core_genome_size=core_size)
snp_heatmap_str = ""
for n, snp_table in enumerate(snp_tables):
snp_heatmap_str += '''
%s
******************************************************
.. raw:: html
%s
''' % (snp_table.split("/")[2],
plot_heatmap_snps(snp_table, id=snp_table.split("/")[2] ))
spanning_tree_str = ""
for n, tree in enumerate(spanning_trees):
tree_path = '/'.join(tree.split('/')[1:])
spanning_tree_str += """
%s
***************************************************************
.. figure:: %s
:alt: %s
:width: 60%%
""" % (tree.split("/")[3], tree_path, tree.split("/")[3])
report_str = f"""
def write_report(output_file, STYLE, SCRIPT, virulence_reports, blast_files,
resistance_reports, spanning_tree_core, low_cov_fasta,
ete_figure_counts, mlst_tree, snp_table, core_genome_size,
reference_genome_size, virulence_table):
import io
from docutils.core import publish_file, publish_parts
from docutils.parsers.rst import directives
multiqc_link = '<a href="%s">MiltiQC</a>' % '/'.join(
multiqc_report.split('/')[1:])
table_lowcoverage_contigs = quality_table(low_cov_fasta)
table_virulence = virulence_table(virulence_reports, blast_files,
ordered_samples)
table_resistance = resistance_table(resistance_reports)
snp_heatmap = plot_heatmap_snps(snp_table)
fraction_core = round(
float(core_genome_size) / float(reference_genome_size) * 100, 2)
report_str = f"""
.. raw:: html
{SCRIPT}
{STYLE}
=============================================================
Diag Pipeline - Complete report
=============================================================
.. contents::
:backlinks: none
:depth: 2
Quality Control
---------------
MultiQC
*******
MultiQC aggregate results from bioinformatics analyses across many samples into a single report.
The analyses covered here include genome assembly with spades, evaluation of the sequencing
depth by mapping of the reads against the assembly and annotation with prokka.
.. raw:: html
{multiqc_link}
Low coverage contigs
********************
.. raw:: html
{table_lowcoverage_contigs}
Typing
------
MLST
*****
The *S. aureus* MLST scheme is based on the sequence of the following seven house-keeping genes:
1. arcC (Carbamate kinase)
2. aroE (Shikimate dehydrogenase)
3. glpF (Glycerol kinase)
4. gmk (Guanylate kinase)
5. pta (Phosphate acetyltransferase)
6. tpi (Triosephosphate isomerase)
7. yqi (Acetyle coenzyme A acetyltransferase)
The MLST was determined using the mlst_ software based on PubMLST_ typing schemes.
.. _PubMLST: https://pubmlst.org/
.. _mlst: https://github.com/tseemann/mlst
Phylogeny + MLST
****************
.. figure:: {mlst_tree}
:alt: MST tree
:width: 40%
MLST as determined by T. Seemann mlst_.
MS tree (R)
*********************
- Size of the reference genome: {reference_genome_size}
- Size of the core genome: {core_genome_size} ({fraction_core} % of the reference)
.. figure:: {spanning_tree_core}
:alt: MST tree
:width: 80%
Minimum spanning tree including all samples as well as the reference genome.
MS tree (js)
***********************
.. raw:: html
<div id="cy" style="width:80%;height:700px; position: relative; border: 2px solid #212523"></div>
SNP table
***********
.. raw:: html
{snp_heatmap}
Virulence (VFDB)
-----------------
Overview
*********
The identification of virulence factors was performed with BLAST. Only hits exhibiting more
than 80% amino acid identity to a known virulence factor from the VFDB database are considered.
.. figure:: {ete_figure_counts}
:alt: VF tree
:width: 50%
Number of identified VFs in each genome.
Details
********
.. raw:: html
{table_virulence}
Resistance (RGI/CARD)
----------------------
.. raw:: html
{table_resistance}
"""
with open(output_file, "w") as fh:
publish_file(
source=io.StringIO(report_str),
destination=fh,
writer_name="html",
settings_overrides={"stylesheet_path": ""},
)