Merge pull request #2 from cokelaer/main

Fix on path to input files and update requirements

Author: cokelaer

.github/workflows/apptainer.yml

@@ -9,15 +9,15 @@ on:
   pull_request:
     branches-ignore: []
   schedule:
-    - cron: '0 0 * * SUN'
+    - cron: '0 0 15 * *'
 
 jobs:
   build-linux:
     runs-on: ubuntu-latest
     strategy:
       max-parallel: 5
       matrix:
-        python: [3.7, 3.8, 3.9]
+        python: [ 3.8, 3.9, '3.10']
       fail-fast: false
 
 

.github/workflows/main.yml

@@ -9,15 +9,15 @@ on:
   pull_request:
     branches-ignore: []
   schedule:
-    - cron: '0 0 * * SUN'
+    - cron: '0 0 15 * *'
 
 jobs:
   build-linux:
     runs-on: ubuntu-latest
     strategy:
       max-parallel: 5
       matrix:
-        python: [3.7, 3.8, 3.9]
+        python: [3.8, 3.9, '3.10']
       fail-fast: false
 
 

README.rst

@@ -9,6 +9,18 @@
 .. image:: https://github.com/sequana/nanomerge/actions/workflows/main.yml/badge.svg
    :target: https://github.com/sequana/nanomerge/actions/workflows
 
+.. image:: https://coveralls.io/repos/github/sequana/nanomerge/badge.svg?branch=main
+   :target: https://coveralls.io/github/sequana/nanomerge?branch=main
+
+
+.. image:: http://joss.theoj.org/papers/10.21105/joss.00352/status.svg
+   :target: http://joss.theoj.org/papers/10.21105/joss.00352
+   :alt: JOSS (journal of open source software) DOI
+
+.. image:: https://img.shields.io/badge/python-3.8%20%7C%203.9%20%7C3.10-blue.svg
+    :target: https://pypi.python.org/pypi/sequana
+    :alt: Python 3.8 | 3.9 | 3.10
+
 
 
 
@@ -28,9 +40,11 @@ You can install the packages using pip::
 
     pip install sequana_nanomerge --upgrade
 
-An optional requirements is pycoQC, which can be install with conda/mamba using e.g.:
+An optional requirements is pycoQC, which can be install with conda/mamba using e.g.::
+
+    conda install pycoQC
 
-    conda install pycoQC.
+you will also need graphviz installed.
 
 Usage
 ~~~~~
@@ -49,9 +63,9 @@ otherwise all fastq files are in DATAPATH/::
     sequana_nanomerge --input-directory DATAPATH --samplesheet samplesheet.csv
         --summary summary.txt --input-pattern '*fastq.gz'
 
-The --summary is optional and takes as input the output of albacore demultiplexing. usually a file called sequencing_summary.txt
+The --summary is optional and takes as input the output of albacore/guppy demultiplexing. usually a file called sequencing_summary.txt
 
-Note that the different between the two is the extra `*/` before the `*.fastq.gz` pattern since barcoded files are in individual subdirectories..
+Note that the different between the two is the extra `*/` before the `*.fastq.gz` pattern since barcoded files are in individual subdirectories.
 
 In both bases, the command creates a directory with the pipeline and configuration file. You will then need to execute the pipeline::
 
@@ -65,19 +79,19 @@ retrieve the pipeline itself and its configuration files and then execute the pi
 
 Or use `sequanix <https://sequana.readthedocs.io/en/master/sequanix.html>`_ interface.
 
-COncerning the sample sheet, whther your data is barcoded or not, it should be a CSV file ::
+Concerning the sample sheet, whether your data is barcoded or not, it should be a CSV file ::
 
     barcode,project,sample
     barcode01,main,A
     barcode02,main,B
     barcode03,main,C
 
-For a non-barcoded run, you must provide a file where the barcode column can be set (empty) or just removed::
+For a non-barcoded run, you must provide a file where the barcode column can be set (empty)::
 
     barcode,project,sample
     ,main,A
 
-or::
+or just removed::
 
     project,sample
     main,A
@@ -109,6 +123,7 @@ Requirements
 This pipelines requires the following executable(s), which is optional:
 
 - pycoQC
+- dot
 
 .. image:: https://raw.githubusercontent.com/sequana/nanomerge/main/sequana_pipelines/nanomerge/dag.png
 
@@ -132,6 +147,7 @@ Changelog
 ========= ====================================================================
 Version   Description
 ========= ====================================================================
+1.0.1     Fix the pyco file paths, update requirements and doc
 1.0.0     Stable release ready for production
 0.0.1     **First release.**
 ========= ====================================================================

requirements.txt

@@ -1 +1,2 @@
 sequana_pipetools>=0.8.1
+sequana

sequana_pipelines/nanomerge/config.yaml

@@ -8,12 +8,10 @@
 # ============================================================================
 
 # Keep input_readtag empty for nanopore
-#input_directory: '/home/cokelaer/TEMP/fastq_pass/barcode21'
-input_directory: '/home/cokelaer/TEMP/fastq_pass/'
+input_directory:
 input_readtag:
 input_pattern: '*/*.fastq.gz'
-summary: /home/cokelaer/TEMP/fastq_pass/sequencing_summary_AOI637_ef78de7c_aef0cc4b.txt
-#samplesheet: "samplesheet1.csv"
+summary:
 samplesheet: "samplesheet.csv"
 
 ################################################################################

sequana_pipelines/nanomerge/nanomerge.rules

@@ -73,12 +73,15 @@ else:
 
 
 if config["summary"]:
-    qc_file = "pyco/pyco.html"
+    qc_file = ["pyco/pyco.html"]
 else:
-    qc_file = ""
+    qc_file = []
 
 # ========================================================================= pipeline starts here
-expected_fastqs = expand("./{project}/{sample}.fastq.gz", zip, project=samples.df['project'], sample=samples.df['sample']),
+expected_fastqs = expand("./{project}/{sample}.fastq.gz", zip, project=samples.df['project'],
+        sample=samples.df['sample'])
+
+
 rule pipeline:
     input:
         expected_fastqs,
@@ -100,22 +103,22 @@ if config["summary"]:
         input:
             config['summary']
         output:
-            temp(qc_file)
+            "pyco/pyco.html"
         log:
-            temp(qc_file)
+            "pyco/pyco.log"
         container:
             config["apptainers"]["pycoqc"]
         shell:
             """
             pycoQC --summary_file {input} -o {output} > {log} 2>&1
             """
 
+
 rule merge:
     input:
         get_input_merge
     output:
         "./{project}/{sample}.fastq.gz"
-
     shell:
         """
         cat {input} > {output}
@@ -134,7 +137,7 @@ rule rulegraph:
 
 rule html_report:
     input:
-        list(expected_fastqs) + [qc_file]
+        list(expected_fastqs) + qc_file
     output:
         "summary.html"
     run:
@@ -144,11 +147,11 @@ rule html_report:
         data = {"name": "nanomerge",
                  "rulegraph": ".sequana/rulegraph.svg",
                  "pipeline_version": nanomerge.version}
-        manager.teardown(extra_files_to_remove=["pyco/pyco.log", qc_file])
+        manager.teardown(extra_files_to_remove=["pyco/pyco.log", "pyco/pyco.html"])
 
         dirs = ",".join([f'<a href="{x}/">{x}</a>' for x in samples.get_projects()])
         if config['summary']:
-            with open(qc_file, "r") as fout:
+            with open("pyco/pyco.html", "r") as fout:
                 pycodata = fout.read()
                 pycodata = '<div class="columns">' + pycodata.split('<div class="columns">')[-1].replace("</div>\n</body>\n</html>","")
 
@@ -163,6 +166,7 @@ onsuccess:
 
     print("Once done, please clean up the directory using\n'make clean'")
     shell("chmod -R g+w .")
+    shell("rm -rf pyco rulegraph")
 
 onerror:
     from sequana_pipetools.errors import PipeError

sequana_pipelines/nanomerge/requirements.txt

@@ -1 +1,2 @@
 pycoQC
+dot

setup.py

@@ -11,7 +11,7 @@
 
 _MAJOR               = 1
 _MINOR               = 0
-_MICRO               = 0
+_MICRO               = 1
 version = f"{_MAJOR}.{_MINOR}.{_MICRO}"
 release = f"{_MAJOR}.{_MINOR}"