Skip to content

Commit

Permalink
Merge pull request #11 from bio-raum/dev
Browse files Browse the repository at this point in the history 
Dev
  • Loading branch information
@marchoeppner
marchoeppner authored Jan 10, 2025
2 parents 2570472 + daff863 commit 0df483a
Show file tree
Hide file tree
Showing 44 changed files with 858 additions and 866 deletions.
41 changes: 0 additions & 41 deletions .github/workflows/documentation_dev.yml
View file

This file was deleted.

161 changes: 124 additions & 37 deletions assets/gabi_template.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
.general { border-style: none; border-spacing: 0px ;}
.table-caption { font-weight: bold; display: block;}
table { border-collapse: collapse;}
tr.row { border-bottom: 1px solid grey;}
tr.row td { border-bottom: 1px solid grey; padding-top: 5px; padding-bottom: 5px;}
td { padding-left: 5px; padding-right: 5px;}
th { border-left: 1px solid white; padding-right: 5px;}
tr td[scope="sample-id"] {background-color: rgb(233, 233, 233); font-weight: bold;}
Expand All @@ -29,6 +29,8 @@
tr th[scope="subcol-inactive"] {background-color: #6e6e6e; color: #fff;}
.versions { font-size: 9px; }
.versions td { padding: 0px; }
.infotext { color:#6e6e6e; font-size: 10px ;}
.infotext a { text-decoration: underline;}
/* Tooltip container */
.tooltip { position: relative; display: inline-block; border-bottom: 1px dotted black; }
.tooltip .tooltiptext { visibility: hidden; width: 250px; background-color: rgb(189, 186, 186); color: black; text-align: center; padding: 5px 0; border-radius: 6px; position: absolute; z-index: 1; }
Expand Down Expand Up @@ -57,14 +59,40 @@ <h1>
{% if Insertsizes %}
<td><a href="#insert-sizes">Insert sizes</a></td>
{% endif %}
<td><a href="#mlst">MLST</a></td>
<td><a href="#busco">Busco</a></td>
{% if Kraken %}
<td><a href="#kraken">Kraken2</a></td>
{% endif %}
<td><a href="#serotypes">Serotypes</a></td>
<td><a href="#mlst">MLST</a></td>
{% if serotypes %}
<td><a href="#serotypes">Serotypes</a></td>
{% endif %}
<td><a href="#software">Software</a></td>
</tr>
</table>

<!--
Some basic information about the analysis run
-->
<h2>Run Infos</h2>
<table class="general">
<tr>
<td>User</td><td>{{user}}</td>
</tr>
<tr>
<td>Date</td><td>{{date}}</td>
</tr>
<tr>
<td>Pipeline version</td><td>{{version}}</td>
</tr>
<tr>
<td>Command line call</td><td>{{call}}</td>
</tr>
<tr>
<td>Work directory</td><td>{{wd}}</td>
</tr>
</table>

<!--
The summary table with all key metrics per sample
-->
Expand All @@ -73,11 +101,11 @@ <h2>Summary</h2>
<tr>
<th scope="col">Sample</th>
<th scope="col"><div class="tooltip">Status<span class="tooltiptext">The overall analysis status: pass: ok to use, warn: potential issues found, fail: most probably not usable</span></div></th>
<th scope="col"><div class="tooltip">Best-guess taxon<span class="tooltiptext">The highest scoring taxon in the Kraken2 analysis - green: robust call, orange: weak call, red: very weak call</span></div></th>
<th scope="col"><div class="tooltip">Best-guess taxon<span class="tooltiptext">The highest scoring taxon using kmer matching (S/MASH)</span></div></th>
<th colspan=2 scope="col"><div class="tooltip">Reference genome<span class="tooltiptext">The highest matching hit in RefSeq to this assembly</span></div></th>
<th colspan=5 scope="col"><div class="tooltip">Assembly<span class="tooltiptext">Information about this assembly</span></div></th>
<th colspan=4 scope="col"><div class="tooltip">Mean coverage<span class="tooltiptext">Mean coverage of reads mapped back to the assembly - bigger is better</span></div></th>
<th scope="col"><div class="tooltip">Mean insert size<span class="tooltiptext">The mean insert size as determined from mapped reads</span></div></th>
<th colspan=3 scope="col"><div class="tooltip">Read quality<span class="tooltiptext">Quality metrics of reads after trimming</span></div></th>
<th colspan=2 scope="col"><div class="tooltip">Contamination<span class="tooltiptext">Indicators of contamination</span></div></th>
</tr>
<tr class="row">
Expand All @@ -90,12 +118,14 @@ <h2>Summary</h2>
<th scope="subcol"><div class="tooltip">#Contigs<span class="tooltiptext">The number of chromosomal contigs, i.e. without plasmids.</span></div></th>
<th scope="subcol"><div class="tooltip">N50 (Kb)<span class="tooltiptext">The size of contigs (>=)in which 50% of the assembly are represented.</span><div></th>
<th scope="subcol"><div class="tooltip">Gene space (%)<span class="tooltiptext">The fraction of broadly conserved genes fully covered in this assembly (BUSCO).</span></div></th>
<th scope="subcol">GC (%)</th>
<th scope="subcol"><div class="tooltip">GC (%)<span class="tooltiptext">GC content of the assembly. Deviations from the species default are highlighted in orange (mild) and red (strong, something likely wrong)</span></div></th>
<th scope="subcol">Total</th>
<th scope="subcol">Illumina</th>
<th scope="subcol">ILM</th>
<th scope="subcol">ONT</th>
<th scope="subcol">HiFi</th>
<th scope="subcol">Illumina</th>
<th scope="subcol"><div class="tooltip">ILM Q30 (%)<span class="tooltiptext">Fraction of Illumina reads above Q30.</span></div></th>
<th scope="subcol"><div class="tooltip">ONT Q15 (#)<span class="tooltiptext">Number of ONT reads above Q15.</span></div></th>
<th scope="subcol"><div class="tooltip">ONT N50 (bp)<span class="tooltiptext">N50 of ONT reads</span></div></th>
<th scope="subcol">Confindr (%)</th>
<th scope="subcol">Taxa >10%</th>
</tr>
Expand All @@ -108,7 +138,7 @@ <h2>Summary</h2>
<td scope="sample-id">{{row.sample}}</td>
<td scope={{row.status}}>{{row.status}}</td>
<td scope="missing">{{row.taxon}}</td>
<td scope="missing"><a href="https://www.ncbi.nlm.nih.gov/datasets/genome/{{row.reference.assembly}}" target="_blank" alt="Genome in GenBank">{{row.reference.assembly}}<br>{{row.reference.definition}}</a></td>
<td scope="missing"><a href="https://www.ncbi.nlm.nih.gov/datasets/genome/{{row.reference.assembly}}" target="_blank" title="{{row.reference.definition}}" alt="Genome in GenBank">{{row.reference.assembly}}</a></td>
<td scope={{row.fraction_status}}>{{row.fraction}}</td>
<td scope={{row.assembly_status}}>{{row.assembly}}</td>
<td scope={{row.contigs_status}}>{{row.contigs}}</td>
Expand All @@ -119,7 +149,9 @@ <h2>Summary</h2>
<td scope={{row.coverage_illumina_status}}>{{row.coverage_illumina}}</td>
<td scope={{row.coverage_nanopore_status}}>{{row.coverage_nanopore}}</td>
<td scope={{row.coverage_pacbio_status}}>{{row.coverage_pacbio}}</td>
<td scope="missing">{{row.samtools.mean_insert_size}}</td>
<td scope={{row.quality_illumina_status}}>{{row.quality_illumina}}</td>
<td scope="missing">{{row.quality_nanopore}}</td>
<td scope="missing">{{row.nanopore_n50}}</td>
<td scope={{row.confindr_status}}>{{row.contamination}}</td>
<td scope={{row.taxon_count_status}}>{{row.taxon_count}}</td>
</tr>
Expand All @@ -133,6 +165,10 @@ <h2>Summary</h2>
-->
<div id="assembly"></div>
<h2>Assembly metrics</h2>
<div class="infotext">
Descriptive metrics of individual assemblies determined by <a href="https://quast.sourceforge.net/" target="_new">Quast</a>.
<p></p>
</div>

<table>
<tr>
Expand Down Expand Up @@ -167,23 +203,75 @@ <h2>Assembly metrics</h2>
<p></p>
<a href="#navigation">top</a>

<!--
Check if insert sizes are present, then render the relevant secion
-->
{% if Insertsizes %}
<div id="insert-sizes"></div>

<h2>Insert size distribution (Illumina)</h2>
<div class="infotext">
Insert size refers to the size of the sequenced DNA fragment. Depending on the exact library protocol, this size will fall fairly uniformly around a mean value (~300-500bp).
For Illumina data, that value should typically be (slightly) larger than the combined length of forward and reverse read for optimal data yield. Very flat curves may (depending on the protocol!)
indicate a failure during fragment size selection/enrichment. Neither small insert sizes nor flat curves are a clear predictor for subsequent assembly issues, but can inform any potential debugging efforts.
</div>
<p></p>

{{Insertsizes}}

<p></p>
<a href="#navigation">top</a>
{% endif %}

<!--
Busco scores
-->
<div id="busco"></div>
<h2>BUSCO scores</h2>

<div class="infotext">
<a href="https://busco.ezlab.org/" target="_new">BUSCO</a> scores describe the coverage of the assemblied gene space against a set of broadly conserved singleton genes (here: bacteria_odb10). A perfect assembly should
have a complete coverage of the gene space (complete: 100%), without any fragmentation or, worse, duplication. A high value of duplication may indicate assembly errors or contamination. Some taxa with very
streamlined gene content, such as <i>Campylobacter</i>, will typically have a completeness score of less than 100%. The Completeness estimates may include duplicated genes, so values greater than 100% are
possible (i.e. all genes present, of which x % are duplicated).
</div>

{{Busco}}

<p></p>
<a href="#navigation">top</a>

<!--
Check if Kraken data is present, then render the relevant section
-->
{% if Kraken %}
<div id="kraken"></div>

<h2>Kraken2 - taxonomic composition</h2>

<div class="infotext">
<a href="https://github.com/DerrickWood/kraken2", target="_new">Kraken2</a> matches kmers from raw sequencing reads against a reference database to determine the taxonomic composition of a read set. For DNA from
pure cultures (which is the focus of GABI), only one species should be identified at dominant proportions. For some taxa, like <i>Campylobacter</i>, several species from the same genus may be found at comparative
abundances due to a lack of sufficient DNA differences. Otherwise, identification of multiple taxa at higher proportions may indicate a contamination issue.
</div>

{{Kraken}}

<a href="#navigation">top</a>
{% endif %}

<!--
MLST sequence types by schema
-->
<div id="mlst"></div>
<h2>MLST</h2>

<div class="infotext">
Taxa-specific <a href="https://github.com/tseemann/mlst" target="_new">MLST schemas</a> classify assemblies into pre-defined types or groups. Results are divided by typing schema (and consequently taxa).
</div>

<p></p>

{% for scheme,mtypes in mlst.items() %}

<div class="table-caption">Scheme: {{scheme}}</div>
Expand All @@ -204,40 +292,39 @@ <h2>MLST</h2>
<p></p>
<a href="#navigation">top</a>

{% if Kraken %}
<div id="kraken"></div>

<h2>Kraken2 - taxonomic composition</h2>

{{Kraken}}

<a href="#navigation">top</a>
{% endif %}
<!--
Results from one or multiple serotyping tools
-->
<div id="serotypes"></div>
<h2>Serotyping</h2>
{% if serotypes %}
<div id="serotypes"></div>
<h2>Serotyping</h2>

{% for stool,stypes in serotypes.items() %}
<div class="table-caption">{{stool}}</div>
<table>
<tr>
<th scope="col">Sample</th>
<th scope="col">Serotype</th>
</tr>
{% for stype in stypes %}
<div class="infotext">
Serotyes, similar to MLST types, classify assemblies based on a set of predefined gene profiles.
</div>

<p></p>

{% for stool,stypes in serotypes.items() %}
<div class="table-caption">{{stool}}</div>
<table>
<tr>
<td scope="sample-id">{{stype.sample}}</td>
<td scope="col">{{stype.serotype}}</td>
<th scope="col">Sample</th>
<th scope="col">Serotype</th>
</tr>
{% endfor %}
</table>
<p></p>
{% endfor %}
{% for stype in stypes %}
<tr>
<td scope="sample-id">{{stype.sample}}</td>
<td scope="col">{{stype.serotype}}</td>
</tr>
{% endfor %}
</table>
<p></p>
{% endfor %}

<p></p>
<a href="#navigation">top</a>
<p></p>
<a href="#navigation">top</a>
{% endif %}

<!--
Information on used software packages
Expand Down
2 changes: 1 addition & 1 deletion assets/test/samples.csv
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
sample_id,platform,single_end,R1,R2
ERR1008684,ILLUMINA,false,ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/004/ERR1008684/ERR1008684_1.fastq.gz,ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/004/ERR1008684/ERR1008684_2.fastq.gz
SAMEA2707761,ILLUMINA,ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR580/ERR580964/ERR580964_1.fastq.gz,ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR580/ERR580964/ERR580964_2.fastq.gz
Loading

0 comments on commit 0df483a

Please sign in to comment.