eva-sub-cli 0.6.1__tar.gz → 0.6.2__tar.gz

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.6.1
+Version: 0.6.2
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.6.1'
-__version_tuple__ = version_tuple = (0, 6, 1)
+__version__ = version = '0.6.2'
+__version_tuple__ = version_tuple = (0, 6, 2)
 
-__commit_id__ = commit_id = 'g13513250e'
+__commit_id__ = commit_id = 'g1dbfe4351'

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli/etc/spreadsheet2json_conf.yaml

@@ -77,6 +77,7 @@ Analysis:
     Phasing: boolean
     Date: date
     Software: list
+    Link(s): list
 
 Sample:
   header_row: 3

eva_sub_cli-0.6.2/eva_sub_cli/executables/format_metadata.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+import argparse
+import json
+import shutil
+
+from ebi_eva_common_pyutils.logger import logging_config
+logger = logging_config.get_logger(__name__)
+
+def format_experiment_type(json_file_input, json_file_output):
+    try:
+        with open(json_file_input, 'r') as input:
+            json_data = json.load(input)
+
+        for analysis_item in json_data.get("analysis", []):
+            original_experiment_type = analysis_item.get("experimentType", "")
+            logger.info(f"Formatting metadata - experiment type to capitalized - {original_experiment_type}")
+            experiment_type_capital = original_experiment_type.capitalize()
+            analysis_item["experimentType"] = experiment_type_capital or ""
+
+        with open(json_file_output, 'w') as output:
+            json.dump(json_data, output, indent=4)
+        return json_file_output
+
+    except (FileNotFoundError, json.JSONDecodeError, KeyError) as e:
+        # if the try block fails, copy the input file (because nextflow is expecting the output file).
+        logger.error(f"Failed to process JSON: {e}")
+        shutil.copy(json_file_input, json_file_output)
+        return None
+
+
+def main():
+    arg_parser = argparse.ArgumentParser(
+        description='Formats experiment type for the metadata.')
+    arg_parser.add_argument('--metadata_json_input', required=True, dest='metadata_json_input',
+                            help='EVA metadata json file INPUT')
+    arg_parser.add_argument('--metadata_json_output', required=True, dest='metadata_json_output',
+                            help='EVA metadata json file OUTPUT')
+    args = arg_parser.parse_args()
+    format_experiment_type(args.metadata_json_input, args.metadata_json_output)
+
+if __name__ == "__main__":
+    main()

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli/file_utils.py

@@ -1,7 +1,6 @@
 import glob
 import gzip
 import os
-import shutil
 import time
 from itertools import groupby
 
@@ -132,28 +131,6 @@ def _assess_vcf_evidence_type_manual(vcf_file):
         open_file.close()
 
 
-def backup_file_or_directory(file_name, max_backups=None):
-    """
-    Rename a file or directory by adding a '.1' at the end. If the '.1' file exists it move it to a '.2' and so on.
-    Keep at most the specified number of backups, if None will keep all.
-    """
-    suffix = 1
-    backup_name = f'{file_name}.{suffix}'
-    while os.path.exists(backup_name):
-        suffix += 1
-        backup_name = f'{file_name}.{suffix}'
-
-    for i in range(suffix, 1, -1):
-        if max_backups and i > max_backups:
-            if os.path.isfile(file_name):
-                os.remove(f'{file_name}.{i - 1}')
-            else:
-                shutil.rmtree(f'{file_name}.{i - 1}')
-        else:
-            os.rename(f'{file_name}.{i - 1}', f'{file_name}.{i}')
-    os.rename(file_name, file_name + '.1')
-
-
 def open_gzip_if_required(input_file, mode='r'):
     """Open a file in read mode using gzip if the file extension says .gz"""
     if input_file.endswith('.gz'):

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli/nextflow/validation.nf

@@ -42,7 +42,8 @@ params.python_scripts = [
     "fasta_checker": "check_fasta_insdc.py",
     "xlsx2json": "xlsx2json.py",
     "semantic_checker": "check_metadata_semantics.py",
-    "trim_down": "trim_down.py"
+    "trim_down": "trim_down.py",
+    "format_metadata": "format_metadata.py"
 ]
 // prefix to prepend to all provided path
 params.base_dir = ""
@@ -98,8 +99,11 @@ workflow {
 		convert_xlsx_2_json(joinBasePath(params.metadata_xlsx))
 		metadata_json = convert_xlsx_2_json.out.metadata_json
 	} else {
-		metadata_json = joinBasePath(params.metadata_json)
+		metadata_json = file(joinBasePath(params.metadata_json), checkIfExists:true)
 	}
+
+    metadata_json_format(metadata_json)
+    metadata_json = metadata_json_format.out.metadata_formatted_json
 	// File size and MD5
 	generate_file_size_and_md5_digests(vcf_files)
 	collect_file_size_and_md5(generate_file_size_and_md5_digests.out.file_size_and_digest_info.collect())
@@ -177,6 +181,7 @@ process check_vcf_valid {
     """
     trap 'if [[ \$? == 1 ]]; then exit 0; fi' EXIT
 
+    rm -rf ${output_dir}/vcf_format
     mkdir -p vcf_format
     $params.executable.vcf_validator -i $vcf -r text -o vcf_format --require-evidence > vcf_format/${vcf}.vcf_format.log 2>&1
     """
@@ -206,6 +211,7 @@ process check_vcf_reference {
     """
     trap 'if [[ \$? == 1 || \$? == 139 ]]; then exit 0; fi' EXIT
 
+    rm -rf ${output_dir}/assembly_check
     mkdir -p assembly_check
     $params.executable.vcf_assembly_checker -i $vcf -f $fasta $report_opt -r summary,text  -o assembly_check --require-genbank > assembly_check/${vcf}.assembly_check.log 2>&1
     """
@@ -274,6 +280,28 @@ process convert_xlsx_2_json {
     """
 }
 
+process metadata_json_format {
+
+    label 'short_time', 'small_mem'
+
+    publishDir output_dir,
+            overwrite: true,
+            mode: "copy"
+
+    input:
+    path(metadata_json)
+
+    output:
+    path "metadata_formatted.log", emit: metadata_formatted
+    path "metadata_formatted_case_insensitive.json", emit: metadata_formatted_json
+
+    script:
+    def output_json = "metadata_formatted_case_insensitive.json"
+    """
+    $params.python_scripts.format_metadata --metadata_json_input $metadata_json --metadata_json_output $output_json > metadata_formatted.log 2>&1
+    """
+}
+
 process metadata_json_validation {
 
     label 'short_time', 'small_mem'

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli/validators/docker_validator.py

@@ -9,7 +9,7 @@ from retry import retry
 from eva_sub_cli.validators.validator import Validator, ALL_VALIDATION_TASKS
 
 default_container_image = 'ebivariation/eva-sub-cli'
-default_container_tag = 'v0.0.12'
+default_container_tag = 'v0.0.13'
 container_validation_dir = '/opt/vcf_validation'
 container_validation_output_dir = 'vcf_validation_output'
 

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli/validators/validator.py

@@ -3,17 +3,18 @@ import csv
 import datetime
 import logging
 import os
+import shutil
 from functools import lru_cache, cached_property
 
 import yaml
 from ebi_eva_common_pyutils.command_utils import run_command_with_output
 from ebi_eva_common_pyutils.config import WritableConfig
-from ebi_eva_common_pyutils.logger import logging_config, AppLogger
+from ebi_eva_common_pyutils.logger import AppLogger
 from packaging import version
 
 import eva_sub_cli
 from eva_sub_cli import ETC_DIR, SUB_CLI_CONFIG_FILE, __version__
-from eva_sub_cli.file_utils import backup_file_or_directory, resolve_single_file_path
+from eva_sub_cli.file_utils import resolve_single_file_path
 from eva_sub_cli.metadata import EvaMetadataJson
 from eva_sub_cli.report import generate_html_report, generate_text_report
 from eva_sub_cli.validators.validation_results_parsers import parse_assembly_check_log, parse_assembly_check_report, \
@@ -43,7 +44,6 @@ RUN_STATUS_KEY = 'run_status'
 PASS = 'pass'
 
 
-
 class Validator(AppLogger):
 
     def __init__(self, mapping_file, submission_dir, project_title=None, metadata_json=None, metadata_xlsx=None,
@@ -54,6 +54,7 @@ class Validator(AppLogger):
         self.tasks = validation_tasks
         self.submission_dir = submission_dir
         self.output_dir = os.path.join(submission_dir, VALIDATION_OUTPUT_DIR)
+        self.nextflow_work_dir = os.path.join(self.submission_dir, 'work') # Default location when we chdir in self.submission_dir
         self.validation_result_file = os.path.join(submission_dir, VALIDATION_RESULTS_FILE)
         self.mapping_file = mapping_file
         vcf_files, fasta_files = self._find_vcf_and_fasta_files()
@@ -130,20 +131,22 @@ class Validator(AppLogger):
         raise NotImplementedError
 
     def set_up_output_dir(self):
-        if os.path.exists(self.output_dir):
-            backup_file_or_directory(self.output_dir, max_backups=9)
-        os.makedirs(self.output_dir, exist_ok=True)
+        if not os.path.exists(self.output_dir):
+            os.makedirs(self.output_dir, exist_ok=True)
 
     def clean_up_output_dir(self):
         # Move intermediate validation outputs into a subdir except metadata.json
         subdir = os.path.join(self.output_dir, 'other_validations')
-        os.mkdir(subdir)
+        os.makedirs(subdir, exist_ok=True)
         for file_name in os.listdir(self.output_dir):
-            if file_name == 'metadata.json':
+            if file_name in ['metadata.json', 'report.txt', 'report.html']:
                 continue
             file_path = os.path.join(self.output_dir, file_name)
             if os.path.isfile(file_path):
                 os.rename(file_path, os.path.join(subdir, file_name))
+        # Remove the nextflow work directory if it exists
+        if os.path.exists(self.nextflow_work_dir):
+            shutil.rmtree(self.nextflow_work_dir)
 
     @staticmethod
     def _validation_file_path_for(file_path):
@@ -210,7 +213,6 @@ class Validator(AppLogger):
                 del self.results[SHALLOW_VALIDATION]['required']
             del self.results[SHALLOW_VALIDATION]['requested']
 
-
     def _collect_validation_workflow_results(self):
         # Collect information from the output and summarise in the config
         if self.shallow_validation:
@@ -550,7 +552,7 @@ class Validator(AppLogger):
                     file_path_2_file_size[vcf_file] = file_size
                     file_name_2_file_size[os.path.basename(vcf_file)] = file_size
         else:
-            error_txt =  f"Cannot locate file_info.txt at {os.path.join(self.output_dir, 'other_validations', 'file_info.txt')}"
+            error_txt = f"Cannot locate file_info.txt at {os.path.join(self.output_dir, 'other_validations', 'file_info.txt')}"
             self.error(error_txt)
             raise FileNotFoundError(error_txt)
 

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.6.1
+Version: 0.6.2
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli.egg-info/SOURCES.txt

@@ -59,6 +59,7 @@ eva_sub_cli/executables/check_fasta_insdc.py
 eva_sub_cli/executables/check_metadata_semantics.py
 eva_sub_cli/executables/cli.py
 eva_sub_cli/executables/evidence_type_checker.py
+eva_sub_cli/executables/format_metadata.py
 eva_sub_cli/executables/samples_checker.py
 eva_sub_cli/executables/trim_down.py
 eva_sub_cli/executables/xlsx2json.py
@@ -91,6 +92,7 @@ tests/test_cli.py
 tests/test_docker_validator.py
 tests/test_evidence_type_checker.py
 tests/test_file_utils.py
+tests/test_format_metadata.py
 tests/test_metadata.py
 tests/test_native_validator_sample_in_vcf.py
 tests/test_orchestrator.py
@@ -110,6 +112,7 @@ tests/resources/EVA_Submission_test_V2.xlsx
 tests/resources/EVA_Submission_test_fails.xlsx
 tests/resources/EVA_Submission_test_version_missing.xlsx
 tests/resources/EVA_Submission_test_with_asm_report.json
+tests/resources/EVA_Submission_test_with_links.xlsx
 tests/resources/EVA_Submission_test_with_non_vcf_files.json
 tests/resources/EVA_Submission_test_with_non_vcf_files.xlsx
 tests/resources/EVA_Submission_test_with_project_accession.json

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/eva_sub_cli.egg-info/entry_points.txt

@@ -3,6 +3,7 @@ check_fasta_insdc.py = eva_sub_cli.executables.check_fasta_insdc:main
 check_metadata_semantics.py = eva_sub_cli.executables.check_metadata_semantics:main
 eva-sub-cli.py = eva_sub_cli.executables.cli:main
 evidence_type_checker.py = eva_sub_cli.executables.evidence_type_checker:main
+format_metadata.py = eva_sub_cli.executables.format_metadata:main
 samples_checker.py = eva_sub_cli.executables.samples_checker:main
 trim_down.py = eva_sub_cli.executables.trim_down:main
 xlsx2json.py = eva_sub_cli.executables.xlsx2json:main

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/pyproject.toml

@@ -37,6 +37,7 @@ classifiers = [
 'evidence_type_checker.py'='eva_sub_cli.executables.evidence_type_checker:main'
 'xlsx2json.py'='eva_sub_cli.executables.xlsx2json:main'
 'trim_down.py'='eva_sub_cli.executables.trim_down:main'
+'format_metadata.py'='eva_sub_cli.executables.format_metadata:main'
 
 [tool.setuptools]
 packages = ['eva_sub_cli', 'eva_sub_cli.exceptions', 'eva_sub_cli.executables', 'eva_sub_cli.validators']

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/tests/test_file_utils.py

@@ -1,11 +1,10 @@
 import glob
 import os
 import shutil
-import time
 from pathlib import Path
 from unittest import TestCase
 
-from eva_sub_cli.file_utils import backup_file_or_directory, DirLock, DirLockError
+from eva_sub_cli.file_utils import DirLock, DirLockError
 
 
 def set_up_test_dir():
@@ -18,36 +17,6 @@ def clean_up():
         shutil.rmtree(file_name)
 
 
-def test_backup_file_or_directory():
-    set_up_test_dir()
-    backup_file_or_directory('backup_test')
-    assert not os.path.exists('backup_test')
-    assert os.path.exists('backup_test.1/nested/dir')
-    assert os.path.exists('backup_test.1/file.txt')
-    clean_up()
-
-
-def test_backup_file_or_directory_max_backups():
-    max_backups = 2
-
-    # Backup directory
-    for i in range(max_backups + 2):
-        set_up_test_dir()
-        backup_file_or_directory('backup_test', max_backups=max_backups)
-    for i in range(1, max_backups + 1):
-        assert os.path.exists(f'backup_test.{i}')
-    assert not os.path.exists(f'backup_test.{max_backups + 1}')
-
-    # Backup file
-    for i in range(max_backups + 2):
-        set_up_test_dir()
-        backup_file_or_directory('backup_test/file.txt', max_backups=max_backups)
-    for i in range(1, max_backups + 1):
-        assert os.path.exists(f'backup_test/file.txt.{i}')
-    assert not os.path.exists(f'backup_test/file.txt.{max_backups + 1}')
-    clean_up()
-
-
 class TestDirLock(TestCase):
     resources_folder = os.path.join(os.path.dirname(__file__), 'resources')
 

eva_sub_cli-0.6.2/tests/test_format_metadata.py

@@ -0,0 +1,64 @@
+import os.path
+from unittest import TestCase
+from eva_sub_cli.executables import format_metadata
+import tempfile
+import json
+
+class TestValidateMetadata(TestCase):
+
+    def test_format_experiment_type(self):
+        expected_experiment_type = "Genotyping by array"
+        unexpected_experiment_type = "GeNoTyPiNg By ArRaY"
+        # testing a correctly formatted JSON file
+        clean_json =  {
+            "submitterDetails": [{"lastName": "", "firstName": "", "email": "", "laboratory": "", "centre": ""}],
+            "project": {"title": "", "description": "", "taxId": 9606, "centre": ""},
+            "analysis": [{"analysisTitle": "", "analysisAlias": "", "description": "",
+                    # CHANGING THE LINE BELOW
+                    "experimentType": expected_experiment_type,
+                    "referenceGenome": ""}],
+            "sample": [{"analysisAlias": [""], "sampleInVCF": "", "bioSampleObject": {"sample_title": "", "scientific_name": "", "tax_id": 9606, "collection date": "not provided", "geographic location (country and/or sea)": "not provided"}}],
+            "files": [{"analysisAlias": "", "fileName": "", "fileSize": 1000, "md5": ""}]
+        }
+        with tempfile.NamedTemporaryFile(mode='w', delete=False) as tmp_out_clean:
+            temp_path_clean_output = tmp_out_clean.name
+            tmp_out_clean.write('')
+        with tempfile.NamedTemporaryFile(mode='w', delete=False) as tmp:
+            json.dump(clean_json, tmp)
+            temp_path_clean = tmp.name
+        format_metadata.format_experiment_type(temp_path_clean, temp_path_clean_output)
+        with open(temp_path_clean_output, 'r') as f:
+            result_data = json.load(f)
+        expected = clean_json
+        self.assertEqual(result_data, expected)
+        self.assertEqual(result_data["analysis"][0]["experimentType"], expected_experiment_type)
+        if os.path.exists(temp_path_clean_output):
+            os.remove(temp_path_clean_output)
+        if os.path.exists(temp_path_clean):
+            os.remove(temp_path_clean)
+        # testing an incorrectly formatted JSON file
+        unclean_json = {
+            "submitterDetails": [{"lastName": "", "firstName": "", "email": "", "laboratory": "", "centre": ""}],
+            "project": {"title": "", "description": "", "taxId": 9606, "centre": "",},
+            "analysis": [{"analysisTitle": "", "analysisAlias": "", "description": "",
+                    # CHANGING THE LINE BELOW
+                    "experimentType": unexpected_experiment_type,
+                    "referenceGenome": ""}],
+            "sample": [{"analysisAlias": [""], "sampleInVCF": "", "bioSampleObject": {"sample_title": "", "scientific_name": "", "tax_id": 9606, "collection date": "not provided", "geographic location (country and/or sea)": "not provided"}}],
+            "files": [{"analysisAlias": "", "fileName": "", "fileSize": 1000, "md5": ""}]
+        }
+        with tempfile.NamedTemporaryFile(mode='w', delete=False) as tmp_out_unclean:
+            temp_path_unclean_output = tmp_out_unclean.name
+        with tempfile.NamedTemporaryFile(mode='w', delete=False) as tmp:
+            json.dump(unclean_json, tmp)
+            temp_path_unclean = tmp.name
+        format_metadata.format_experiment_type(temp_path_unclean, temp_path_unclean_output)
+        with open(temp_path_unclean_output, 'r') as f:
+            result_data = json.load(f)
+        expected = clean_json
+        self.assertEqual(result_data, expected)
+        self.assertEqual(result_data["analysis"][0]["experimentType"], expected_experiment_type)
+        if os.path.exists(temp_path_unclean_output):
+            os.remove(temp_path_unclean_output)
+        if os.path.exists(temp_path_unclean):
+            os.remove(temp_path_unclean)

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/tests/test_validator.py

@@ -1,6 +1,7 @@
 import os.path
 import shutil
 from copy import deepcopy
+from tempfile import TemporaryDirectory
 from unittest import TestCase
 
 import yaml
@@ -174,6 +175,38 @@ class TestValidator(TestCase):
         with open(validator.validation_result_file, 'w') as val_res_file:
             yaml.safe_dump(results, val_res_file)
 
+
+    def create_validator(self, submission_dir):
+        mapping_file = os.path.join(submission_dir, 'vcf_files_mapping.csv')
+        create_mapping_file(mapping_file,
+                            [os.path.join(self.vcf_files, 'input_passed.vcf')],
+                            [os.path.join(self.fasta_files, 'input_passed.fa')]
+                            )
+        return Validator(mapping_file, submission_dir, metadata_json=self.metadata_json_file)
+
+    def test_clean_up_output_dir_moves_intermediate_files_and_removes_nextflow_work_dir(self):
+        with TemporaryDirectory() as submission_dir:
+            validator = self.create_validator(submission_dir)
+            os.makedirs(validator.output_dir)
+            os.makedirs(os.path.join(validator.nextflow_work_dir, 'nested'))
+
+            files_to_keep = ['metadata.json', 'report.txt', 'report.html']
+            files_to_move = ['metadata_validation.txt', 'sample_checker.yml']
+            for file_name in files_to_keep + files_to_move:
+                with open(os.path.join(validator.output_dir, file_name), 'w') as output_file:
+                    output_file.write(file_name)
+
+            validator.clean_up_output_dir()
+
+            other_validations_dir = os.path.join(validator.output_dir, 'other_validations')
+            assert not os.path.exists(validator.nextflow_work_dir)
+            for file_name in files_to_keep:
+                assert os.path.exists(os.path.join(validator.output_dir, file_name))
+            for file_name in files_to_move:
+                assert not os.path.exists(os.path.join(validator.output_dir, file_name))
+                assert os.path.exists(os.path.join(other_validations_dir, file_name))
+
+
     def test__collect_validation_workflow_results_with_metadata_json(self):
         self.run_collect_results(self.validator_json)
         assert self.validator_json.results == self.format_data_structure(expected_validation_results)
@@ -290,7 +323,6 @@ class TestValidator(TestCase):
         assert saved_results == self.format_data_structure(expected_results)
 
 
-
     def test__collect_validation_workflow_results_for_shallow_validation_no_effect_when_task_not_in_vcf_check_or_assembly_check(
             self):
         validator_json_shallow = Validator(self.mapping_file, self.output_dir, validation_tasks=[METADATA_CHECK],
@@ -633,4 +665,3 @@ class TestValidator(TestCase):
 
 
 
-

{eva_sub_cli-0.6.1 → eva_sub_cli-0.6.2}/tests/test_xlsx2json.py

@@ -126,6 +126,35 @@ class TestXlsReader(TestCase):
 
         jsonschema.validate(json_data, eva_json_schema)
 
+    def test_conversion_2_json_with_links(self) -> None:
+        xls_filename = os.path.join(self.resource_dir, 'EVA_Submission_test_with_links.xlsx')
+        self.parser = XlsxParser(xls_filename, self.conf_filename)
+        output_json = os.path.join(self.resource_dir, 'EVA_Submission_test_output.json')
+        errors_yaml = os.path.join(self.resource_dir, 'EVA_Submission_test_errors.yml')
+        self.parser.json(output_json)
+        self.parser.save_errors(errors_yaml)
+
+        # confirm no errors
+        with open(errors_yaml) as open_file:
+            errors_data = yaml.safe_load(open_file)
+            assert errors_data == []
+
+        with open(output_json) as open_file:
+            json_data = json.load(open_file)
+            # assert json file is created with expected data
+            assert sorted(json_data.keys()) == ['$schema', 'analysis', 'files', 'project', 'sample', 'submitterDetails']
+            json_data.pop('$schema', None)
+            expected_json = self.get_expected_json()
+            expected_json['analysis'][0]['links'] = ['BioProject:PRJNA1435562']
+            self.assertEqual(expected_json, json_data)
+
+        # assert json schema
+        with open(self.eva_schema) as eva_schema_file:
+            eva_json_schema = json.load(eva_schema_file)
+
+        # assert created json file conform to eva_schema
+        jsonschema.validate(json_data, eva_json_schema)
+
     def test_create_xls_template(self):
         metadata_file = os.path.join(self.resource_dir, 'metadata_not_existing.xlsx')
         create_xls_template_from_yaml(metadata_file, self.conf_filename)