- Size of the reference genome: %s
- Size of the core genome: %s (%s %% of the reference)
""" % (ref_size,
core_size,
fraction_core)
else:
core_size = False
core_str = ""
multiqc_table = report.get_multiqc_table(multiqc_assembly,
multiqc_mapping_list)
table_lowcoverage_contigs = quality_table(low_cov_fastas,
sample2gc,
sample2median_depth,
sampls2cumulated_size,
sample2n_contigs,
sample2scientific_name,
undetermined_snps_files=undetermined_snp_tables,
core_genome_size=core_size)
snp_heatmap_str = ""
for n, snp_table in enumerate(snp_tables):
snp_heatmap_str += '''
%s
******************************************************
.. raw:: html
%s
sample2gc[sample] = data_whole_gnome["gc_content"]
sample2median_depth[sample] = data_whole_gnome["mean_depth"]
sampls2cumulated_size[sample] = data_whole_gnome["contig_size"]
sample2n_contigs[sample] = n_contigs
sampls2cumulated_size_filtered[sample] = int(
table.query('median_depth>=5 & contig != "TOTAL"')[["contig_size"
]].sum())
sample2scientific_name = snakemake.params["sample_table"].to_dict(
)["ScientificName"]
table_lowcoverage_contigs = report.quality_table(
low_cov_fastas,
sample2gc,
sample2median_depth,
sampls2cumulated_size,
sampls2cumulated_size_filtered,
sample2n_contigs,
sample2scientific_name,
low_cov_detail=low_cov_detail)
table_virulence = report.virulence_table(virulence_reports, blast_files,
ordered_samples)
mash_table = report.get_mash_table(mash_results, mash_detail,
sample2scientific_name)
centrifuge_table = report.get_centrifuge_table(centrifuge_tables,
sample2scientific_name)
multiqc_table = report.get_multiqc_table(assembly_multiqc=multiqc_assembly)
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": ""},
)
