Merge pull request #327 from BU-ISCIII/develop

Release 1.2.0
BU-ISCIII · Oct 11, 2024 · 9acb6cf · 9acb6cf
2 parents 9ec59c7 + 6ef3a10
commit 9acb6cf
Show file tree

Hide file tree

Showing 26 changed files with 1,190 additions and 426 deletions.
diff --git a/.github/workflows/pypi_publish.yml b/.github/workflows/pypi_publish.yml
@@ -47,42 +47,3 @@ jobs:
           path: dist/
       - name: Publish to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
-
-    github-release:
-        name: Sign dist with Sigstore and upload to GitHub Release
-        needs:
-        - publish-to-pypi
-        runs-on: ubuntu-latest
-        permissions:
-          contents: write
-          id-token: write
-        steps:
-        - name: Download all the dists
-          uses: actions/download-artifact@v4
-          with:
-            name: python-package-distributions
-            path: dist/
-        - name: Sign the dists with Sigstore
-          uses: sigstore/[email protected]
-          with:
-            inputs: >-
-              ./dist/*.tar.gz
-              ./dist/*.whl
-        - name: Create GitHub Release
-          env:
-            GITHUB_TOKEN: ${{ github.token }}
-          run: >-
-            gh release create
-            '${{ github.ref_name }}'
-            --repo '${{ github.repository }}'
-            --notes ""
-        - name: Upload artifact signatures to GitHub Release
-          env:
-            GITHUB_TOKEN: ${{ github.token }}
-          # Upload to GitHub Release using the `gh` CLI.
-          # `dist/` contains the built packages, and the
-          # sigstore-produced signatures and certificates.
-          run: >-
-            gh release upload
-            '${{ github.ref_name }}' dist/**
-            --repo '${{ github.repository }}'
diff --git a/.github/workflows/python_lint.yml b/.github/workflows/python_lint.yml
@@ -21,8 +21,19 @@ jobs:
         uses: actions/checkout@master
       - name: Install flake8
         run: pip install flake8
+      - name: Check for Python file changes
+        id: file_check
+        uses: tj-actions/changed-files@v44
+        with:
+          sha: ${{ github.event.pull_request.head.sha }}
+          files: |
+             **.py
       - name: Run flake8
+        if: steps.file_check.outputs.any_changed == 'true'
         run: flake8 --ignore E501,W503,E203,W605
+      - name: No Python files changed
+        if: steps.file_check.outputs.any_changed != 'true'
+        run: echo "No Python files have been changed."
 
   black_lint:
     runs-on: ubuntu-latest
@@ -31,5 +42,15 @@ jobs:
           uses: actions/checkout@v2
         - name: Install black in jupyter
           run: pip install black[jupyter]
+        - name: Check for Python file changes
+          id: file_check
+          uses: tj-actions/changed-files@v44
+          with:
+            sha: ${{ github.event.pull_request.head.sha }}
+            files: '**.py'
         - name: Check code lints with Black
+          if: steps.file_check.outputs.any_changed == 'true'
           uses: psf/black@stable
+        - name: No Python files changed
+          if: steps.file_check.outputs.any_changed != 'true'
+          run: echo "No Python files have been changed."
diff --git a/.github/workflows/test_sftp_handle.yml b/.github/workflows/test_sftp_handle.yml
@@ -1,12 +1,14 @@
 name: test_sftp_handle
 
 on:
-  push:
-    branches: "**"
   pull_request_target:
-    types: [opened, reopened, synchronize, closed]
+    types: [opened, reopened, synchronize]
     branches: "**"
-
+
+concurrency:
+  group: ${{ github.repository }}-test_sftp_handle
+  cancel-in-progress: false
+
 jobs:
   security_check:
     runs-on: ubuntu-latest
@@ -24,21 +26,10 @@ jobs:
         echo "Current permission level is ${{ steps.checkAccess.outputs.user-permission }}"
         echo "Job originally triggered by ${{ github.actor }}"
         exit 1
-
-  sleep_to_ensure_concurrency:
-    needs: security_check
-    runs-on: ubuntu-latest
-    steps:
-    - name: 
-      run: sleep 10s
-      shell: bash
       
   test_sftp_handle:
-    needs: [security_check, sleep_to_ensure_concurrency]
+    needs: security_check
     if: github.repository_owner == 'BU-ISCIII'
-    concurrency:
-      group: ${{ github.repository }}-test_sftp_handle
-      cancel-in-progress: false
     runs-on: ubuntu-latest
     strategy:
       max-parallel: 1

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,29 +4,71 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [1.X.Xdev] - 2024-XX-XX : https://github.com/BU-ISCIII/relecov-tools/releases/tag/1.X.X
+## [1.2.0] - 2024-10-11 : https://github.com/BU-ISCIII/relecov-tools/releases/tag/1.2.0
 
 ### Credits
 
-Code contributions to the hotfix:
+Code contributions to the release:
+
+- [Juan Ledesma](https://github.com/juanledesma78)
+- [Pablo Mata](https://github.com/Shettland)
+- [Sergio Olmos](https://github.com/OPSergio)
 
 ### Modules
 
+- Included wrapper module to launch download, read-lab-metadata and validate processes sequentially [#322](https://github.com/BU-ISCIII/relecov-tools/pull/322)
+- Changed launch-pipeline name for pipeline-manager when tools are used via CLI [#324](https://github.com/BU-ISCIII/relecov-tools/pull/324)
+
 #### Added enhancements
 
+- Now also check for gzip file integrity after download. Moved cleaning process to end of workflow [#313](https://github.com/BU-ISCIII/relecov-tools/pull/313)
+- Introduced a decorator in sftp_client.py to reconnect when conection is lost [#313](https://github.com/BU-ISCIII/relecov-tools/pull/313)
+- Add Hospital Universitari Doctor Josep Trueta to laboratory_address.json [#316] (https://github.com/BU-ISCIII/relecov-tools/pull/316)
+- samples_data json file is no longer mandatory as input in read-lab-metadata [#314](https://github.com/BU-ISCIII/relecov-tools/pull/314)
+- Included handling of alternative column names to support two distinct headers using the same schema in read-lab-metadata [#314](https://github.com/BU-ISCIII/relecov-tools/pull/314)
+- Included a new hospital (Hospital Universitario Araba) to laboratory_address.json [#315](https://github.com/BU-ISCIII/relecov-tools/pull/315) 
+- More accurate cleaning process, skipping only sequencing files instead of whole folder [#321](https://github.com/BU-ISCIII/relecov-tools/pull/321)
+- Now single logs summaries are also created for each folder during download [#321](https://github.com/BU-ISCIII/relecov-tools/pull/321)
+- Introduced handling for missing/dup files and more accurate information in prompt for pipeline_manager [#321](https://github.com/BU-ISCIII/relecov-tools/pull/321)
+- Included excel resize, brackets removal in messages and handled exceptions in log_summary.py [#322](https://github.com/BU-ISCIII/relecov-tools/pull/322)
+- Included processed batchs and samples in read-bioinfo-metadata log summary [#324](https://github.com/BU-ISCIII/relecov-tools/pull/324)
+- When no samples_data.json is given, read-lab-metadata now creates a new one [#324](https://github.com/BU-ISCIII/relecov-tools/pull/324)
+- Handling for missing sample ids in read-lab-metadata [#324](https://github.com/BU-ISCIII/relecov-tools/pull/324)
+- Better logging for download, read-lab-metadata and wrapper [#324](https://github.com/BU-ISCIII/relecov-tools/pull/324)
+
 #### Fixes
 
+- Fixed wrong city name in relecov_tools/conf/laboratory_address.json [#320](https://github.com/BU-ISCIII/relecov-tools/pull/320)
+- Fixed wrong single-paired layout detection in metadata due to Capital letters [#321](https://github.com/BU-ISCIII/relecov-tools/pull/321)
+- Error handling in merge_logs() and create_logs_excel() methods for log_summary.py [#322](https://github.com/BU-ISCIII/relecov-tools/pull/322)
+- Included handling of multiple empty rows in metadata xlsx file [#322](https://github.com/BU-ISCIII/relecov-tools/pull/322)
+
 #### Changed
 
+- Renamed and refactored "bioinfo_lab_heading" for "alt_header_equivalences" in configuration.json [#314](https://github.com/BU-ISCIII/relecov-tools/pull/314)
+- Included a few schema fields that were missing or outdated, related to bioinformatics results [#314](https://github.com/BU-ISCIII/relecov-tools/pull/314)
+- Updated metadata excel template, moved to relecov_tools/assets [#320](https://github.com/BU-ISCIII/relecov-tools/pull/320)
+- Now python lint only triggers when PR includes python files [#320](https://github.com/BU-ISCIII/relecov-tools/pull/320)
+- Moved concurrency to whole workflow instead of each step in test_sftp-handle.yml [#320](https://github.com/BU-ISCIII/relecov-tools/pull/320)
+- Updated test_sftp-handle.yml testing datasets [#320](https://github.com/BU-ISCIII/relecov-tools/pull/320)
+- Now download skips folders containing "invalid_samples" in its name [#321](https://github.com/BU-ISCIII/relecov-tools/pull/321)
+- read-lab-metadata: Some warnings now include label. Also removed trailing spaces [#322](https://github.com/BU-ISCIII/relecov-tools/pull/322)
+- Renamed launch-pipeline for pipeline-manager and updated keys in configuration.json [#324](https://github.com/BU-ISCIII/relecov-tools/pull/324)
+- Pipeline manager now splits data based on enrichment_panel and version. One folder for each group [#324](https://github.com/BU-ISCIII/relecov-tools/pull/324) 
+
 #### Removed
 
+- Removed duplicated tests with pushes after PR was merged in test_sftp-handle [#312](https://github.com/BU-ISCIII/relecov-tools/pull/312)
+- Deleted deprecated auto-release in pypi_publish as it does not work with tag pushes anymore [#312](https://github.com/BU-ISCIII/relecov-tools/pull/312)
+- Removed first sleep time for reconnection decorator in sftp_client.py, sleep time now increases in the second attempt [#321](https://github.com/BU-ISCIII/relecov-tools/pull/321)
+
 ### Requirements
 
 ## [1.1.0] - 2024-09-13 : https://github.com/BU-ISCIII/relecov-tools/releases/tag/1.1.0
 
 ### Credits
 
-Code contributions to the hotfix:
+Code contributions to the release:
 
 - [Pablo Mata](https://github.com/Shettland)
 - [Sara Monzón](https://github.com/saramonzon)

diff --git a/README.md b/README.md
@@ -24,7 +24,8 @@ relecov-tools is a set of helper tools for the assembly of the different element
       - [upload-to-ena](#upload-to-ena)
       - [upload-to-gisaid](#upload-to-gisaid)
       - [update-db](#update-db)
-      - [launch-pipeline](#launch-pipeline)
+      - [pipeline-manager](#pipeline-manager)
+      - [wrapper](#wrapper)
       - [logs-to-excel](#logs-to-excel)
     - [build-schema](#build-schema)
       - [Mandatory Fields](#mandatory-fields)
@@ -63,7 +64,7 @@ $ relecov-tools --help
 \    \  /   |__ / |__  |    |___ |    |   |  \    /
 /    /  \   |  \  |    |    |    |    |   |   \  /
 /    |--|   |   \ |___ |___ |___ |___ |___|    \/
-RELECOV-tools version 1.1.0
+RELECOV-tools version 1.2.0
 Usage: relecov-tools [OPTIONS] COMMAND [ARGS]...
 
 Options:
@@ -73,16 +74,19 @@ Options:
 --help                     Show this message and exit.
 
 Commands:
-    download                Download files located in sftp server.
-    read-lab-metadata       Create the json compliant to the relecov schema from...
-    read-bioinfo-metadata   Create the json compliant to the relecov schema with Bioinfo Metadata.
-    validate                Validate json file against schema.
-    map                     Convert data between phage plus schema to ENA,...
-    upload-to-ena           parsed data to create xml files to upload to ena
-    upload-to-gisaid        parsed data to create files to upload to gisaid
-    update-db               feed database with metadata jsons
-    build-schema            Generates and updates JSON Schema files from...
-    launch-pipeline         Create the symbolic links for the samples which...
+  download               Download files located in sftp server.
+  read-lab-metadata      Create the json compliant to the relecov schema...
+  validate               Validate json file against schema.
+  map                    Convert data between phage plus schema to ENA,...
+  upload-to-ena          parse data to create xml files to upload to ena
+  upload-to-gisaid       parsed data to create files to upload to gisaid
+  update-db              upload the information included in json file to...
+  read-bioinfo-metadata  Create the json compliant from the Bioinfo...
+  metadata-homogeneizer  Parse institution metadata lab to the one used...
+  pipeline-manager       Create the symbolic links for the samples which...
+  wrapper                Execute download, read-lab-metadata and validate...
+  build-schema           Generates and updates JSON Schema files from...
+  logs-to-excel          Creates a merged xlsx report from all the log...
 ```
 #### download
 The command `download` connects to a transfer protocol (currently sftp) and downloads all files in the different available folders in the passed credentials. In addition, it checks if the files in the current folder match the files in the metadata file and also checks if there are md5sum for each file. Else, it creates one before storing in the final repository.
@@ -247,10 +251,10 @@ Usage: relecov-tools upload-to-gisaid [OPTIONS]
     -t, --type                         Select the type of information to upload to database [sample,bioinfodata,variantdata]
     -d, --databaseServer               Name of the database server receiving the data [iskylims,relecov]
 
-#### launch-pipeline
+#### pipeline-manager
 Create the folder structure to execute the given pipeline for the latest sample batches after executing download, read-lab-metadata and validate modules. This module will create symbolic links for each sample and generate the necessary files for pipeline execution using the information from validated_BATCH-NAME_DATE.json.
 ```
-Usage: relecov-tools launch-pipeline [OPTIONS]
+Usage: relecov-tools pipeline-manager [OPTIONS]
 
   Create the symbolic links for the samples which are validated to prepare for
   bioinformatics pipeline execution.
@@ -263,6 +267,19 @@ Options:
   --help                    Show this message and exit.
 ```
 
+#### wrapper
+Execute download, read-lab-metadata and validate sequentially using a config file to fill the arguments for each one. It also creates a global report with all the logs for the three processes in a user-friendly .xlsx format. The config file should include the name of each module that is executed, along with the necessary parameters in YAML format.
+```
+Usage: relecov-tools wrapper [OPTIONS]
+
+  Executes the modules in config file sequentially
+
+Options:
+  -c, --config_file PATH    Path to config file in yaml format  [required]
+  -o, --output_folder PATH  Path to folder where global results are saved [required]
+  --help                    Show this message and exit.
+```
+
 #### logs-to-excel
 Creates an xlsx file with all the entries found for a specified laboratory in a given set of log_summary.json files (from log-summary module). The laboratory name must match the name of one of the keys in the provided logs to work.
 ```

diff --git a/relecov_tools/__main__.py b/relecov_tools/__main__.py
@@ -24,6 +24,7 @@
 import relecov_tools.upload_ena_protocol
 import relecov_tools.pipeline_manager
 import relecov_tools.build_schema
+import relecov_tools.dataprocess_wrapper
 
 log = logging.getLogger()
 
@@ -61,7 +62,7 @@ def run_relecov_tools():
     )
 
     # stderr.print("[green]                                          `._,._,'\n", highlight=False)
-    __version__ = "1.1.0"
+    __version__ = "1.2.0"
     stderr.print(
         "\n" "[grey39]    RELECOV-tools version {}".format(__version__), highlight=False
     )
@@ -476,12 +477,12 @@ def metadata_homogeneizer(institution, directory, output):
     help="select the template config file",
 )
 @click.option("-o", "--output", type=click.Path(), help="select output folder")
-def launch_pipeline(input, template, output, config):
+def pipeline_manager(input, template, output, config):
     """
     Create the symbolic links for the samples which are validated to prepare for
     bioinformatics pipeline execution.
     """
-    new_launch = relecov_tools.pipeline_manager.LaunchPipeline(
+    new_launch = relecov_tools.pipeline_manager.PipelineManager(
         input, template, output, config
     )
     new_launch.pipeline_exc()
@@ -565,22 +566,23 @@ def logs_to_excel(lab_code, output_folder, files):
     logsum = relecov_tools.log_summary.LogSum(output_location=output_folder)
     merged_logs = logsum.merge_logs(key_name=lab_code, logs_list=all_logs)
     final_logs = logsum.prepare_final_logs(logs=merged_logs)
-    logsum.create_logs_excel(logs=final_logs)
+    excel_outpath = os.path.join(output_folder, lab_code + "_logs_report.xlsx")
+    logsum.create_logs_excel(logs=final_logs, excel_outpath=excel_outpath)
 
 
 @relecov_tools_cli.command(help_priority=16)
 @click.option(
     "-c",
     "--config_file",
     type=click.Path(),
-    help="Path to config file in yaml format",
+    help="Path to config file in yaml format [required]",
     required=True,
 )
 @click.option(
     "-o",
     "--output_folder",
     type=click.Path(),
-    help="Path to the base schema file. This file is used as a reference to compare it with the schema generated using this module. (Default: installed schema in 'relecov-tools/relecov_tools/schema/relecov_schema.json')",
+    help="Path to folder where global results are saved [required]",
     required=False,
 )
 def wrapper(config_file, output_folder):

diff --git a/relecov_tools/assets/Relecov_metadata_template_v2.0.11.xlsx b/relecov_tools/assets/Relecov_metadata_template_v2.0.11.xlsx