters["2"] = {}
- workflow_parameters["3"] = {}
- workflow_parameters["4"] = {"organism": al.org_id,
- "analysis_id": al.genome_analysis_id,
- "do_update": "true"}
- workflow_parameters["5"] = {"organism": al.org_id,
- "analysis_id": al.ogs_analysis_id}
- workflow_parameters["6"] = {"organism_id": al.org_id}
- workflow_parameters["7"] = {"analysis_id": al.ogs_analysis_id}
- workflow_parameters["8"] = {"analysis_id": al.genome_analysis_id}
- workflow_parameters["9"] = {"organism_id": al.org_id}
- workflow_parameters["10"] = {}
- workflow_parameters["11"] = {}
-
- al.datamap = dict()
- al.datamap["0"] = {"src": "hda", "id": al.datasets["genome_file"]}
- al.datamap["1"] = {"src": "hda", "id": al.datasets["gff_file"]}
- al.datamap["2"] = {"src": "hda", "id": al.datasets["proteins_file"]}
- al.datamap["3"] = {"src": "hda", "id": al.datasets["transcripts_file"]}
-
- al.run_workflow(workflow_name="main", workflow_parameters=workflow_parameters, datamap=al.datamap)
+if __name__ == "main":
+ parser = argparse.ArgumentParser(description="Automatic loading and interaction with galaxy instance (GGA)"
+ ", following the protocol @ "
+ "http://gitlab.sb-roscoff.fr/abims/e-infra/gga")
+ parser.add_argument("-j", "--json", type=str, help="Input JSON file, alternative"
+ " to input csv file", action="store_true")
+ parser.add_argument("table", type=str, help="Input table (tabulated file that describes all data)",
+ action="store_true")
+ parser.add_argument("-v", "--verbose",
+ help="Increase output verbosity",
+ action="store_true")
+ parser.add_argument("--init-instance",
+ help="Initialization of galaxy instance. Run first in an empty instance",
+ action="store_true")
+ parser.add_argument("--load-data",
+ help="Create src_data directory tree and load its data into the instance",
+ action="store_true")
+ parser.add_argument("--run-main",
+ help="Run main workflow (load data into chado, sync all with tripal, "
+ "index tripal data, populate materialized view, "
+ "create a jbrowse for the current genus_species_strain_sex and add organism to jbrowse",
+ action="store_true")
+ args = parser.parse_args()
+
+ if args.verbose:
+ logging.basicConfig(level=logging.DEBUG)
+ else:
+ logging.basicConfig(level=logging.INFO)
+
+ sp_dict_list = list()
+ with open(args.json, 'r') as infile:
+ json_sp_dict = json.load(infile)
+ json_sp_dump = json.dumps(json_sp_dict, indent=4, sort_keys=True)
+ for json_sp in json_sp_dict:
+ sp_dict_list.append(json_sp)
+
+ for sp_dict in sp_dict_list:
+ al = Autoload(species_parameters_dictionary=sp_dict, args=args)
+ if args.init_instance:
+ logging.info("initializing the galaxy instance")
+ al.init_instance()
+ al.get_instance_attributes()
+ if args.load_data:
+ logging.info("loading data into galaxy")
+ al.load_data_in_galaxy()
+ if args.run_main:
+ logging.info("running main workflow")
+ al.get_organism_and_analyses_ids()
+ workflow_parameters = dict()
+ workflow_parameters["0"] = {}
+ workflow_parameters["1"] = {}
+ workflow_parameters["2"] = {}
+ workflow_parameters["3"] = {}
+ workflow_parameters["4"] = {"organism": al.org_id,
+ "analysis_id": al.genome_analysis_id,
+ "do_update": "true"}
+ workflow_parameters["5"] = {"organism": al.org_id,
+ "analysis_id": al.ogs_analysis_id}
+ workflow_parameters["6"] = {"organism_id": al.org_id}
+ workflow_parameters["7"] = {"analysis_id": al.ogs_analysis_id}
+ workflow_parameters["8"] = {"analysis_id": al.genome_analysis_id}
+ workflow_parameters["9"] = {"organism_id": al.org_id}
+ workflow_parameters["10"] = {}
+ workflow_parameters["11"] = {}
+
+ al.datamap = dict()
+ al.datamap["0"] = {"src": "hda", "id": al.datasets["genome_file"]}
+ al.datamap["1"] = {"src": "hda", "id": al.datasets["gff_file"]}
+ al.datamap["2"] = {"src": "hda", "id": al.datasets["proteins_file"]}
+ al.datamap["3"] = {"src": "hda", "id": al.datasets["transcripts_file"]}
+
+ al.run_workflow(workflow_name="main", workflow_parameters=workflow_parameters, datamap=al.datamap)
--
GitLab