Added the fastp log to the final report

Plant-Food-Research-Open · Oct 31, 2024 · d4624de · d4624de
1 parent 14ca56e
commit d4624de
Show file tree

Hide file tree

Showing 8 changed files with 117 additions and 22 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -15,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 6. Added a sequence labels table below the HiC contact map [#147](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/147)
 7. Added parameter `hic_samtools_ext_args` and set its default value to `-F 3852` [#159](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/159)
 8. Added the HiC QC report to the final report so that users don't have to navigate to the results folder [#162](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/162)
+9. Added the fastp log to the final report [#163](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/163)
 
 ### `Fixed`
 

diff --git a/bin/report_modules/parsers/hic_parser.py b/bin/report_modules/parsers/hic_parser.py
@@ -7,6 +7,50 @@
 from report_modules.parsers.parsing_commons import sort_list_of_results
 
 
+def colorize_fastp_log(log: Path):
+    section_colors = {
+        "adapter": "color: blue;",
+        "before_filtering": "color: goldenrod;",
+        "after_filtering": "color: green;",
+        "filtering_result": "color: green;",
+        "duplication": "color: red;",
+        "fastp": "color: gray;",
+        "version": "color: blue;",
+    }
+
+    patterns = {
+        "adapter": re.compile(r"Detecting adapter sequence for read\d..."),
+        "before_filtering": re.compile(r"Read\d before filtering:"),
+        "after_filtering": re.compile(r"Read\d after filtering:"),
+        "filtering_result": re.compile(r"Filtering result:"),
+        "duplication": re.compile(r"Duplication rate:"),
+        "fastp": re.compile(r"fastp --in"),
+        "version": re.compile(r"fastp v"),
+    }
+
+    html_log = "<pre>\n"
+
+    for line in log.read_text().split("\n"):
+        colored_line = line.strip()
+        # Apply HTML color style based on section patterns
+        for section, pattern in patterns.items():
+            if pattern.search(line):
+                colored_line = (
+                    f"<span style='{section_colors[section]}'>{line.strip()}</span>"
+                )
+                break
+        else:
+            # Default styling for uncolored lines
+            colored_line = f"<span>{line.strip()}</span>"
+
+        html_log += f"{colored_line}\n"
+
+    # Close HTML tags
+    html_log += "</pre>"
+
+    return html_log
+
+
 def parse_hic_folder(folder_name="hic_outputs"):
     dir = os.getcwdb().decode()
     hic_folder_path = Path(f"{dir}/{folder_name}")
@@ -44,6 +88,15 @@ def parse_hic_folder(folder_name="hic_outputs"):
             if re.match(rf"[\S]+\.on\.{tag}_qc_report\.pdf", x.name)
         ][0]
 
+        # Get FASTP log if it is there
+        fastp_log = [x for x in hic_folder_path.glob("*.log")]
+
+        if fastp_log != []:
+            fastp_log = fastp_log[0]
+            fastp_log = colorize_fastp_log(fastp_log)
+        else:
+            fastp_log = None
+
         data["HIC"].append(
             {
                 "hap": tag,
@@ -57,6 +110,7 @@ def parse_hic_folder(folder_name="hic_outputs"):
                     showindex=False,
                 ),
                 "hicqc_report_pdf": os.path.basename(str(hicqc_report)),
+                "fastp_log": fastp_log,
             }
         )
 

diff --git a/bin/report_modules/templates/hic/hic.html b/bin/report_modules/templates/hic/hic.html
@@ -1,18 +1,45 @@
 <div id="HIC" class="tabcontent" style="display: none">
-    <div class="section-para-wrapper">
-        <p class="section-para">
-            Hi-C contact mapping experiments measure the frequency of physical contact between loci in the genome. The
-            resulting dataset, called a “contact map,” is represented using a two-dimensional heatmap where the
-            intensity of each pixel indicates the frequency of contact between a pair of loci.
-        </p>
-        <p class="section-para"><b>Reference:</b></p>
-        <p class="section-para">
-            Robinson JT, Turner D, Durand NC, Thorvaldsdóttir H, Mesirov JP, Aiden EL. Juicebox.js Provides a
-            Cloud-Based Visualization System for Hi-C Data. Cell Syst. 2018 Feb 28;6(2):256-258.e1.
-            <a href="https://doi.org/10.1016/j.cels.2018.01.001" target="_blank">10.1016/j.cels.2018.01.001</a>. Epub
-            2018 Feb 7. PMID: 29428417; PMCID: PMC6047755.
-        </p>
-        <p class="section-para"><b>Version: {{ all_stats_dicts['VERSIONS']['JUICEBOX_JS'] }}</b></p>
-    </div>
-    {% include 'hic/dropdown.html' %} {% include 'hic/report_contents.html' %}
+  <div class="section-para-wrapper">
+    <p class="section-para">
+      Hi-C contact mapping experiments measure the frequency of physical contact between loci in the genome. The
+      resulting dataset, called a “contact map,” is represented using a two-dimensional heatmap where the
+      intensity of each pixel indicates the frequency of contact between a pair of loci.
+    </p>
+    <p class="section-para"><b>References:</b></p>
+
+    <p class="section-para">
+      <b>fastp</b> Chen, Yanqing Zhou, Yaru Chen, Jia Gu, fastp: an ultra-fast all-in-one FASTQ preprocessor, Bioinformatics,
+      Volume 34, Issue 17, September 2018, Pages i884–i890, <a href="https://doi.org/10.1093/bioinformatics/bty560"
+        target="_blank">10.1093/bioinformatics/bty560</a>
+    </p>
+
+    <p class="section-para">
+      <b>BWA</b> Li, H. (2013). Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM. arXiv preprint <a
+        href="https://arxiv.org/abs/1303.3997" target="_blank">arXiv: 1303.3997</a>.
+    </p>
+
+    <p class="section-para">
+      <b>SAMBLASTER</b> Gregory G. Faust, Ira M. Hall, SAMBLASTER: fast duplicate marking and structural variant read extraction,
+      Bioinformatics, Volume 30, Issue 17, September 2014, Pages 2503–2505, <a
+        href="https://doi.org/10.1093/bioinformatics/btu314" target="_blank">10.1093/bioinformatics/btu314</a>
+    </p>
+
+    <p class="section-para">
+      <b>SAMtools</b> Petr Danecek, James K Bonfield, Jennifer Liddle, John Marshall, Valeriu Ohan, Martin O Pollard, Andrew Whitwham,
+      Thomas Keane, Shane A McCarthy, Robert M Davies, Heng Li, Twelve years of SAMtools and BCFtools, GigaScience,
+      Volume
+      10, Issue 2, February 2021, giab008, <a href="https://doi.org/10.1093/gigascience/giab008"
+        target="_blank">10.1093/gigascience/giab008</a>
+    </p>
+
+    <p class="section-para">
+      <b>Juicebox.js</b> Robinson JT, Turner D, Durand NC, Thorvaldsdóttir H, Mesirov JP, Aiden EL. Juicebox.js Provides a
+      Cloud-Based Visualization System for Hi-C Data. Cell Syst. 2018 Feb 28;6(2):256-258.e1.
+      <a href="https://doi.org/10.1016/j.cels.2018.01.001" target="_blank">10.1016/j.cels.2018.01.001</a>. Epub
+      2018 Feb 7. PMID: 29428417; PMCID: PMC6047755.
+    </p>
+
+    <p class="section-para"><b>Version: {{ all_stats_dicts['VERSIONS']['JUICEBOX_JS'] }}</b></p>
+  </div>
+  {% include 'hic/dropdown.html' %} {% include 'hic/report_contents.html' %}
 </div>
diff --git a/bin/report_modules/templates/hic/report_contents.html b/bin/report_modules/templates/hic/report_contents.html
@@ -8,8 +8,6 @@
     <div class="iframe-wrapper-hic">
       <iframe src="./hic/{{ all_stats_dicts['HIC'][item]['hic_html_file_name'] }}" width="700px" height="850px"></iframe>
     </div>
-  </div>
-  <div class="results-section">
     <div class="section-para-wrapper">
       <p class="section-para"><b>Sequence labels and lengths</b></p>
     </div>
@@ -22,6 +20,14 @@
     <div class="iframe-wrapper">
       <iframe src="./hic/hicqc/{{ all_stats_dicts['HIC'][item]['hicqc_report_pdf'] }}" width="100%" height="100%"></iframe>
     </div>
+    {% if all_stats_dicts['HIC'][item]['fastp_log'] is not none %}
+    <div class="section-para-wrapper">
+      <p class="section-para"><b>fastp log</b></p>
+    </div>
+    <div class="section-para-wrapper">
+      {{ all_stats_dicts['HIC'][item]['fastp_log'] }}
+    </div>
+    {% endif %}
   </div>
 </div>
 {% if vars.update({'is_first': False}) %} {% endif %} {% endfor %}
diff --git a/docs/images/fastp.png b/docs/images/fastp.png
diff --git a/docs/output.md b/docs/output.md
@@ -199,8 +199,9 @@ Kraken2 [assigns taxonomic labels](https://ccb.jhu.edu/software/kraken2/) to seq
 Hi-C contact mapping experiments measure the frequency of physical contact between loci in the genome. The resulting dataset, called a “contact map,” is represented using a [two-dimensional heatmap](https://github.com/igvteam/juicebox.js) where the intensity of each pixel indicates the frequency of contact between a pair of loci.
 
 <div align="center">
-<img src="images/hicqc.png" alt="AssemblyQC - HiC QC report" width="44.59%">
-<img src="images/hic_map.png" alt="AssemblyQC - HiC interactive contact map" width="40%">
+<img src="images/fastp.png" alt="AssemblyQC - fastp log for HiC reads" width="31%">
+<img src="images/hicqc.png" alt="AssemblyQC - HiC QC report" width="46.6%">
+<img src="images/hic_map.png" alt="AssemblyQC - HiC interactive contact map" width="50%">
 <hr>
 <em>AssemblyQC - HiC results</em>
 </div>

diff --git a/subworkflows/local/fq2hic.nf b/subworkflows/local/fq2hic.nf
@@ -34,6 +34,7 @@ workflow FQ2HIC {
         1                           // min_trimmed_reads
     )
 
+    ch_fastp_log                    = FASTQ_FASTQC_UMITOOLS_FASTP.out.trim_log
     ch_trim_reads                   = FASTQ_FASTQC_UMITOOLS_FASTP.out.reads
     ch_versions                     = ch_versions.mix(FASTQ_FASTQC_UMITOOLS_FASTP.out.versions)
 
@@ -64,7 +65,7 @@ workflow FQ2HIC {
 
     HICQC ( ch_bam_and_ref.map { meta3, bam, fa -> [ meta3, bam ] } )
 
-    ch_hicqc_pdf                   = HICQC.out.pdf
+    ch_hicqc_pdf                    = HICQC.out.pdf
     ch_versions                     = ch_versions.mix(HICQC.out.versions)
 
     // MODULE: MAKEAGPFROMFASTA | AGP2ASSEMBLY | ASSEMBLY2BEDPE
@@ -96,7 +97,8 @@ workflow FQ2HIC {
     ch_versions                     = ch_versions.mix(HIC2HTML.out.versions.first())
 
     emit:
-    hicqc_pdf                      = ch_hicqc_pdf
+    fastp_log                       = ch_fastp_log
+    hicqc_pdf                       = ch_hicqc_pdf
     hic                             = ch_hic
     html                            = HIC2HTML.out.html
     assembly                        = AGP2ASSEMBLY.out.assembly

diff --git a/workflows/assemblyqc.nf b/workflows/assemblyqc.nf
@@ -590,6 +590,7 @@ workflow ASSEMBLYQC {
         params.hic_skip_fastqc
     )
 
+    ch_hic_fastp_log                        = FQ2HIC.out.fastp_log
     ch_hicqc_pdf                            = FQ2HIC.out.hicqc_pdf
     ch_hic_html                             = FQ2HIC.out.html
     ch_hic_assembly                         = FQ2HIC.out.assembly
@@ -600,6 +601,9 @@ workflow ASSEMBLYQC {
                                             | mix(
                                                 ch_hicqc_pdf.map { meta, pdf -> pdf }
                                             )
+                                            | mix(
+                                                ch_hic_fastp_log.map { meta, log -> log }
+                                            )
     ch_versions                             = ch_versions.mix(FQ2HIC.out.versions)
 
     // SUBWORKFLOW: FASTA_SYNTENY