eva-sub-cli 0.4.10__tar.gz → 0.4.12__tar.gz

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/.github/workflows/trigger-eva-sub-cli-integration-tests.yml

@@ -2,7 +2,7 @@ name: Trigger Eva Sub Cli Integration Tests
 
 on:
   push:
-    branches: [main, test-trigger-integration-tests]
+    branches: [main]
 
 jobs:
   trigger-integration-tests:
@@ -11,6 +11,6 @@ jobs:
       - name: Trigger eva sub cli integration tests
         uses: peter-evans/repository-dispatch@v2
         with:
-          token: ${{ secrets.TRIGGER_INTEGRATION_TESTS }}
+          token: ${{ secrets.WORKFLOW_ACCESS_TOKEN }}
           repository: EBIvariation/eva-integration-tests
           event-type: trigger-eva-sub-cli-tests

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eva_sub_cli
-Version: 0.4.10
+Version: 0.4.12
 Summary: EBI EVA - validation and submission command line tool
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
@@ -19,11 +19,12 @@ Classifier: License :: OSI Approved :: Apache Software License
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: ebi_eva_common_pyutils==0.*,>=0.7.3
+Requires-Dist: ebi_eva_common_pyutils==0.*,>=0.7.4
 Requires-Dist: jinja2==3.*,>=3.0.0
 Requires-Dist: jsonschema==4.*
 Requires-Dist: openpyxl==3.*
 Requires-Dist: pyyaml==6.*
+Requires-Dist: pysam==0.*,>=0.23.3
 Requires-Dist: requests==2.*
 Requires-Dist: packaging==24.*
 Requires-Dist: setuptools-scm

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.10
 
-ENV vcf_validator_version=0.10.0
+ENV vcf_validator_version=0.10.2
 ENV NXF_VER=22.10.6
 
 WORKDIR /opt

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/eva_sub_cli/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.4.10'
-__version_tuple__ = version_tuple = (0, 4, 10)
+__version__ = version = '0.4.12'
+__version_tuple__ = version_tuple = (0, 4, 12)

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/eva_sub_cli/etc/eva_schema.json

@@ -168,6 +168,14 @@
             "type": "string",
             "description": "Reference against which the analysis was performed. ENA or NCBI accession (starting with GCA) accepted."
           },
+          "evidenceType": {
+            "type": "string",
+            "description": "The type of evidence (allele frequencies or genotypes) provided in the VCF files of the analysis",
+            "enum": [
+              "genotype",
+              "allele_frequency"
+            ]
+          },
           "referenceFasta": {
             "type": "string",
             "description": "The path to the reference in fasta format that was used to create the VCF. (This is a local path)"
@@ -322,7 +330,7 @@
                 "$ref": "eva-biosamples.json"
               },
               {
-                "$ref": "https://www.ebi.ac.uk/biosamples/schema/store/registry/schemas/ERC000011"
+                "$ref": "https://www.ebi.ac.uk/biosamples/schema-store/registry/schemas/ERC000011"
               },
               {
                 "$ref": "https://www.ebi.ac.uk/biosamples/schemas/certification/plant-miappe.json"
@@ -366,7 +374,7 @@
     "projectAccession": {
       "type": "string",
       "description": "ENA project accession",
-      "pattern": "^PRJ(EB|NA)\\d+$"
+      "pattern": "^PRJ(E|D|N)[A-Z][0-9]+$"
     }
   }
 }

eva_sub_cli-0.4.12/eva_sub_cli/executables/evidence_type_checker.py

@@ -0,0 +1,61 @@
+import argparse
+
+import yaml
+from ebi_eva_common_pyutils.logger import logging_config
+
+from eva_sub_cli.file_utils import detect_vcf_evidence_type, associate_vcf_path_with_analysis
+from eva_sub_cli.metadata import EvaMetadataJson
+
+logger = logging_config.get_logger(__name__)
+
+
+def check_evidence_type(metadata_json, vcf_files, output_yaml):
+    metadata = EvaMetadataJson(metadata_json)
+    file_path_per_analysis = associate_vcf_path_with_analysis(metadata, vcf_files)
+
+    results_per_analysis_alias = {}
+
+    all_analysis_alias = set(metadata.files_per_analysis) | set(file_path_per_analysis)
+    for analysis_alias in all_analysis_alias:
+        results_per_analysis_alias[analysis_alias] = {
+            'evidence_type': None,
+            'errors': None
+        }
+        vcf_files = list(file_path_per_analysis.get(analysis_alias, []))
+
+        if not vcf_files:
+            results_per_analysis_alias[analysis_alias]['errors'] = f'No VCF file found for the analysis'
+            continue
+
+        evidence_types_for_vcf_files = [detect_vcf_evidence_type(vcf_file) for vcf_file in vcf_files]
+
+        if len(set(evidence_types_for_vcf_files)) == 1 and None not in evidence_types_for_vcf_files:
+            results_per_analysis_alias[analysis_alias]['evidence_type'] = set(evidence_types_for_vcf_files).pop()
+        elif None in evidence_types_for_vcf_files:
+            indices = [i for i, x in enumerate(evidence_types_for_vcf_files) if x is None]
+            results_per_analysis_alias[analysis_alias][
+                'errors'] = f'VCF file evidence type could not be determined: {", ".join([vcf_files[i] for i in indices])}'
+        else:
+            results_per_analysis_alias[analysis_alias][
+                'errors'] = f'Multiple evidence types found: {", ".join(set(evidence_types_for_vcf_files))}'
+
+    write_result_yaml(output_yaml, results_per_analysis_alias)
+
+
+def write_result_yaml(output_yaml, results_per_analysis_alias):
+    with open(output_yaml, 'w') as open_yaml:
+        yaml.safe_dump(data=results_per_analysis_alias, stream=open_yaml, default_flow_style=False)
+
+
+def main():
+    arg_parser = argparse.ArgumentParser(description='Check the evidence type in the VCF files for all analysis')
+    arg_parser.add_argument('--metadata_json', required=True, dest='metadata_json',
+                            help='EVA metadata json file')
+    arg_parser.add_argument('--vcf_files', dest='vcf_files', nargs='+',
+                            help='Path to the vcf files to compare to the metadata')
+    arg_parser.add_argument('--output_yaml', required=True, dest='output_yaml',
+                            help='Path to the location of the results')
+
+    args = arg_parser.parse_args()
+    logging_config.add_stdout_handler()
+    check_evidence_type(args.metadata_json, args.vcf_files, args.output_yaml)

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/eva_sub_cli/executables/samples_checker.py

@@ -5,7 +5,7 @@ from ebi_eva_common_pyutils.logger import logging_config
 
 import yaml
 
-from eva_sub_cli.file_utils import open_gzip_if_required
+from eva_sub_cli.file_utils import open_gzip_if_required, detect_vcf_evidence_type, associate_vcf_path_with_analysis
 from eva_sub_cli.metadata import EvaMetadataJson
 
 logger = logging_config.get_logger(__name__)
@@ -64,44 +64,39 @@ def compare_all_analysis(metadata, files_per_analysis):
             file_path: get_samples_from_vcf(file_path)
             for file_path in files_per_analysis.get(analysis_alias, [])
         }
-        (
-            has_difference, more_per_submitted_files_metadata,
-            more_submitted_files_metadata, more_metadata_submitted_files
-        ) = compare_names_in_files_and_samples(sample_name_in_analysis, sample_name_per_file)
-        overall_differences = overall_differences or has_difference
-        results_per_analysis_alias[analysis_alias] = {
-            'difference': has_difference,
-            'more_per_submitted_files_metadata': more_per_submitted_files_metadata,
-            'more_submitted_files_metadata': more_submitted_files_metadata,
-            'more_metadata_submitted_files': more_metadata_submitted_files
-        }
+
+        if need_to_check_samples(sample_name_per_file):
+            (
+                has_difference, more_per_submitted_files_metadata,
+                more_submitted_files_metadata, more_metadata_submitted_files
+            ) = compare_names_in_files_and_samples(sample_name_in_analysis, sample_name_per_file)
+            overall_differences = overall_differences or has_difference
+            results_per_analysis_alias[analysis_alias] = {
+                'difference': has_difference,
+                'more_per_submitted_files_metadata': more_per_submitted_files_metadata,
+                'more_submitted_files_metadata': more_submitted_files_metadata,
+                'more_metadata_submitted_files': more_metadata_submitted_files
+            }
+        else:
+            results_per_analysis_alias[analysis_alias] = {
+                'difference': False,
+                'more_per_submitted_files_metadata': [],
+                'more_submitted_files_metadata': [],
+                'more_metadata_submitted_files': []
+            }
+
+
     return overall_differences, results_per_analysis_alias
 
 
-def associate_vcf_path_with_analysis(metadata, vcf_files):
-    """
-    Match the files names associated with analysis provided in the metadata with the file path given on the command
-    line.
-    :param vcf_files the list of full path to the vcf files
-    :param files_per_analysis: dictionary of the analysis and their associated VCF file names
-    :returns dictionary of analysis and their associated vcf file path
-    """
-    result_files_per_analysis = dict()
-    for analysis in metadata.files_per_analysis:
-        result_files_per_analysis[analysis] = []
-    for vcf_file in vcf_files:
-        analysis_aliases = metadata.get_analysis_for_vcf_file(vcf_file)
-        if len(analysis_aliases) == 1:
-            result_files_per_analysis[analysis_aliases[0]].append(vcf_file)
-        elif len(analysis_aliases) == 0:
-            logger.error(f'No analysis found for vcf {vcf_file}')
-            if 'No analysis' not in result_files_per_analysis:
-                result_files_per_analysis['No analysis'] = []
-            result_files_per_analysis['No analysis'].append(vcf_file)
-        else:
-            logger.error(f'More than one analysis were match to vcf {vcf_file}')
+def need_to_check_samples(sample_name_per_file):
+    no_samples_in_vcf = all(len(v) == 0 for v in sample_name_per_file.values())
+    if no_samples_in_vcf:
+        evidence_types_for_vcf_files = [detect_vcf_evidence_type(vcf_file) for vcf_file in sample_name_per_file.keys()]
+        if set(evidence_types_for_vcf_files) == {'allele_frequency'}:
+            return False
 
-    return result_files_per_analysis
+    return True
 
 
 def write_result_yaml(output_yaml, overall_differences, results_per_analysis_alias):

eva_sub_cli-0.4.12/eva_sub_cli/file_utils.py

@@ -0,0 +1,224 @@
+import glob
+import gzip
+import os
+import shutil
+import time
+from itertools import groupby
+
+import pysam
+from ebi_eva_common_pyutils.logger import logging_config
+
+logger = logging_config.get_logger(__name__)
+
+
+def resolve_single_file_path(file_path):
+    files = glob.glob(file_path)
+    if len(files) == 0:
+        return None
+    elif len(files) > 0:
+        return files[0]
+
+
+def is_submission_dir_writable(submission_dir):
+    if not os.path.exists(submission_dir):
+        os.makedirs(submission_dir)
+    if not os.path.isdir(submission_dir):
+        return False
+    if not os.access(submission_dir, os.W_OK):
+        return False
+    return True
+
+
+def is_vcf_file(file_path):
+    if file_path:
+        file_path = file_path.strip().lower()
+        return file_path.endswith('.vcf') or file_path.endswith('.vcf.gz')
+    return False
+
+def associate_vcf_path_with_analysis(metadata, vcf_files):
+    """
+    Match the files names associated with analysis provided in the metadata with the given file path
+
+    :param vcf_files the list of full path to the vcf files
+    :param files_per_analysis: dictionary of the analysis and their associated VCF file names
+    :returns dictionary of analysis and their associated vcf file path
+    """
+    result_files_per_analysis = dict()
+    for analysis in metadata.files_per_analysis:
+        result_files_per_analysis[analysis] = []
+    for vcf_file in vcf_files:
+        analysis_aliases = metadata.get_analysis_for_vcf_file(vcf_file)
+        if len(analysis_aliases) == 1:
+            result_files_per_analysis[analysis_aliases[0]].append(vcf_file)
+        elif len(analysis_aliases) == 0:
+            logger.error(f'No analysis found for vcf {vcf_file}')
+            if 'No analysis' not in result_files_per_analysis:
+                result_files_per_analysis['No analysis'] = []
+            result_files_per_analysis['No analysis'].append(vcf_file)
+        else:
+            logger.error(f'More than one analysis were match to vcf {vcf_file}')
+
+    return result_files_per_analysis
+
+def detect_vcf_evidence_type(vcf_file):
+    """
+    Detect the type of evidence (genotype aggregation) provided in the VCF file by checking the first 10 data lines
+    The evidence type is determined to be "genotype" (meaning genotype are all present) if a GT field can be found in
+    all the samples. It is determined to be "allele_frequency" if it is not "genotype" and an AF field or AN and AC fields are found
+    in every line checked.
+    Otherwise, it returns None meaning that the evidence type could not be determined.
+    """
+
+    try:
+        samples, af_in_info, gt_in_format = _assess_vcf_evidence_type_with_pysam(vcf_file)
+    except Exception:
+        logger.error(f"Pysam Failed to open and read {vcf_file}")
+        try:
+            samples, af_in_info, gt_in_format = _assess_vcf_evidence_type_manual(vcf_file)
+        except Exception:
+            logger.error(f"Manual parsing Failed to open or read {vcf_file}")
+            return None
+    if len(samples) > 0 and gt_in_format:
+        return 'genotype'
+    elif len(samples) == 0 and af_in_info:
+        return 'allele_frequency'
+    else:
+        logger.error(f'Aggregation type could not be detected for {vcf_file}')
+        return None
+
+
+def _assess_vcf_evidence_type_with_pysam(vcf_file):
+    with pysam.VariantFile(vcf_file, 'r') as vcf_in:
+        samples = list(vcf_in.header.samples)
+        # check that the first 10 lines have genotypes for all the samples present and if they have allele frequency
+        nb_line_checked = 0
+        max_line_check = 10
+        gt_in_format = True
+        af_in_info = True
+        for vcf_rec in vcf_in:
+            gt_in_format = gt_in_format and all('GT' in vcf_rec.samples.get(sample, {}) for sample in samples)
+            af_in_info = af_in_info and ('AF' in vcf_rec.info or ('AC' in vcf_rec.info and 'AN' in vcf_rec.info))
+            nb_line_checked += 1
+            if nb_line_checked >= max_line_check:
+                break
+        return samples, af_in_info, gt_in_format
+
+
+def _assess_vcf_evidence_type_manual(vcf_file):
+    try:
+        if vcf_file.endswith('.gz'):
+            open_file = gzip.open(vcf_file, 'rt')
+        else:
+            open_file = open(vcf_file, 'r')
+
+        nb_line_checked = 0
+        max_line_check = 10
+        gt_in_format = True
+        af_in_info = True
+        samples = []
+        for line in open_file:
+            sp_line = line.strip().split('\t')
+            if line.startswith('#CHROM'):
+                if len(sp_line) > 9:
+                    samples = sp_line[9:]
+            if not line.startswith('#'):
+                gt_in_format = gt_in_format and len(sp_line) > 8 and 'GT' in sp_line[8]
+                af_in_info = af_in_info and (
+                        sp_line[7].find('AF=') or (sp_line[7].find('AC=') and sp_line[7].find('AN=')))
+            if nb_line_checked >= max_line_check:
+                break
+        return samples, af_in_info, gt_in_format
+    finally:
+        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'):
+        return gzip.open(input_file, mode + 't')
+    else:
+        return open(input_file, mode)
+
+
+def fasta_iter(input_fasta):
+    """
+    Given a fasta file. yield tuples of header, sequence
+    """
+    # first open the file outside
+    with open_gzip_if_required(input_fasta) as open_file:
+        # ditch the boolean (x[0]) and just keep the header or sequence since
+        # we know they alternate.
+        faiter = (x[1] for x in groupby(open_file, lambda line: line[0] == ">"))
+
+        for header in faiter:
+            # drop the ">"
+            headerStr = header.__next__()[1:].strip()
+
+            # join all sequence lines to one.
+            seq = "".join(s.strip() for s in faiter.__next__())
+            yield (headerStr, seq)
+
+
+class DirLockError(Exception):
+    pass
+
+
+class DirLock(object):
+    _SPIN_PERIOD_SECONDS = 0.05
+
+    def __init__(self, dirname, timeout=3):
+        """Prepare a file lock to protect access to dirname. timeout is the
+        period (in seconds) after an acquisition attempt is aborted.
+        The directory must exist, otherwise aquire() will timeout.
+        """
+        self._lockfilename = os.path.join(dirname, ".lock")
+        self._timeout = timeout
+
+    def acquire(self):
+        start_time = time.time()
+        while True:
+            try:
+                # O_EXCL: fail if file exists or create it (atomically)
+                os.close(os.open(self._lockfilename,
+                                 os.O_CREAT | os.O_EXCL | os.O_RDWR))
+                break
+            except OSError:
+                if (time.time() - start_time) > self._timeout:
+                    raise DirLockError(f"could not create {self._lockfilename} after {self._timeout} seconds")
+                else:
+                    time.sleep(self._SPIN_PERIOD_SECONDS)
+
+    def release(self):
+        try:
+            os.remove(self._lockfilename)
+        except OSError:
+            pass
+
+    def __enter__(self):
+        self.acquire()
+        return self
+
+    def __exit__(self, type_, value, traceback):
+        self.release()

eva_sub_cli-0.4.12/eva_sub_cli/jinja_templates/html/project_details.html

@@ -0,0 +1,65 @@
+{% macro project_details_report(validation_results, project_title, validation_date, submission_dir, consent_statement_required, vcf_fasta_analysis_mapping) -%}
+    <div class="report-section info">
+          {% if project_title %}
+             <p><b>Project Title:</b> {{ project_title }}</p>
+         {% else %}
+             <p><b>Project Title:</b> Not Found</p>
+         {% endif %}
+        <p><b>Validation Date:</b> {{ validation_date }}</p>
+        <p><b>Submission Directory:</b> {{ submission_dir }}</p>
+        {% if consent_statement_required %}
+        <br>
+        <p><b>Note for human genotype data:</b></p> <p>You will need to provide a signed copy of our <a href="https://docs.google.com/document/d/1UaRmimAe919IZYIH55mDXMe-4sHsRVqaP4moqx2IYE4" target="_blank">Consent Statement</a> via email to <a href="mailto:eva-helpdesk@ebi.ac.uk">eva-helpdesk@ebi.ac.uk</a> after submission.
+            Your submission will only be processed after receiving the consent statement. For more info, please see our <a href="https://www.ebi.ac.uk/eva/?Help#submissionPanel&link=consent-statement-for-human-genotype-data" target="_blank">help</a> section.</p>
+        {% endif %}
+    </div>
+
+
+    {% if vcf_fasta_analysis_mapping %}
+        {% set row_class = "report-section info collapsible" %}
+        {% set expand_icon = "&#9654;" %}
+        <div class='{{ row_class }}'><span class="expand_icon">{{ expand_icon }}</span> Files mapping</div>
+            <div class="no-show">
+                <table>
+                    <tr>
+                        <th><strong>VCF File</strong></th>
+                        <th><strong>Fasta File</strong></th>
+                        <th><strong>Analysis</strong></th>
+                    </tr>
+                    {% for mapping in vcf_fasta_analysis_mapping %}
+                    <tr>
+                        <td>{{ mapping.vcf_file }}</td>
+                        <td>{{ mapping.fasta_file }}</td>
+                        <td>{{ mapping.analysis }}</td>
+                    </tr>
+                    {% endfor %}
+                </table>
+            </div>
+        </div>
+    {% endif %}
+
+
+    {% set evidence_type_check_results = validation_results.get('evidence_type_check', {}) %}
+    {% set evidence_check_type_pass = evidence_type_check_results.get('pass', true) %}
+    {% if not evidence_check_type_pass %}
+        <div class="report-section fail collapsible"><span class="expand_icon">&#9654;</span>&#10060; Evidence Type Check Failures </div>
+         <div class="error-list">
+            <table>
+                <tr>
+                    <th>Analysis Alias</th><th>Errors</th>
+                </tr>
+                    {% for alias, alias_result in evidence_type_check_results.items() if alias != 'pass' %}
+                        {% if alias_result.evidence_type is none and alias_result.errors %}
+                             <tr>
+                                <td><strong>{{ alias }} </strong></td>
+                                <td>{{ alias_result.errors }}</td>
+                            </tr>
+                        {% endif %}
+                    {% endfor %}
+            </table>
+        </div>
+    {% endif %}
+
+
+
+{%- endmacro %}

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/eva_sub_cli/jinja_templates/html/report.html

@@ -54,7 +54,7 @@
     <div class="description">
         General details about the project
     </div>
-    {{ project_details_report(project_title, validation_date, submission_dir, vcf_fasta_analysis_mapping) }}
+    {{ project_details_report(validation_results, project_title, validation_date, submission_dir, consent_statement_required, vcf_fasta_analysis_mapping) }}
 </section>
 
 <section>

eva_sub_cli-0.4.12/eva_sub_cli/jinja_templates/text/project_details.txt

@@ -0,0 +1,37 @@
+{% macro project_details_report(validation_results, project_title, validation_date, submission_dir, consent_statement_required, vcf_fasta_analysis_mapping) -%}
+
+{% if project_title %}
+	Project Title: {{ project_title }}
+{% else %}
+	Project Title: Not Found
+{% endif %}
+	Validation Date: {{ validation_date }}
+	Submission Directory: {{ submission_dir }}
+{% if consent_statement_required %}
+    Note for human genotype data:
+        You will need to provide a signed copy of our Consent Statement (https://docs.google.com/document/d/1UaRmimAe919IZYIH55mDXMe-4sHsRVqaP4moqx2IYE4) via email to eva-helpdesk@ebi.ac.uk after submission.
+        Your submission will only be processed after receiving the consent statement.For more info, please see our help section (https://www.ebi.ac.uk/eva/?Help#submissionPanel&link=consent-statement-for-human-genotype-data).
+{% endif %}
+
+{% if vcf_fasta_analysis_mapping %}
+	Files mapping:
+	{% for mapping in vcf_fasta_analysis_mapping %}
+		---
+		VCF File: {{ mapping.vcf_file }}
+		Fasta File: {{ mapping.fasta_file }}
+		Analysis: {{ mapping.analysis }}
+	{% endfor %}
+{% endif %}
+
+{% set evidence_type_check_results = validation_results.get('evidence_type_check', {}) %}
+{% set evidence_check_type_pass = evidence_type_check_results.get('pass', true) %}
+{% if not evidence_check_type_pass %}
+    Evidence Type Check Failures:
+    {% for alias, alias_result in evidence_type_check_results.items() if alias != 'pass' %}
+        {% if alias_result.evidence_type is none and alias_result.errors %}
+            {{ alias }}: {{ alias_result.errors }}
+        {% endif %}
+    {% endfor %}
+{% endif %}
+
+{%- endmacro %}

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/eva_sub_cli/jinja_templates/text/report.txt

@@ -15,7 +15,7 @@ eva-sub-cli v{{cli_version}}
 PROJECT SUMMARY
 General details about the project
 
-{{ project_details_report(project_title, validation_date, submission_dir, vcf_fasta_analysis_mapping) }}
+{{ project_details_report(validation_results, project_title, validation_date, submission_dir, consent_statement_required, vcf_fasta_analysis_mapping) }}
 
 -
 

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/eva_sub_cli/metadata.py

@@ -49,6 +49,10 @@ class EvaMetadataJson(AppLogger):
         if self.resolved_files:
             del self.resolved_files
 
+    def set_analyses(self, analysis_list):
+        assert isinstance(analysis_list, list)
+        self.content['analysis'] = analysis_list
+
     @cached_property
     def samples_per_analysis(self):
         """Returns mapping of analysis alias to sample names, based on metadata."""

{eva_sub_cli-0.4.10 → eva_sub_cli-0.4.12}/eva_sub_cli/nextflow/validation.nf

@@ -28,6 +28,7 @@ params.executable = [
 // python scripts - installed as part of eva-sub-cli
 params.python_scripts = [
     "samples_checker": "samples_checker.py",
+    "evidence_type_checker": "evidence_type_checker.py",
     "fasta_checker": "check_fasta_insdc.py",
     "xlsx2json": "xlsx2json.py",
     "semantic_checker": "check_metadata_semantics.py",
@@ -99,6 +100,7 @@ workflow {
         metadata_json_validation(metadata_json)
         metadata_semantic_check(metadata_json)
         sample_name_concordance(metadata_json, vcf_files.collect())
+        evidence_type_check(metadata_json, vcf_files.collect())
         insdc_checker(metadata_json, fasta_to_vcfs)
     }
 }
@@ -265,6 +267,26 @@ process sample_name_concordance {
 }
 
 
+process evidence_type_check {
+    publishDir output_dir,
+            overwrite: true,
+            mode: "copy"
+
+    input:
+    path(metadata_json)
+    path(vcf_files)
+
+    output:
+    path "evidence_type_checker.yml", emit: evidence_type_checker_yml
+    path "evidence_type_checker.log", emit: evidence_type_checker_log
+
+    script:
+    """
+    $params.python_scripts.evidence_type_checker --metadata_json $metadata_json --vcf_files $vcf_files --output_yaml evidence_type_checker.yml > evidence_type_checker.log 2>&1
+    """
+}
+
+
 process insdc_checker {
     publishDir output_dir,
             overwrite: true,