diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 76da7a557..ccf5aeee8 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -203,7 +203,6 @@ jobs: benchmark_strain_calling, benchmark_assembly, benchmark_mixtures, - benchmark_non_sars_cov_2, benchmark_reads, compare_assemblers, ] diff --git a/workflow/envs/ragoo.yaml b/workflow/envs/ragtag.yaml similarity index 87% rename from workflow/envs/ragoo.yaml rename to workflow/envs/ragtag.yaml index 3e3edfcd9..70be69420 100644 --- a/workflow/envs/ragoo.yaml +++ b/workflow/envs/ragtag.yaml @@ -4,4 +4,4 @@ channels: - imperial-college-research-computing - nodefaults dependencies: - - ragoo =1.1 + - ragtag =2.1 diff --git a/workflow/report/assembly_illumina.rst b/workflow/report/assembly_illumina.rst index ae9beea45..6b107cf2d 100644 --- a/workflow/report/assembly_illumina.rst +++ b/workflow/report/assembly_illumina.rst @@ -1,3 +1,3 @@ Assembly of sample {{ snakemake.wildcards.sample }}. -Reads were assembled with {{ "`metaSPAdes `_" if snakemake.params.is_amp else "`Megahit `_" }}, followed by reference based contig ordering and concatenation with `RaGOO `_. +Reads were assembled with {{ "`metaSPAdes `_" if snakemake.params.is_amp else "`Megahit `_" }}, followed by reference based contig ordering and concatenation with `RagTag `_. Then, assembly was polished by applying variants with an allele frequency of 100% (called by `Varlociraptor `_ at FDR 5%). diff --git a/workflow/report/assembly_ont.rst b/workflow/report/assembly_ont.rst index 6644f1cac..b6f96bc12 100644 --- a/workflow/report/assembly_ont.rst +++ b/workflow/report/assembly_ont.rst @@ -1,2 +1,2 @@ Assembly of sample {{ snakemake.wildcards.sample }}. -Reads were assembled with `SPAdes `_, followed by reference based contig ordering and concatenation with `RaGOO `_. +Reads were assembled with `SPAdes `_, followed by reference based contig ordering and concatenation with `RagTag `_. diff --git a/workflow/report/qc-report.rst b/workflow/report/qc-report.rst index c9983b328..967e9b428 100644 --- a/workflow/report/qc-report.rst +++ b/workflow/report/qc-report.rst @@ -1,3 +1,3 @@ QC overview for samples from {{ snakemake.wildcards.date }}. -Readcounts for raw, trimmed and filtered reads, length of initially assembled (`Megahit `_/`metaSPAdes `_) and reference ordered contigs (`RaGOO `_). +Readcounts for raw, trimmed and filtered reads, length of initially assembled (`Megahit `_/`metaSPAdes `_) and reference ordered contigs (`RagTag `_). Percentil overview for contamination in the raw reads (`kraken `_) and called COVID-19-strain including defining SNPs (`Pangolin `_) and variants of interest from variant calling (`Varlociraptor `_). diff --git a/workflow/rules/assembly.smk b/workflow/rules/assembly.smk index 08c92dbbb..7b6b9a267 100644 --- a/workflow/rules/assembly.smk +++ b/workflow/rules/assembly.smk @@ -128,17 +128,17 @@ rule order_contigs: output: temp("results/{date}/contigs/ordered-unfiltered/{sample}.fasta"), log: - "logs/{date}/ragoo/{sample}.log", + "logs/{date}/ragtag/{sample}.log", params: outdir=get_output_dir, conda: - "../envs/ragoo.yaml" + "../envs/ragtag.yaml" shadow: "minimal" shell: "(mkdir -p {params.outdir}/{wildcards.sample} && cd {params.outdir}/{wildcards.sample} &&" - " ragoo.py ../../../../../{input.contigs} ../../../../../{input.reference} &&" - " cd ../../../../../ && mv {params.outdir}/{wildcards.sample}/ragoo_output/ragoo.fasta {output})" + " ragtag.py scaffold -C -w ../../../../../{input.reference} ../../../../../{input.contigs} &&" + " cd ../../../../../ && mv {params.outdir}/{wildcards.sample}/ragtag_output/ragtag.scaffold.fasta {output})" " > {log} 2>&1" @@ -148,11 +148,11 @@ rule filter_chr0: output: temp("results/{date}/contigs/ordered/{sample}.fasta"), log: - "logs/{date}/ragoo/{sample}_cleaned.log", + "logs/{date}/ragtag/{sample}_cleaned.log", conda: "../envs/python.yaml" script: - "../scripts/ragoo-remove-chr0.py" + "../scripts/ragtag-remove-chr0.py" # polish illumina de novo assembly diff --git a/workflow/rules/benchmarking.smk b/workflow/rules/benchmarking.smk index 6f455f0ce..906353f3b 100644 --- a/workflow/rules/benchmarking.smk +++ b/workflow/rules/benchmarking.smk @@ -277,17 +277,17 @@ rule order_contigs_assembly_comparison: "results/{date}/assembly/{sample}/{assembler}/{sample}.ordered.contigs.fasta" ), log: - "logs/{date}/ragoo/{assembler}/{sample}.log", + "logs/{date}/ragtag/{assembler}/{sample}.log", params: outdir=get_output_dir, conda: - "../envs/ragoo.yaml" + "../envs/ragtag.yaml" shadow: "minimal" shell: "(cd {params.outdir} &&" - " ragoo.py ../../../../../{input.contigs} ../../../../../{input.reference} &&" - " cd ../../../../../ && mv {params.outdir}/ragoo_output/ragoo.fasta {output})" + " ragtag.py scaffold -C -w ../../../../../{input.reference} ../../../../../{input.contigs} &&" + " cd ../../../../../ && mv {params.outdir}/ragtag_output/ragtag.scaffold.fasta {output})" " > {log} 2>&1" @@ -297,7 +297,7 @@ use rule filter_chr0 as filter_chr0_assembly_comparison with: output: "results/{date}/assembly/{sample}/{assembler}/{sample}.contigs.ordered.filtered.fasta", log: - "logs/{date}/ragoo/{assembler}/{sample}_cleaned.log", + "logs/{date}/ragtag/{assembler}/{sample}_cleaned.log", use rule align_contigs as align_contigs_assembly_comparison with: diff --git a/workflow/scripts/ragoo-remove-chr0.py b/workflow/scripts/ragtag-remove-chr0.py similarity index 96% rename from workflow/scripts/ragoo-remove-chr0.py rename to workflow/scripts/ragtag-remove-chr0.py index 70a3c0384..6cb9c2509 100644 --- a/workflow/scripts/ragoo-remove-chr0.py +++ b/workflow/scripts/ragtag-remove-chr0.py @@ -14,7 +14,7 @@ def remove_chr0(data_path, out_path): - """This function removes the Chr0 contig generated by raGOO. + """This function removes the Chr0 contig generated by ragTag. It also renames the id in the FASTA file to the actual sample name. In the case where no pseudomolecule is constructed other than the Chr0, it ensures, that the FASTA fill contains a 'filler-contig' with a sequence of 'N'.