Merge pull request #145 from Plant-Food-Research-Open/add/gfastats

Added gfastats

CHANGELOG.md

@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+1. Added Gfastats [#126](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/126)
+
 ### `Fixed`
 
 ### `Dependencies`
@@ -16,8 +18,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Deprecated`
 
-1. Reduced the GenomeTools stats figures to 300 DPI
-2. Now `synteny_mummer_min_bundle_size` is set to `1000000` by default
+1. Reduced the GenomeTools stats figures to 300 DPI [#142](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/142)
+2. Now `synteny_mummer_min_bundle_size` is set to `1000000` by default [#142](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/142)
 
 ## v2.1.1 - [20-Sep-2024]
 

CITATIONS.md

@@ -36,6 +36,10 @@
   >
   > Forked from: <https://github.com/ucdavis-bioinformatics/assemblathon2-analysis>
 
+- GFASTATS, [MIT](https://github.com/vgl-hub/gfastats/blob/main/LICENSE)
+
+  > Giulio Formenti, Linelle Abueg, Angelo Brajuka, Nadolina Brajuka, Cristóbal Gallardo-Alba, Alice Giani, Olivier Fedrigo, Erich D Jarvis, Gfastats: conversion, evaluation and manipulation of genome sequences using assembly graphs, Bioinformatics, Volume 38, Issue 17, September 2022, Pages 4214–4216, <https://doi.org/10.1093/bioinformatics/btac460>
+
 - BUSCO, [MIT](https://gitlab.com/ezlab/busco/-/blob/master/LICENSE)
 
   > Manni M, Berkeley MR, Seppey M, Simão FA, Zdobnov EM. 2021. BUSCO Update: Novel and Streamlined Workflows along with Broader and Deeper Phylogenetic Coverage for Scoring of Eukaryotic, Prokaryotic, and Viral Genomes, Molecular Biology and Evolution, Volume 38, Issue 10, October 2021, Pages 4647–4654, <https://doi.org/10.1093/molbev/msab199>

README.md

@@ -42,7 +42,7 @@ flowchart LR
 
   VALIDATE_FORMAT ==> GFF_STATS[<span style="white-space: nowrap;">GENOMETOOLS GT STAT</span>]
 
-  Run ==> ASS_STATS[<span style="white-space: nowrap;">ASSEMBLATHON STATS</span>]
+  Run ==> ASS_STATS[<span style="white-space: nowrap;">STATS</span>]
   Run ==> BUSCO
   Run ==> TIDK
   Run ==> LAI
@@ -72,7 +72,7 @@ flowchart LR
 
 - [FASTA VALIDATOR](https://github.com/linsalrob/fasta_validator) + [SEQKIT RMDUP](https://github.com/shenwei356/seqkit): FASTA validation
 - [GENOMETOOLS GT GFF3VALIDATOR](https://genometools.org/tools/gt_gff3validator.html): GFF3 validation
-- [ASSEMBLATHON STATS](https://github.com/PlantandFoodResearch/assemblathon2-analysis/blob/a93cba25d847434f7eadc04e63b58c567c46a56d/assemblathon_stats.pl): Assembly statistics
+- [ASSEMBLATHON STATS](https://github.com/PlantandFoodResearch/assemblathon2-analysis/blob/a93cba25d847434f7eadc04e63b58c567c46a56d/assemblathon_stats.pl), [GFASTATS](https://github.com/vgl-hub/gfastats): Assembly statistics
 - [GENOMETOOLS GT STAT](https://genometools.org/tools/gt_stat.html): Annotation statistics
 - [NCBI FCS ADAPTOR](https://github.com/ncbi/fcs): Adaptor contamination pass/fail
 - [NCBI FCS GX](https://github.com/ncbi/fcs): Foreign organism contamination pass/fail

bin/assemblyqc.py

@@ -16,6 +16,9 @@
 from report_modules.parsers.assemblathon_stats_parser import (
     parse_assemblathon_stats_folder,
 )
+from report_modules.parsers.gfastats_parser import (
+    parse_gfastats_folder,
+)
 from report_modules.parsers.genometools_gt_stat_parser import (
     parse_genometools_gt_stat_folder,
 )
@@ -41,6 +44,7 @@
     data_from_tools = {**data_from_tools, **parse_ncbi_fcs_adaptor_folder()}
     data_from_tools = {**data_from_tools, **parse_ncbi_fcs_gx_folder()}
     data_from_tools = {**data_from_tools, **parse_assemblathon_stats_folder()}
+    data_from_tools = {**data_from_tools, **parse_gfastats_folder()}
     data_from_tools = {**data_from_tools, **parse_genometools_gt_stat_folder()}
     data_from_tools = {**data_from_tools, **parse_busco_folder()}
     data_from_tools = {

bin/report_modules/parsers/gfastats_parser.py

@@ -0,0 +1,46 @@
+import os
+from pathlib import Path
+import pandas as pd
+from tabulate import tabulate
+import re
+
+from report_modules.parsers.parsing_commons import sort_list_of_results
+
+
+def parse_gfastats_folder(folder_name="gfastats"):
+    dir = os.getcwdb().decode()
+    reports_folder_path = Path(f"{dir}/{folder_name}")
+
+    if not os.path.exists(reports_folder_path):
+        return {}
+
+    list_of_report_files = reports_folder_path.glob("*.assembly_summary")
+
+    data = {"GFASTATS": []}
+
+    for report_path in list_of_report_files:
+        report_table = pd.read_csv(report_path, sep="\t")
+        report_table.columns = ['Stat', 'Value']
+
+        file_tokens = re.findall(
+            r"([\w]+).assembly_summary",
+            os.path.basename(str(report_path)),
+        )[0]
+
+        data["GFASTATS"].append(
+            {
+                "hap": file_tokens,
+                "report_table": report_table.to_dict("records"),
+                "report_table_html": tabulate(
+                    report_table,
+                    headers=["Stat", "Value"],
+                    tablefmt="html",
+                    numalign="left",
+                    showindex=False,
+                ),
+            }
+        )
+
+    return {
+        "GFASTATS": sort_list_of_results(data["GFASTATS"], "hap")
+    }

bin/report_modules/templates/base.html

@@ -32,6 +32,10 @@
     <button class="tablinks active" onclick="openTool(event, 'ASSEMBLATHON_STATS')">ASSEMBLATHON STATS</button>
     {% endif %}
 
+    {% if 'GFASTATS' in all_stats_dicts %}
+    <button class="tablinks active" onclick="openTool(event, 'GFASTATS')">GFASTATS</button>
+    {% endif %}
+
     {% if 'GENOMETOOLS_GT_STAT' in all_stats_dicts %}
     <button class="tablinks active" onclick="openTool(event, 'GENOMETOOLS_GT_STAT')">GENOMETOOLS GT STAT</button>
     {% endif %}
@@ -100,6 +104,10 @@
   {% include 'assemblathon_stats/assemblathon_stats.html' %}
   {% endif %}
 
+  {% if 'GFASTATS' in all_stats_dicts %}
+  {% include 'gfastats/gfastats.html' %}
+  {% endif %}
+
   {% if 'GENOMETOOLS_GT_STAT' in all_stats_dicts %}
   {% include 'genometools_gt_stat/genometools_gt_stat.html' %}
   {% endif %}

bin/report_modules/templates/gfastats/dropdown.html

@@ -0,0 +1,10 @@
+<div class="dropdown">
+    <div class="dropdown_content">
+        <select id="selector_GFASTATS" onchange="showContent('GFASTATS')">
+            {% set str_hap = 'hap' %} {% for item in range(all_stats_dicts["GFASTATS"]|length) %}
+            <option value="tabcontent_GFASTATS_{{all_stats_dicts['GFASTATS'][item]['hap']}}">
+                {{ all_stats_dicts['GFASTATS'][item][str_hap] }} {% endfor %}
+            </option>
+        </select>
+    </div>
+</div>

bin/report_modules/templates/gfastats/gfastats.html

@@ -0,0 +1,16 @@
+<div id="GFASTATS" class="tabcontent" style="display: none">
+  <div class="section-para-wrapper">
+    <p class="section-para">A fast and exhaustive tool for summary statistics.</p>
+    <p class="section-para"><b>Reference:</b></p>
+    <p class="section-para">
+      Giulio Formenti, Linelle Abueg, Angelo Brajuka, Nadolina Brajuka, Cristóbal Gallardo-Alba, Alice Giani, Olivier
+      Fedrigo, Erich D Jarvis, Gfastats: conversion, evaluation and manipulation of genome sequences using assembly
+      graphs, Bioinformatics, Volume 38, Issue 17, September 2022, Pages 4214–4216,
+      <a href="https://doi.org/10.1093/bioinformatics/btac460" target="_blank">10.1093/bioinformatics/btac460</a>
+    </p>
+    <p class="section-para">
+      <b>Version: {{ all_stats_dicts['VERSIONS']['GFASTATS']['gfastats'] }}</b>
+    </p>
+  </div>
+  {% include 'gfastats/dropdown.html' %} {% include 'gfastats/report_contents.html' %}
+</div>

bin/report_modules/templates/gfastats/report_contents.html

@@ -0,0 +1,17 @@
+{% set vars = {'is_first': True} %} {% for item in range(all_stats_dicts["GFASTATS"]|length) %} {% set
+active_text = 'display: block' if vars.is_first else 'display: none' %}
+<div
+    id="tabcontent_GFASTATS_{{ all_stats_dicts['GFASTATS'][item]['hap'] }}"
+    class="tabcontent-GFASTATS"
+    style="{{ active_text }}"
+>
+    <div class="results-section">
+        <div class="section-heading-wrapper">
+            <div class="section-heading">{{ all_stats_dicts['GFASTATS'][item]['hap'] }}</div>
+        </div>
+    </div>
+    <div class="table-outer">
+        <div class="table-wrapper">{{ all_stats_dicts['GFASTATS'][item]['report_table_html'] }}</div>
+    </div>
+</div>
+{% if vars.update({'is_first': False}) %} {% endif %} {% endfor %}

conf/modules.config

@@ -50,6 +50,16 @@ process {
         ]
     }
 
+    withName: GFASTATS {
+        ext.args = '--stats -t --nstar-report'
+        publishDir = [
+            path: { "${params.outdir}/gfastats" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals("versions.yml") ? null : filename },
+            pattern: '*.assembly_summary'
+        ]
+    }
+
     withName: FCS_FCSADAPTOR {
         ext.args = params.ncbi_fcs_adaptor_empire ? "--${params.ncbi_fcs_adaptor_empire}" : '--prok'
 

conf/test_full.config

@@ -16,6 +16,8 @@ params {
 
     input                       = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheetv2.csv'
 
+    gfastats_skip               = false
+
     ncbi_fcs_adaptor_skip       = false
     ncbi_fcs_adaptor_empire     = 'euk'
 

docs/output.md

@@ -14,7 +14,8 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 - [FASTA and GFF3 validation](#fasta-and-gff3-validation)
 - [Assemblathon stats](#assemblathon-stats)
-- [Genometools gt stat](#genometools-gt-stat)
+- [Gfastats](#gfastats)
+- [GenomeTools gt stat](#genometools-gt-stat)
 - [NCBI FCS adaptor](#ncbi-fcs-adaptor)
 - [NCBI FCS GX](#ncbi-fcs-gx)
 - [BUSCO](#busco)
@@ -45,7 +46,19 @@ The pipeline prints a warning in the pipeline log if FASTA or GFF3 validation fa
 > [!WARNING]
 > Contig-related stats are based on the assumption that `assemblathon_stats_n_limit` is specified correctly. If you are not certain of the value of `assemblathon_stats_n_limit`, please ignore the contig-related stats.
 
-### Genometools gt stat
+### Gfastats
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `gfastats/`
+  - `*.assembly_summary`: Assembly stats in TSV format.
+
+</details>
+
+Gfastats is a fast and exhaustive tool for summary statistics.
+
+### GenomeTools gt stat
 
 <details markdown="1">
 <summary>Output files</summary>

docs/parameters.md

@@ -21,6 +21,7 @@ A Nextflow pipeline which evaluates assembly quality with multiple QC tools and
 | Parameter                    | Description                                                             | Type      | Default | Required | Hidden |
 | ---------------------------- | ----------------------------------------------------------------------- | --------- | ------- | -------- | ------ |
 | `assemblathon_stats_n_limit` | The number of 'N's for the unknown gap size. NCBI recommendation is 100 | `integer` | 100     |          |        |
+| `gfastats_skip`              | Skip Gfastats                                                           | `boolean` | True    |          |        |
 
 ## NCBI FCS options
 

modules.json

@@ -165,6 +165,11 @@
                         "git_sha": "06c8865e36741e05ad32ef70ab3fac127486af48",
                         "installed_by": ["modules"]
                     },
+                    "gfastats": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "gunzip": {
                         "branch": "master",
                         "git_sha": "06c8865e36741e05ad32ef70ab3fac127486af48",

modules/local/createreport.nf

@@ -10,6 +10,7 @@ process CREATEREPORT {
     path ncbi_fcs_adaptor_reports   , stageAs: 'ncbi_fcs_adaptor_reports/*'
     path fcs_gx_reports             , stageAs: 'fcs_gx_reports/*'
     path assemblathon_stats         , stageAs: 'assemblathon_stats/*'
+    path gfastats                   , stageAs: 'gfastats/*'
     path genometools_gt_stats       , stageAs: 'genometools_gt_stat/*'
     path busco_outputs              , stageAs: 'busco_outputs/*'
     path busco_gff_outputs          , stageAs: 'busco_gff_outputs/*'