Merge pull request #65 from sanjaynagi/qc-notebooks-05-07-23

Quality control notebooks

.test/config/config.yaml

@@ -5,7 +5,7 @@ dataset: "AgamDao"
 metadata: "config/metadata.tsv"
 
 # Directory of Illumina Miseq Run
-illumina-dir: /home/sanj/projects/AmpSeqVIGG2022/resources/220329_M05658_0010_000000000-K9TYL
+illumina-dir: ""
 
 # Genome fasta reference files 
 reference-name: 'AgamP4'

config/config.yaml

@@ -5,7 +5,7 @@ dataset: gaard-sanger
 metadata: config/metadata.tsv
 
 # Directory of Illumina Miseq Run
-illumina-dir: resources/230530_M02853_0061_000000000-L23TH/
+illumina-dir: resources/230629_M05658_0009_000000000-DL7P9/
 
 # Specify whether reference  provided is amplicon or wholegenome sequence data
 # Genome fasta reference files
@@ -17,7 +17,7 @@ reference-gff3: resources/reference/Anopheles-gambiae-PEST_BASEFEATURES_AgamP4.1
 targets: config/AgamDao.bed
 
 # Specify whether to convert bcl files to fastq
-bcl-convert: False
+bcl-convert: True
 
 # Specify whether to run quality-control analyses
 quality-control:

docs/ampseeker-results/_toc.yml

@@ -4,10 +4,13 @@
 format: jb-book
 root: intro
 parts:
+- caption: QC
+  chapters:
+  - file: notebooks/read-quality
+  - file: notebooks/reads-per-well
 - caption: Results
   chapters:
   - file: notebooks/sample-map
-  - file: notebooks/IGV-explore
   - file: notebooks/coverage
   - file: notebooks/principal-component-analysis
   - file: notebooks/allele-frequencies

workflow/Snakefile

@@ -6,6 +6,7 @@ import numpy as np
 configfile:"config/config.yaml"
 dataset = config['dataset']
 metadata = pd.read_csv(config['metadata'], sep="\t")
+plate_info = np.isin(['plate', 'well_letter', 'well_number'], metadata.columns).all()
 samples = metadata['sampleID']
 
 import os
@@ -16,6 +17,7 @@ include: "rules/utilities.smk"
 include: "rules/bcl-convert.smk"
 include: "rules/qc.smk"
 include: "rules/alignment-variantcalling.smk"
+include: "rules/qc-notebooks.smk"
 include: "rules/analysis.smk"
 include: "rules/jupyter-book.smk"
 

workflow/envs/AmpSeeker-python.yaml

@@ -15,4 +15,5 @@ dependencies:
   - pip:
     - igv_notebook
     - papermill
-    - scikit-allel
+    - scikit-allel
+    - pysam

workflow/envs/AmpSeeker-qc.yaml

@@ -1,7 +1,8 @@
 name: AmpSeeker-qc
 channels:
   - bioconda
-  - dranew
+  - conda-forge
+  - anaconda
 dependencies:
-  - fastqc
-  - bcl2fastq
+  - python=3.9
+  - fastqc

workflow/notebooks/read-quality.ipynb

@@ -0,0 +1,121 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "parameters",
+     "remove-input"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "metadata_path = '../../config/metadata.tsv'\n",
+    "index_read_qc = True\n",
+    "wkdir = \"\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Read quality\n",
+    "\n",
+    "In this notebook, we link to the quality reports from MultiQC, index read QC and per sample from FastQC and FastP.   "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "remove-input"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "# load panel metadata\n",
+    "import pandas as pd\n",
+    "metadata = pd.read_csv(metadata_path, sep=\"\\t\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "remove-input"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "from IPython.display import display, Markdown\n",
+    "display(Markdown('## MultiQC'))\n",
+    "display(Markdown('MultiQC is a tool which integrates information from various tools in the workflow (Currently, it is not quite configured correctly)'))\n",
+    "display(Markdown(f'<a href={wkdir}/results/multiqc/multiqc_report.html>MultiQC report</a>'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "remove-input"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "if index_read_qc:\n",
+    "    display(Markdown('## Index read QC'))\n",
+    "    display(Markdown('Index reads with average quality score below 30 for a given run may be unreliable and cause demultiplexing errors.'))\n",
+    "    display(Markdown(f'<a href={wkdir}/results/index-read-qc/I1.html>Index 1 FASTQC report</a>'))\n",
+    "    display(Markdown(f'<a href={wkdir}/results/index-read-qc/I2.html>Index 2 FASTQC report</a>'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": false,
+    "tags": [
+     "remove-input"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "display(Markdown('## Sample read QC'))\n",
+    "for sample in metadata.sampleID:\n",
+    "    display(Markdown(f'<a href={wkdir}/results/fastp_reports/{sample}.html>{sample} fastp report</a>'))"
+   ]
+  }
+ ],
+ "metadata": {
+  "celltoolbar": "Tags",
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.10"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "ce681de973941d5edd9bd94c9a2926b7fe65e17e578a68317f38265a230b8ca7"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}