add md_to_pdf

Author: DanHUMassMed

.gitignore

@@ -4,6 +4,7 @@
 **/results/
 work/
 **/deseq_out
+**/__pycache__
 
 # Files to ignore
 docs/overview.pdf

bin/md_to_pdf.py

@@ -0,0 +1,60 @@
+# RNA-Seq Pipeline Overview
+    
+### <div class="job-title">{title}</div>
+
+* __Prepared for__: 
+
+{prepared_for}
+
+* __Prepared by__ : {prepared_by}
+
+* __Process Executed on__ : {process_date}
+
+<br>
+
+--- 
+### Data Access
+* __Dropbox Folder__: {dropbox_folder}
+* __Dropbox URL__: [{dropbox_link}]({dropbox_link})
+
+<br>
+
+#### FASTQ files
+```
+{fastq_files}
+```
+
+<br>
+
+#### Gene Index files
+
+Gene Index based on Wormbase Version: _{wormbase_version}_
+
+--- 
+
+### RNA Seq Process
+
+<img src="./rna-seq-process-1-700.png" width=700>
+
+### Pipeline Outputs
+
+* MD5 Checksum Report
+* FAST QC Report
+* Multi QC Report
+* Isoform Quantification
+* Gene Quantification
+* DESeq2 Gene Normalizations (Up, Down, All Expressed) & Visualizations
+* WormCat Annotations and Visualizations of gene set enrichment data
+
+### Source Code
+
+The provided tagged repository is available to create reproducible outputs from the RNA-Seq Pipeline.
+
+<div class="blue-background">
+
+<table>
+<tr><td><b>Repo</b></td><td><a href="{github_release}">{github_release}</a></td></tr>
+<tr><td><b>Source</b></td><td><a href="{github_release}/{github_tag}">{github_release}/{github_tag}</a></td></tr>
+</table>
+
+</div>

docs/RANSeq_Analysis.png bin/md_to_pdf/RANSeq_Analysis.png

@@ -0,0 +1,135 @@
+#!/usr/bin/env python3
+
+import argparse
+import subprocess
+import json
+import sys
+import os
+import markdown
+from markdown_include.include import MarkdownInclude
+from weasyprint import HTML
+
+
+REPORT_TEMPLATE_FILE="overview_report_template.md"
+
+
+def get_dropbox_link(remote_location):
+    # rclone command to get dropbox link
+    command = f'rclone link remote:"{remote_location}"'
+
+    try:
+        output = subprocess.check_output(command, shell=True, text=True)
+        dropbox_link = output.strip()
+        return dropbox_link
+    except subprocess.CalledProcessError as e:
+        return f"Error: {str(e)}"
+
+def get_fastq_names(remote_location):
+    # rclone command to get fastq files
+    command = f'rclone lsl remote:"{remote_location}" --human-readable|grep .fq.gz|sed "s/\.000000000//"'
+
+    try:
+        output = subprocess.check_output(command, shell=True, text=True)
+        return output
+    except subprocess.CalledProcessError as e:
+         return f"Error: {str(e)}"
+
+
+def generate_markdown_from_json(json_file):
+    # Read JSON data from file
+    with open(json_file, 'r') as file:
+        json_data = json.load(file)
+
+    with open(REPORT_TEMPLATE_FILE, 'r') as file:
+        report_template = file.read()
+
+    # Extract values from JSON data
+    title = json_data['title']
+    process_date = json_data['process_date']
+    prepared_by = json_data['prepared_by']
+    prepared_for = ""
+    for person in json_data['prepared_for']:
+        prepared_for += f"  * {person} \n"
+    
+    dropbox_folder = json_data['dropbox_folder']
+    dropbox_link = get_dropbox_link(dropbox_folder)
+    fastq_files = get_fastq_names(dropbox_folder)
+    wormbase_version = json_data['wormbase_version']
+    github_release = json_data['GitHub_release']
+    github_tag = json_data['GitHub_tag']
+
+    markdown_content = report_template.format(title=title,
+                                              process_date=process_date,
+                                              prepared_by=prepared_by,
+                                              prepared_for=prepared_for,
+                                              dropbox_folder=dropbox_folder,
+                                              dropbox_link=dropbox_link,
+                                              fastq_files=fastq_files,
+                                              wormbase_version=wormbase_version,
+                                              github_release=github_release,
+                                              github_tag=github_tag)
+
+    # Write Markdown content to output file
+    with open('overview_report.md', 'w') as file:
+        file.write(markdown_content)
+
+    print("Markdown file generated successfully.")
+
+def convert_to_html(markdown_file_name, css_file_name):
+    with open(markdown_file_name, mode="r", encoding="utf-8") as markdown_file:
+        with open(css_file_name, mode="r", encoding="utf-8") as css_file:
+            markdown_input = markdown_file.read()
+            css_input = css_file.read()
+
+            markdown_path = os.path.dirname(markdown_file_name)
+            markdown_include = MarkdownInclude(configs={"base_path": markdown_path})
+            html = markdown.markdown(
+                markdown_input, extensions=["extra", markdown_include, "meta", "tables"]
+            )
+
+            return f"""
+            <html>
+              <head>
+                <style>{css_input}</style>
+              </head>
+              <body>{html}</body>
+            </html>
+            """
+
+def convert_to_pdf(markdown_file_name, css_file_name):
+    file_name = os.path.splitext(markdown_file_name)[0]
+    html_string = convert_to_html(markdown_file_name, css_file_name)
+
+    with open(
+        file_name + ".html", "w", encoding="utf-8", errors="xmlcharrefreplace"
+    ) as output_file:
+        output_file.write(html_string)
+
+    markdown_path = os.path.dirname(markdown_file_name)
+    html = HTML(string=html_string, base_url=markdown_path)
+    html.write_pdf(file_name + ".pdf")
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-c', '--report-config', help='JSON Config file for report')
+    #parser.add_argument('-o', '--output-path', help='The outpout path for the report')
+    args = parser.parse_args()
+    cmd_line_msg = "overview_report.py --report-config [<report.json>] --output-path [<base_directory>]"
+        
+    if not args.report_config:
+        print(cmd_line_msg)
+        print("JSON Config is missing.")
+        return
+    
+    # if not args.output_path:
+    #     print(cmd_line_msg)
+    #     print("Ouput path is missing.")
+    #     return
+
+    generate_markdown_from_json(args.report_config)
+    convert_to_pdf('overview_report.md','overview_report_template.css')
+
+if __name__ == '__main__':
+    main()
+

docs/overview.css bin/md_to_pdf/overview_report_template.css

@@ -115,3 +115,5 @@ process CHECK_MD5 {
     path "md5_report.html"
 
 }
+
+

bin/md_to_pdf/overview_report_template.md

@@ -36,3 +36,21 @@ process FASTQC_SINGLE {
     """
 }
 
+process OVERVIEW_REPORT {
+    container 'danhumassmed/qc-tools:1.0.1'
+    publishDir params.outdir, mode:'copy'
+
+    input:
+    path report_config
+    
+    script:
+    """
+    cp -r ${launchDir}/bin/md_to_pdf/* .
+    ${launchDir}/bin/overview_report.py --report-config "${report_config}"
+    """
+
+    output:
+    path "overview_report.pdf"
+
+}
+

docs/rna-seq-process-1-700.png bin/md_to_pdf/rna-seq-process-1-700.png

@@ -0,0 +1,36 @@
+#!/usr/bin/env nextflow 
+
+// nextflow run pipelines/alex_byrne/06-overview-report-alex.nf -bg -N [email protected]
+
+
+nextflow.enable.dsl = 2
+
+/*
+ * RNA SEQ Pipeline 
+ */
+
+params.report_config = "${projectDir}/data/Experiment1/experiment1.json"
+params.outdir = "${projectDir}/results"
+
+
+log.info """\
+ R N A S E Q - N F   P I P E L I N E
+ ===================================
+ report_config : ${params.report_config}
+ outdir        : ${params.outdir}
+ """
+
+// import modules
+include { OVERVIEW_REPORT } from "${launchDir}/modules/fastqc"
+
+/* 
+ * main script flow
+ */
+workflow { 
+  report_config_ch = channel.fromPath( params.report_config, checkIfExists: true ) 
+  OVERVIEW_REPORT( report_config_ch )
+}
+
+workflow.onComplete {
+	log.info ( workflow.success ? "\nDone! Open the following report in your browser --> ${params.outdir}/overview_report.pdf\n" : "Oops .. something went wrong" )
+}