feat: Quast wrapper (#525)

* Added quast wrapper

* Fixed typos

* Added more read options

* Updated URL

* Update bio/quast/environment.yaml

Co-authored-by: Johannes Köster <johannes.koester@uni-due.de>

bio/quast/environment.yaml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - quast =5.2

bio/quast/meta.yaml

@@ -0,0 +1,31 @@
+name: QuAsT
+description: |
+  Quality Assessment Tool for Genome Assemblies
+url: https://github.com/ablab/quast
+authors:
+  - Filipe G. Vieira
+input:
+  - Sequences in FASTA format
+  - Reference genome (optional)
+  - GFF (optional)
+  - Paired end read (optional)
+  - Mate-pair reads (optional)
+  - Unpaired reads (optional)
+  - PacBio SMRT reads (optional)
+  - Oxford Nanopore reads (optional)
+  - Mapped reads against the reference in SAM/BAM (optional)
+  - Mapped reads against each of the assemblies in SAM/BAM (same order; optional)
+  - Structural variants in BEDPE (optional)
+output:
+  - Assessment summary in plain text format
+  - Tab-separated version of the summary
+  - LaTeX version of the summary
+  - Icarus main menu with links to interactive viewers
+  - PDF report of all plots combined with all tables
+  - HTML version of the report with interactive plots inside
+  - Report on misassemblies
+  - Report on unaligned and partially unaligned contigs
+  - Report on k-mer-based metrics
+  - Report on mapped reads statistics.
+notes: |
+  * The `extra` param allows for additional program arguments.

bio/quast/test/Snakefile

@@ -0,0 +1,48 @@
+rule quast:
+    input:
+        fasta="genome.fasta",
+        ref="genome.fasta",
+        #gff="annotations.gff",
+        #pe1="reads_R1.fastq",
+        #pe2="reads_R2.fastq",
+        #pe12="reads.fastq",
+        #mp1="matereads_R1.fastq",
+        #mp2="matereads_R2.fastq",
+        #mp12="matereads.fastq",
+        #single="single.fastq",
+        #pacbio="pacbio.fas",
+        #nanopore="nanopore.fastq",
+        #ref_bam="ref.bam",
+        #ref_sam="ref.sam",
+        #bam=["s1.bam","s2.bam"],
+        #sam=["s1.sam","s2.sam"],
+        #sv_bedpe="sv.bed",
+    output:
+        multiext("{sample}/report.", "html", "tex", "txt", "pdf", "tsv"),
+        multiext("{sample}/transposed_report.", "tex", "txt", "tsv"),
+        multiext(
+            "{sample}/basic_stats/",
+            "cumulative_plot.pdf",
+            "GC_content_plot.pdf",
+            "gc.icarus.txt",
+            "genome_GC_content_plot.pdf",
+            "NGx_plot.pdf",
+            "Nx_plot.pdf",
+        ),
+        multiext(
+            "{sample}/contigs_reports/",
+            "all_alignments_genome.tsv",
+            "contigs_report_genome.mis_contigs.info",
+            "contigs_report_genome.stderr",
+            "contigs_report_genome.stdout",
+        ),
+        "{sample}/contigs_reports/minimap_output/genome.coords_tmp",
+        "{sample}/icarus.html",
+        "{sample}/icarus_viewers/contig_size_viewer.html",
+        "{sample}/quast.log",
+    log:
+        "logs/{sample}.quast.log",
+    params:
+        extra="--min-contig 5 --min-identity 95.0",
+    wrapper:
+        "master/bio/quast"

bio/quast/test/genome.fasta

@@ -0,0 +1,2 @@
+>Sheila
+GCTAGCTCAGAAAAAAAAAA

bio/quast/wrapper.py

@@ -0,0 +1,75 @@
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2022, Filipe G. Vieira"
+__license__ = "MIT"
+
+
+import os
+from snakemake.shell import shell
+
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+ref = snakemake.input.get("ref", "")
+if ref:
+    ref = f"-r {ref}"
+
+gff = snakemake.input.get("gff", "")
+if gff:
+    gff = f"--features {gff}"
+
+pe1 = snakemake.input.get("pe1", "")
+if pe1:
+    pe1 = f"--pe1 {pe1}"
+pe2 = snakemake.input.get("pe2", "")
+if pe2:
+    pe2 = f"--pe2 {pe2}"
+pe12 = snakemake.input.get("pe12", "")
+if pe12:
+    pe12 = f"--pe12 {pe12}"
+mp1 = snakemake.input.get("mp1", "")
+if mp1:
+    mp1 = f"--mp1 {mp1}"
+mp2 = snakemake.input.get("mp2", "")
+if mp2:
+    mp2 = f"--mp2 {mp2}"
+mp12 = snakemake.input.get("mp12", "")
+if mp12:
+    mp12 = f"--mp12 {mp12}"
+single = snakemake.input.get("single", "")
+if single:
+    single = f"--single {single}"
+pacbio = snakemake.input.get("pacbio", "")
+if pacbio:
+    pacbio = f"--pacbio {pacbio}"
+nanopore = snakemake.input.get("nanopore", "")
+if nanopore:
+    nanopore = f"--nanopore {nanopore}"
+ref_bam = snakemake.input.get("ref_bam", "")
+if ref_bam:
+    ref_bam = f"--ref-bam {ref_bam}"
+ref_sam = snakemake.input.get("ref_sam", "")
+if ref_sam:
+    ref_sam = f"--ref-sam {ref_sam}"
+bam = snakemake.input.get("bam", "")
+if bam:
+    if isinstance(bam, list):
+        bam = ",".join(bam)
+    bam = f"--bam {bam}"
+sam = snakemake.input.get("sam", "")
+if sam:
+    if isinstance(sam, list):
+        sam = ",".join(sam)
+    sam = f"--sam {sam}"
+sv_bedpe = snakemake.input.get("sv_bedpe", "")
+if sv_bedpe:
+    sv_bedpe = f"--sv-bedpe {sv_bedpe}"
+
+
+output_dir = os.path.commonpath(snakemake.output)
+
+
+shell(
+    "quast --threads {snakemake.threads} {ref} {gff} {pe1} {pe2} {pe12} {mp1} {mp2} {mp12} {single} {pacbio} {nanopore} {ref_bam} {ref_sam} {bam} {sam} {sv_bedpe} {extra} -o {output_dir} {snakemake.input.fasta} {log}"
+)

test.py

@@ -139,6 +139,15 @@ def run(wrapper, cmd, check_log=None):
             os.chdir(origdir)
 
 
+
+@skip_if_not_modified
+def test_quast():
+    run(
+        "bio/quast",
+        ["snakemake", "--cores", "1", "a/quast.log", "--use-conda", "-F"],
+    )
+
+
 @skip_if_not_modified
 def test_gfatools():
     run(