diff --git a/Dockerfile b/Dockerfile
index a861df27ca4c8544c1ecd482543794baad34491e..4f837065c9c7ecb64aae692a9550ebb51c17c3a5 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -2,8 +2,9 @@ FROM centos:7
RUN yum install -y epel-release wget gcc https://repo.ius.io/ius-release-el7.rpm
RUN yum update -y
-RUN yum install -y python35u python35u-libs python35u-devel python35u-pip openssl-devel libffi-devel
-RUN pip3.5 install ansible
+RUN yum install -y python36u python36u-libs python36u-devel python36u-pip openssl-devel libffi-devel
+RUN pip3.6 install --upgrade pip
+RUN pip3.6 install ansible
RUN yum install -y python-pip
RUN python -m pip install --upgrade pip
COPY . /code
diff --git a/jass/__init__.py b/jass/__init__.py
index e27073c7f61922fed66faf175167e9ddc9d6ff8c..a88eb7abf651d44a7e45578285661a85262703a3 100644
--- a/jass/__init__.py
+++ b/jass/__init__.py
@@ -17,4 +17,4 @@ Submodules
"""
import os
-from jass.tasks import celery
\ No newline at end of file
+from jass.tasks import celery
diff --git a/jass/__main__.py b/jass/__main__.py
index c3d79337ae16503bfde99f52b7bb713acebe546b..9bd45225639dd9733cc201ba192250d0b41e0685 100644
--- a/jass/__main__.py
+++ b/jass/__main__.py
@@ -5,59 +5,66 @@ import os
import sys
import argparse
-from jass.server import get_jass_app
+from jass.server import jass_app
from jass.config import config
from jass.models.phenotype import get_available_phenotypes
from jass.models.inittable import create_inittable_file, add_gene_annotation
from jass.models.worktable import create_worktable_file
-from jass.models.plots import ( create_global_plot,
- create_quadrant_plot,
- create_local_plot,
- create_qq_plot)
+from jass.models.plots import (
+ create_global_plot,
+ create_quadrant_plot,
+ create_local_plot,
+ create_qq_plot,
+)
-def absolute_path_of_the_file(fileName, output_file = False):
+
+def absolute_path_of_the_file(fileName, output_file=False):
"""
Builds the absolute path of the file : fileName
This makes the execution of JASS functions more robust and flexible
"""
-
+
# Build an absolute path if possible
absoluteFilePath = os.path.abspath(fileName)
# Test if the file name is a pattern
- is_a_pattern = (os.path.basename(fileName).find("*") > -1)
+ is_a_pattern = os.path.basename(fileName).find("*") > -1
- if (is_a_pattern or output_file) :
+ if is_a_pattern or output_file:
# Test if the directory path exist
Directory_path_exist = os.path.exists(os.path.dirname(absoluteFilePath))
- if (Directory_path_exist == False):
+ if Directory_path_exist == False:
# Test the path using the Jass data directory
- absoluteFilePath = os.path.normpath(os.path.join(config["DATA_DIR"], fileName))
+ absoluteFilePath = os.path.normpath(
+ os.path.join(config["DATA_DIR"], fileName)
+ )
Directory_path_exist = os.path.exists(os.path.dirname(absoluteFilePath))
- if (Directory_path_exist == False):
+ if Directory_path_exist == False:
Message = "The directory of the file {} does not exist".format(fileName)
raise NameError(Message)
else:
# Test if the file path exist
File_path_exist = os.path.exists(absoluteFilePath)
- if (File_path_exist == False):
+ if File_path_exist == False:
# Test the path using the Jass data directory
- absoluteFilePath = os.path.normpath(os.path.join(config["DATA_DIR"], fileName))
+ absoluteFilePath = os.path.normpath(
+ os.path.join(config["DATA_DIR"], fileName)
+ )
File_path_exist = os.path.exists(absoluteFilePath)
- if (File_path_exist == False):
+ if File_path_exist == False:
Message = "The file {} does not exist".format(fileName)
raise NameError(Message)
# Test if it is realy a file
Is_a_file = os.path.isfile(absoluteFilePath)
- if (not Is_a_file) :
+ if not Is_a_file:
Message = "{} is not a file".format(fileName)
raise NameError(Message)
@@ -65,8 +72,7 @@ def absolute_path_of_the_file(fileName, output_file = False):
def serve(args):
- app = get_jass_app()
- app.run(host=config["HOST"], port=config["PORT"])
+ jass_app.flask_app.run(host=config["HOST"], port=config["PORT"])
def w_list_phenotypes(args):
@@ -77,12 +83,12 @@ def w_list_phenotypes(args):
def compute_worktable(args):
csv_file_path = args.csv_file_path
- if (csv_file_path is not None):
+ if csv_file_path is not None:
csv_file_path = absolute_path_of_the_file(csv_file_path, True)
init_table_path = absolute_path_of_the_file(args.init_table_path)
worktable_path = absolute_path_of_the_file(args.worktable_path, True)
selected_phenotypes = args.phenotypes
- remove_nan = (args.remove_nans)
+ remove_nan = args.remove_nans
significance_treshold = float(args.significance_treshold)
post_filtering = bool(args.post_filtering)
custom_loadings = args.custom_loadings
@@ -91,9 +97,9 @@ def compute_worktable(args):
pos_End = args.end_position
if args.omnibus:
- strategy = 'jass.models.stats:omnibus_stat'
+ strategy = "jass.models.stats:omnibus_stat"
elif args.sumz:
- strategy = 'jass.models.stats:sumz_stat'
+ strategy = "jass.models.stats:sumz_stat"
elif args.fisher_test:
strategy = "jass.models.stats:fisher_test"
elif args.meta_analysis:
@@ -102,21 +108,21 @@ def compute_worktable(args):
strategy = args.strategy
create_worktable_file(
- phenotype_ids = selected_phenotypes,
- init_file_path = init_table_path,
- project_hdf_path = worktable_path,
- remove_nan = remove_nan,
- stat = strategy,
- optim_na = True,
- csv_file = csv_file_path,
- chunk_size = int(args.chunk_size),
- significance_treshold = significance_treshold,
- post_filtering = post_filtering,
- delayed_gen_csv_file = False,
- chromosome = chromosome,
- pos_Start = pos_Start,
- pos_End = pos_End,
- custom_loadings = custom_loadings
+ phenotype_ids=selected_phenotypes,
+ init_file_path=init_table_path,
+ project_hdf_path=worktable_path,
+ remove_nan=remove_nan,
+ stat=strategy,
+ optim_na=True,
+ csv_file=csv_file_path,
+ chunk_size=int(args.chunk_size),
+ significance_treshold=significance_treshold,
+ post_filtering=post_filtering,
+ delayed_gen_csv_file=False,
+ chromosome=chromosome,
+ pos_Start=pos_Start,
+ pos_End=pos_End,
+ custom_loadings=custom_loadings,
)
@@ -126,28 +132,25 @@ def w_create_worktable(args):
def w_create_project_data(args):
compute_worktable(args)
-
worktable_path = absolute_path_of_the_file(args.worktable_path, True)
-
manhattan_plot_path = args.manhattan_plot_path
- if (manhattan_plot_path is not None):
+ if manhattan_plot_path is not None:
manhattan_plot_path = absolute_path_of_the_file(manhattan_plot_path, True)
create_global_plot(worktable_path, manhattan_plot_path)
-
quadrant_plot_path = args.quadrant_plot_path
- if (quadrant_plot_path is not None):
- quadrant_plot_path = absolute_path_of_the_file(quadrant_plot_path, True)
- create_quadrant_plot(worktable_path,
- quadrant_plot_path,
- significance_treshold = float(args.significance_treshold))
-
+ if quadrant_plot_path is not None:
+ quadrant_plot_path = absolute_path_of_the_file(quadrant_plot_path, True)
+ create_quadrant_plot(
+ worktable_path,
+ quadrant_plot_path,
+ significance_treshold=float(args.significance_treshold),
+ )
zoom_plot_path = args.zoom_plot_path
- if (zoom_plot_path is not None):
+ if zoom_plot_path is not None:
zoom_plot_path = absolute_path_of_the_file(zoom_plot_path, True)
create_local_plot(worktable_path, zoom_plot_path)
-
qq_plot_path = args.qq_plot_path
- if (qq_plot_path is not None):
+ if qq_plot_path is not None:
qq_plot_path = absolute_path_of_the_file(qq_plot_path, True)
create_qq_plot(worktable_path, qq_plot_path)
@@ -155,7 +158,9 @@ def w_create_project_data(args):
def w_create_inittable(args):
input_data_path = absolute_path_of_the_file(args.input_data_path)
init_covariance_path = absolute_path_of_the_file(args.init_covariance_path)
- init_genetic_covariance_path = absolute_path_of_the_file(args.init_genetic_covariance_path)
+ init_genetic_covariance_path = absolute_path_of_the_file(
+ args.init_genetic_covariance_path
+ )
regions_map_path = absolute_path_of_the_file(args.regions_map_path)
description_file_path = absolute_path_of_the_file(args.description_file_path)
init_table_path = absolute_path_of_the_file(args.init_table_path, True)
@@ -166,7 +171,7 @@ def w_create_inittable(args):
description_file_path,
init_table_path,
init_covariance_path,
- init_genetic_covariance_path
+ init_genetic_covariance_path,
)
@@ -180,9 +185,9 @@ def w_plot_quadrant(args):
worktable_path = absolute_path_of_the_file(args.worktable_path)
plot_path = absolute_path_of_the_file(args.plot_path)
significance_treshold = float(args.significance_treshold)
- create_quadrant_plot(worktable_path,
- plot_path,
- significance_treshold=significance_treshold)
+ create_quadrant_plot(
+ worktable_path, plot_path, significance_treshold=significance_treshold
+ )
def w_gene_annotation(args):
@@ -190,10 +195,9 @@ def w_gene_annotation(args):
initTable_path = absolute_path_of_the_file(args.init_table_path, True)
df_gene_csv_path = absolute_path_of_the_file(args.gene_csv_path, True)
df_exon_csv_path = absolute_path_of_the_file(args.exon_csv_path, True)
- add_gene_annotation(gene_data_path,
- initTable_path,
- df_gene_csv_path,
- df_exon_csv_path)
+ add_gene_annotation(
+ gene_data_path, initTable_path, df_gene_csv_path, df_exon_csv_path
+ )
def get_parser():
@@ -256,7 +260,7 @@ def get_parser():
)
parser_create_pd.add_argument(
"--significance-treshold",
- default=5*10**-8,
+ default=5 * 10 ** -8,
help="The treshold at which a p-value is considered significant",
)
parser_create_pd.add_argument(
@@ -279,27 +283,25 @@ def get_parser():
)
parser_create_pd.add_argument(
- "--csv-file-path",
- required=False,
- help="path to the results file in csv format"
+ "--csv-file-path", required=False, help="path to the results file in csv format"
)
parser_create_pd.add_argument(
"--chromosome-number",
required=False,
- help="option used only for local analysis: chromosome number studied"
+ help="option used only for local analysis: chromosome number studied",
)
parser_create_pd.add_argument(
"--start-position",
required=False,
- help="option used only for local analysis: start position of the region studied"
+ help="option used only for local analysis: start position of the region studied",
)
parser_create_pd.add_argument(
"--end-position",
required=False,
- help="option used only for local analysis: end position of the region studied"
+ help="option used only for local analysis: end position of the region studied",
)
strategies = parser_create_pd.add_mutually_exclusive_group()
@@ -344,7 +346,7 @@ def get_parser():
parser_create_it.add_argument(
"--init-genetic-covariance-path",
default=None,
- help = "path to the genetic covariance file to import",
+ help="path to the genetic covariance file to import",
)
parser_create_it.set_defaults(func=w_create_inittable)
# ------- create-worktable -------
@@ -366,13 +368,13 @@ def get_parser():
)
parser_create_wt.add_argument(
"--significance-treshold",
- default=5*10**-8,
- help="threshold at which a p-value is considered significant"
- )
+ default=5 * 10 ** -8,
+ help="threshold at which a p-value is considered significant",
+ )
parser_create_wt.add_argument(
"--post-filtering",
default=True,
- help="If a filtering to remove outlier will be applied (in this case the result of SNPs considered aberant will not appear in the worktable)"
+ help="If a filtering to remove outlier will be applied (in this case the result of SNPs considered aberant will not appear in the worktable)",
)
parser_create_wt.add_argument(
@@ -382,9 +384,7 @@ def get_parser():
)
parser_create_wt.add_argument(
- "--csv-file-path",
- required=False,
- help="path to the results file in csv format"
+ "--csv-file-path", required=False, help="path to the results file in csv format"
)
parser_create_wt.add_argument(
@@ -399,19 +399,19 @@ def get_parser():
parser_create_wt.add_argument(
"--chromosome-number",
required=False,
- help="option used only for local analysis: chromosome number studied"
+ help="option used only for local analysis: chromosome number studied",
)
parser_create_wt.add_argument(
"--start-position",
required=False,
- help="option used only for local analysis: start position of the region studied"
+ help="option used only for local analysis: start position of the region studied",
)
parser_create_wt.add_argument(
"--end-position",
required=False,
- help="option used only for local analysis: end position of the region studied"
+ help="option used only for local analysis: end position of the region studied",
)
strategies = parser_create_wt.add_mutually_exclusive_group()
@@ -435,9 +435,7 @@ def get_parser():
help="path to the worktable file containing the data",
)
parser_create_mp.add_argument(
- "--plot-path",
- required=True,
- help="path to the manhattan plot file to generate"
+ "--plot-path", required=True, help="path to the manhattan plot file to generate"
)
parser_create_mp.set_defaults(func=w_plot_manhattan)
@@ -452,21 +450,20 @@ def get_parser():
help="path to the worktable file containing the data",
)
parser_create_mp.add_argument(
- "--plot-path",
- required=True,
- help="path to the quadrant plot file to generate"
+ "--plot-path", required=True, help="path to the quadrant plot file to generate"
)
parser_create_mp.add_argument(
"--significance-treshold",
- default=5*10**-8,
- help="threshold at which a p-value is considered significant"
+ default=5 * 10 ** -8,
+ help="threshold at which a p-value is considered significant",
)
parser_create_mp.set_defaults(func=w_plot_quadrant)
# ------- add-gene-annotation -------
parser_create_mp = subparsers.add_parser(
- "add-gene-annotation", help="add information about genes ansd exons to the inittable"
+ "add-gene-annotation",
+ help="add information about genes ansd exons to the inittable",
)
parser_create_mp.add_argument(
"--gene-data-path",
@@ -476,17 +473,13 @@ def get_parser():
parser_create_mp.add_argument(
"--init-table-path",
required=True,
- help="path to the initial table file to update"
+ help="path to the initial table file to update",
)
parser_create_mp.add_argument(
- "--gene-csv-path",
- required=False,
- help="path to the file df_gene.csv"
+ "--gene-csv-path", required=False, help="path to the file df_gene.csv"
)
parser_create_mp.add_argument(
- "--exon-csv-path",
- required=False,
- help="path to the file df_exon.csv"
+ "--exon-csv-path", required=False, help="path to the file df_exon.csv"
)
parser_create_mp.set_defaults(func=w_gene_annotation)
@@ -494,16 +487,16 @@ def get_parser():
def main():
- print("", file = sys.stderr)
- print(" ** ******* ******* *******", file = sys.stderr)
- print(" ** ** ** ** **", file = sys.stderr)
- print(" ** ** ** ** **", file = sys.stderr)
- print(" ** ** ** ****** ******", file = sys.stderr)
- print(" ** *********** ** **", file = sys.stderr)
- print(" ** ** ** ** ** **", file = sys.stderr)
- print(" ******* ** ** ******* *******", file = sys.stderr)
- print("", file = sys.stderr)
- print("", file = sys.stderr)
+ print("", file=sys.stderr)
+ print(" ** ******* ******* *******", file=sys.stderr)
+ print(" ** ** ** ** **", file=sys.stderr)
+ print(" ** ** ** ** **", file=sys.stderr)
+ print(" ** ** ** ****** ******", file=sys.stderr)
+ print(" ** *********** ** **", file=sys.stderr)
+ print(" ** ** ** ** ** **", file=sys.stderr)
+ print(" ******* ** ** ******* *******", file=sys.stderr)
+ print("", file=sys.stderr)
+ print("", file=sys.stderr)
parser = get_parser()
args = parser.parse_args()
args.func(args)
diff --git a/jass/celeryconfig.py b/jass/celeryconfig.py
index 2350b9a27b31c525734b5c7fddeadc038fc7ff6e..1530851f931f986320b72add4f8fa19d316d3ea5 100644
--- a/jass/celeryconfig.py
+++ b/jass/celeryconfig.py
@@ -1,17 +1,15 @@
import os
## Broker settings.
-broker_url = os.getenv('JASS_RABBITMQ_URL','amqp://guest:guest@localhost:5672//')
+broker_url = os.getenv("JASS_RABBITMQ_URL", "amqp://guest:guest@localhost:5672//")
## Broker settings.
-#result_backend = os.getenv('JASS_RABBITMQ_URL','amqp://guest2:guest@localhost:5672//')
-result_backend='rpc://'
+# result_backend = os.getenv('JASS_RABBITMQ_URL','amqp://guest2:guest@localhost:5672//')
+result_backend = "rpc://"
# List of modules to import when the Celery worker starts.
-#imports = ('myapp.tasks',)
+# imports = ('myapp.tasks',)
## Using the database to store task state and results.
-#result_backend = 'db+sqlite:///results.db'
-
-#task_annotations = {'tasks.add': {'rate_limit': '10/s'}}
-
+# result_backend = 'db+sqlite:///results.db'
+# task_annotations = {'tasks.add': {'rate_limit': '10/s'}}
diff --git a/jass/controllers/__init__.py b/jass/controllers/__init__.py
deleted file mode 100644
index 0e94abd262a9ad33a4968618f3ba933bf97c6740..0000000000000000000000000000000000000000
--- a/jass/controllers/__init__.py
+++ /dev/null
@@ -1,11 +0,0 @@
-"""
-the list of controller functions called by the JASS REST web services
-
-Submodules
-==========
-
-.. autosummary::
- :toctree: _autosummary
-
- default_controller
-"""
diff --git a/jass/controllers/default_controller.py b/jass/controllers/default_controller.py
deleted file mode 100644
index 8f1f7838e39e8f7abc47e63e132b08dd27f89528..0000000000000000000000000000000000000000
--- a/jass/controllers/default_controller.py
+++ /dev/null
@@ -1,234 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""
-default_controller ensures the connection between the web interface and the Python JASS-analysis module
-"""
-import os
-from typing import List, Dict
-
-import connexion
-from flask import send_file, abort
-from six import iteritems
-
-from jass.config import config
-from jass.models.project import Project
-from jass.models.phenotype import Phenotype, get_available_phenotypes
-from jass.tasks import create_project
-
-PHENOTYPES = get_available_phenotypes(
- os.path.join(config["DATA_DIR"], "initTable.hdf5")
-) # FIXME part of the config
-
-
-def phenotypes_get():
- """
- phenotypes_get
- Gets the list of available phenotypes
-
- :rtype: List[Phenotype]
- """
- return PHENOTYPES
-
-
-def projects_post(phenotypeID):
- """
- projects_post
- Create a new project from a selection of phenotypes
- :param phenotypeID: IDs of the phenotypes selected for the project
- :type phenotypeID: List[str]
-
- :rtype: str
- """
- return create_project(phenotypeID, PHENOTYPES)
-
-
-def local_project_post(phenotypeID, chromosome, start, end):
- """
- local_project_post
- Create a new local project from a chromosome number, start and end positions
- and a selection of phenotypes
- :param param: IDs of the phenotypes selected for the project
- :type phenotypeID: List[str]
-
- :rtype: str
- """
- return create_project(phenotypeID, PHENOTYPES, chromosome, start, end)
-
-
-def projects_project_id_csv_status_get(projectID):
- """
- projects_project_id_csv_status_get
- Retrieve the generation status of the genome full csv file
- :param projectID: project ID
- :type projectID: str
-
- :rtype: str
- """
- return Project(id=projectID).get_csv_file_generation()
-
-
-def projects_project_id_summary_statistics(projectID):
- """
- projects_project_id_summary_statistics
- Retrieve project summary statistics
- """
- return Project(id=projectID).get_project_summary_statistics()
-
-
-def projects_project_id_genome_get(projectID, threshold=None):
- """
- projects_project_id_genome_get
- Retrieve genome data for a given project
- :param projectID: project ID
- :type projectID: str
-
- :rtype: str
- """
- return Project(id=projectID).get_project_genomedata()
-
-
-def projects_project_id_global_manhattan_plot_get(projectID):
- """
- projects_project_id_global_manhattan_plot_get
- Gets the global Manhattan plot stored in the Project folder to display it on the Web interface
- """
- try:
- return send_file(
- Project(id=projectID).get_global_manhattan_plot_path(), mimetype="image/png"
- )
- except FileNotFoundError:
- status = Project(id=projectID).status
- if status == Project.DOES_NOT_EXIST:
- abort(404)
- elif status["global_manhattan"] == Project.CREATING:
- return (
- "Plot is not ready yet",
- 202,
- {"Content-Type": "text/plain; charset=utf-8"},
- )
- else:
- abort(500)
-
-
-def projects_project_id_zoom_plot_get(projectID):
- """
- projects_project_id_zoom_plot_get
- Gets the zoom plot stored in the local Project folder to display it on the Web interface
- """
- try:
- return send_file(
- Project(id=projectID).get_zoom_plot_path(), mimetype="image/png"
- )
- except FileNotFoundError:
- status = Project(id=projectID).status
- if status == Project.DOES_NOT_EXIST:
- abort(404)
- elif status["zoom_plot"] == Project.CREATING:
- return (
- "Plot is not ready yet",
- 202,
- {"Content-Type": "text/plain; charset=utf-8"},
- )
- else:
- abort(500)
-
-
-def projects_project_id_quadrant_plot_get(projectID):
- """
- projects_project_id_quadrant_plot_get
- Gets the quadrant plot stored in the Project folder to display it on the Web interface
- """
- try:
- return send_file(
- Project(id=projectID).get_quadrant_plot_path(), mimetype="image/png"
- )
- except FileNotFoundError:
- status = Project(id=projectID).status
- if status == Project.DOES_NOT_EXIST:
- abort(404)
- elif status["quadrant_plot_status"] == Project.CREATING:
- return (
- "Plot is not ready yet",
- 202,
- {"Content-Type": "text/plain; charset=utf-8"},
- )
- else:
- abort(500)
-
-
-def projects_project_id_genome_full_get(projectID):
- """
- projects_project_id_genome_full_get
- Downloads the file genome_full.csv stored in the Project folder
- """
-
- Type_of_Analysis = Project(id=projectID).get_type_of_analysis()
- if(Type_of_Analysis == Project.LOCAL_ANALYSIS):
- Fichier = "local_analysis_result.csv"
- else:
- Fichier = "genome_full.csv"
-
- try:
- return send_file(
- Project(id=projectID).get_csv_path(),
- mimetype = "text/csv",
- as_attachment = True,
- attachment_filename = Fichier
- )
- except FileNotFoundError:
- status = Project(id=projectID).status
- if status == Project.DOES_NOT_EXIST:
- abort(404)
- elif status["worktable"] == Project.CREATING:
- return (
- "CSV is not ready yet",
- 202,
- {"Content-Type": "text/plain; charset=utf-8"},
- )
- else:
- abort(500)
-
-
-def projects_project_id_local_manhattan_data_get(projectID, chromosome, region):
- """
- projects_project_id_local_manhattan_data_get
- Return the SumStatTab dataframe of the Project for a given chromosome and region for the Manhattan plot
- """
- return Project(id=projectID).get_project_local_manhattan_data(chromosome, region)
-
-
-def projects_project_id_local_heatmap_data_get(projectID, chromosome, region):
- """
- projects_project_id_local_heatmap_data_get
- Return the SumStatTab dataframe of the Project for a given chromosome and region for the Heatmap plot
- """
- return Project(id=projectID).get_project_local_heatmap_data(chromosome, region)
-
-
-def projects_project_id_zoom_manhattan_data_get(projectID):
- """
- projects_project_id_local_manhattan_data_get
- Return the SumStatTab dataframe of the Project for a given chromosome and region for the Manhattan plot
- """
- print("... projects_project_id_zoom_manhattan_data_get({})".format(projectID))
- return Project(id=projectID).get_project_local_manhattan_data()
-
-
-def projects_project_id_zoom_heatmap_data_get(projectID):
- """
- projects_project_id_local_heatmap_data_get
- Return the SumStatTab dataframe of the Project for a given chromosome and region for the Heatmap plot
- """
- return Project(id=projectID).get_project_local_heatmap_data()
-
-
-def projects_project_idget(projectID):
- """
- projects_project_idget
- Retrieve a project definition
- :param projectID: project ID
- :type projectID: str
-
- :rtype: Phenotype
- """
- return Project(id=projectID)
diff --git a/jass/encoder.py b/jass/encoder.py
deleted file mode 100644
index 175502a4df6e905113b701e38214b296e82af577..0000000000000000000000000000000000000000
--- a/jass/encoder.py
+++ /dev/null
@@ -1,25 +0,0 @@
-from connexion.apps.flask_app import FlaskJSONEncoder
-
-# from connexion.decorators import produces
-from six import iteritems
-from jass.models.base_model_ import Model
-from pandas import isnull
-
-
-class JSONEncoder(FlaskJSONEncoder):
- include_nulls = False
-
- def default(self, o):
- if isinstance(o, Model):
- dikt = {}
- for attr, _ in iteritems(o.swagger_types):
- value = getattr(o, attr)
- if not (isinstance(value, list)) and (value is None or isnull(value)):
- if not self.include_nulls:
- continue
- else:
- return None
- attr = o.attribute_map[attr]
- dikt[attr] = value
- return dikt
- return produces.JSONEncoder.default(self, o)
diff --git a/jass/models/inittable.py b/jass/models/inittable.py
index 15fcd0fb051bf73ecb2578efc1122ff45cafc8f2..7a2849dd59bec963d53866aab2f3754a72b40cf3 100644
--- a/jass/models/inittable.py
+++ b/jass/models/inittable.py
@@ -18,6 +18,7 @@ from functools import reduce
options.mode.chained_assignment = None
warnings.filterwarnings("ignore", category=tables.NaturalNameWarning)
+
def get_gwasname(file_name):
return "_".join(os.path.basename(file_name).split("_")[0:3])
@@ -33,9 +34,9 @@ def check_if_SNP_unique(z_gwas_chrom):
def get_gwas_dict(input_data_path):
gwas_dict = {}
- #retrieve all files corresponding to glob patterns
+ # retrieve all files corresponding to glob patterns
files_by_pattern = list(map(glob.glob, input_data_path.split(";")))
- all_path = reduce(lambda x,y:x+y, files_by_pattern)
+ all_path = reduce(lambda x, y: x + y, files_by_pattern)
print(all_path)
for x in all_path:
gwas_name = get_gwasname(x)
@@ -60,17 +61,27 @@ def create_pheno_summary(description):
"internalDataLink",
"Nsample",
"Ncase",
- "Ncontrol"
+ "Ncontrol",
]
]
- pheno_summary_data["ID"] = "z_" + pheno_summary_data.Consortium.str.upper() + "_" + pheno_summary_data.Outcome.str.upper()
+ pheno_summary_data["ID"] = (
+ "z_"
+ + pheno_summary_data.Consortium.str.upper()
+ + "_"
+ + pheno_summary_data.Outcome.str.upper()
+ )
- is_quantitatif = pheno_summary_data['Ncase'].isnull()
+ is_quantitatif = pheno_summary_data["Ncase"].isnull()
pheno_summary_data["Effective_sample_size"] = np.nan
- pheno_summary_data.loc[~is_quantitatif,"Effective_sample_size"] = (pheno_summary_data.loc[~is_quantitatif, "Ncase"]*pheno_summary_data.loc[~is_quantitatif, "Ncontrol"]) / pheno_summary_data.loc[~is_quantitatif, "Nsample"]
+ pheno_summary_data.loc[~is_quantitatif, "Effective_sample_size"] = (
+ pheno_summary_data.loc[~is_quantitatif, "Ncase"]
+ * pheno_summary_data.loc[~is_quantitatif, "Ncontrol"]
+ ) / pheno_summary_data.loc[~is_quantitatif, "Nsample"]
- pheno_summary_data.loc[is_quantitatif,"Effective_sample_size"] = pheno_summary_data.loc[is_quantitatif, "Nsample"]
+ pheno_summary_data.loc[
+ is_quantitatif, "Effective_sample_size"
+ ] = pheno_summary_data.loc[is_quantitatif, "Nsample"]
# reorder columns in the dataframe
pheno_summary_data = pheno_summary_data[
@@ -87,7 +98,7 @@ def create_pheno_summary(description):
"Nsample",
"Ncase",
"Ncontrol",
- "Effective_sample_size"
+ "Effective_sample_size",
]
]
pheno_summary_data.index = pheno_summary_data["ID"]
@@ -121,21 +132,23 @@ def format_chr_gwas(gwas_file_chri, chrom, study_name, regions_bychr):
z_gwas["Region"] = 0
z_gwas["MiddlePosition"] = 0.0
- for region_index, region_row in regions_bychr.get_group(
- "chr%d" % chrom
- ).iterrows():
+ for region_index, region_row in regions_bychr.get_group("chr%d" % chrom).iterrows():
left = region_row["start"]
right = region_row["stop"]
ind = (z_gwas["position"] >= left) & (z_gwas["position"] <= right)
(z_gwas.loc[ind, "Region"]) = np.int(region_index + 1)
(z_gwas.loc[ind, "MiddlePosition"]) = (left + right) / 2
- return(z_gwas)
+ return z_gwas
def compute_covariance_zscore(init_file_path):
print("## Compute covariance ##")
- sum_stat_jost_tab = read_hdf(init_file_path, 'SumStatTab', where='Region >= {0} and Region < {1}'.format(0, 3))
- trait = [i for i in sum_stat_jost_tab.columns if i[:2]=="z_"]
+ sum_stat_jost_tab = read_hdf(
+ init_file_path,
+ "SumStatTab",
+ where="Region >= {0} and Region < {1}".format(0, 3),
+ )
+ trait = [i for i in sum_stat_jost_tab.columns if i[:2] == "z_"]
NSNP_matrix = DataFrame(index=trait, columns=trait)
cov_matrix = DataFrame(index=trait, columns=trait)
@@ -143,31 +156,35 @@ def compute_covariance_zscore(init_file_path):
cov_matrix.fillna(0, inplace=True)
NSNP_matrix.fillna(0, inplace=True)
- bi = range(0,1751,50)
- n_len = len(bi)-1
+ bi = range(0, 1751, 50)
+ n_len = len(bi) - 1
for i in range(n_len):
binf = bi[i]
- bsup = bi[(i+1)]
- sum_stat_jost_tab = read_hdf(init_file_path, 'SumStatTab', where='Region >= {0} and Region < {1}'.format(binf, bsup))
+ bsup = bi[(i + 1)]
+ sum_stat_jost_tab = read_hdf(
+ init_file_path,
+ "SumStatTab",
+ where="Region >= {0} and Region < {1}".format(binf, bsup),
+ )
print("Regions {0} to {1}\r".format(binf, bsup))
j = 0
for tr1 in trait:
for tr2 in trait[j:]:
- cc = sum_stat_jost_tab[[tr1,tr2]].dropna()
+ cc = sum_stat_jost_tab[[tr1, tr2]].dropna()
cc = cc.loc[cc.max(1) < 4]
- cov_matrix.loc[tr1,tr2] += cc.iloc[:,0].dot(cc.iloc[:,1])
- NSNP_matrix.loc[tr1,tr2] += cc.shape[0]
+ cov_matrix.loc[tr1, tr2] += cc.iloc[:, 0].dot(cc.iloc[:, 1])
+ NSNP_matrix.loc[tr1, tr2] += cc.shape[0]
- cov_matrix.loc[tr2,tr1] += cc.iloc[:,0].dot(cc.iloc[:,1])
- NSNP_matrix.loc[tr2,tr1] += cc.shape[0]
- j=j+1
+ cov_matrix.loc[tr2, tr1] += cc.iloc[:, 0].dot(cc.iloc[:, 1])
+ NSNP_matrix.loc[tr2, tr1] += cc.shape[0]
+ j = j + 1
- #(cov_matrix/NSNP_matrix).to_csv("Covariance_on_Zscores.csv", sep="\t")
+ # (cov_matrix/NSNP_matrix).to_csv("Covariance_on_Zscores.csv", sep="\t")
hdf_init = HDFStore(init_file_path)
- hdf_init.put("COV", (cov_matrix/NSNP_matrix), format="table", data_columns=True)
+ hdf_init.put("COV", (cov_matrix / NSNP_matrix), format="table", data_columns=True)
hdf_init.close()
@@ -177,18 +194,20 @@ def create_inittable_file(
description_file_path: str,
init_table_path: str,
init_covariance_path=None,
- init_genetic_covariance_path=None
+ init_genetic_covariance_path=None,
):
# Read region file
- regions = read_csv(regions_map_path, sep='\s+', memory_map=True)
+ regions = read_csv(regions_map_path, sep="\s+", memory_map=True)
# Create HDFStore
if os.path.exists(init_table_path):
os.remove(init_table_path)
hdf_init = HDFStore(init_table_path)
# Read covariance file
- if init_covariance_path!=None:
- covariance = read_csv(init_covariance_path, sep="\t", index_col=0, memory_map=True)
+ if init_covariance_path != None:
+ covariance = read_csv(
+ init_covariance_path, sep="\t", index_col=0, memory_map=True
+ )
compute_covariance = False
else:
compute_covariance = True
@@ -206,18 +225,20 @@ def create_inittable_file(
"z_" + meta_row["Consortium"].upper() + "_" + meta_row["Outcome"].upper()
)
- pheno_select = list(phenotypes_list) & gwas_dict.keys() #&covariance.columns
+ pheno_select = list(phenotypes_list) & gwas_dict.keys() # &covariance.columns
pheno_summary_data = create_pheno_summary(description)
# select only phenotypes for which there is a covariance
pheno_list = pheno_summary_data.loc[pheno_select, :]
- if compute_covariance==False:
+ if compute_covariance == False:
COV = covariance.loc[pheno_select, pheno_select]
hdf_init.put("COV", COV, format="table", data_columns=True)
# Read Genetic Covariance file and add genetic correlation if available
- if init_genetic_covariance_path!=None:
- genetic_covariance = read_csv(init_genetic_covariance_path, sep="\t", index_col=0, memory_map=True)
+ if init_genetic_covariance_path != None:
+ genetic_covariance = read_csv(
+ init_genetic_covariance_path, sep="\t", index_col=0, memory_map=True
+ )
GEN_COV = genetic_covariance.loc[pheno_select, pheno_select]
hdf_init.put("GEN_COV", GEN_COV, format="table", data_columns=True)
@@ -234,7 +255,7 @@ def create_inittable_file(
which_cols.extend(list(pheno_select))
hdf_init.put("PhenoList", pheno_list, format="table", data_columns=True)
hdf_init.put("Regions", regions, format="table", data_columns=True)
- sum_stat_tab_min_itemsizes = {"snp_ids": 80, "Ref_allele":70,"Alt_allele":70}
+ sum_stat_tab_min_itemsizes = {"snp_ids": 80, "Ref_allele": 70, "Alt_allele": 70}
regions_bychr = regions.groupby("chr")
@@ -326,16 +347,15 @@ def create_inittable_file(
compute_covariance_zscore(init_table_path)
-def add_gene_annotation(gene_data_path,
- initTable_path=None,
- df_gene_csv_path=None,
- df_exon_csv_path=None):
+def add_gene_annotation(
+ gene_data_path, initTable_path=None, df_gene_csv_path=None, df_exon_csv_path=None
+):
"""
add_gene_annotation
- for the first 22 chromosomes, retrieves the label of the genes
+ for the first 22 chromosomes, retrieves the label of the genes
and their position as well as those of the exons associated with the genes.
Then store this information in a hdf5 file
-
+
:param gene_data_path: path to the GFF file containing gene and exon data (for example, GRCh37_latest_genomic.gff)
:type gene_data_path: str
:param initTable_path: path to the file initTable.hdf5
@@ -344,7 +364,7 @@ def add_gene_annotation(gene_data_path,
:type df_gene_csv_path: str
:param df_exon_csv_path: path to the file df_exon.csv
:type df_exon_csv_path: str
-
+
:return: the dataframes df_gene and df_exon
:rtype: 2 PANDAS dataframes
"""
@@ -355,7 +375,7 @@ def add_gene_annotation(gene_data_path,
gene_start = []
gene_end = []
gene_direction = []
-
+
# lists containing exon data
exon_id_label = []
exon_GeneID = []
@@ -363,7 +383,7 @@ def add_gene_annotation(gene_data_path,
exon_start = []
exon_end = []
exon_direction = []
-
+
# temporary list containing the data of all exons
TMP__exon_id_label = []
TMP__exon_GeneID = []
@@ -371,18 +391,18 @@ def add_gene_annotation(gene_data_path,
TMP__exon_start = []
TMP__exon_end = []
TMP__exon_direction = []
-
+
fichier = open(gene_data_path, "r")
lignes = fichier.readlines()
fichier.close()
-
+
for ligne in lignes:
elements = ligne.split("\t")
- if elements[0].startswith('NC_'):
+ if elements[0].startswith("NC_"):
decode_chr = elements[0].strip("NC_").split(".")
chr = int(decode_chr[0])
- if (chr <= 22):
- if (elements[2] == "gene"):
+ if chr <= 22:
+ if elements[2] == "gene":
gene_chr.append(chr)
gene_start.append(int(elements[3]))
gene_end.append(int(elements[4]))
@@ -394,8 +414,8 @@ def add_gene_annotation(gene_data_path,
decode_id_4 = decode_id_3[0].split("=")
decode_id_5 = decode_id_4[1].split(":")
gene_GeneID.append(decode_id_5[1])
-
- elif (elements[2] == "exon"):
+
+ elif elements[2] == "exon":
TMP__exon_chr.append(chr)
TMP__exon_start.append(int(elements[3]))
TMP__exon_end.append(int(elements[4]))
@@ -407,49 +427,56 @@ def add_gene_annotation(gene_data_path,
decode_id_4 = decode_id_3[0].split("=")
decode_id_5 = decode_id_4[1].split(":")
TMP__exon_GeneID.append(decode_id_5[1])
-
-
- # We only keep the exons that correspond to a gene
+
+ # We only keep the exons that correspond to a gene
for i in range(len(TMP__exon_id_label)):
- if (TMP__exon_GeneID[i] in gene_GeneID) :
+ if TMP__exon_GeneID[i] in gene_GeneID:
exon_id_label.append(TMP__exon_id_label[i])
exon_GeneID.append(TMP__exon_GeneID[i])
exon_chr.append(TMP__exon_chr[i])
exon_start.append(TMP__exon_start[i])
exon_end.append(TMP__exon_end[i])
exon_direction.append(TMP__exon_direction[i])
-
+
# We insert genes and exons into dataframes
- df_gene = DataFrame({"Chr": gene_chr,
- "GeneID" : gene_GeneID,
- "gene_label" : gene_id_label,
- "start" : gene_start,
- "end" : gene_end,
- "direction" : gene_direction})
- df_exon = DataFrame({"Chr": exon_chr,
- "exon_label" : exon_id_label,
- "GeneID" : exon_GeneID,
- "start" : exon_start,
- "end" : exon_end,
- "direction" : exon_direction})
-
+ df_gene = DataFrame(
+ {
+ "Chr": gene_chr,
+ "GeneID": gene_GeneID,
+ "gene_label": gene_id_label,
+ "start": gene_start,
+ "end": gene_end,
+ "direction": gene_direction,
+ }
+ )
+ df_exon = DataFrame(
+ {
+ "Chr": exon_chr,
+ "exon_label": exon_id_label,
+ "GeneID": exon_GeneID,
+ "start": exon_start,
+ "end": exon_end,
+ "direction": exon_direction,
+ }
+ )
+
# The rows of the dataframes are sorted by chromosome number and start position (and end position for exon)
df_gene.sort_values(by=["Chr", "start"], inplace=True, ignore_index=True)
df_exon.sort_values(by=["Chr", "start", "end"], inplace=True, ignore_index=True)
-
+
# This information about genes and exons is stored in an hdf5 file if possible
- if (initTable_path is not None):
+ if initTable_path is not None:
hdf_file = HDFStore(initTable_path)
hdf_file.put("Gene", df_gene, format="table", data_columns=True)
hdf_file.put("Exon", df_exon, format="table", data_columns=True)
hdf_file.close()
-
+
# Dataframe df_gene is stored in a csv file if possible
- if (df_gene_csv_path is not None):
+ if df_gene_csv_path is not None:
df_gene.to_csv(df_gene_csv_path)
-
+
# Dataframe df_exon is stored in a csv file if possible
- if (df_exon_csv_path is not None):
+ if df_exon_csv_path is not None:
df_exon.to_csv(df_exon_csv_path)
-
- return (df_gene, df_exon)
\ No newline at end of file
+
+ return (df_gene, df_exon)
diff --git a/jass/models/project.py b/jass/models/project.py
index d2ddd6f8b8dbe44246061fe17df2aa08ce517d79..15a1eb540a2bc5aa45951bbd7d89848b8927c650 100644
--- a/jass/models/project.py
+++ b/jass/models/project.py
@@ -1,279 +1,289 @@
-# -*- coding: utf-8 -*-
-"""
-compute joint statistics and generate plots for a given set of phenotypes
-"""
-from __future__ import absolute_import
-from typing import List, Dict
-import os, sys
-import shutil
-import hashlib
-import traceback
-
-from jass.models.base_model_ import Model
-from jass.util import deserialize_model
-from jass.models.phenotype import Phenotype
-from jass.models.worktable import (get_worktable_summary,
- get_worktable_genomedata,
- get_worktable_local_manhattan_data,
- get_worktable_local_heatmap_data)
-
-from jass.config import config
-
-class Project(Model):
-
- DOES_NOT_EXIST = "DOES_NOT_EXIST"
-
- CREATING = "CREATING"
-
- READY = "READY"
-
- ERROR = "ERROR"
-
- # Type of analysis
- LOCAL_ANALYSIS = "LOCAL_ANALYSIS"
- GENOME_WIDE_ANALYSIS = "GENOME_WIDE_ANALYSIS"
-
- # Upper bound of the chromosome length (bp)
- K_POS_MAX = 250000000
-
- def __init__(self, id: str = None,
- phenotypes: List[Phenotype] = None,
- chromosome: str = None,
- start: str = None,
- end: str = None):
- """
- Project - a project (list of phenotypes)
-
- :param id: project ID.
- :type id: str
- """
- self.swagger_types = {"id": str,
- "status": str,
- "phenotypes": List[Phenotype],
- "progress": str}
-
- self.attribute_map = {
- "id": "id",
- "status": "status",
- "phenotypes": "phenotypes",
- "progress": "progress",
- }
-
- self._phenotypes = phenotypes
-
- self._id = id
-
- if self._id is None:
- self._id = self.get_id(chromosome, start, end)
-
- @classmethod
- def from_dict(cls, dikt) -> "Project":
- """
- Returns the dict as a model
-
- :param dikt: A dict.
- :type: dict
- :return: The Project.
- :rtype: Project
- """
- return deserialize_model(dikt, cls)
-
- @property
- def id(self) -> str:
- """
- Gets the id of this Project.
-
- :return: The id of this Project.
- :rtype: str
- """
- return self._id
-
- @id.setter
- def id(self, id: str):
- """
- Lists the id of this Project.
-
- :param id: The id of this Project.
- :type id: str
- """
-
- self._id = id
-
- @property
- def phenotypes(self) -> List[Phenotype]:
- """
- Gets the phenotypes list for this project.
-
- :return: The phenotypes.
- :rtype: str
- """
- return self._phenotypes
-
- @phenotypes.setter
- def cohort(self, phenotypes: List[Phenotype]):
- """
- Lists the phenotypes list for this project.
-
- :param phenotypes: The phenotypes.
- :type phenotypes: str
- """
-
- self._phenotypes = phenotypes
-
- def get_type_of_analysis(self):
- """
- get_type_of_analysis
- Gets the type of analysis : local or genome wide
- """
- if((self._id).split("_")[0] == "local"):
- return Project.LOCAL_ANALYSIS
- else :
- return Project.GENOME_WIDE_ANALYSIS
-
- def get_folder_path(self):
- """
- get_folder_path
- Gets the path of the folder where the project data are stored
- """
- return os.path.join(config["DATA_DIR"], "project_{}".format(self.id))
-
- def get_worktable_path(self):
- """
- get_worktable_path
- Gets the path of the file workTable.hdf5
- """
- return os.path.join(self.get_folder_path(), "workTable.hdf5")
-
- def get_csv_path(self):
- """
- get_csv_path
- Gets the path of the file genome_full.csv
- """
- return os.path.join(self.get_folder_path(), "workTable.csv")
-
- def get_progress_path(self):
- """
- get_progress_path
- Gets the path of the file containing the current progress percentage of \
- the analysis performed within the project
- """
- return os.path.join(self.get_folder_path(), "JASS_progress.txt")
-
- def get_csv_lock_path(self):
- """
- get_csv_lock_path
- Gets the path of the lock set-on when the csv file is not available yet
- """
- return os.path.join(self.get_folder_path(), "the_lock.txt")
-
- def get_project_summary_statistics(self):
- return get_worktable_summary(self.get_worktable_path())
-
- def get_project_genomedata(self):
- return get_worktable_genomedata(self.get_worktable_path())
-
- def get_project_local_manhattan_data(self, chromosome: str = None, region: str = None):
- print("project::get_project_local_manhattan_data")
- return get_worktable_local_manhattan_data(
- self.get_worktable_path(), chromosome, region
- )
-
- def get_project_local_heatmap_data(self, chromosome: str = None, region: str = None):
- return get_worktable_local_heatmap_data(
- self.get_worktable_path(), chromosome, region
- )
-
- def get_id(self, chromosome=None, start=None, end=None):
- m = hashlib.md5()
- for phenotype_id in [phenotype.id for phenotype in self._phenotypes]:
- m.update(str(phenotype_id).encode("utf-8"))
-
- if (chromosome is not None):
- # Local analysis
- if start is None:
- start = 0
- if end is None:
- end = Project.K_POS_MAX
- Loc_An = "_{}_{}_{}".format(chromosome, start, end)
- m.update(str(Loc_An).encode("utf-8"))
- id_project = "local_{}".format(m.hexdigest())
- else:
- id_project = m.hexdigest()
-
- return id_project
-
- def get_global_manhattan_plot_path(self):
- return os.path.join(self.get_folder_path(), "Manhattan_Plot_Omnibus.png")
-
- def get_quadrant_plot_path(self):
- return os.path.join(self.get_folder_path(), "Quadrant_Plot_Omnibus.png")
-
- def get_zoom_plot_path(self):
- return os.path.join(self.get_folder_path(), "Zoom_Plot_Omnibus.png")
-
-
- @property
- def status(self):
- """
- status
- Gets the status of the project
- """
- if not os.path.exists(self.get_folder_path()):
- return Project.DOES_NOT_EXIST
- else:
- if (self.get_type_of_analysis() == Project.LOCAL_ANALYSIS):
- Return_status = get_file_status(self.get_zoom_plot_path())
- else:
- Return_status = get_file_status(self.get_quadrant_plot_path())
-
- return {
- # WARNING: project status is hacked so that everything is ready
- # only once the final step has completed.
- # This avoids the apparent "corrupted hdf5" file situation
- "worktable": Return_status,
- "global_manhattan": Return_status,
- "quadrant_plot_status": Return_status,
- "zoom_plot": Return_status
- }
-
- @property
- def progress(self):
- """
- progress
- Gets the percentage of completion of the phenotype analysis
- """
- JASS_progress = 0
- progress_path = self.get_progress_path()
- if os.path.exists(progress_path):
- file_progress = open(progress_path, "r")
- JASS_progress = file_progress.read()
- file_progress.close()
- return JASS_progress
-
- def get_csv_file_generation(self):
- """
- csv_file_generation
- Gets the status of the genome_full csv file generation
- """
- the_lock_path = self.get_csv_lock_path()
- csv_file = self.get_csv_path()
- csv_file_status = Project.CREATING
- if (not os.path.isfile(the_lock_path)):
- if(os.path.isfile(csv_file)):
- csv_file_status = Project.READY
- else :
- csv_file_status = Project.ERROR
- print("csv_file_generation:csv_file_status={}".format(csv_file_status))
- return csv_file_status
-
-def get_file_building_tb_path(file_path):
- return file_path + ".log"
-
-
-def get_file_status(file_path):
- if os.path.exists(file_path):
- return Project.READY
- elif os.path.exists(get_file_building_tb_path(file_path)):
- return Project.ERROR
- else:
- return Project.CREATING
\ No newline at end of file
+# -*- coding: utf-8 -*-
+"""
+compute joint statistics and generate plots for a given set of phenotypes
+"""
+from __future__ import absolute_import
+from typing import List
+import os
+import hashlib
+
+from jass.models.base_model_ import Model
+from jass.util import deserialize_model
+from jass.models.phenotype import Phenotype
+from jass.models.worktable import (
+ get_worktable_summary,
+ get_worktable_genomedata,
+ get_worktable_local_manhattan_data,
+ get_worktable_local_heatmap_data,
+)
+
+from jass.config import config
+
+
+class Project(Model):
+
+ DOES_NOT_EXIST = "DOES_NOT_EXIST"
+
+ CREATING = "CREATING"
+
+ READY = "READY"
+
+ ERROR = "ERROR"
+
+ # Type of analysis
+ LOCAL_ANALYSIS = "LOCAL_ANALYSIS"
+ GENOME_WIDE_ANALYSIS = "GENOME_WIDE_ANALYSIS"
+
+ # Upper bound of the chromosome length (bp)
+ K_POS_MAX = 250000000
+
+ def __init__(
+ self,
+ id: str = None,
+ phenotypes: List[Phenotype] = None,
+ chromosome: str = None,
+ start: str = None,
+ end: str = None,
+ ):
+ """
+ Project - a project (list of phenotypes)
+
+ :param id: project ID.
+ :type id: str
+ """
+ self.swagger_types = {
+ "id": str,
+ "status": str,
+ "phenotypes": List[Phenotype],
+ "progress": str,
+ }
+
+ self.attribute_map = {
+ "id": "id",
+ "status": "status",
+ "phenotypes": "phenotypes",
+ "progress": "progress",
+ }
+
+ self._phenotypes = phenotypes
+
+ self._id = id
+
+ if self._id is None:
+ self._id = self.get_id(chromosome, start, end)
+
+ @classmethod
+ def from_dict(cls, dikt) -> "Project":
+ """
+ Returns the dict as a model
+
+ :param dikt: A dict.
+ :type: dict
+ :return: The Project.
+ :rtype: Project
+ """
+ return deserialize_model(dikt, cls)
+
+ @property
+ def id(self) -> str:
+ """
+ Gets the id of this Project.
+
+ :return: The id of this Project.
+ :rtype: str
+ """
+ return self._id
+
+ @id.setter
+ def id(self, id: str):
+ """
+ Lists the id of this Project.
+
+ :param id: The id of this Project.
+ :type id: str
+ """
+
+ self._id = id
+
+ @property
+ def phenotypes(self) -> List[Phenotype]:
+ """
+ Gets the phenotypes list for this project.
+
+ :return: The phenotypes.
+ :rtype: str
+ """
+ return self._phenotypes
+
+ @phenotypes.setter
+ def cohort(self, phenotypes: List[Phenotype]):
+ """
+ Lists the phenotypes list for this project.
+
+ :param phenotypes: The phenotypes.
+ :type phenotypes: str
+ """
+
+ self._phenotypes = phenotypes
+
+ def get_type_of_analysis(self):
+ """
+ get_type_of_analysis
+ Gets the type of analysis : local or genome wide
+ """
+ if (self._id).split("_")[0] == "local":
+ return Project.LOCAL_ANALYSIS
+ else:
+ return Project.GENOME_WIDE_ANALYSIS
+
+ def get_folder_path(self):
+ """
+ get_folder_path
+ Gets the path of the folder where the project data are stored
+ """
+ return os.path.join(config["DATA_DIR"], "project_{}".format(self.id))
+
+ def get_worktable_path(self):
+ """
+ get_worktable_path
+ Gets the path of the file workTable.hdf5
+ """
+ return os.path.join(self.get_folder_path(), "workTable.hdf5")
+
+ def get_csv_path(self):
+ """
+ get_csv_path
+ Gets the path of the file genome_full.csv
+ """
+ return os.path.join(self.get_folder_path(), "workTable.csv")
+
+ def get_progress_path(self):
+ """
+ get_progress_path
+ Gets the path of the file containing the current progress percentage
+ of the analysis performed within the project
+ """
+ return os.path.join(self.get_folder_path(), "JASS_progress.txt")
+
+ def get_csv_lock_path(self):
+ """
+ get_csv_lock_path
+ Gets the path of the lock set-on when the csv file is not available yet
+ """
+ return os.path.join(self.get_folder_path(), "the_lock.txt")
+
+ def get_project_summary_statistics(self):
+ return get_worktable_summary(self.get_worktable_path())
+
+ def get_project_genomedata(self):
+ return get_worktable_genomedata(self.get_worktable_path())
+
+ def get_project_local_manhattan_data(
+ self, chromosome: str = None, region: str = None
+ ):
+ print("project::get_project_local_manhattan_data")
+ return get_worktable_local_manhattan_data(
+ self.get_worktable_path(), chromosome, region
+ )
+
+ def get_project_local_heatmap_data(
+ self, chromosome: str = None, region: str = None
+ ):
+ return get_worktable_local_heatmap_data(
+ self.get_worktable_path(), chromosome, region
+ )
+
+ def get_id(self, chromosome=None, start=None, end=None):
+ m = hashlib.md5()
+ for phenotype_id in [phenotype.id for phenotype in self._phenotypes]:
+ m.update(str(phenotype_id).encode("utf-8"))
+
+ if chromosome is not None:
+ # Local analysis
+ if start is None:
+ start = 0
+ if end is None:
+ end = Project.K_POS_MAX
+ Loc_An = "_{}_{}_{}".format(chromosome, start, end)
+ m.update(str(Loc_An).encode("utf-8"))
+ id_project = "local_{}".format(m.hexdigest())
+ else:
+ id_project = m.hexdigest()
+
+ return id_project
+
+ def get_global_manhattan_plot_path(self):
+ return os.path.join(self.get_folder_path(), "Manhattan_Plot_Omnibus.png")
+
+ def get_quadrant_plot_path(self):
+ return os.path.join(self.get_folder_path(), "Quadrant_Plot_Omnibus.png")
+
+ def get_zoom_plot_path(self):
+ return os.path.join(self.get_folder_path(), "Zoom_Plot_Omnibus.png")
+
+ @property
+ def status(self):
+ """
+ status
+ Gets the status of the project
+ """
+ if not os.path.exists(self.get_folder_path()):
+ return Project.DOES_NOT_EXIST
+ else:
+ if self.get_type_of_analysis() == Project.LOCAL_ANALYSIS:
+ Return_status = get_file_status(self.get_zoom_plot_path())
+ else:
+ Return_status = get_file_status(self.get_quadrant_plot_path())
+
+ return {
+ # WARNING: project status is hacked so that everything is ready
+ # only once the final step has completed.
+ # This avoids the apparent "corrupted hdf5" file situation
+ "worktable": Return_status,
+ "global_manhattan": Return_status,
+ "quadrant_plot_status": Return_status,
+ "zoom_plot": Return_status,
+ }
+
+ @property
+ def progress(self):
+ """
+ progress
+ Gets the percentage of completion of the phenotype analysis
+ """
+ JASS_progress = 0
+ progress_path = self.get_progress_path()
+ if os.path.exists(progress_path):
+ file_progress = open(progress_path, "r")
+ JASS_progress = file_progress.read()
+ file_progress.close()
+ return JASS_progress
+
+ def get_csv_file_generation(self):
+ """
+ csv_file_generation
+ Gets the status of the genome_full csv file generation
+ """
+ the_lock_path = self.get_csv_lock_path()
+ csv_file = self.get_csv_path()
+ csv_file_status = Project.CREATING
+ if not os.path.isfile(the_lock_path):
+ if os.path.isfile(csv_file):
+ csv_file_status = Project.READY
+ else:
+ csv_file_status = Project.ERROR
+ print("csv_file_generation:csv_file_status={}".format(csv_file_status))
+ return csv_file_status
+
+
+def get_file_building_tb_path(file_path):
+ return file_path + ".log"
+
+
+def get_file_status(file_path):
+ if os.path.exists(file_path):
+ return Project.READY
+ elif os.path.exists(get_file_building_tb_path(file_path)):
+ return Project.ERROR
+ else:
+ return Project.CREATING
diff --git a/jass/models/stats.py b/jass/models/stats.py
index ff2649b5b1d8d6e5c0021c9de22f58cba6b3e0e1..8d6b815106164ee809df48ea98f815c8ba9a1b01 100644
--- a/jass/models/stats.py
+++ b/jass/models/stats.py
@@ -16,21 +16,22 @@ def make_stat_computer_nopattern(cov, stat_func, **kwargs):
:rtype: function
"""
# invcov is only computed once
- invcov = np.linalg.pinv(cov, rcond=0.001)#np.linalg.inv(cov)
+ invcov = np.linalg.pinv(cov, rcond=0.001) # np.linalg.inv(cov)
def compute(z):
- return stat_func(z, cov, invcov,**kwargs)
+ return stat_func(z, cov, invcov, **kwargs)
+
return compute
def make_stat_computer_pattern(cov, stat_func):
"""
Create the function that computes the joint statistics if NaN values are in z
- and if the number of selected phenotypes is less than or equal to 16.
+ and if the number of selected phenotypes is less than or equal to 16.
It uses a covariance matrix corresponding
to the pattern of non-NaN values in z.
- This function is implemented using the currying technique:
- the first part which declares the data structure and the stat function
+ This function is implemented using the currying technique:
+ the first part which declares the data structure and the stat function
is called only once while the second part (compute) is called for each pattern.
:param cov: covariance matrix
:type cov: pandas.core.frame.DataFrame
@@ -41,13 +42,15 @@ def make_stat_computer_pattern(cov, stat_func):
"""
if not stat_func.can_use_pattern:
raise ValueError("this computation strategy cannot be used with patterns")
-
+
# invcov_bypattern is a dictionary of invcovs where the key is the
# corresponding pattern of non-NaN values in z
invcov_bypattern = {}
def compute(z, pattern_code):
- z_na_bool = z.iloc[0,].notnull()
+ z_na_bool = z.iloc[
+ 0,
+ ].notnull()
if pattern_code in invcov_bypattern:
invcov = invcov_bypattern[pattern_code]
else:
@@ -67,8 +70,8 @@ def make_stat_computer_pattern_big(cov, stat_func):
and if the number of selected phenotypes is greater than or equal to 17.
It uses a covariance matrix corresponding
to the pattern of non-NaN values in z.
- This function is implemented using the currying technique:
- the first part which declares the data structure and the stat function
+ This function is implemented using the currying technique:
+ the first part which declares the data structure and the stat function
is called only once while the second part (compute) is called for each pattern.
:param cov: covariance matrix
:type cov: numpy.ndarray
@@ -87,7 +90,7 @@ def make_stat_computer_pattern_big(cov, stat_func):
if pattern_code in invcov_bypattern:
invcov = invcov_bypattern[pattern_code]
else:
- mini_cov = (cov.take(Num,axis=1)).take(Num,axis=0)
+ mini_cov = (cov.take(Num, axis=1)).take(Num, axis=0)
invcov = np.linalg.pinv(mini_cov, rcond=0.001)
invcov_bypattern[pattern_code] = invcov
@@ -111,6 +114,7 @@ def make_stat_computer_nan_dumb(cov, stat_func):
return compute
+
def omnibus_stat(z, cov, invcov):
"""
joint statistics "omnibus" strategy
@@ -163,7 +167,7 @@ def fisher_test(z, cov, invcov):
print(z)
print(cov)
print(invcov)
- p_val = 2*spst.norm.sf(np.abs(z))
+ p_val = 2 * spst.norm.sf(np.abs(z))
stat = -2 * np.log(np.nansum(p_val, axis=1))
return spst.chi2.sf(stat, df=p)
except ValueError:
@@ -171,8 +175,10 @@ def fisher_test(z, cov, invcov):
print(invcov.shape)
print("Error in Fisher stat")
+
fisher_test.can_use_pattern = False
+
def meta_analysis(z, cov, invcov, **kwargs):
"""
Meta analysis using global sample size to weight z-score
@@ -189,16 +195,16 @@ def meta_analysis(z, cov, invcov, **kwargs):
:type samp_size : pandas.Series
"""
- Effective_sample_size = kwargs.get('samp_size', None)
+ Effective_sample_size = kwargs.get("samp_size", None)
if Effective_sample_size is None:
- raise Error('no sample size available to perform meta_analysis')
+ raise Error("no sample size available to perform meta_analysis")
else:
- loading = Effective_sample_size.loc[z.columns]**0.5
+ loading = Effective_sample_size.loc[z.columns] ** 0.5
- M_loadings = np.full(z.shape, loading**2)
+ M_loadings = np.full(z.shape, loading ** 2)
M_loadings[np.isnan(z)] = 0
- z = np.nan_to_num(z) # fill na with zero
+ z = np.nan_to_num(z) # fill na with zero
numi = loading.dot(z.transpose())
deno = np.sqrt(np.sum(M_loadings, axis=1))
@@ -208,8 +214,10 @@ def meta_analysis(z, cov, invcov, **kwargs):
return spst.chi2.sf(stat, df=1)
+
meta_analysis.can_use_pattern = False
+
def sumz_stat(z, cov, invcov, **kwargs):
"""
joint statistics "sumZ" strategy
@@ -223,7 +231,7 @@ def sumz_stat(z, cov, invcov, **kwargs):
:return: the joint statistics
:rtype: numpy.ndarray float64
"""
- loading = kwargs.get('loadings', None)
+ loading = kwargs.get("loadings", None)
if loading is None:
p = z.shape[1]
@@ -238,11 +246,11 @@ def sumz_stat(z, cov, invcov, **kwargs):
z = np.nan_to_num(z)
numi = np.square(loading.dot(z.transpose()))
- deno = np.einsum('ij,jk,ki->i', M_loadings, cov, M_loadings.T)
+ deno = np.einsum("ij,jk,ki->i", M_loadings, cov, M_loadings.T)
# fill na with 0 = don't take the missing GWAS into account in the test
stat = numi / deno
return spst.chi2.sf(stat, df=1)
-sumz_stat.can_use_pattern = False
\ No newline at end of file
+sumz_stat.can_use_pattern = False
diff --git a/jass/models/worktable.py b/jass/models/worktable.py
index 64042d57563da83e2aab2bfd348560cec61534ae..b21ce807627a6c6f62fbea988b286a4eb38e2998 100644
--- a/jass/models/worktable.py
+++ b/jass/models/worktable.py
@@ -61,29 +61,37 @@ def signif(x, digit):
return round(x, digit - int(math.floor(math.log10(abs(x)))) - 1)
-def choose_stat_function(smart_na_computation, optim_na, big, function_name, stat_function, sub_cov, **kwargs):
+def choose_stat_function(
+ smart_na_computation, optim_na, big, function_name, stat_function, sub_cov, **kwargs
+):
if smart_na_computation:
# If stat is sumz use normal computer even with na
if function_name == "omnibus_stat":
if optim_na:
if big:
- stat_compute = make_stat_computer_pattern_big(sub_cov, stat_function)
+ stat_compute = make_stat_computer_pattern_big(
+ sub_cov, stat_function
+ )
else:
stat_compute = make_stat_computer_pattern(sub_cov, stat_function)
else:
stat_compute = make_stat_computer_nan_dumb(sub_cov, stat_function)
else:
if function_name == "meta_analysis":
- stat_compute = make_stat_computer_nopattern(sub_cov, stat_function, **kwargs)
+ stat_compute = make_stat_computer_nopattern(
+ sub_cov, stat_function, **kwargs
+ )
elif function_name == "sumz_stat":
- loading_file = kwargs.get('loadings', None)
+ loading_file = kwargs.get("loadings", None)
if loading_file is None:
# Default loadings would be one for every phenotypes
stat_compute = make_stat_computer_nopattern(sub_cov, stat_function)
else:
loadings = read_csv(loading_file, index_col=0)
loadings = loadings.iloc[:, 0]
- stat_compute = make_stat_computer_nopattern(sub_cov, stat_function, loadings=loadings)
+ stat_compute = make_stat_computer_nopattern(
+ sub_cov, stat_function, loadings=loadings
+ )
else:
stat_compute = make_stat_computer_nopattern(sub_cov, stat_function)
else:
@@ -92,39 +100,47 @@ def choose_stat_function(smart_na_computation, optim_na, big, function_name, sta
return stat_compute
-def add_signif_status_column(region_sub_tab, significance_treshold=5*10**-8):
+def add_signif_status_column(region_sub_tab, significance_treshold=5 * 10 ** -8):
region_sub_tab["signif_status"] = ""
# blue: significant pvalues for omnibus and univariate tests
- cond = np.where((region_sub_tab.JASS_PVAL < significance_treshold) & (
- region_sub_tab.UNIVARIATE_MIN_PVAL < significance_treshold))[0]
+ cond = np.where(
+ (region_sub_tab.JASS_PVAL < significance_treshold)
+ & (region_sub_tab.UNIVARIATE_MIN_PVAL < significance_treshold)
+ )[0]
region_sub_tab.loc[region_sub_tab.index[cond], "signif_status"] = "Both"
# red: significant pvalues for omnibus test only
- cond = np.where((region_sub_tab.JASS_PVAL < significance_treshold) & (
- region_sub_tab.UNIVARIATE_MIN_PVAL > significance_treshold))[0]
+ cond = np.where(
+ (region_sub_tab.JASS_PVAL < significance_treshold)
+ & (region_sub_tab.UNIVARIATE_MIN_PVAL > significance_treshold)
+ )[0]
region_sub_tab.loc[region_sub_tab.index[cond], "signif_status"] = "Joint"
# green: significant pvalues for univariate test only
- cond = np.where((region_sub_tab.JASS_PVAL > significance_treshold) & (
- region_sub_tab.UNIVARIATE_MIN_PVAL < significance_treshold))[0]
- region_sub_tab.loc[region_sub_tab.index[cond],
- "signif_status"] = "Univariate"
+ cond = np.where(
+ (region_sub_tab.JASS_PVAL > significance_treshold)
+ & (region_sub_tab.UNIVARIATE_MIN_PVAL < significance_treshold)
+ )[0]
+ region_sub_tab.loc[region_sub_tab.index[cond], "signif_status"] = "Univariate"
# grey: non significant pvalues
- cond = np.where((region_sub_tab.JASS_PVAL > significance_treshold) & (
- region_sub_tab.UNIVARIATE_MIN_PVAL > significance_treshold))[0]
+ cond = np.where(
+ (region_sub_tab.JASS_PVAL > significance_treshold)
+ & (region_sub_tab.UNIVARIATE_MIN_PVAL > significance_treshold)
+ )[0]
region_sub_tab.loc[region_sub_tab.index[cond], "signif_status"] = "None"
return region_sub_tab
-def get_region_summary(sum_stat_tab, phenotype_ids, significance_treshold=5*10**-8):
+def get_region_summary(sum_stat_tab, phenotype_ids, significance_treshold=5 * 10 ** -8):
# Select the most significant SNP for the joint test for each region
- region_sub_tab = sum_stat_tab.sort_values(
- "JASS_PVAL").groupby("Region").first() # .reset_index()
+ region_sub_tab = (
+ sum_stat_tab.sort_values("JASS_PVAL").groupby("Region").first()
+ ) # .reset_index()
# add minimum univariate p-value
univar = sum_stat_tab.groupby("Region").min().UNIVARIATE_MIN_PVAL
@@ -132,18 +148,29 @@ def get_region_summary(sum_stat_tab, phenotype_ids, significance_treshold=5*10**
# Tag SNPs depending on which test is significant
region_sub_tab.reset_index(inplace=True)
- region_sub_tab = add_signif_status_column(
- region_sub_tab, significance_treshold)
+ region_sub_tab = add_signif_status_column(region_sub_tab, significance_treshold)
# reorder columns
- region_sub_tab = region_sub_tab[['Region', "MiddlePosition", "snp_ids", "CHR", "position",
- "Ref_allele", "Alt_allele", "JASS_PVAL", "UNIVARIATE_MIN_PVAL",
- "signif_status"] + phenotype_ids]
+ region_sub_tab = region_sub_tab[
+ [
+ "Region",
+ "MiddlePosition",
+ "snp_ids",
+ "CHR",
+ "position",
+ "Ref_allele",
+ "Alt_allele",
+ "JASS_PVAL",
+ "UNIVARIATE_MIN_PVAL",
+ "signif_status",
+ ]
+ + phenotype_ids
+ ]
return region_sub_tab
-def post_computation_filtering(worktable_chunk, significant_treshold=5*10**-8):
+def post_computation_filtering(worktable_chunk, significant_treshold=5 * 10 ** -8):
"""
Remove SNPs that seems aberrant: SNPs with a very low p-value that are isolated
in their region
@@ -155,17 +182,20 @@ def post_computation_filtering(worktable_chunk, significant_treshold=5*10**-8):
"""
def count_nearly_significant(rsnp):
- return((rsnp.JASS_PVAL < (significant_treshold*20)).sum())
+ return (rsnp.JASS_PVAL < (significant_treshold * 20)).sum()
res = worktable_chunk.groupby("Region").apply(count_nearly_significant)
# select region with only one SNP that is significant which is
- # suspect
+ # suspect
reg = res.loc[res == 1].index
for reg_aberant in reg:
- aberant_SNP = worktable_chunk.loc[worktable_chunk.Region == reg_aberant].sort_values(
- "JASS_PVAL").index[0]
+ aberant_SNP = (
+ worktable_chunk.loc[worktable_chunk.Region == reg_aberant]
+ .sort_values("JASS_PVAL")
+ .index[0]
+ )
worktable_chunk.drop(aberant_SNP, inplace=True)
return worktable_chunk
@@ -173,11 +203,12 @@ def post_computation_filtering(worktable_chunk, significant_treshold=5*10**-8):
def compute_pleiotropy_index(W, significance_treshold):
- N_significatif = (2.0 * spst.norm.sf(W.fillna(0,
- inplace=False).abs()) < significance_treshold).sum(1)
+ N_significatif = (
+ 2.0 * spst.norm.sf(W.fillna(0, inplace=False).abs()) < significance_treshold
+ ).sum(1)
N_pheno = (~W.isnull()).sum(1)
# pleiotropy index is not meaningful for too few phenotype
- S = N_significatif/N_pheno
+ S = N_significatif / N_pheno
S.loc[N_pheno < 4] = np.nan
return S
@@ -191,14 +222,14 @@ def create_worktable_file(
optim_na: bool = True,
csv_file: str = None,
chunk_size: int = 50,
- significance_treshold=5*10**-8,
+ significance_treshold=5 * 10 ** -8,
post_filtering=True,
delayed_gen_csv_file=False,
chromosome: str = None,
pos_Start: str = None,
pos_End: str = None,
**kwargs
- ):
+):
"""
Create a worktable file from an initial data table by specifying the
@@ -248,49 +279,107 @@ def create_worktable_file(
K_POS_MAX = 250000000
# Minimum and maximum limit of regions for each chromosome (multiples of 50)
- Min_pos_chr = [ 0, 100, 250, 400, 500, 600, 700, 800, 900, 1000, 1050,
- 1150, 1250, 1300, 1350, 1400, 1450, 1500, 1550, 1600, 1650, 1650]
- Max_pos_chr = [150, 300, 400, 550, 650, 750, 850, 950, 1050, 1100, 1200,
- 1300, 1350, 1400, 1450, 1500, 1550, 1600, 1650, 1700, 1700, 1750]
+ Min_pos_chr = [
+ 0,
+ 100,
+ 250,
+ 400,
+ 500,
+ 600,
+ 700,
+ 800,
+ 900,
+ 1000,
+ 1050,
+ 1150,
+ 1250,
+ 1300,
+ 1350,
+ 1400,
+ 1450,
+ 1500,
+ 1550,
+ 1600,
+ 1650,
+ 1650,
+ ]
+ Max_pos_chr = [
+ 150,
+ 300,
+ 400,
+ 550,
+ 650,
+ 750,
+ 850,
+ 950,
+ 1050,
+ 1100,
+ 1200,
+ 1300,
+ 1350,
+ 1400,
+ 1450,
+ 1500,
+ 1550,
+ 1600,
+ 1650,
+ 1700,
+ 1700,
+ 1750,
+ ]
N_pheno = len(phenotype_ids)
# Controls the number of phenotypes
- if (N_pheno > 64):
- print("ERROR: {} phenotypes are selected. \nThe current version of JASS cannot analyze more than 64 phenotypes" \
- .format(N_pheno))
+ if N_pheno > 64:
+ print(
+ "ERROR: {} phenotypes are selected. \nThe current version of JASS cannot analyze more than 64 phenotypes".format(
+ N_pheno
+ )
+ )
raise ValueError("Maximum number of phenotypes exceeded")
- elif (N_pheno >= 20):
- print("WARNING: {} phenotypes are selected. The computation will be very long!".format(N_pheno))
+ elif N_pheno >= 20:
+ print(
+ "WARNING: {} phenotypes are selected. The computation will be very long!".format(
+ N_pheno
+ )
+ )
- if (chromosome is None):
+ if chromosome is None:
local_analysis = False
print("============== Whole genome analysis ===============")
else:
local_analysis = True
print("============== Local analysis ===============")
- if not(chromosome.isdigit()):
- print("ERROR: when performing a local analysis, the chromosome number (between 1 and 22) is mandatory")
- raise ValueError("create_worktable_file: the required argument chromosome is not a number")
+ if not (chromosome.isdigit()):
+ print(
+ "ERROR: when performing a local analysis, the chromosome number (between 1 and 22) is mandatory"
+ )
+ raise ValueError(
+ "create_worktable_file: the required argument chromosome is not a number"
+ )
else:
num_Chr = int(chromosome)
- if ((pos_Start is None) and (pos_End is None)):
+ if (pos_Start is None) and (pos_End is None):
chromosome_full = True
print("------ Chromosome : {} ------".format(num_Chr))
else:
chromosome_full = False
- if ((pos_Start is None) or (not pos_Start.isdigit())):
+ if (pos_Start is None) or (not pos_Start.isdigit()):
pos_Start = 0
- if ((pos_End is None) or (not pos_End.isdigit())):
+ if (pos_End is None) or (not pos_End.isdigit()):
pos_End = K_POS_MAX
- print("------ Chromosome : {} ({} - {}) ------".format(num_Chr, pos_Start, pos_End))
+ print(
+ "------ Chromosome : {} ({} - {}) ------".format(
+ num_Chr, pos_Start, pos_End
+ )
+ )
print("Phenotypes = {}".format(phenotype_ids))
# Initialization of Jass_progress
- progress_path = os.path.join(os.path.dirname(
- project_hdf_path), "JASS_progress.txt")
+ progress_path = os.path.join(os.path.dirname(project_hdf_path), "JASS_progress.txt")
JASS_progress = 0
file_progress = open(progress_path, "w")
file_progress.write(str(JASS_progress))
@@ -309,7 +398,9 @@ def create_worktable_file(
if delayed_gen_csv_file:
# setting a lock to generate the csv_file asynchronously
- the_lock_path = os.path.join(os.path.dirname(project_hdf_path), "the_lock.txt")
+ the_lock_path = os.path.join(
+ os.path.dirname(project_hdf_path), "the_lock.txt"
+ )
the_lock = "The lock is set on : workTable.csv is not yet available"
file_lock = open(the_lock_path, "w")
file_lock.write(the_lock)
@@ -318,59 +409,66 @@ def create_worktable_file(
# subset of phenotypes that have been selected
phenolist = read_hdf(init_file_path, "PhenoList")
phenolist = phenolist.loc[phenotype_ids]
- hdf_work.put(
- "PhenoList", phenolist
- )
+ hdf_work.put("PhenoList", phenolist)
# subset of covariance matrix for the selected phenotypes
cov = read_hdf(init_file_path, "COV")
sub_cov = cov.loc[phenotype_ids, phenotype_ids]
# Covariance matrix
- hdf_work.put(
- "COV", sub_cov, format="table", data_columns=True
- )
+ hdf_work.put("COV", sub_cov, format="table", data_columns=True)
- #If available extract genetic covariance
+ # If available extract genetic covariance
try:
gcov = read_hdf(init_file_path, "GEN_COV")
sub_gcov = gcov.loc[phenotype_ids, phenotype_ids]
# Covariance matrix
- hdf_work.put(
- "GEN_COV", sub_gcov, format="table", data_columns=True
- )
+ hdf_work.put("GEN_COV", sub_gcov, format="table", data_columns=True)
except KeyError:
print("Genetic correlation not available in inittable. ")
-
-
regions = read_hdf(init_file_path, "Regions").index.tolist()
- sum_stat_tab_min_itemsizes = {"snp_ids": 80, "Region": 10, "CHR": 5, "Ref_allele" : 70, "Alt_allele":70}
+ sum_stat_tab_min_itemsizes = {
+ "snp_ids": 80,
+ "Region": 10,
+ "CHR": 5,
+ "Ref_allele": 70,
+ "Alt_allele": 70,
+ }
region_sub_table_min_itemsizes = {
- "Region": 10, "index": 10, "CHR": 5, "snp_ids": 80, "signif_status": 20,"Ref_allele" : 70, "Alt_allele":70}
+ "Region": 10,
+ "index": 10,
+ "CHR": 5,
+ "snp_ids": 80,
+ "signif_status": 20,
+ "Ref_allele": 70,
+ "Alt_allele": 70,
+ }
smart_na_computation = not (remove_nan)
module_name, function_name = stat.split(":")
stat_module = importlib.import_module(module_name)
stat_fn = getattr(stat_module, function_name)
- if (N_pheno < K_NB_PHENOTYPES_BIG):
+ if N_pheno < K_NB_PHENOTYPES_BIG:
big = False
sub_cov_matrix = sub_cov
else:
big = True
sub_cov_matrix = sub_cov.to_numpy()
- stat_compute = choose_stat_function(smart_na_computation,
- optim_na,
- big,
- function_name,
- stat_fn,
- sub_cov_matrix,
- samp_size=phenolist['Effective_sample_size'],
- **kwargs)
+ stat_compute = choose_stat_function(
+ smart_na_computation,
+ optim_na,
+ big,
+ function_name,
+ stat_fn,
+ sub_cov_matrix,
+ samp_size=phenolist["Effective_sample_size"],
+ **kwargs
+ )
# read data by chunks to optimize memory usage
- if (not local_analysis):
+ if not local_analysis:
Nchunk = len(regions) // chunk_size + 1
start_value = 0
else:
@@ -379,11 +477,14 @@ def create_worktable_file(
start_value = Min_pos_chr[num_Chr - 1] // chunk_size
# selection criterion in the case of a partial analysis by chromosome and position
- if (chromosome_full):
+ if chromosome_full:
Local_criteria = "(CHR == {})".format(chromosome)
else:
- Local_criteria = "(CHR == {}) and (position >= {}) and (position <= {})"\
- .format(chromosome, pos_Start, pos_End)
+ Local_criteria = (
+ "(CHR == {}) and (position >= {}) and (position <= {})".format(
+ chromosome, pos_Start, pos_End
+ )
+ )
Nsnp_total = 0
Nsnp_jassed = 0
@@ -394,52 +495,63 @@ def create_worktable_file(
JASS_progress = round((chunk + 1) * 100 / (Nchunk + 2))
binf = chunk * chunk_size
- bsup = (chunk+1) * chunk_size
-
- sum_stat_tab = read_hdf(init_file_path, 'SumStatTab', columns=[
- 'Region', 'CHR', 'position', 'snp_ids', 'Ref_allele', 'Alt_allele', 'MiddlePosition'] + phenotype_ids,
- where='Region >= {0} and Region < {1}'.format(binf, bsup))
+ bsup = (chunk + 1) * chunk_size
+
+ sum_stat_tab = read_hdf(
+ init_file_path,
+ "SumStatTab",
+ columns=[
+ "Region",
+ "CHR",
+ "position",
+ "snp_ids",
+ "Ref_allele",
+ "Alt_allele",
+ "MiddlePosition",
+ ]
+ + phenotype_ids,
+ where="Region >= {0} and Region < {1}".format(binf, bsup),
+ )
print("Regions {0} to {1}\r".format(binf, bsup))
- if(local_analysis):
+ if local_analysis:
# Data extraction in the case of a partial analysis
sum_stat_tab.query(Local_criteria, inplace=True)
# Remake row index unique: IMPORTANT for assignation with .loc
- sum_stat_tab.dropna(
- axis=0, subset=phenotype_ids, how=how_dropna, inplace=True
- )
+ sum_stat_tab.dropna(axis=0, subset=phenotype_ids, how=how_dropna, inplace=True)
sum_stat_tab.reset_index(drop=True, inplace=True)
if sum_stat_tab.shape[0] == 0:
- print(
- "No data available for region {0} to region {1}".format(binf, bsup))
+ print("No data available for region {0} to region {1}".format(binf, bsup))
continue # skip region if no data are available
Nsnp_total = Nsnp_total + sum_stat_tab.shape[0]
if remove_nan or stat.split(":")[-1] != "omnibus_stat":
- sum_stat_tab['JASS_PVAL'] = stat_compute(
- sum_stat_tab[phenotype_ids])
+ sum_stat_tab["JASS_PVAL"] = stat_compute(sum_stat_tab[phenotype_ids])
else:
if not big:
# Algorithm optimized for a small number of phenotypes
# Sort SumStatTab by missing patterns
patterns_missing, frequent_pattern = compute_frequent_missing_pattern(
- sum_stat_tab[phenotype_ids])
+ sum_stat_tab[phenotype_ids]
+ )
sum_stat_tab["patterns_missing"] = patterns_missing
z1 = sum_stat_tab[phenotype_ids]
# Apply the statistic computation by missing patterns
for pattern in frequent_pattern:
- bool_serie = (patterns_missing == pattern)
+ bool_serie = patterns_missing == pattern
Selection_criteria = sum_stat_tab["patterns_missing"] == pattern
try:
- sum_stat_tab.loc[bool_serie, "JASS_PVAL"] = stat_compute(z1[Selection_criteria], pattern)
+ sum_stat_tab.loc[bool_serie, "JASS_PVAL"] = stat_compute(
+ z1[Selection_criteria], pattern
+ )
except ValueError:
print("worktable")
@@ -447,8 +559,11 @@ def create_worktable_file(
# Algorithm optimized for a high number of phenotypes
# Sort SumStatTab by missing patterns
- patterns_missing, frequent_pattern, dico_index_y = \
- compute_frequent_missing_pattern_Big(sum_stat_tab[phenotype_ids])
+ (
+ patterns_missing,
+ frequent_pattern,
+ dico_index_y,
+ ) = compute_frequent_missing_pattern_Big(sum_stat_tab[phenotype_ids])
sum_stat_tab["index"] = sum_stat_tab.index.tolist()
sum_stat_tab["patterns_missing"] = patterns_missing
@@ -463,7 +578,9 @@ def create_worktable_file(
dico_z = {}
dico_index_x = {}
- sum_stat_tab[Liste_colonnes].apply(lambda x: store_pattern(dico_z, dico_index_x, *x), axis=1)
+ sum_stat_tab[Liste_colonnes].apply(
+ lambda x: store_pattern(dico_z, dico_index_x, *x), axis=1
+ )
Retour_omnibus_bypattern = {}
@@ -471,9 +588,7 @@ def create_worktable_file(
for pattern in frequent_pattern:
try:
Retour_omnibus_bypattern[pattern] = stat_compute(
- np.array(dico_z[pattern]),
- pattern,
- dico_index_y[pattern]
+ np.array(dico_z[pattern]), pattern, dico_index_y[pattern]
)
except ValueError:
print("worktable")
@@ -482,7 +597,9 @@ def create_worktable_file(
for pattern in frequent_pattern:
for ligne, indice in enumerate(dico_index_x[pattern]):
- Retour_omnibus[int(indice)] = (Retour_omnibus_bypattern[pattern])[int(ligne)]
+ Retour_omnibus[int(indice)] = (
+ Retour_omnibus_bypattern[pattern]
+ )[int(ligne)]
sum_stat_tab["JASS_PVAL"] = Retour_omnibus
@@ -490,25 +607,39 @@ def create_worktable_file(
sum_stat_tab.sort_values(by=["Region", "CHR"], inplace=True)
sum_stat_tab["UNIVARIATE_MIN_PVAL"] = DataFrame(
- 2.0 *
- spst.norm.sf(sum_stat_tab[phenotype_ids].fillna(
- 0, inplace=False).abs()),
+ 2.0
+ * spst.norm.sf(sum_stat_tab[phenotype_ids].fillna(0, inplace=False).abs()),
index=sum_stat_tab.index,
).min(axis=1)
- sum_stat_tab["UNIVARIATE_MIN_QVAL"] = sum_stat_tab["UNIVARIATE_MIN_PVAL"] * \
- (1-np.isnan(sum_stat_tab[phenotype_ids]).astype(int)).sum(1)
- sum_stat_tab.loc[sum_stat_tab.UNIVARIATE_MIN_QVAL >
- 1, "UNIVARIATE_MIN_QVAL"] = 1
+ sum_stat_tab["UNIVARIATE_MIN_QVAL"] = sum_stat_tab["UNIVARIATE_MIN_PVAL"] * (
+ 1 - np.isnan(sum_stat_tab[phenotype_ids]).astype(int)
+ ).sum(1)
+ sum_stat_tab.loc[
+ sum_stat_tab.UNIVARIATE_MIN_QVAL > 1, "UNIVARIATE_MIN_QVAL"
+ ] = 1
# Computing pleiotropy
sum_stat_tab["PLEIOTROPY_INDEX"] = compute_pleiotropy_index(
- sum_stat_tab[phenotype_ids], significance_treshold)
+ sum_stat_tab[phenotype_ids], significance_treshold
+ )
sum_stat_tab = sum_stat_tab[
- ["Region", "CHR", "snp_ids", "position", 'Ref_allele', 'Alt_allele', "MiddlePosition",
- "JASS_PVAL", "UNIVARIATE_MIN_PVAL", "UNIVARIATE_MIN_QVAL", "PLEIOTROPY_INDEX"]
- + phenotype_ids]
+ [
+ "Region",
+ "CHR",
+ "snp_ids",
+ "position",
+ "Ref_allele",
+ "Alt_allele",
+ "MiddlePosition",
+ "JASS_PVAL",
+ "UNIVARIATE_MIN_PVAL",
+ "UNIVARIATE_MIN_QVAL",
+ "PLEIOTROPY_INDEX",
+ ]
+ + phenotype_ids
+ ]
if post_filtering:
sum_stat_tab = post_computation_filtering(sum_stat_tab)
@@ -517,16 +648,16 @@ def create_worktable_file(
"SumStatTab", sum_stat_tab, min_itemsize=sum_stat_tab_min_itemsizes
)
- if ((csv_file is not None) and (not delayed_gen_csv_file)):
- with open(csv_file, 'a') as f:
- sum_stat_tab.to_csv(f, header=f.tell()==0)
+ if (csv_file is not None) and (not delayed_gen_csv_file):
+ with open(csv_file, "a") as f:
+ sum_stat_tab.to_csv(f, header=f.tell() == 0)
region_sub_table = get_region_summary(
- sum_stat_tab, phenotype_ids, significance_treshold=significance_treshold)
+ sum_stat_tab, phenotype_ids, significance_treshold=significance_treshold
+ )
hdf_work.append(
- "Regions",
- region_sub_table, min_itemsize=region_sub_table_min_itemsizes
+ "Regions", region_sub_table, min_itemsize=region_sub_table_min_itemsizes
)
file_progress = open(progress_path, "w")
@@ -545,16 +676,24 @@ def create_worktable_file(
np.array(
[
[
- sum((jost_min < significance_treshold) &
- (pval_min < significance_treshold)),
- sum((jost_min < significance_treshold) &
- (pval_min > significance_treshold)),
+ sum(
+ (jost_min < significance_treshold)
+ & (pval_min < significance_treshold)
+ ),
+ sum(
+ (jost_min < significance_treshold)
+ & (pval_min > significance_treshold)
+ ),
],
[
- sum((jost_min > significance_treshold) &
- (pval_min < significance_treshold)),
- sum((jost_min > significance_treshold) &
- (pval_min > significance_treshold)),
+ sum(
+ (jost_min > significance_treshold)
+ & (pval_min < significance_treshold)
+ ),
+ sum(
+ (jost_min > significance_treshold)
+ & (pval_min > significance_treshold)
+ ),
],
]
)
@@ -593,10 +732,10 @@ def binary_code_Big(dico_index_y, *args):
Codage = int(Chaine, 2)
- if (not (Codage in dico_index_y)):
+ if not (Codage in dico_index_y):
dico_index_y[Codage] = []
for indice, valeur in enumerate(args):
- if (valeur == 1):
+ if valeur == 1:
dico_index_y[Codage].append(indice)
return Codage
@@ -610,7 +749,7 @@ def store_pattern(dico_z, dico_index_x, *colonne):
Index = int(colonne[0])
Codage = int(colonne[1])
- if (not (Codage in dico_z)):
+ if not (Codage in dico_z):
dico_z[Codage] = []
dico_index_x[Codage] = []
@@ -628,10 +767,12 @@ def compute_frequent_missing_pattern(sum_stat_tab):
"""
Compute the frequency of missing pattern in the dataset
"""
- Pheno_is_present = 1- sum_stat_tab.isnull()
+ Pheno_is_present = 1 - sum_stat_tab.isnull()
# The coding of patterns missing is not guaranteed if there are more than 64 phenotypes
- patterns_missing = Pheno_is_present[Pheno_is_present.columns].apply(lambda x: binary_code(*x), axis=1)
+ patterns_missing = Pheno_is_present[Pheno_is_present.columns].apply(
+ lambda x: binary_code(*x), axis=1
+ )
pattern_frequency = patterns_missing.value_counts() / len(patterns_missing)
n_pattern = pattern_frequency.shape[0]
@@ -647,17 +788,17 @@ def compute_frequent_missing_pattern_Big(sum_stat_tab):
"""
dico_index_y = {}
- Pheno_is_present = 1- sum_stat_tab.isnull()
+ Pheno_is_present = 1 - sum_stat_tab.isnull()
# The coding of patterns missing is not guaranteed if there are more than 64 phenotypes
- patterns_missing = Pheno_is_present[Pheno_is_present.columns] \
- .apply(lambda x: binary_code_Big(dico_index_y, *x), axis=1)
-
+ patterns_missing = Pheno_is_present[Pheno_is_present.columns].apply(
+ lambda x: binary_code_Big(dico_index_y, *x), axis=1
+ )
pattern_frequency = patterns_missing.value_counts() / len(patterns_missing)
n_pattern = pattern_frequency.shape[0]
print("Number of pattern {}".format(n_pattern))
- frequent_pattern = pattern_frequency.index.tolist()
+ frequent_pattern = pattern_frequency.index.tolist()
return patterns_missing, frequent_pattern, dico_index_y
@@ -675,11 +816,9 @@ def stringize_dataframe_region_chr(dataframe: DataFrame):
:return: The dataframe with converted Region and CHR columns
:rtype: pandas.DataFrame
"""
- dataframe["Region"] = dataframe["Region"].apply(
- lambda x: "Region" + str(x))
+ dataframe["Region"] = dataframe["Region"].apply(lambda x: "Region" + str(x))
dataframe["CHR"] = dataframe["CHR"].apply(lambda x: "chr" + str(x))
- dataframe["JASS_PVAL"] = dataframe["JASS_PVAL"].apply(
- lambda x: str(signif(x, 4)))
+ dataframe["JASS_PVAL"] = dataframe["JASS_PVAL"].apply(lambda x: str(signif(x, 4)))
return dataframe
@@ -713,19 +852,22 @@ def get_worktable_genomedata(project_hdf_path: str):
:rtype: str
"""
region_subtable = stringize_dataframe_region_chr(
- read_hdf(project_hdf_path, "Regions"))
+ read_hdf(project_hdf_path, "Regions")
+ )
- region_subtable.rename(index=str, columns={
- 'JASS_PVAL': 'JOSTmin'}, inplace=True)
+ region_subtable.rename(index=str, columns={"JASS_PVAL": "JOSTmin"}, inplace=True)
- region_subtable['PVALmin'] = region_subtable['UNIVARIATE_MIN_PVAL']
- region_subtable['PVALmin'] = region_subtable['PVALmin']. apply(
- lambda x: str(signif(x, 4)))
+ region_subtable["PVALmin"] = region_subtable["UNIVARIATE_MIN_PVAL"]
+ region_subtable["PVALmin"] = region_subtable["PVALmin"].apply(
+ lambda x: str(signif(x, 4))
+ )
return region_subtable.to_csv(index=False)
-def get_worktable_local_manhattan_data(project_hdf_path: str, chromosome: str = None, region: str = None):
+def get_worktable_local_manhattan_data(
+ project_hdf_path: str, chromosome: str = None, region: str = None
+):
"""
Read and return the SumStatTab dataframe from a worktable file
for a given chromosome and region for the Manhattan plot
@@ -739,20 +881,24 @@ def get_worktable_local_manhattan_data(project_hdf_path: str, chromosome: str =
:return: The dataframe subset corresponding to the chromosome and region, as a CSV formatted text
:rtype: str
"""
- if ((chromosome is None) and (region is None)):
+ if (chromosome is None) and (region is None):
# Local analysis : the file project_hdf_path contains only useful information.
# No data filter is needed
- dataframe = read_hdf(project_hdf_path, "SumStatTab",
- columns=["Region", "CHR", "position",
- "snp_ids", "JASS_PVAL"])
+ dataframe = read_hdf(
+ project_hdf_path,
+ "SumStatTab",
+ columns=["Region", "CHR", "position", "snp_ids", "JASS_PVAL"],
+ )
else:
# Genome full analysis
region_int = region[6:]
chromosome_int = chromosome[3:]
- dataframe = read_hdf(project_hdf_path, "SumStatTab",
- columns=["Region", "CHR", "position",
- "snp_ids", "JASS_PVAL"],
- where=['Region='+str(region_int), 'CHR='+str(chromosome_int)])
+ dataframe = read_hdf(
+ project_hdf_path,
+ "SumStatTab",
+ columns=["Region", "CHR", "position", "snp_ids", "JASS_PVAL"],
+ where=["Region=" + str(region_int), "CHR=" + str(chromosome_int)],
+ )
dataframe = stringize_dataframe_region_chr(dataframe)
dataframe = dataframe.sort_values("position")
@@ -760,7 +906,9 @@ def get_worktable_local_manhattan_data(project_hdf_path: str, chromosome: str =
return dataframe.to_csv(index=False)
-def get_worktable_local_heatmap_data(project_hdf_path: str, chromosome: str = None, region: str = None):
+def get_worktable_local_heatmap_data(
+ project_hdf_path: str, chromosome: str = None, region: str = None
+):
"""
Read and return the SumStatTab dataframe from a worktable file
for a given chromosome and region for the Heatmap plot
@@ -775,7 +923,7 @@ def get_worktable_local_heatmap_data(project_hdf_path: str, chromosome: str = No
pivoted and as a CSV formatted text
:rtype: str
"""
- if ((chromosome is None) and (region is None)):
+ if (chromosome is None) and (region is None):
# Local analysis : the file project_hdf_path contains only useful information.
# No data filter is needed
dataframe = read_hdf(project_hdf_path, "SumStatTab")
@@ -783,16 +931,28 @@ def get_worktable_local_heatmap_data(project_hdf_path: str, chromosome: str = No
# Genome full analysis
region_int = region[6:]
chromosome_int = chromosome[3:]
- dataframe = read_hdf(project_hdf_path, "SumStatTab",
- where=['Region='+str(region_int), 'CHR='+str(chromosome_int)])
+ dataframe = read_hdf(
+ project_hdf_path,
+ "SumStatTab",
+ where=["Region=" + str(region_int), "CHR=" + str(chromosome_int)],
+ )
dataframe = stringize_dataframe_region_chr(dataframe)
dataframe = dataframe.sort_values("position")
- dataframe.drop(["Region", "CHR", "position", "JASS_PVAL", "MiddlePosition", "UNIVARIATE_MIN_PVAL",
- "UNIVARIATE_MIN_QVAL", "PLEIOTROPY_INDEX"],
- axis=1,
- inplace=True,
- )
+ dataframe.drop(
+ [
+ "Region",
+ "CHR",
+ "position",
+ "JASS_PVAL",
+ "MiddlePosition",
+ "UNIVARIATE_MIN_PVAL",
+ "UNIVARIATE_MIN_QVAL",
+ "PLEIOTROPY_INDEX",
+ ],
+ axis=1,
+ inplace=True,
+ )
dataframe.rename(columns={"snp_ids": "ID"}, inplace=True)
column_order = list(dataframe.ID)
pivoted_dataframe = dataframe.pivot_table(columns="ID")
@@ -822,11 +982,10 @@ def create_genome_full_csv(project_hdf_path, csv_file, chunk_size=50, Nchunk=35)
"""
# path of the lock that indicates that the csv file is not available
- the_lock_path = os.path.join(os.path.dirname(project_hdf_path),
- "the_lock.txt")
- if (os.path.isfile(the_lock_path)):
+ the_lock_path = os.path.join(os.path.dirname(project_hdf_path), "the_lock.txt")
+ if os.path.isfile(the_lock_path):
# The lock is set on
- if (os.path.isfile(csv_file)):
+ if os.path.isfile(csv_file):
# An error occurred: the csv file must not exist if the lock is set
# The existing csv file is deleted
os.remove(csv_file)
@@ -837,17 +996,20 @@ def create_genome_full_csv(project_hdf_path, csv_file, chunk_size=50, Nchunk=35)
bsup = (chunk + 1) * chunk_size
# read workTable.hdf5
- df_for_csv = read_hdf(project_hdf_path, "SumStatTab",
- where='Region >= {0} and Region < {1}'.format(binf, bsup))
+ df_for_csv = read_hdf(
+ project_hdf_path,
+ "SumStatTab",
+ where="Region >= {0} and Region < {1}".format(binf, bsup),
+ )
# append the data to the csv file
- with open(csv_file, 'a') as f:
+ with open(csv_file, "a") as f:
df_for_csv.to_csv(f, header=f.tell() == 0)
# The lock is deleted
os.remove(the_lock_path)
- if (os.path.isfile(csv_file)):
+ if os.path.isfile(csv_file):
The_file_is_available = True
else:
The_file_is_available = False
diff --git a/jass/server.py b/jass/server.py
index a6900afbf9c4b68ca8d5413578ebb403a5d5031b..a667b5ec6beb5a5178a2d9d502a993fbbcfad70a 100644
--- a/jass/server.py
+++ b/jass/server.py
@@ -1,30 +1,396 @@
#!/usr/bin/env python3
-"""
-Module that creates the flask app used to run JASS as a web server
-"""
-import connexion
-import flask
+import os
-from .encoder import JSONEncoder
-from .config import config
+from flask import Flask, redirect, send_file
+from flask.views import MethodView
+import marshmallow as ma
+from flask_smorest import Api, Blueprint, abort
+from webargs.flaskparser import FlaskParser
+from jass.config import config
+from jass.models.phenotype import get_available_phenotypes
+from jass.models.project import Project
+from jass.tasks import create_project
-class JassFlaskApp(connexion.FlaskApp):
+
+class PhenotypeSchema(ma.Schema):
+ id = ma.fields.String()
+ consortium = ma.fields.String()
+ outcome = ma.fields.String()
+ full_name = ma.fields.String()
+ typ = ma.fields.String()
+ ref = ma.fields.String()
+ ref_link = ma.fields.String()
+ data_link = ma.fields.String()
+ data_path = ma.fields.String()
+
+
+class ProjectParamsSchema(ma.Schema):
+ class Meta:
+ unknown = ma.EXCLUDE
+
+ phenotypeID = ma.fields.List(ma.fields.String())
+
+
+class LocalProjectParamsSchema(ma.Schema):
+ class Meta:
+ unknown = ma.EXCLUDE
+
+ phenotypeID = ma.fields.List(ma.fields.String())
+ chromosome = ma.fields.Integer()
+ start = ma.fields.Integer()
+ end = ma.fields.Integer()
+
+
+class ProjectStatusSchema(ma.Schema):
+ STATUS_VALUES = ["DOES_NOT_EXIST", "CREATING", "READY", "ERROR"]
+ global_manhattan = ma.fields.String(validate=ma.validate.OneOf(STATUS_VALUES))
+ quadrant_plot_status = ma.fields.String(validate=ma.validate.OneOf(STATUS_VALUES))
+ worktable = ma.fields.String(validate=ma.validate.OneOf(STATUS_VALUES))
+
+
+class ProjectSchema(ma.Schema):
+ id = ma.fields.String()
+ status = ma.fields.Nested(ProjectStatusSchema)
+ phenotypes = ma.fields.List(ma.fields.Nested(PhenotypeSchema()))
+ progress = ma.fields.String()
+
+
+blp_phenotypes = Blueprint(
+ "phenotypes",
+ "phenotypes",
+ url_prefix="/phenotypes",
+ description="Operations on phenotypes",
+)
+
+blp_projects = Blueprint(
+ "projects", "projects", url_prefix="/projects", description="Operations on projects"
+)
+
+blp_local_projects = Blueprint(
+ "local_projects",
+ "local_projects",
+ url_prefix="/local_projects",
+ description="Operations on local projects",
+)
+
+
+def get_phenotypes():
+ return get_available_phenotypes(os.path.join(config["DATA_DIR"], "initTable.hdf5"))
+
+
+@blp_phenotypes.route("")
+class PhenotypesMethodView(MethodView):
+ @blp_phenotypes.response(200, PhenotypeSchema(many=True))
+ def get(self):
+ """List phenotypes"""
+ return get_phenotypes()
+
+
+@blp_projects.route("")
+class ProjectCreateMethodView(MethodView):
+ @blp_projects.arguments(ProjectParamsSchema(), location="form")
+ @blp_projects.response(200, ProjectSchema())
+ def post(self, parameters):
+ """List projects"""
+ phenotype_ids = [
+ phenotype_id
+ for ids_with_commas in parameters["phenotypeID"]
+ for phenotype_id in ids_with_commas.split(",")
+ ]
+ phenotypes = list(filter(lambda d: d.id in phenotype_ids, get_phenotypes()))
+ return create_project([p.id for p in phenotypes], get_phenotypes())
+
+
+@blp_local_projects.route("")
+class LocalProjectCreateMethodView(MethodView):
+ @blp_projects.arguments(LocalProjectParamsSchema(), location="form")
+ @blp_projects.response(200, ProjectSchema())
+ def post(self, parameters):
+ """List projects"""
+ phenotype_ids = [
+ phenotype_id
+ for ids_with_commas in parameters["phenotypeID"]
+ for phenotype_id in ids_with_commas.split(",")
+ ]
+ phenotypes = list(filter(lambda d: d.id in phenotype_ids, get_phenotypes()))
+ return create_project(
+ [p.id for p in phenotypes],
+ get_phenotypes(),
+ str(parameters["chromosome"]),
+ str(parameters["start"]),
+ str(parameters["end"]),
+ )
+
+
+@blp_projects.route("/<project_id>")
+class ProjectDetailMethodView(MethodView):
+ @blp_projects.response(200, ProjectSchema())
+ def get(self, project_id):
+ return Project(id=project_id)
+
+
+@blp_projects.route("/<project_id>/csv_status")
+class ProjectCSVStatusMethodView(MethodView):
+ def get(self, project_id):
+ return Project(id=project_id).get_csv_file_generation()
+
+
+@blp_projects.route("/<project_id>/summary")
+class ProjectSummaryMethodView(MethodView):
+ @blp_projects.response(200, ProjectSchema())
+ def get(self, project_id):
+ return Project(id=project_id).get_project_summary_statistics()
+
+
+@blp_projects.route("/<project_id>/genome")
+class ProjectGenomeMethodView(MethodView):
+
+ # @blp_projects.response(200, headers={"Content-Type": "text/csv"})
+ def get(self, project_id):
+ try:
+ return (
+ Project(id=project_id).get_project_genomedata(),
+ 200,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ abort(404)
+ elif status["worktable"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+@blp_projects.route("/<project_id>/genome_full")
+class ProjectGenomeFullMethodView(MethodView):
+ def get(self, project_id):
+ Type_of_Analysis = Project(id=project_id).get_type_of_analysis()
+ if(Type_of_Analysis == Project.LOCAL_ANALYSIS):
+ Fichier = "local_analysis_result.csv"
+ else:
+ Fichier = "genome_full.csv"
+
+ try:
+ return send_file(
+ Project(id=project_id).get_csv_path(),
+ mimetype="text/csv",
+ as_attachment=True,
+ attachment_filename=Fichier,
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ elif status["worktable"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+@blp_projects.route("/<project_id>/globalmanhattan")
+class ProjectGlobalManhattanMethodView(MethodView):
+ def get(self, project_id):
+ try:
+ return send_file(
+ Project(id=project_id).get_global_manhattan_plot_path(),
+ mimetype="image/png",
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ elif status["global_manhattan"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+@blp_projects.route("/<project_id>/quadrant")
+class ProjectQuadrantMethodView(MethodView):
+ def get(self, project_id):
+ try:
+ return send_file(
+ Project(id=project_id).get_quadrant_plot_path(),
+ mimetype="image/png",
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ elif status["quadrant_plot_status"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+@blp_projects.route("/<project_id>/manhattan/<chromosome>/<region>")
+class ProjectLocalManhattanMethodView(MethodView):
+ def get(self, project_id, chromosome, region):
+ try:
+ return (
+ Project(id=project_id).get_project_local_manhattan_data(
+ chromosome, region
+ ),
+ 200,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ elif status["worktable"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+@blp_projects.route("/<project_id>/zoom_manhattan")
+class ProjectZoomManhattanMethodView(MethodView):
+ def get(self, project_id):
+ try:
+ return (
+ Project(id=project_id).get_project_local_manhattan_data(),
+ 200,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ elif status["worktable"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+@blp_projects.route("/<project_id>/zoom_heatmap")
+class ProjectZoomHeatmapMethodView(MethodView):
+ def get(self, project_id):
+ try:
+ return (
+ Project(id=project_id).get_project_local_heatmap_data(),
+ 200,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ elif status["worktable"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+@blp_projects.route("/<project_id>/zoomplot")
+class ProjectZoomPlotMethodView(MethodView):
+ def get(self, project_id):
+ try:
+ return send_file(
+ Project(id=project_id).get_zoom_plot_path(), mimetype="image/png"
+ )
+ except FileNotFoundError:
+ status = Project(id=project_id).status
+ if status == Project.DOES_NOT_EXIST:
+ return (
+ f"project {project_id} does not exist",
+ 404,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ elif status["worktable"] == Project.CREATING:
+ return (
+ "data not ready yet",
+ 202,
+ {"Content-Type": "text/plain; charset=utf-8"},
+ )
+ else:
+ abort(500)
+
+
+class JassApp(Flask):
"""
- JassFlaskApp subclasses connexion's FlaskApp only to customize the static url path
+ JassApp builds the JASS Flask application
"""
+ def __init__(self):
+ self.flask_app = Flask(__name__, static_url_path="", static_folder="static")
+ self.flask_app.config["API_TITLE"] = "JASS API"
+ self.flask_app.config["API_VERSION"] = "v2.0"
+ self.flask_app.config["OPENAPI_VERSION"] = "3.0.2"
+ self.flask_app.route("/")(self.redirect_to_index)
+ self.api = Api(self.flask_app)
+
def create_app(self):
- app = flask.Flask(self.import_name, static_url_path="", static_folder="static")
- app.json_encoder = JSONEncoder
- app.route("/")(self.redirect_to_index)
- return app
+ return self.flask_app
def redirect_to_index(self):
- return flask.redirect("index.html")
+ return redirect("index.html")
+
+ def register_api_blueprint(self, blp):
+ self.api.register_blueprint(blp, url_prefix=f"/api/{blp.url_prefix}")
-def get_jass_app():
- app = JassFlaskApp(__name__, specification_dir="./swagger/")
- app.add_api("swagger.yaml", arguments={"title": "JASS"}, base_path="/api")
- return app
+jass_app = JassApp()
+jass_app.register_api_blueprint(blp_phenotypes)
+jass_app.register_api_blueprint(blp_projects)
+jass_app.register_api_blueprint(blp_local_projects)
diff --git a/jass/static/directLink.html b/jass/static/directLink.html
index fd91f5533de584d1d9e8057f43caa726964e7afb..926cedfd3ce0e47c878887625bdcc0c388f4f0c8 100644
--- a/jass/static/directLink.html
+++ b/jass/static/directLink.html
@@ -3,7 +3,7 @@
<style>
div.blockMe { padding: 30px; margin: 30px; border: 10px solid #ccc; background-color: #ffd }
#question { background-color: #ffc; padding: 10px; }
- #question input { width: 4em }
+ #question input { width: 4em ; }
</style>
<script src="https://code.jquery.com/jquery-3.2.1.min.js"></script>
@@ -111,10 +111,10 @@
}
}
if (Local_Analysis == true) {
- var The_Project = "/api/local_project/" +
- chromosome + "/" +
- start + "/" +
- end;
+ phe['chromosome'] = chromosome;
+ phe['start'] = start;
+ phe['end'] = end;
+ var The_Project = "/api/local_projects";
}
else{
var The_Project = "/api/projects";
diff --git a/jass/static/index.html b/jass/static/index.html
index ed0b6c46858cff5ed45e069a7976ae48b6e1558e..eaeb43e8ecaaa41364368298c4fa559e347dc537 100644
--- a/jass/static/index.html
+++ b/jass/static/index.html
@@ -60,10 +60,10 @@
<div id="tabs-3">
<p><b>JASS: command line and web interface for the joint analysis of GWAS results</b><br />
Hanna Julienne, Pierre Lechat, Vincent Guillemot, Carla Lasry, Chunzi Yao, Robinson Araud, Vincent Laville, Bjarni Vilhjalmsson, Hervé Ménager, Hugues Aschard<br />
- in: NAR Genomics and Bioinformatics, Volume 2, Issue 1, March 2020, lqaa003, <a href="https://doi.org/10.1093/nargab/lqaa003"> <FONT color=#0000FF>https://doi.org/10.1093/nargab/lqaa003</FONT></a></p>
+ in: NAR Genomics and Bioinformatics, Volume 2, Issue 1, March 2020, lqaa003, <a href="https://urldefense.com/v3/__https://doi.org/10.1093/nargab/lqaa003__;!!JFdNOqOXpB6UZW0!75infPACk5lQWcBTD-rE5FQb6Yk4WckKROxH7a5qa4ERTDyiliWfWLGe8-HIgjvh3Gk$"> <FONT color=#0000FF>https://doi.org/10.1093/nargab/lqaa003</FONT></a></p>
<p><b>Multitrait genetic-phenotype associations to connect disease variants and biological mechanisms</b><br />
Hanna Julienne, Vincent Laville, Zachary R. McCaw, Zihuai He, Vincent Guillemot, Carla Lasry, Andrey Ziyatdinov, Amaury Vaysse, Pierre Lechat, Hervé Ménager, Wilfried Le Goff, Marie-Pierre Dube, Peter Kraft, Iuliana Ionita-Laza, Bjarni J. Vilhjálmsson, Hugues Aschard<br />
- preprint in: biorxiv, <a href=https://www.biorxiv.org/content/10.1101/2020.06.26.172999v1.full> <FONT color=#0000FF>https://www.biorxiv.org/content/10.1101/2020.06.26.172999v1.full</FONT></a></p>
+ preprint in: biorxiv, <a href="https://urldefense.com/v3/__https://www.biorxiv.org/content/10.1101/2020.06.26.172999v1.full__;!!JFdNOqOXpB6UZW0!75infPACk5lQWcBTD-rE5FQb6Yk4WckKROxH7a5qa4ERTDyiliWfWLGe8-HIV8Z7Cco$"> <FONT color=#0000FF>https://www.biorxiv.org/content/10.1101/2020.06.26.172999v1.full</FONT></a></p>
</div>
</div>
</body>
diff --git a/jass/static/selectPhenotypes_for_region.html b/jass/static/selectPhenotypes_for_region.html
index eb8db36bcdf6f8c81005e1fc755c08e74ca0e3df..51b518a53dc7faa172dc2960b775b7561f55ab95 100644
--- a/jass/static/selectPhenotypes_for_region.html
+++ b/jass/static/selectPhenotypes_for_region.html
@@ -262,6 +262,10 @@
if(selectedString != ''){
var phe = {};
phe['phenotypeID'] = selectedString;
+ phe['chromosome'] = selectedChromosome;
+ phe['start'] = region_start;
+ phe['end'] = region_end;
+
console.log("!!! "+selectedString);
console.log("!!! "+phe['phenotypeID']);
@@ -277,8 +281,7 @@
var JASS_progress = 0;
var Old_progress = 0;
var getProjectStatus = function(){
- $.post( "/api/local_project/" + selectedChromosome + "/" + region_start + "/" + region_end,
- phe).done(function( data ) {
+ $.post( "/api/local_projects", phe).done(function( data ) {
status = data.status.worktable;
console.log("!! status "+status);
JASS_progress = data.progress;
diff --git a/jass/swagger/swagger.yaml b/jass/swagger/swagger.yaml
index ebde594444f28ce9dcf627fce503388ec0745f54..03378e691554407361bd2c7df356863cd0b2eeca 100644
--- a/jass/swagger/swagger.yaml
+++ b/jass/swagger/swagger.yaml
@@ -1,595 +1,566 @@
-openapi: 3.0.0
-info:
- version: 0.0.0
- title: JASS API Specification
-paths:
- /phenotypes:
- get:
- description: |
- Gets the list of available phenotypes
- operationId: phenotypes_get
- responses:
- "200":
- description: List of the available phenotypes
- content:
- "application/json":
- schema:
- type: array
- title: ArrayOfPhenotypes
- items:
- $ref: "#/components/schemas/Phenotype"
- example:
- - "consortium": "IHEC"
- "data_link": "http://www.bloodcellgenetics.org"
- "full_name": "Monocyte percentage of white cells"
- "id": "z_IHEC_MONOP"
- "outcome": "MONOP"
- "ref": " Astle et al. 2016"
- "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/27863262"
- "type": "Cellular"
- - "consortium": "RA"
- "data_link": "http://plaza.umin.ac.jp/~yokada/datasource/software.htm"
- "full_name": "Rheumatoid Arthritis"
- "id": "z_RA_RA"
- "outcome": "RA"
- "ref": "Okada et al. 2014"
- "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/24390342"
- "type": "Immunity"
- x-openapi-router-controller: jass.controllers.default_controller
- /projects:
- post:
- description: |
- Create a new project from a selection of phenotypes
- operationId: projects_post
- requestBody:
- content:
- application/x-www-form-urlencoded:
- schema:
- type: object
- properties:
- phenotypeID:
- description: IDs of the phenotypes selected for the project
- type: array
- items:
- type: string
- required:
- - phenotypeID
- example:
- - z_IHEC_MONOP
- - z_RA_RA
- responses:
- "200":
- description: Project created
- content:
- "application/json":
- schema:
- $ref: "#/components/schemas/Phenotype"
- examples:
- Creating:
- value:
- id: "bca9d414e0f9a67b9e0d2131a47c316c"
- phenotypes:
- - "consortium": "IHEC"
- "data_link": "http://www.bloodcellgenetics.org"
- "full_name": "Monocyte percentage of white cells"
- "id": "z_IHEC_MONOP"
- "outcome": "MONOP"
- "ref": " Astle et al. 2016"
- "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/27863262"
- "type": "Cellular"
- - "consortium": "RA"
- "data_link": "http://plaza.umin.ac.jp/~yokada/datasource/software.htm"
- "full_name": "Rheumatoid Arthritis"
- "id": "z_RA_RA"
- "outcome": "RA"
- "ref": "Okada et al. 2014"
- "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/24390342"
- "type": "Immunity"
- status":
- "global_manhattan": "CREATING"
- "quadrant_plot_status": "CREATING"
- "worktable": "CREATING"
- progress":
- "progress": "0"
- Ready:
- value:
- id: "bca9d414e0f9a67b9e0d2131a47c316c"
- phenotypes:
- - "consortium": "IHEC"
- "data_link": "http://www.bloodcellgenetics.org"
- "full_name": "Monocyte percentage of white cells"
- "id": "z_IHEC_MONOP"
- "outcome": "MONOP"
- "ref": " Astle et al. 2016"
- "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/27863262"
- "type": "Cellular"
- - "consortium": "RA"
- "data_link": "http://plaza.umin.ac.jp/~yokada/datasource/software.htm"
- "full_name": "Rheumatoid Arthritis"
- "id": "z_RA_RA"
- "outcome": "RA"
- "ref": "Okada et al. 2014"
- "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/24390342"
- "type": "Immunity"
- status":
- "global_manhattan": "READY"
- "quadrant_plot_status": "READY"
- "worktable": "READY"
- progress":
- "progress": "100"
- x-openapi-router-controller: jass.controllers.default_controller
-
-
- "/local_project/{chromosome}/{start}/{end}":
- post:
- description: |
- Create a new local project from a selection of phenotypes
- operationId: local_project_post
- parameters:
- - name: chromosome
- in: path
- description: chromosome number
- required: true
- schema:
- type: string
- - name: start
- in: path
- description: start position of the region
- required: true
- schema:
- type: string
- - name: end
- in: path
- description: end position of the region
- required: true
- schema:
- type: string
- requestBody:
- content:
- application/x-www-form-urlencoded:
- schema:
- type: object
- properties:
- phenotypeID:
- description: IDs of the phenotypes selected for the project
- type: array
- items:
- type: string
- required:
- - phenotypeID
- responses:
- "200":
- description: Project created
- content:
- "application/json":
- schema:
- $ref: "#/components/schemas/Phenotype"
- x-openapi-router-controller: jass.controllers.default_controller
-
- "/projects/{projectID}":
- get:
- description: |
- Retrieve a project definition
- operationId: projects_project_idget
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: Retrieved project
- content:
- "application/json":
- schema:
- $ref: "#/components/schemas/Phenotype"
- example:
- id: "bca9d414e0f9a67b9e0d2131a47c316c"
- status":
- "global_manhattan": "READY"
- "quadrant_plot_status": "READY"
- "worktable": "READY"
- progress":
- "progress": "100"
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/summary":
- get:
- description: Retrieve summary statistics for a given project
- operationId: projects_project_id_summary_statistics
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: Summary statistics in JSON
- content:
- "*/*":
- schema:
- type: string
- title: Project summary statistics
- example:
- "JOSTSignif":
- "NoPhenoSignif": 10
- "PhenoSignif": 210
- "NoJOSTSignif":
- "NoPhenoSignif": 1470
- "PhenoSignif": 14
- x-openapi-router-controller: jass.controllers.default_controller
-
- "/projects/{projectID}/csv_status":
- get:
- description: |
- Retrieve the generation status of the genome full csv file
- operationId: projects_project_id_csv_status_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: |
- Generation status of the genome full csv file
- content:
- text/csv; charset=utf-8:
- schema:
- type: string
- title: csv_file_generation
- example: |
- READY
- x-openapi-router-controller: jass.controllers.default_controller
-
- "/projects/{projectID}/genome":
- get:
- description: |
- Retrieve whole genome summary data for a given project
- operationId: projects_project_id_genome_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: |
- Whole genome summary data in CSV format
- content:
- text/csv; charset=utf-8:
- schema:
- type: string
- title: Genome data
- example: |
- Region,MiddlePosition,snp_ids,CHR,position,Ref_allele,Alt_allele,JOSTmin,UNIVARIATE_MIN_PVAL,signif_status,z_IHEC_MONOP,z_RA_RA
- Region0,0.0,rs61997853,chr15,20001087,C,A,0.3085010612493116,0.300300000000003,None,-1.0357902654077036,
- Region1,951595.0,rs28635530,chr1,1649392,T,C,4.038788020606384e-06,2.7559999999999873e-06,None,4.688213804974398,2.999976992703393
- Region2,2737671.5,rs72644697,chr1,2533605,A,G,2.4600636176583336e-10,1.6188949607934016e-10,Both,-1.4356568827860683,-6.393727818324495
- Region3,3981773.5,rs12145992,chr1,3760309,A,G,0.0002538976722549933,0.00026034845141981964,None,-1.6164363711150218,3.651859369008055
- Region4,5147352.0,rs2649072,chr1,5754088,G,A,0.0007863952492527496,0.0006378999999999985,None,3.4149658871961184,-2.999976992703393
- Region5,6580614.0,rs2986741,chr1,6548774,G,A,0.0013472918321710914,0.0011119999999999993,None,-3.260540717377886,2.726551316504396
- Region6,8306267.0,rs79412885,chr1,9241839,A,G,2.0889091093474285e-13,8.106999999999937e-14,Both,7.46857160133221,-1.2003588580308502
- Region7,10086091.5,rs113829298,chr1,10061038,T,C,4.3158209846991565e-05,6.135999999999996e-06,None,-4.5216481219798474,0.5100734569685951
- x-openapi-router-controller: jass.controllers.default_controller
-
- "/projects/{projectID}/genome_full":
- get:
- description: |
- Retrieve whole genome complete (not summarized) data for a given project
- operationId: projects_project_id_genome_full_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: >
- Retrieve whole genome complete (not summarized) data for a given
- project in CSV format
- content:
- text/csv; charset=utf-8:
- schema:
- type: string
- title: Genome data
- example: |
- Region,CHR,snp_ids,position,Ref_allele,Alt_allele,MiddlePosition,JASS_PVAL,UNIVARIATE_MIN_PVAL,UNIVARIATE_MIN_QVAL,PLEIOTROPY_INDEX,z_IHEC_MONOP,z_RA_RA
- 194218,0,6,rs530120680,63980,G,A,0.0,0.6556994470547299,0.6501999999999999,0.6501999999999999,,0.4534843639637209,
- 194219,0,6,rs561313667,63979,T,C,0.0,0.538722344719537,0.5318,0.5318,,0.6252606526209208,
- 194220,0,15,rs113772187,20000538,T,C,0.0,0.5218942699938458,0.5148000000000001,0.5148000000000001,,-0.651381887083556,
- 194221,0,15,rs61997852,20001079,C,A,0.0,0.33819737748654505,0.33000000000000274,0.33000000000000274,,-0.9741138770593036,
- 194222,0,15,rs61997853,20001087,C,A,0.0,0.3085010612493116,0.300300000000003,0.300300000000003,,-1.0357902654077036,
- 867,1,1,rs10454464,1833495,A,G,951595.0,0.2523888759643953,0.19000000000000383,0.38000000000000766,,-0.9817967289175548,1.3105791121681174
- 4836,1,1,rs10907175,1130727,C,A,951595.0,0.3313846158840952,0.21180000000000354,0.4236000000000071,,1.2486311872236304,0.8380752842791193
- 4837,1,1,rs10907176,1130855,C,T,951595.0,0.3455642965805482,0.2251000000000033,0.4502000000000066,,1.213078000845954,0.8380752842791193
- 4838,1,1,rs10907185,1733219,A,G,951595.0,0.3919109214945312,0.25000000000000333,0.5000000000000067,,-0.7010048315295425,1.1503493803760003
- 4839,1,1,rs10907187,1759054,A,G,951595.0,0.16161974795348924,0.09099999999999998,0.18199999999999997,,-0.8114627085037827,1.6901461375274702
- 4840,1,1,rs10907188,1768894,T,C,951595.0,0.15366147518120524,0.08599999999999992,0.17199999999999985,,-0.8149516264832889,1.7168860184310413
- 4841,1,1,rs10907190,1773772,A,G,951595.0,0.12979175667585227,0.07999999999999982,0.15999999999999964,,-0.938281041511616,1.7506860712521708
- 4842,1,1,rs10907193,1805391,A,G,951595.0,0.09562672355608258,0.06299999999999988,0.12599999999999975,,-1.0405165049626888,1.8591914944718688
- 4843,1,1,rs10907194,1712230,T,C,951595.0,0.2669995168398967,0.16000000000000425,0.3200000000000085,,-0.7600913211933399,1.4050715603096189
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/globalmanhattan":
- get:
- description: |
- Retrieve global manhattan plot for a given project
- operationId: projects_project_id_global_manhattan_plot_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: |
- Global manhattan plot in PNG format
- content:
- image/png:
- schema:
- type: string
- title: Global manhattan plot
- example:
- externalValue: 'globalmanhattan_example.png'
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/zoomplot":
- get:
- description: |
- Retrieve zoom plot for a given local project
- operationId: projects_project_id_zoom_plot_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- responses:
- "200":
- description: |
- Zoom plot in PNG format
- content:
- image/png:
- schema:
- type: string
- title: Zoom plot
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/quadrant":
- get:
- description: |
- Retrieve quadrant plot for a given project
- operationId: projects_project_id_quadrant_plot_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: |
- Quadrant plot in PNG format
- content:
- image/png:
- schema:
- type: string
- title: Quadrant plot
- example:
- externalValue: 'quadrant_example.png'
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/manhattan/{chromosome}/{region}":
- get:
- description: Retrieve local manhattan data
- operationId: projects_project_id_local_manhattan_data_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- - name: chromosome
- in: path
- description: chromosome number
- required: true
- schema:
- type: string
- example: "chr1"
- - name: region
- in: path
- description: region number
- required: true
- schema:
- type: string
- example: "Region1"
- responses:
- "200":
- description: |
- Local manhattan plot data in CSV format
- content:
- text/csv; charset=utf-8:
- schema:
- type: string
- title: Local manhattan plot data
- example: |
- Region,CHR,position,snp_ids,JASS_PVAL
- Region1,chr1,636285,rs545945172,0.7216577092326355
- Region1,chr1,662414,rs371628865,0.6725666758876788
- Region1,chr1,662622,rs61769339,0.405683282952658
- Region1,chr1,665266,rs539032812,0.3348008598497511
- Region1,chr1,693731,rs12238997,0.4952464035829177
- Region1,chr1,701835,rs189800799,0.666563580963709
- Region1,chr1,706778,rs113462541,0.861641963454806
- Region1,chr1,711310,rs200531508,0.07463266395489108
- Region1,chr1,714019,rs114983708,0.6667198743938074
- Region1,chr1,715265,rs12184267,0.6666055494294745
- Region1,chr1,715367,rs12184277,0.7657858702655146
- Region1,chr1,720381,rs116801199,0.6816390671665746
- Region1,chr1,723742,rs28375378,0.7124933618852456
- Region1,chr1,724324,rs28692873,0.9212425499680825
- Region1,chr1,725196,rs377099097,0.594983644175122
- Region1,chr1,725389,rs375619475,0.7032290172253173
- Region1,chr1,727841,rs116587930,0.9078685880041112
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/heatmap/{chromosome}/{region}":
- get:
- description: Retrieve local heatmap data
- operationId: projects_project_id_local_heatmap_data_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- - name: chromosome
- in: path
- description: chromosome number
- required: true
- schema:
- type: string
- example: "chr1"
- - name: region
- in: path
- description: region number
- required: true
- schema:
- type: string
- example: "Region1"
- responses:
- "200":
- description: |
- Local manhattan plot data in CSV format
- content:
- text/csv; charset=utf-8:
- schema:
- type: string
- title: Local heatmap plot data
- example: |
- ID,rs545945172,rs371628865,rs61769339,rs539032812,rs12238997,rs189800799
- z_IHEC_MONOP,-0.3623372836601329,-0.429856541533544,-0.8457360635272954,-0.9809852811227732,-0.6936527568935886,0.4382385293216385
- z_RA_RA,,,,,,
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/zoom_manhattan":
- get:
- description: Retrieve local manhattan data
- operationId: projects_project_id_zoom_manhattan_data_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: |
- Local manhattan plot data in CSV format
- content:
- text/csv; charset=utf-8:
- schema:
- type: string
- title: Local manhattan plot data
- example: |
- Region,CHR,position,snp_ids,JASS_PVAL
- Region1,chr1,636285,rs545945172,0.7216577092326355
- Region1,chr1,662414,rs371628865,0.6725666758876788
- Region1,chr1,662622,rs61769339,0.405683282952658
- Region1,chr1,665266,rs539032812,0.3348008598497511
- Region1,chr1,693731,rs12238997,0.4952464035829177
- Region1,chr1,701835,rs189800799,0.666563580963709
- Region1,chr1,706778,rs113462541,0.861641963454806
- Region1,chr1,711310,rs200531508,0.07463266395489108
- Region1,chr1,714019,rs114983708,0.6667198743938074
- Region1,chr1,715265,rs12184267,0.6666055494294745
- Region1,chr1,715367,rs12184277,0.7657858702655146
- Region1,chr1,720381,rs116801199,0.6816390671665746
- Region1,chr1,723742,rs28375378,0.7124933618852456
- Region1,chr1,724324,rs28692873,0.9212425499680825
- Region1,chr1,725196,rs377099097,0.594983644175122
- Region1,chr1,725389,rs375619475,0.7032290172253173
- Region1,chr1,727841,rs116587930,0.9078685880041112
- x-openapi-router-controller: jass.controllers.default_controller
- "/projects/{projectID}/zoom_heatmap":
- get:
- description: Retrieve local heatmap data
- operationId: projects_project_id_zoom_heatmap_data_get
- parameters:
- - name: projectID
- in: path
- description: project ID
- required: true
- schema:
- type: string
- example: "bca9d414e0f9a67b9e0d2131a47c316c"
- responses:
- "200":
- description: |
- Local manhattan plot data in CSV format
- content:
- text/csv; charset=utf-8:
- schema:
- type: string
- title: Local heatmap plot data
- example: |
- ID,rs545945172,rs371628865,rs61769339,rs539032812,rs12238997,rs189800799
- z_IHEC_MONOP,-0.3623372836601329,-0.429856541533544,-0.8457360635272954,-0.9809852811227732,-0.6936527568935886,0.4382385293216385
- z_RA_RA,,,,,,
- x-openapi-router-controller: jass.controllers.default_controller
-components:
- schemas:
- Phenotype:
- properties:
- id:
- type: string
- consortium:
- type: string
- outcome:
- type: string
- full_name:
- type: string
- type:
- type: string
- ref:
- type: string
- ref_link:
- type: string
- data_link:
- type: string
- data_path:
- type: string
- Project:
- properties:
- id:
- type: string
- status:
- type: string
- progress:
- type: string
- outcome:
- type: array
- items:
- $ref: "#/components/schemas/Phenotype"
-
+openapi: 3.0.0
+info:
+ version: 0.0.0
+ title: JASS API Specification
+paths:
+ /phenotypes:
+ get:
+ description: |
+ Gets the list of available phenotypes
+ operationId: phenotypes_get
+ responses:
+ "200":
+ description: List of the available phenotypes
+ content:
+ "application/json":
+ schema:
+ type: array
+ title: ArrayOfPhenotypes
+ items:
+ $ref: "#/components/schemas/Phenotype"
+ example:
+ - "consortium": "IHEC"
+ "data_link": "http://www.bloodcellgenetics.org"
+ "full_name": "Monocyte percentage of white cells"
+ "id": "z_IHEC_MONOP"
+ "outcome": "MONOP"
+ "ref": " Astle et al. 2016"
+ "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/27863262"
+ "type": "Cellular"
+ - "consortium": "RA"
+ "data_link": "http://plaza.umin.ac.jp/~yokada/datasource/software.htm"
+ "full_name": "Rheumatoid Arthritis"
+ "id": "z_RA_RA"
+ "outcome": "RA"
+ "ref": "Okada et al. 2014"
+ "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/24390342"
+ "type": "Immunity"
+ /projects:
+ post:
+ description: |
+ Create a new project from a selection of phenotypes
+ operationId: projects_post
+ requestBody:
+ content:
+ application/x-www-form-urlencoded:
+ schema:
+ type: object
+ properties:
+ phenotypeID:
+ description: IDs of the phenotypes selected for the project
+ type: array
+ items:
+ type: string
+ required:
+ - phenotypeID
+ example:
+ - z_IHEC_MONOP
+ - z_RA_RA
+ responses:
+ "200":
+ description: Project created
+ content:
+ "application/json":
+ schema:
+ $ref: "#/components/schemas/Phenotype"
+ examples:
+ Creating:
+ value:
+ id: "bca9d414e0f9a67b9e0d2131a47c316c"
+ phenotypes:
+ - "consortium": "IHEC"
+ "data_link": "http://www.bloodcellgenetics.org"
+ "full_name": "Monocyte percentage of white cells"
+ "id": "z_IHEC_MONOP"
+ "outcome": "MONOP"
+ "ref": " Astle et al. 2016"
+ "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/27863262"
+ "type": "Cellular"
+ - "consortium": "RA"
+ "data_link": "http://plaza.umin.ac.jp/~yokada/datasource/software.htm"
+ "full_name": "Rheumatoid Arthritis"
+ "id": "z_RA_RA"
+ "outcome": "RA"
+ "ref": "Okada et al. 2014"
+ "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/24390342"
+ "type": "Immunity"
+ status":
+ "global_manhattan": "CREATING"
+ "quadrant_plot_status": "CREATING"
+ "worktable": "CREATING"
+ progress":
+ "progress": "0"
+ Ready:
+ value:
+ id: "bca9d414e0f9a67b9e0d2131a47c316c"
+ phenotypes:
+ - "consortium": "IHEC"
+ "data_link": "http://www.bloodcellgenetics.org"
+ "full_name": "Monocyte percentage of white cells"
+ "id": "z_IHEC_MONOP"
+ "outcome": "MONOP"
+ "ref": " Astle et al. 2016"
+ "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/27863262"
+ "type": "Cellular"
+ - "consortium": "RA"
+ "data_link": "http://plaza.umin.ac.jp/~yokada/datasource/software.htm"
+ "full_name": "Rheumatoid Arthritis"
+ "id": "z_RA_RA"
+ "outcome": "RA"
+ "ref": "Okada et al. 2014"
+ "ref_link": "https://www.ncbi.nlm.nih.gov/pubmed/24390342"
+ "type": "Immunity"
+ status":
+ "global_manhattan": "READY"
+ "quadrant_plot_status": "READY"
+ "worktable": "READY"
+ progress":
+ "progress": "100"
+ /local_project:
+ post:
+ description: |
+ Create a new local project from a selection of phenotypes
+ operationId: local_project_post
+ requestBody:
+ content:
+ application/x-www-form-urlencoded:
+ schema:
+ type: object
+ properties:
+ phenotypeID:
+ description: IDs of the phenotypes selected for the project
+ type: array
+ items:
+ type: string
+ chromosome:
+ description: chromosome number
+ type: string
+ start:
+ description: start position of the region
+ type: string
+ end:
+ description: end position of the region
+ type: string
+ required:
+ - phenotypeID
+ - chromosome
+ - start
+ - end
+ responses:
+ "200":
+ description: Project created
+ content:
+ "application/json":
+ schema:
+ $ref: "#/components/schemas/Phenotype"
+ "/projects/{projectID}":
+ get:
+ description: |
+ Retrieve a project definition
+ operationId: projects_project_idget
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: Retrieved project
+ content:
+ "application/json":
+ schema:
+ $ref: "#/components/schemas/Phenotype"
+ example:
+ id: "bca9d414e0f9a67b9e0d2131a47c316c"
+ status":
+ "global_manhattan": "READY"
+ "quadrant_plot_status": "READY"
+ "worktable": "READY"
+ progress":
+ "progress": "100"
+ "/projects/{projectID}/summary":
+ get:
+ description: Retrieve summary statistics for a given project
+ operationId: projects_project_id_summary_statistics
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: Summary statistics in JSON
+ content:
+ "*/*":
+ schema:
+ type: string
+ title: Project summary statistics
+ example:
+ "JOSTSignif":
+ "NoPhenoSignif": 10
+ "PhenoSignif": 210
+ "NoJOSTSignif":
+ "NoPhenoSignif": 1470
+ "PhenoSignif": 14
+ "/projects/{projectID}/csv_status":
+ get:
+ description: |
+ Retrieve the generation status of the genome full csv file
+ operationId: projects_project_id_csv_status_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: |
+ Generation status of the genome full csv file
+ content:
+ text/csv; charset=utf-8:
+ schema:
+ type: string
+ title: csv_file_generation
+ example: |
+ READY
+ "/projects/{projectID}/genome":
+ get:
+ description: |
+ Retrieve whole genome summary data for a given project
+ operationId: projects_project_id_genome_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: |
+ Whole genome summary data in CSV format
+ content:
+ text/csv; charset=utf-8:
+ schema:
+ type: string
+ title: Genome data
+ example: |
+ Region,MiddlePosition,snp_ids,CHR,position,Ref_allele,Alt_allele,JOSTmin,UNIVARIATE_MIN_PVAL,signif_status,z_IHEC_MONOP,z_RA_RA
+ Region0,0.0,rs61997853,chr15,20001087,C,A,0.3085010612493116,0.300300000000003,None,-1.0357902654077036,
+ Region1,951595.0,rs28635530,chr1,1649392,T,C,4.038788020606384e-06,2.7559999999999873e-06,None,4.688213804974398,2.999976992703393
+ Region2,2737671.5,rs72644697,chr1,2533605,A,G,2.4600636176583336e-10,1.6188949607934016e-10,Both,-1.4356568827860683,-6.393727818324495
+ Region3,3981773.5,rs12145992,chr1,3760309,A,G,0.0002538976722549933,0.00026034845141981964,None,-1.6164363711150218,3.651859369008055
+ Region4,5147352.0,rs2649072,chr1,5754088,G,A,0.0007863952492527496,0.0006378999999999985,None,3.4149658871961184,-2.999976992703393
+ Region5,6580614.0,rs2986741,chr1,6548774,G,A,0.0013472918321710914,0.0011119999999999993,None,-3.260540717377886,2.726551316504396
+ Region6,8306267.0,rs79412885,chr1,9241839,A,G,2.0889091093474285e-13,8.106999999999937e-14,Both,7.46857160133221,-1.2003588580308502
+ Region7,10086091.5,rs113829298,chr1,10061038,T,C,4.3158209846991565e-05,6.135999999999996e-06,None,-4.5216481219798474,0.5100734569685951
+ "/projects/{projectID}/genome_full":
+ get:
+ description: |
+ Retrieve whole genome complete (not summarized) data for a given project
+ operationId: projects_project_id_genome_full_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: >
+ Retrieve whole genome complete (not summarized) data for a given
+ project in CSV format
+ content:
+ text/csv; charset=utf-8:
+ schema:
+ type: string
+ title: Genome data
+ example: |
+ Region,CHR,snp_ids,position,Ref_allele,Alt_allele,MiddlePosition,JASS_PVAL,UNIVARIATE_MIN_PVAL,UNIVARIATE_MIN_QVAL,PLEIOTROPY_INDEX,z_IHEC_MONOP,z_RA_RA
+ 194218,0,6,rs530120680,63980,G,A,0.0,0.6556994470547299,0.6501999999999999,0.6501999999999999,,0.4534843639637209,
+ 194219,0,6,rs561313667,63979,T,C,0.0,0.538722344719537,0.5318,0.5318,,0.6252606526209208,
+ 194220,0,15,rs113772187,20000538,T,C,0.0,0.5218942699938458,0.5148000000000001,0.5148000000000001,,-0.651381887083556,
+ 194221,0,15,rs61997852,20001079,C,A,0.0,0.33819737748654505,0.33000000000000274,0.33000000000000274,,-0.9741138770593036,
+ 194222,0,15,rs61997853,20001087,C,A,0.0,0.3085010612493116,0.300300000000003,0.300300000000003,,-1.0357902654077036,
+ 867,1,1,rs10454464,1833495,A,G,951595.0,0.2523888759643953,0.19000000000000383,0.38000000000000766,,-0.9817967289175548,1.3105791121681174
+ 4836,1,1,rs10907175,1130727,C,A,951595.0,0.3313846158840952,0.21180000000000354,0.4236000000000071,,1.2486311872236304,0.8380752842791193
+ 4837,1,1,rs10907176,1130855,C,T,951595.0,0.3455642965805482,0.2251000000000033,0.4502000000000066,,1.213078000845954,0.8380752842791193
+ 4838,1,1,rs10907185,1733219,A,G,951595.0,0.3919109214945312,0.25000000000000333,0.5000000000000067,,-0.7010048315295425,1.1503493803760003
+ 4839,1,1,rs10907187,1759054,A,G,951595.0,0.16161974795348924,0.09099999999999998,0.18199999999999997,,-0.8114627085037827,1.6901461375274702
+ 4840,1,1,rs10907188,1768894,T,C,951595.0,0.15366147518120524,0.08599999999999992,0.17199999999999985,,-0.8149516264832889,1.7168860184310413
+ 4841,1,1,rs10907190,1773772,A,G,951595.0,0.12979175667585227,0.07999999999999982,0.15999999999999964,,-0.938281041511616,1.7506860712521708
+ 4842,1,1,rs10907193,1805391,A,G,951595.0,0.09562672355608258,0.06299999999999988,0.12599999999999975,,-1.0405165049626888,1.8591914944718688
+ 4843,1,1,rs10907194,1712230,T,C,951595.0,0.2669995168398967,0.16000000000000425,0.3200000000000085,,-0.7600913211933399,1.4050715603096189
+ "/projects/{projectID}/globalmanhattan":
+ get:
+ description: |
+ Retrieve global manhattan plot for a given project
+ operationId: projects_project_id_global_manhattan_plot_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: |
+ Global manhattan plot in PNG format
+ content:
+ image/png:
+ schema:
+ type: string
+ title: Global manhattan plot
+ example:
+ externalValue: "globalmanhattan_example.png"
+ "/projects/{projectID}/zoomplot":
+ get:
+ description: |
+ Retrieve zoom plot for a given local project
+ operationId: projects_project_id_zoom_plot_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ responses:
+ "200":
+ description: |
+ Zoom plot in PNG format
+ content:
+ image/png:
+ schema:
+ type: string
+ title: Zoom plot
+ "/projects/{projectID}/quadrant":
+ get:
+ description: |
+ Retrieve quadrant plot for a given project
+ operationId: projects_project_id_quadrant_plot_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: |
+ Quadrant plot in PNG format
+ content:
+ image/png:
+ schema:
+ type: string
+ title: Quadrant plot
+ example:
+ externalValue: "quadrant_example.png"
+ "/projects/{projectID}/manhattan/{chromosome}/{region}":
+ get:
+ description: Retrieve local manhattan data
+ operationId: projects_project_id_local_manhattan_data_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ - name: chromosome
+ in: path
+ description: chromosome number
+ required: true
+ schema:
+ type: string
+ example: "chr1"
+ - name: region
+ in: path
+ description: region number
+ required: true
+ schema:
+ type: string
+ example: "Region1"
+ responses:
+ "200":
+ description: |
+ Local manhattan plot data in CSV format
+ content:
+ text/csv; charset=utf-8:
+ schema:
+ type: string
+ title: Local manhattan plot data
+ example: |
+ Region,CHR,position,snp_ids,JASS_PVAL
+ Region1,chr1,636285,rs545945172,0.7216577092326355
+ Region1,chr1,662414,rs371628865,0.6725666758876788
+ Region1,chr1,662622,rs61769339,0.405683282952658
+ Region1,chr1,665266,rs539032812,0.3348008598497511
+ Region1,chr1,693731,rs12238997,0.4952464035829177
+ Region1,chr1,701835,rs189800799,0.666563580963709
+ Region1,chr1,706778,rs113462541,0.861641963454806
+ Region1,chr1,711310,rs200531508,0.07463266395489108
+ Region1,chr1,714019,rs114983708,0.6667198743938074
+ Region1,chr1,715265,rs12184267,0.6666055494294745
+ Region1,chr1,715367,rs12184277,0.7657858702655146
+ Region1,chr1,720381,rs116801199,0.6816390671665746
+ Region1,chr1,723742,rs28375378,0.7124933618852456
+ Region1,chr1,724324,rs28692873,0.9212425499680825
+ Region1,chr1,725196,rs377099097,0.594983644175122
+ Region1,chr1,725389,rs375619475,0.7032290172253173
+ Region1,chr1,727841,rs116587930,0.9078685880041112
+ "/projects/{projectID}/heatmap/{chromosome}/{region}":
+ get:
+ description: Retrieve local heatmap data
+ operationId: projects_project_id_local_heatmap_data_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ - name: chromosome
+ in: path
+ description: chromosome number
+ required: true
+ schema:
+ type: string
+ example: "chr1"
+ - name: region
+ in: path
+ description: region number
+ required: true
+ schema:
+ type: string
+ example: "Region1"
+ responses:
+ "200":
+ description: |
+ Local manhattan plot data in CSV format
+ content:
+ text/csv; charset=utf-8:
+ schema:
+ type: string
+ title: Local heatmap plot data
+ example: |
+ ID,rs545945172,rs371628865,rs61769339,rs539032812,rs12238997,rs189800799
+ z_IHEC_MONOP,-0.3623372836601329,-0.429856541533544,-0.8457360635272954,-0.9809852811227732,-0.6936527568935886,0.4382385293216385
+ z_RA_RA,,,,,,
+ "/projects/{projectID}/zoom_manhattan":
+ get:
+ description: Retrieve local manhattan data
+ operationId: projects_project_id_zoom_manhattan_data_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: |
+ Local manhattan plot data in CSV format
+ content:
+ text/csv; charset=utf-8:
+ schema:
+ type: string
+ title: Local manhattan plot data
+ example: |
+ Region,CHR,position,snp_ids,JASS_PVAL
+ Region1,chr1,636285,rs545945172,0.7216577092326355
+ Region1,chr1,662414,rs371628865,0.6725666758876788
+ Region1,chr1,662622,rs61769339,0.405683282952658
+ Region1,chr1,665266,rs539032812,0.3348008598497511
+ Region1,chr1,693731,rs12238997,0.4952464035829177
+ Region1,chr1,701835,rs189800799,0.666563580963709
+ Region1,chr1,706778,rs113462541,0.861641963454806
+ Region1,chr1,711310,rs200531508,0.07463266395489108
+ Region1,chr1,714019,rs114983708,0.6667198743938074
+ Region1,chr1,715265,rs12184267,0.6666055494294745
+ Region1,chr1,715367,rs12184277,0.7657858702655146
+ Region1,chr1,720381,rs116801199,0.6816390671665746
+ Region1,chr1,723742,rs28375378,0.7124933618852456
+ Region1,chr1,724324,rs28692873,0.9212425499680825
+ Region1,chr1,725196,rs377099097,0.594983644175122
+ Region1,chr1,725389,rs375619475,0.7032290172253173
+ Region1,chr1,727841,rs116587930,0.9078685880041112
+ "/projects/{projectID}/zoom_heatmap":
+ get:
+ description: Retrieve local heatmap data
+ operationId: projects_project_id_zoom_heatmap_data_get
+ parameters:
+ - name: projectID
+ in: path
+ description: project ID
+ required: true
+ schema:
+ type: string
+ example: "bca9d414e0f9a67b9e0d2131a47c316c"
+ responses:
+ "200":
+ description: |
+ Local manhattan plot data in CSV format
+ content:
+ text/csv; charset=utf-8:
+ schema:
+ type: string
+ title: Local heatmap plot data
+ example: |
+ ID,rs545945172,rs371628865,rs61769339,rs539032812,rs12238997,rs189800799
+ z_IHEC_MONOP,-0.3623372836601329,-0.429856541533544,-0.8457360635272954,-0.9809852811227732,-0.6936527568935886,0.4382385293216385
+ z_RA_RA,,,,,,
+components:
+ schemas:
+ Phenotype:
+ properties:
+ id:
+ type: string
+ consortium:
+ type: string
+ outcome:
+ type: string
+ full_name:
+ type: string
+ type:
+ type: string
+ ref:
+ type: string
+ ref_link:
+ type: string
+ data_link:
+ type: string
+ data_path:
+ type: string
+ Project:
+ properties:
+ id:
+ type: string
+ status:
+ type: string
+ progress:
+ type: string
+ outcome:
+ type: array
+ items:
+ $ref: "#/components/schemas/Phenotype"
diff --git a/jass/tasks.py b/jass/tasks.py
index dede914577cb4a755bbb35f2b9bc1e840c89d504..a17a8bcae4dc1be36545778c9e58d6ce16ffa671 100644
--- a/jass/tasks.py
+++ b/jass/tasks.py
@@ -9,24 +9,25 @@ from flask import Flask
import jass.models.project
from jass.models.project import Project, get_file_building_tb_path
-from jass.models.plots import (create_global_plot,
- create_local_plot,
- create_quadrant_plot,
- create_qq_plot)
+from jass.models.plots import (
+ create_global_plot,
+ create_local_plot,
+ create_quadrant_plot,
+ create_qq_plot,
+)
+
+from jass.models.worktable import create_worktable_file, create_genome_full_csv
-from jass.models.worktable import (create_worktable_file,
- create_genome_full_csv)
-
from jass.models.phenotype import Phenotype
from jass.config import config
def make_celery(app):
celery = Celery()
- if 'CELERY_CONFIG_MODULE' in os.environ:
- celery.config_from_envvar('CELERY_CONFIG_MODULE')
+ if "CELERY_CONFIG_MODULE" in os.environ:
+ celery.config_from_envvar("CELERY_CONFIG_MODULE")
else:
- celery.config_from_object('jass.celeryconfig')
+ celery.config_from_object("jass.celeryconfig")
celery.conf.update(app.config)
TaskBase = celery.Task
@@ -41,45 +42,46 @@ def make_celery(app):
return celery
-
flask_app = Flask(__name__)
celery = make_celery(flask_app)
+
@celery.task
def create_project_worktable_file(
- phenotype_ids,
- init_file_path,
- project_hdf_path,
- remove_nan,
- stat,
- optim_na,
- csv_file,
- chunk_size,
- significance_treshold,
- post_filtering,
- delayed_gen_csv_file,
- chromosome,
- pos_Start,
- pos_End,
- custom_loadings):
+ phenotype_ids,
+ init_file_path,
+ project_hdf_path,
+ remove_nan,
+ stat,
+ optim_na,
+ csv_file,
+ chunk_size,
+ significance_treshold,
+ post_filtering,
+ delayed_gen_csv_file,
+ chromosome,
+ pos_Start,
+ pos_End,
+ custom_loadings,
+):
try:
return create_worktable_file(
- phenotype_ids = phenotype_ids,
- init_file_path = init_file_path,
- project_hdf_path = project_hdf_path,
- remove_nan = remove_nan,
- stat = stat,
- optim_na = True,
- csv_file = csv_file,
- chunk_size = chunk_size,
- significance_treshold = significance_treshold,
- post_filtering = post_filtering,
- delayed_gen_csv_file = delayed_gen_csv_file,
- chromosome = chromosome,
- pos_Start = pos_Start,
- pos_End = pos_End,
- custom_loadings = custom_loadings
- )
+ phenotype_ids=phenotype_ids,
+ init_file_path=init_file_path,
+ project_hdf_path=project_hdf_path,
+ remove_nan=remove_nan,
+ stat=stat,
+ optim_na=True,
+ csv_file=csv_file,
+ chunk_size=chunk_size,
+ significance_treshold=significance_treshold,
+ post_filtering=post_filtering,
+ delayed_gen_csv_file=delayed_gen_csv_file,
+ chromosome=chromosome,
+ pos_Start=pos_Start,
+ pos_End=pos_End,
+ custom_loadings=custom_loadings,
+ )
except Exception as e:
exc_type, exc_value, exc_traceback = sys.exc_info()
log_path = get_file_building_tb_path(project_hdf_path)
@@ -147,77 +149,78 @@ def create_project_csv_file(Nchunk, worktable_path, csv_file_path):
traceback.print_exception(exc_type, exc_value, exc_traceback, file=log_fh)
log_fh.close()
+
def launch_create_project(
- phenotype_ids,
- init_table_path,
+ phenotype_ids,
+ init_table_path,
worktable_path,
- remove_nan = False,
- stat = "jass.models.stats:omnibus_stat",
- csv_file = None,
- chunk_size = 50,
- significance_treshold = 5*10**-8,
- post_filtering = True,
- delayed_gen_csv_file = False,
- chromosome = None,
- start = None,
- end = None,
- custom_loadings = None,
- global_plot_path = None,
- quadrant_plot_path = None,
- zoom_plot_path = None,
- qq_plot_path = None
- ):
+ remove_nan=False,
+ stat="jass.models.stats:omnibus_stat",
+ csv_file=None,
+ chunk_size=50,
+ significance_treshold=5 * 10 ** -8,
+ post_filtering=True,
+ delayed_gen_csv_file=False,
+ chromosome=None,
+ start=None,
+ end=None,
+ custom_loadings=None,
+ global_plot_path=None,
+ quadrant_plot_path=None,
+ zoom_plot_path=None,
+ qq_plot_path=None,
+):
post_worktable_jobs = []
- if (global_plot_path is not None):
+ if global_plot_path is not None:
post_worktable_jobs.append(
create_project_global_plot.si(worktable_path, global_plot_path)
)
- if (quadrant_plot_path is not None):
+ if quadrant_plot_path is not None:
post_worktable_jobs.append(
create_project_quadrant_plot.si(worktable_path, quadrant_plot_path),
)
- if (zoom_plot_path is not None):
+ if zoom_plot_path is not None:
post_worktable_jobs.append(
create_project_zoom_plot.si(worktable_path, zoom_plot_path)
)
- if (qq_plot_path is not None):
+ if qq_plot_path is not None:
post_worktable_jobs.append(
create_project_qq_plot.si(worktable_path, qq_plot_path)
)
- if (delayed_gen_csv_file and (csv_file is not None)):
- post_worktable_jobs.append(
- create_project_csv_file.s(worktable_path, csv_file)
- )
+ if delayed_gen_csv_file and (csv_file is not None):
+ post_worktable_jobs.append(create_project_csv_file.s(worktable_path, csv_file))
post_worktable_tasks_group = group(post_worktable_jobs)
- main_wf = chain(create_project_worktable_file.si(
- phenotype_ids = phenotype_ids,
- init_file_path = init_table_path,
- project_hdf_path = worktable_path,
- remove_nan = remove_nan,
- stat = stat,
- optim_na = True,
- csv_file = csv_file,
- chunk_size = chunk_size,
- significance_treshold = significance_treshold,
- post_filtering = post_filtering,
- delayed_gen_csv_file = delayed_gen_csv_file,
- chromosome = chromosome,
- pos_Start = start,
- pos_End = end,
- custom_loadings = custom_loadings
- ),
- post_worktable_tasks_group)
+ main_wf = chain(
+ create_project_worktable_file.si(
+ phenotype_ids=phenotype_ids,
+ init_file_path=init_table_path,
+ project_hdf_path=worktable_path,
+ remove_nan=remove_nan,
+ stat=stat,
+ optim_na=True,
+ csv_file=csv_file,
+ chunk_size=chunk_size,
+ significance_treshold=significance_treshold,
+ post_filtering=post_filtering,
+ delayed_gen_csv_file=delayed_gen_csv_file,
+ chromosome=chromosome,
+ pos_Start=start,
+ pos_End=end,
+ custom_loadings=custom_loadings,
+ ),
+ post_worktable_tasks_group,
+ )
main_wf.delay()
def create_project(
- phenotype_ids: List[str],
+ phenotype_ids: List[str],
available_phenotypes: List[Phenotype],
chromosome: str = None,
start: str = None,
- end: str = None
- ):
-
+ end: str = None,
+):
+
available_phenotype_ids = [phenotype.id for phenotype in available_phenotypes]
unavailable_requested_ids = set(phenotype_ids).difference(
set(available_phenotype_ids)
@@ -227,12 +230,11 @@ def create_project(
phenotypes = [
phenotype for phenotype in available_phenotypes if phenotype.id in phenotype_ids
]
- project = Project(phenotypes = phenotypes,
- chromosome = chromosome,
- start = start,
- end = end)
-
- if (project.get_type_of_analysis() == Project.LOCAL_ANALYSIS):
+ project = Project(
+ phenotypes=phenotypes, chromosome=chromosome, start=start, end=end
+ )
+
+ if project.get_type_of_analysis() == Project.LOCAL_ANALYSIS:
# Local Analysis
global_plot_path = None
quadrant_plot_path = None
@@ -244,21 +246,21 @@ def create_project(
quadrant_plot_path = project.get_quadrant_plot_path()
zoom_plot_path = None
delayed_gen_csv_file = True
-
+
# if project does not exist
if project.status == Project.DOES_NOT_EXIST:
os.makedirs(project.get_folder_path())
launch_create_project(
- phenotype_ids = phenotype_ids,
- init_table_path = os.path.join(config["DATA_DIR"], "initTable.hdf5"),
- worktable_path = project.get_worktable_path(),
- csv_file = project.get_csv_path(),
- global_plot_path = global_plot_path,
- quadrant_plot_path = quadrant_plot_path,
- zoom_plot_path = zoom_plot_path,
- delayed_gen_csv_file = delayed_gen_csv_file,
- chromosome = chromosome,
- start = start,
- end = end
+ phenotype_ids=phenotype_ids,
+ init_table_path=os.path.join(config["DATA_DIR"], "initTable.hdf5"),
+ worktable_path=project.get_worktable_path(),
+ csv_file=project.get_csv_path(),
+ global_plot_path=global_plot_path,
+ quadrant_plot_path=quadrant_plot_path,
+ zoom_plot_path=zoom_plot_path,
+ delayed_gen_csv_file=delayed_gen_csv_file,
+ chromosome=chromosome,
+ start=start,
+ end=end,
)
- return project
\ No newline at end of file
+ return project
diff --git a/jass/test/__init__.py b/jass/test/__init__.py
index 86f967d82f02120c4f61393f690934c58972ad34..5dae7a40b36352ec4c95c25fbbf67ca6a7c985fd 100644
--- a/jass/test/__init__.py
+++ b/jass/test/__init__.py
@@ -1,12 +1,21 @@
import unittest
-from ..encoder import JSONEncoder
import logging
import os, shutil, tempfile
import unittest
-import connexion
+
import flask_testing
+
+# replace delay() and si() method with mocks
+# to avoid freezing calls in unit tests
+from celery.app.task import Task
+from unittest.mock import MagicMock
+
+Task.delay = MagicMock()
+Task.si = MagicMock()
+
+from jass.server import jass_app
from jass.models.inittable import create_inittable_file
@@ -20,16 +29,17 @@ class JassTestCase(unittest.TestCase):
class JassFlaskTestCase(JassTestCase, flask_testing.TestCase):
def create_app(self):
- logging.getLogger("connexion.operation").setLevel("ERROR")
from jass.config import config
self.test_dir = tempfile.mkdtemp()
config["DATA_DIR"] = self.test_dir
shutil.copy(self.get_file_path_fn("initTable.hdf5"), self.test_dir)
- app = connexion.App(__name__, specification_dir="../swagger/")
- app.app.json_encoder = JSONEncoder
- app.add_api("swagger.yaml")
- return app.app
+
+ self.jass_app = jass_app
+ application = self.jass_app.create_app()
+ application.config["TESTING"] = True
+ self.testing_client = application.test_client()
+ return application
def tearDown(self):
shutil.rmtree(self.test_dir)
diff --git a/jass/test/test_default_controller.py b/jass/test/test_default_controller.py
deleted file mode 100644
index 839f48375abe67b5f4acc4fd5e9623ca0790f032..0000000000000000000000000000000000000000
--- a/jass/test/test_default_controller.py
+++ /dev/null
@@ -1,31 +0,0 @@
-# coding: utf-8
-
-from __future__ import absolute_import
-import os, shutil, tempfile
-
-from six import BytesIO
-from flask import json
-
-from jass.config import config
-from . import JassFlaskTestCase
-
-
-class TestDefaultController(JassFlaskTestCase):
- """ DefaultController integration test stubs """
-
- test_folder = "data_test1"
-
- def test_phenotypes_get(self):
- """
- Test case for phenotypes_get
-
-
- """
- response = self.client.open("/phenotypes", method="GET")
- self.assert200(response, "Response body is : " + response.data.decode("utf-8"))
-
-
-if __name__ == "__main__":
- import unittest
-
- unittest.main()
diff --git a/jass/test/test_init_table.py b/jass/test/test_init_table.py
index 5df8b9abe7b6a08de3031642a0952bd99ec925c5..d0a428f2a435095861a9aad5f20712b7cbe96eb5 100644
--- a/jass/test/test_init_table.py
+++ b/jass/test/test_init_table.py
@@ -40,20 +40,24 @@ class TestInitTable(object):
def tearDown(self):
# Remove the directory after the test
- #shutil.rmtree(self.test_dir)
+ # shutil.rmtree(self.test_dir)
print(self.test_dir)
def test_compare_phenolist(self):
"""
Compare result and expected PhenoList
"""
- assert_frame_equal(self.expected_phenolist, self.result_phenolist, check_like=True)
+ assert_frame_equal(
+ self.expected_phenolist, self.result_phenolist, check_like=True
+ )
def test_compare_sumstattab(self):
"""
Compare result and expected SumStatTab
"""
- assert_frame_equal(self.expected_sum_stat_tab, self.result_sum_stat_tab, check_like=True)
+ assert_frame_equal(
+ self.expected_sum_stat_tab, self.result_sum_stat_tab, check_like=True
+ )
def test_compare_cov(self):
"""
diff --git a/jass/test/test_plots.py b/jass/test/test_plots.py
index 9bdbdf0fb7dd42ff4e24493dd763c2ae0a1ad3f9..7748ccbabb60dfe47cb3a3e260d4af3fda9fd3c3 100644
--- a/jass/test/test_plots.py
+++ b/jass/test/test_plots.py
@@ -32,6 +32,7 @@ class TestPlots(JassTestCase):
"""
create_global_plot(self.worktable_hdf_path, self.global_plot_path)
+
if __name__ == "__main__":
import unittest
diff --git a/jass/test/test_server.py b/jass/test/test_server.py
new file mode 100644
index 0000000000000000000000000000000000000000..8547712218608cbc2abb5ba1ae6236c7197870c5
--- /dev/null
+++ b/jass/test/test_server.py
@@ -0,0 +1,40 @@
+# coding: utf-8
+
+from __future__ import absolute_import
+import os, shutil, tempfile
+
+from six import BytesIO
+from flask import json, url_for
+
+from jass.config import config
+from . import JassFlaskTestCase
+
+
+class TestDefaultController(JassFlaskTestCase):
+ """DefaultController integration test stubs"""
+
+ test_folder = "data_test1"
+
+ def test_phenotypes_get(self):
+ """
+ Test case retrieving available phenotypes
+ """
+ response = self.testing_client.open("/api/phenotypes", method="GET")
+ self.assert200(response, "Response body is : " + response.data.decode("utf-8"))
+
+ def test_create_project(self):
+ """
+ Test case for creating a project
+ """
+ response = self.testing_client.open(
+ "/api/projects",
+ method="POST",
+ data={"phenotypeID": "z_IHEC_MONOP,z_RA_RA"},
+ )
+ self.assert200(response, "Response body is : " + response.data.decode("utf-8"))
+
+
+if __name__ == "__main__":
+ import unittest
+
+ unittest.main()
diff --git a/jass/test/test_worktable.py b/jass/test/test_worktable.py
index bed2941a036ee945616cf08f1e4b5074dcde4758..5e9b3ce23e2e7802c6fa73754a52ed13b72ba676 100644
--- a/jass/test/test_worktable.py
+++ b/jass/test/test_worktable.py
@@ -47,19 +47,25 @@ class TestWorkTable(object):
"""
Compare result and expected SumStatJostTab
"""
- assert_frame_equal(self.expected_sumstatjosttab, self.result_sumstatjosttab, check_like=True)
+ assert_frame_equal(
+ self.expected_sumstatjosttab, self.result_sumstatjosttab, check_like=True
+ )
def test_compare_regionsubtable(self):
"""
Compare result and expected RegionSubTable
"""
- assert_frame_equal(self.expected_regionsubtable, self.result_regionsubtable, check_like=True)
+ assert_frame_equal(
+ self.expected_regionsubtable, self.result_regionsubtable, check_like=True
+ )
def test_compare_summarytable(self):
"""
Compare result and expected SummaryTable
"""
- assert_frame_equal(self.expected_summarytable, self.result_summarytable, check_like=True)
+ assert_frame_equal(
+ self.expected_summarytable, self.result_summarytable, check_like=True
+ )
def test_compare_subcov(self):
"""
@@ -71,8 +77,9 @@ class TestWorkTable(object):
"""
Compare result and expected PhenoList
"""
- assert_frame_equal(self.expected_phenolist, self.result_phenolist, check_like=True)
-
+ assert_frame_equal(
+ self.expected_phenolist, self.result_phenolist, check_like=True
+ )
phenotypes_disney = ["z_DISNEY_POCAHONT", "z_DISNEY_RATATOUY"]
diff --git a/jass/util.py b/jass/util.py
index 4e0189d061b34135f812df61a1365fa1bb6d666c..6c0445b46bc57465be84d8a9a1c2ed98c85a51d3 100644
--- a/jass/util.py
+++ b/jass/util.py
@@ -68,6 +68,7 @@ def deserialize_date(string):
"""
try:
from dateutil.parser import parse
+
return parse(string).date()
except ImportError:
return string
@@ -85,6 +86,7 @@ def deserialize_datetime(string):
"""
try:
from dateutil.parser import parse
+
return parse(string)
except ImportError:
return string
@@ -104,9 +106,11 @@ def deserialize_model(data, klass):
return data
for attr, attr_type in six.iteritems(instance.swagger_types):
- if data is not None \
- and instance.attribute_map[attr] in data \
- and isinstance(data, (list, dict)):
+ if (
+ data is not None
+ and instance.attribute_map[attr] in data
+ and isinstance(data, (list, dict))
+ ):
value = data[instance.attribute_map[attr]]
setattr(instance, attr, _deserialize(value, attr_type))
@@ -123,8 +127,7 @@ def _deserialize_list(data, boxed_type):
:return: deserialized list.
:rtype: list
"""
- return [_deserialize(sub_data, boxed_type)
- for sub_data in data]
+ return [_deserialize(sub_data, boxed_type) for sub_data in data]
def _deserialize_dict(data, boxed_type):
@@ -137,5 +140,4 @@ def _deserialize_dict(data, boxed_type):
:return: deserialized dict.
:rtype: dict
"""
- return {k: _deserialize(v, boxed_type)
- for k, v in six.iteritems(data)}
\ No newline at end of file
+ return {k: _deserialize(v, boxed_type) for k, v in six.iteritems(data)}
diff --git a/requirements.txt b/requirements.txt
index 25400d93c0388519cea98149d04e2cacbade82a3..f6fc215883a802969f2cf7bcf01d9f501d150a46 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-git+https://github.com/hmenager/connexion.git@master#egg=connexion[swagger-ui]
+flask-smorest
aiohttp
python_dateutil
setuptools
diff --git a/setup.py b/setup.py
index 19675e52aa5d51210c488a360066df4de0043581..67e274e329c3082dabf0228d1e82f7e5dd93eea1 100644
--- a/setup.py
+++ b/setup.py
@@ -11,7 +11,7 @@ README = os.path.join(SETUP_DIR, 'README.md')
readme = open(README).read()
REQUIRES = [
- "connexion[swagger-ui] @ git+https://github.com/hmenager/connexion.git@master#egg=connexion[swagger-ui]",
+ "flask-smorest",
"aiohttp",
"python_dateutil",
"setuptools",