From c5f47bb55914b1109ebf0479c2f80fd4e008edb3 Mon Sep 17 00:00:00 2001 From: Lili Andersson-Li <64467552+LilyAnderssonLee@users.noreply.github.com> Date: Tue, 2 Jul 2024 14:24:55 +0200 Subject: [PATCH 1/6] add output files to tower.yml --- docs/output.md | 2 +- tower.yml | 134 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 133 insertions(+), 3 deletions(-) diff --git a/docs/output.md b/docs/output.md index 59f50cb0..edc90bd2 100644 --- a/docs/output.md +++ b/docs/output.md @@ -227,7 +227,7 @@ The resulting `.fastq` files may _not_ always be the 'final' reads that go into Output files - `filtlong/` - - `_filtered.fastq.gz`: Quality or short read data filtered file + - `_filtered.fastq.gz`: Quality or long read data filtered file - `_filtered.log`: log file containing summary statistics diff --git a/tower.yml b/tower.yml index 787aedfe..f71f88fc 100644 --- a/tower.yml +++ b/tower.yml @@ -1,5 +1,135 @@ reports: multiqc_report.html: display: "MultiQC HTML report" - samplesheet.csv: - display: "Auto-created samplesheet with collated metadata and FASTQ paths" + "**/untar/database/": + display: "A directory containing contents of the decompressed archive. It will only be present if `--save_untarred_databases` is supplied." + "**/{fastqc,falco}/{raw,preprocessed}/*.html": + display: "A FastQC or Falco report contains quality metrics in HTML format." + "**/{fastqc,falco}/{raw,preprocessed}/*.txt": + display: "A FastQC or Falco report containing quality metrics in TXT format." + "**/fastqc/{raw,preprocessed}/*.zip": + display: "A zip archive contains the FastQC report, tab-delimited data file and plot images." + "**/fastp/*.fastp.fastq.gz": + display: "A file with the trimmed unmerged fastq reads." + "**/fastp/*.merged.fastq.gz": + display: "A file with the reads that were successfully merged." + "**/fastp/*.{log,html,json}": + display: "Log files in different formats." + "**/porechop/*.log": + display: "A log file containing trimming statistics." + "**/porechop/*.fastq.gz": + display: "Adapter-trimmed fastq files." + "**/bbduk/*.bbduk.log": + display: "A log file containing filtering statistics." + "**/bbduk/*.fastq.gz": + display: "Resulting FASTQ file without low-complexity reads." + "**/filtlong/*_filtered.log": + display: "A log file containing summary statistics." + "**/filtlong/*_filtered.fastq.gz": + display: "A quality or long read data filtered file." + "**/bowtie2/build/*.bt2": + display: "Bowtie2 indicies of reference genome, only if `--save_hostremoval_index` supplied." + "**/bowtie2/align/*.bam": + display: "A bam file containing reads that aligned against the user-supplied reference genome as well as unmapped reads." + "**/bowtie2/align/*.bowtie2.log": + display: "A log file about the mapped reads." + "**/bowtie2/align/*.unmapped.fastq.gz": + display: "A FASTQ file containing off-target reads from the mapping that is used in downstream steps." + "**/minimap2/build/*.mmi2": + display: "minimap2 indices of reference genome, only if `--save_hostremoval_index` supplied." + "**/minimap2/align/*.bam": + display: "A alignment file in BAM format containing both mapped and unmapped reads." + "**/samtools/stats/*_interleaved.fq.gz": + display: "Unmapped reads only in FASTQ gzip format." + "**/samtools/stats/*.stats": + display: "A file containing samtools stats output." + "**/analysis_ready_fastqs/": + display: "A results directory will contain the 'final' processed reads used as input for classification/profiling. This optional results directory will only be present in the pipeline results when supplying `--save_analysis_ready_reads`." + "**/bracken/*_combined_reports.txt": + display: "Combined bracken results as output from Bracken's `combine_bracken_outputs.py` script." + "**/bracken/*/*.tsv": + display: "A TSV file containing per-sample summary of Bracken results with abundance information." + "**/bracken/*/*report_bracken_species.txt": + display: "A Kraken2 style report with Bracken abundance information." + "**/kraken2/kraken2_*_combined_reports.txt": + display: "A combined profile of all samples aligned to a given database (as generated by `krakentools`)." + "**/kraken2/*/*.kraken2.report.txt": + display: "A Kraken2 report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits in the Kraken2 run for a given sample. Will be 6 column rather than 8 if `--save_minimizers` specified." + "**/kraken2/*/*.kraken2.classifiedreads.txt": + display: "A list of read IDs and the hits each read had against each database for a given sample." + "**/kraken2/*/*.classified.fastq.gz": + display: "A FASTQ file containing all reads that mapped to a reference in the database for a specific sample." + "**/kraken2/*/*.unclassified.fastq.gz": + display: "A FASTQ file containing all reads that did not have a hit in the database for a given sample." + "**/krakenuniq/*.krakenuniq.report.txt": + display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits, with an additional column for k-mer coverage, that allows for more accurate distinguishing between false-positive/true-postitive hits." + "**/krakenuniq/*.classified.fast{a,q}.gz": + display: "An optional FASTA file containing all reads that had a hit against a reference in the database for a given sample. Paired-end input reads are merged in this output." + "**/krakenuniq/*.unclassified.fast{a,q}.gz": + display: "An optional FASTA file containing all reads that did not have a hit in the database for a given sample. Paired-end input reads are merged in this output." + "**/krakenuniq/*.krakenuniq.classified.txt": + display: "An optional list of read IDs and the hits each read had against each database for a given sample." + "**/centrifuge/*_combined_reports.txt": + display: "A combined profile of all samples aligned to a given database (as generated by `centrifuge-kreport`)." + "**/centrifuge/*/*.centrifuge.report.txt": + display: "A classification report that summarises the taxonomic ID, the taxonomic rank, length of genome sequence, number of classified and uniquely classified reads." + "**/centrifuge/*/*.centrifuge.results.txt": + display: "A file that summarises the classification assignment for a read, i.e read ID, sequence ID, score for the classification, score for the next best classification, number of classifications for this read." + "**/centrifuge/*/*.centrifuge.txt": + display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of k-mers, taxonomic path of all the hits in the centrifuge run for a given sample." + "**/centrifuge/*/*.mapped.fastq.gz": + display: "FASTQ files containing all mapped reads." + "**/centrifuge/*/*.unmapped.fastq.gz": + display: "FASTQ files containing all unmapped reads." + "**/diamond/*/*.{blast,xml,txt,daa,sam,tsv,paf}": + display: "A file containing alignment information in various formats, or taxonomic information in a text-based format. Exact output depends on user choice." + "**/ganon/*_combined_reports.txt": + display: "A combined profile of all samples aligned to a given database (as generated by `ganon table`)." + "**/ganon/*/*.ganon.all": + display: "A per-read summary of all hits of each reads." + "**/ganon/*/*.ganon.lca": + display: "A per-read summary of the best single hit after LCA for each read." + "**/ganon/*/*.ganon.rep": + display: "A 'raw' report of counts against each taxon." + "**/ganon/*/*.ganon.tre": + display: "Output of `ganon report` containing taxonomic classifications with possible formatting and/or filtering depending on options specified." + "**/ganon/*/*.ganon.unc": + display: "A list of read IDs with no hits." + "**/ganon/*/*.ganon_report.tre": + display: "Output of `ganon report` containing taxonomic classifications with possible formatting and/or filtering depending on options specified." + "**/kaiju/*_combined_reports.txt": + display: "A combined profile of all samples aligned to a given database (as generated by kaiju2table)" + "**/kaiju/*/*.kaiju.tsv": + display: "Raw output from Kaiju with taxonomic rank, read ID and taxonic ID" + "**/kaiju/*/*.kaijutable.txt": + display: "Summarised Kaiju output with fraction abundance, taxonomic ID, number of reads, and taxonomic names (as generated by `kaiju2table`)" + "**/kmcp/*/*.kmcp.profile": + display: "Output of `kmcp_profile` containing the taxonomic profile from search results." + "**/kmcp/*/*.kmcp_search.gz": + display: "Output of `kmcp_search` containing search sequences against a database in tab-delimited format with 15 columns." + "**/krona/*.html": + display: "Per-tool/per-database interactive HTML file containing hierarchical piecharts." + "**/malt/*/*.rma6": + display: "A binary file containing all alignments and taxonomic information of hits that can be loaded into the MEGAN6." + "**/malt/*/*.txt.gz": + display: "A text file containing taxonomic IDs and read counts against each taxon. Generated by MEGAN6 companion tool `rma2info`." + "**/malt/*/*.megan": + display: "A summary file that can be loaded into the MEGAN6." + "**/malt/*/*.blastn.sam": + display: "A sparse SAM file containing alignments of each hit." + "**/metaphlan/*/*_combined_reports.txt": + display: "A combined profile of all samples aligned to a given database (as generated by `metaphlan_merge_tables`)." + "**/metaphlan/*/*.biom": + display: "A taxonomic profile in BIOM format." + "**/metaphlan/*/*.bowtie2out.txt": + display: "BowTie2 alignment information (can be re-used for skipping alignment when re-running MetaPhlAn with different parameters)." + "**/metaphlan/*/*_profile.txt": + display: "A MetaPhlAn taxonomic profile including abundance estimates." + "**/motus/*/*_combined_reports.txt": + display: "A combined profile of all samples aligned to a given database (as generated by `motus_merge`)." + "**/motus/*/*.log": + display: "A log file that contains summary statistics." + "**/motus/*/*.out": + display: "A classification file that summarises taxonomic identifiers, by default at the rank of mOTUs (i.e., species level), and their relative abundances in the profiled sample." + "**/taxpasta/*tsv": + display: "Standardised taxon table containing multiple samples. The first column describes the taxonomy ID and the rest of the columns describe the read counts for each sample." From e65ccd26af13300437035b4388b99ffc7d2a372f Mon Sep 17 00:00:00 2001 From: Lili Andersson-Li <64467552+LilyAnderssonLee@users.noreply.github.com> Date: Tue, 2 Jul 2024 14:31:02 +0200 Subject: [PATCH 2/6] update changelog --- CHANGELOG.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 680c5047..6dda53a8 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,7 +8,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### `Added` - [#417](https://github.com/nf-core/taxprofiler/pull/417) - Added reference-free metagenome estimation with Nonpareil (added by @jfy133) -- [#466](https://github.com/nf-core/taxprofiler/pull/466) - Input database sheets now require a `db_type` column to distinguish between short- and long-read databases +- [#466](https://github.com/nf-core/taxprofiler/pull/466) - Input database sheets now require a `db_type` column to distinguish between short- and long-read databases (added by @LilyAnderssonLee) +- [#505](https://github.com/nf-core/taxprofiler/pull/505) - Add output files information to the file `tower.yml` (added by @LilyAnderssonLee) ## v1.1.8dev - Augmented Akita Patch [] From f91562eb1452af4aa7724157fac7f9a7b38303f3 Mon Sep 17 00:00:00 2001 From: Lili Andersson-Li <64467552+LilyAnderssonLee@users.noreply.github.com> Date: Wed, 3 Jul 2024 09:54:53 +0200 Subject: [PATCH 3/6] delete non-supported files in tower.yml --- tower.yml | 106 ++++++++++-------------------------------------------- 1 file changed, 19 insertions(+), 87 deletions(-) diff --git a/tower.yml b/tower.yml index f71f88fc..d2f84211 100644 --- a/tower.yml +++ b/tower.yml @@ -1,50 +1,24 @@ reports: multiqc_report.html: display: "MultiQC HTML report" - "**/untar/database/": - display: "A directory containing contents of the decompressed archive. It will only be present if `--save_untarred_databases` is supplied." - "**/{fastqc,falco}/{raw,preprocessed}/*.html": - display: "A FastQC or Falco report contains quality metrics in HTML format." - "**/{fastqc,falco}/{raw,preprocessed}/*.txt": - display: "A FastQC or Falco report containing quality metrics in TXT format." - "**/fastqc/{raw,preprocessed}/*.zip": - display: "A zip archive contains the FastQC report, tab-delimited data file and plot images." - "**/fastp/*.fastp.fastq.gz": - display: "A file with the trimmed unmerged fastq reads." - "**/fastp/*.merged.fastq.gz": - display: "A file with the reads that were successfully merged." - "**/fastp/*.{log,html,json}": - display: "Log files in different formats." - "**/porechop/*.log": - display: "A log file containing trimming statistics." - "**/porechop/*.fastq.gz": - display: "Adapter-trimmed fastq files." - "**/bbduk/*.bbduk.log": - display: "A log file containing filtering statistics." - "**/bbduk/*.fastq.gz": - display: "Resulting FASTQ file without low-complexity reads." - "**/filtlong/*_filtered.log": - display: "A log file containing summary statistics." - "**/filtlong/*_filtered.fastq.gz": - display: "A quality or long read data filtered file." - "**/bowtie2/build/*.bt2": - display: "Bowtie2 indicies of reference genome, only if `--save_hostremoval_index` supplied." - "**/bowtie2/align/*.bam": - display: "A bam file containing reads that aligned against the user-supplied reference genome as well as unmapped reads." - "**/bowtie2/align/*.bowtie2.log": - display: "A log file about the mapped reads." - "**/bowtie2/align/*.unmapped.fastq.gz": - display: "A FASTQ file containing off-target reads from the mapping that is used in downstream steps." - "**/minimap2/build/*.mmi2": - display: "minimap2 indices of reference genome, only if `--save_hostremoval_index` supplied." - "**/minimap2/align/*.bam": - display: "A alignment file in BAM format containing both mapped and unmapped reads." - "**/samtools/stats/*_interleaved.fq.gz": - display: "Unmapped reads only in FASTQ gzip format." - "**/samtools/stats/*.stats": - display: "A file containing samtools stats output." - "**/analysis_ready_fastqs/": - display: "A results directory will contain the 'final' processed reads used as input for classification/profiling. This optional results directory will only be present in the pipeline results when supplying `--save_analysis_ready_reads`." + "**/fastqc/raw/*.html": + display: "A FastQC report contains quality metrics of raw reads in HTML format." + "**/fastqc/raw/*.txt": + display: "A FastQC report containing quality metrics of raw reads in TXT format." + "**/fastqc/preprocessed/*.html": + display: "A FastQC report contains quality metrics of processed reads in HTML format." + "**/fastqc/preprocessed/*.txt": + display: "A FastQC report containing quality metrics of processed reads in TXT format." + "**/falco/raw/*.html": + display: "A Falco report contains quality metrics of raw reads in HTML format." + "**/falco/raw/*.txt": + display: "A Falco report containing quality metrics of raw reads in TXT format." + "**/falco/preprocessed/*.html": + display: "A Falco report contains quality metrics of raw reads in HTML format." + "**/falco/preprocessed/*.txt": + display: "A Falco report containing quality metrics of raw reads in TXT format." + "**/fastp/*.html": + display: "A Log file in HTML format." "**/bracken/*_combined_reports.txt": display: "Combined bracken results as output from Bracken's `combine_bracken_outputs.py` script." "**/bracken/*/*.tsv": @@ -57,16 +31,8 @@ reports: display: "A Kraken2 report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits in the Kraken2 run for a given sample. Will be 6 column rather than 8 if `--save_minimizers` specified." "**/kraken2/*/*.kraken2.classifiedreads.txt": display: "A list of read IDs and the hits each read had against each database for a given sample." - "**/kraken2/*/*.classified.fastq.gz": - display: "A FASTQ file containing all reads that mapped to a reference in the database for a specific sample." - "**/kraken2/*/*.unclassified.fastq.gz": - display: "A FASTQ file containing all reads that did not have a hit in the database for a given sample." "**/krakenuniq/*.krakenuniq.report.txt": display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits, with an additional column for k-mer coverage, that allows for more accurate distinguishing between false-positive/true-postitive hits." - "**/krakenuniq/*.classified.fast{a,q}.gz": - display: "An optional FASTA file containing all reads that had a hit against a reference in the database for a given sample. Paired-end input reads are merged in this output." - "**/krakenuniq/*.unclassified.fast{a,q}.gz": - display: "An optional FASTA file containing all reads that did not have a hit in the database for a given sample. Paired-end input reads are merged in this output." "**/krakenuniq/*.krakenuniq.classified.txt": display: "An optional list of read IDs and the hits each read had against each database for a given sample." "**/centrifuge/*_combined_reports.txt": @@ -77,59 +43,25 @@ reports: display: "A file that summarises the classification assignment for a read, i.e read ID, sequence ID, score for the classification, score for the next best classification, number of classifications for this read." "**/centrifuge/*/*.centrifuge.txt": display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of k-mers, taxonomic path of all the hits in the centrifuge run for a given sample." - "**/centrifuge/*/*.mapped.fastq.gz": - display: "FASTQ files containing all mapped reads." - "**/centrifuge/*/*.unmapped.fastq.gz": - display: "FASTQ files containing all unmapped reads." - "**/diamond/*/*.{blast,xml,txt,daa,sam,tsv,paf}": + "**/diamond/*/*.tsv": display: "A file containing alignment information in various formats, or taxonomic information in a text-based format. Exact output depends on user choice." "**/ganon/*_combined_reports.txt": display: "A combined profile of all samples aligned to a given database (as generated by `ganon table`)." - "**/ganon/*/*.ganon.all": - display: "A per-read summary of all hits of each reads." - "**/ganon/*/*.ganon.lca": - display: "A per-read summary of the best single hit after LCA for each read." - "**/ganon/*/*.ganon.rep": - display: "A 'raw' report of counts against each taxon." - "**/ganon/*/*.ganon.tre": - display: "Output of `ganon report` containing taxonomic classifications with possible formatting and/or filtering depending on options specified." - "**/ganon/*/*.ganon.unc": - display: "A list of read IDs with no hits." - "**/ganon/*/*.ganon_report.tre": - display: "Output of `ganon report` containing taxonomic classifications with possible formatting and/or filtering depending on options specified." "**/kaiju/*_combined_reports.txt": display: "A combined profile of all samples aligned to a given database (as generated by kaiju2table)" "**/kaiju/*/*.kaiju.tsv": display: "Raw output from Kaiju with taxonomic rank, read ID and taxonic ID" "**/kaiju/*/*.kaijutable.txt": display: "Summarised Kaiju output with fraction abundance, taxonomic ID, number of reads, and taxonomic names (as generated by `kaiju2table`)" - "**/kmcp/*/*.kmcp.profile": - display: "Output of `kmcp_profile` containing the taxonomic profile from search results." - "**/kmcp/*/*.kmcp_search.gz": - display: "Output of `kmcp_search` containing search sequences against a database in tab-delimited format with 15 columns." "**/krona/*.html": display: "Per-tool/per-database interactive HTML file containing hierarchical piecharts." - "**/malt/*/*.rma6": - display: "A binary file containing all alignments and taxonomic information of hits that can be loaded into the MEGAN6." - "**/malt/*/*.txt.gz": - display: "A text file containing taxonomic IDs and read counts against each taxon. Generated by MEGAN6 companion tool `rma2info`." - "**/malt/*/*.megan": - display: "A summary file that can be loaded into the MEGAN6." - "**/malt/*/*.blastn.sam": - display: "A sparse SAM file containing alignments of each hit." "**/metaphlan/*/*_combined_reports.txt": display: "A combined profile of all samples aligned to a given database (as generated by `metaphlan_merge_tables`)." - "**/metaphlan/*/*.biom": - display: "A taxonomic profile in BIOM format." "**/metaphlan/*/*.bowtie2out.txt": display: "BowTie2 alignment information (can be re-used for skipping alignment when re-running MetaPhlAn with different parameters)." "**/metaphlan/*/*_profile.txt": display: "A MetaPhlAn taxonomic profile including abundance estimates." "**/motus/*/*_combined_reports.txt": display: "A combined profile of all samples aligned to a given database (as generated by `motus_merge`)." - "**/motus/*/*.log": - display: "A log file that contains summary statistics." - "**/motus/*/*.out": - display: "A classification file that summarises taxonomic identifiers, by default at the rank of mOTUs (i.e., species level), and their relative abundances in the profiled sample." "**/taxpasta/*tsv": display: "Standardised taxon table containing multiple samples. The first column describes the taxonomy ID and the rest of the columns describe the read counts for each sample." From 72978f343502d7629cf26a579e64a5c55a0ab3d0 Mon Sep 17 00:00:00 2001 From: Lili Andersson-Li <64467552+LilyAnderssonLee@users.noreply.github.com> Date: Wed, 3 Jul 2024 10:33:14 +0200 Subject: [PATCH 4/6] delete big txt or tsv files from tower.yml --- tower.yml | 8 -------- 1 file changed, 8 deletions(-) diff --git a/tower.yml b/tower.yml index d2f84211..2e8c99c9 100644 --- a/tower.yml +++ b/tower.yml @@ -29,8 +29,6 @@ reports: display: "A combined profile of all samples aligned to a given database (as generated by `krakentools`)." "**/kraken2/*/*.kraken2.report.txt": display: "A Kraken2 report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits in the Kraken2 run for a given sample. Will be 6 column rather than 8 if `--save_minimizers` specified." - "**/kraken2/*/*.kraken2.classifiedreads.txt": - display: "A list of read IDs and the hits each read had against each database for a given sample." "**/krakenuniq/*.krakenuniq.report.txt": display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits, with an additional column for k-mer coverage, that allows for more accurate distinguishing between false-positive/true-postitive hits." "**/krakenuniq/*.krakenuniq.classified.txt": @@ -39,18 +37,12 @@ reports: display: "A combined profile of all samples aligned to a given database (as generated by `centrifuge-kreport`)." "**/centrifuge/*/*.centrifuge.report.txt": display: "A classification report that summarises the taxonomic ID, the taxonomic rank, length of genome sequence, number of classified and uniquely classified reads." - "**/centrifuge/*/*.centrifuge.results.txt": - display: "A file that summarises the classification assignment for a read, i.e read ID, sequence ID, score for the classification, score for the next best classification, number of classifications for this read." "**/centrifuge/*/*.centrifuge.txt": display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of k-mers, taxonomic path of all the hits in the centrifuge run for a given sample." - "**/diamond/*/*.tsv": - display: "A file containing alignment information in various formats, or taxonomic information in a text-based format. Exact output depends on user choice." "**/ganon/*_combined_reports.txt": display: "A combined profile of all samples aligned to a given database (as generated by `ganon table`)." "**/kaiju/*_combined_reports.txt": display: "A combined profile of all samples aligned to a given database (as generated by kaiju2table)" - "**/kaiju/*/*.kaiju.tsv": - display: "Raw output from Kaiju with taxonomic rank, read ID and taxonic ID" "**/kaiju/*/*.kaijutable.txt": display: "Summarised Kaiju output with fraction abundance, taxonomic ID, number of reads, and taxonomic names (as generated by `kaiju2table`)" "**/krona/*.html": From 3202ea59901c3c378b28a5ecc89cd84a77426467 Mon Sep 17 00:00:00 2001 From: Lili Andersson-Li <64467552+LilyAnderssonLee@users.noreply.github.com> Date: Wed, 3 Jul 2024 10:33:58 +0200 Subject: [PATCH 5/6] update changelog --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6dda53a8..2bb1ce9c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,7 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [#417](https://github.com/nf-core/taxprofiler/pull/417) - Added reference-free metagenome estimation with Nonpareil (added by @jfy133) - [#466](https://github.com/nf-core/taxprofiler/pull/466) - Input database sheets now require a `db_type` column to distinguish between short- and long-read databases (added by @LilyAnderssonLee) -- [#505](https://github.com/nf-core/taxprofiler/pull/505) - Add output files information to the file `tower.yml` (added by @LilyAnderssonLee) +- [#505](https://github.com/nf-core/taxprofiler/pull/505) - Add small files to the file `tower.yml` (added by @LilyAnderssonLee) ## v1.1.8dev - Augmented Akita Patch [] From fce5e6f273b305c5e647527036ea635856a1c0b9 Mon Sep 17 00:00:00 2001 From: Lili Andersson-Li <64467552+LilyAnderssonLee@users.noreply.github.com> Date: Wed, 3 Jul 2024 10:38:54 +0200 Subject: [PATCH 6/6] update tower.yml --- tower.yml | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/tower.yml b/tower.yml index 2e8c99c9..1101572e 100644 --- a/tower.yml +++ b/tower.yml @@ -2,58 +2,58 @@ reports: multiqc_report.html: display: "MultiQC HTML report" "**/fastqc/raw/*.html": - display: "A FastQC report contains quality metrics of raw reads in HTML format." + display: "A FastQC report containing quality metrics of raw reads in HTML format." "**/fastqc/raw/*.txt": display: "A FastQC report containing quality metrics of raw reads in TXT format." "**/fastqc/preprocessed/*.html": - display: "A FastQC report contains quality metrics of processed reads in HTML format." + display: "A FastQC report containing quality metrics of processed reads in HTML format." "**/fastqc/preprocessed/*.txt": display: "A FastQC report containing quality metrics of processed reads in TXT format." "**/falco/raw/*.html": - display: "A Falco report contains quality metrics of raw reads in HTML format." + display: "A Falco report containing quality metrics of raw reads in HTML format." "**/falco/raw/*.txt": display: "A Falco report containing quality metrics of raw reads in TXT format." "**/falco/preprocessed/*.html": - display: "A Falco report contains quality metrics of raw reads in HTML format." + display: "A Falco report containing quality metrics of processed reads in HTML format." "**/falco/preprocessed/*.txt": - display: "A Falco report containing quality metrics of raw reads in TXT format." + display: "A Falco report containing quality metrics of processed reads in TXT format." "**/fastp/*.html": display: "A Log file in HTML format." "**/bracken/*_combined_reports.txt": - display: "Combined bracken results as output from Bracken's `combine_bracken_outputs.py` script." + display: "Combined bracken results as output from Bracken's combine_bracken_outputs.py script." "**/bracken/*/*.tsv": display: "A TSV file containing per-sample summary of Bracken results with abundance information." "**/bracken/*/*report_bracken_species.txt": display: "A Kraken2 style report with Bracken abundance information." "**/kraken2/kraken2_*_combined_reports.txt": - display: "A combined profile of all samples aligned to a given database (as generated by `krakentools`)." + display: "A combined profile of all samples aligned to a given database (as generated by krakentools)." "**/kraken2/*/*.kraken2.report.txt": - display: "A Kraken2 report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits in the Kraken2 run for a given sample. Will be 6 column rather than 8 if `--save_minimizers` specified." + display: "A Kraken2 report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits in the Kraken2 run for a given sample. Will be 6 column rather than 8 if --save_minimizers specified." "**/krakenuniq/*.krakenuniq.report.txt": display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits, with an additional column for k-mer coverage, that allows for more accurate distinguishing between false-positive/true-postitive hits." "**/krakenuniq/*.krakenuniq.classified.txt": display: "An optional list of read IDs and the hits each read had against each database for a given sample." "**/centrifuge/*_combined_reports.txt": - display: "A combined profile of all samples aligned to a given database (as generated by `centrifuge-kreport`)." + display: "A combined profile of all samples aligned to a given database (as generated by centrifuge-kreport)." "**/centrifuge/*/*.centrifuge.report.txt": display: "A classification report that summarises the taxonomic ID, the taxonomic rank, length of genome sequence, number of classified and uniquely classified reads." "**/centrifuge/*/*.centrifuge.txt": display: "A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of k-mers, taxonomic path of all the hits in the centrifuge run for a given sample." "**/ganon/*_combined_reports.txt": - display: "A combined profile of all samples aligned to a given database (as generated by `ganon table`)." + display: "A combined profile of all samples aligned to a given database (as generated by ganon table)." "**/kaiju/*_combined_reports.txt": display: "A combined profile of all samples aligned to a given database (as generated by kaiju2table)" "**/kaiju/*/*.kaijutable.txt": - display: "Summarised Kaiju output with fraction abundance, taxonomic ID, number of reads, and taxonomic names (as generated by `kaiju2table`)" + display: "Summarised Kaiju output with fraction abundance, taxonomic ID, number of reads, and taxonomic names (as generated by kaiju2table)" "**/krona/*.html": display: "Per-tool/per-database interactive HTML file containing hierarchical piecharts." "**/metaphlan/*/*_combined_reports.txt": - display: "A combined profile of all samples aligned to a given database (as generated by `metaphlan_merge_tables`)." + display: "A combined profile of all samples aligned to a given database (as generated by metaphlan_merge_tables)." "**/metaphlan/*/*.bowtie2out.txt": - display: "BowTie2 alignment information (can be re-used for skipping alignment when re-running MetaPhlAn with different parameters)." + display: "Bowtie2 alignment information (can be re-used for skipping alignment when re-running MetaPhlAn with different parameters)." "**/metaphlan/*/*_profile.txt": display: "A MetaPhlAn taxonomic profile including abundance estimates." "**/motus/*/*_combined_reports.txt": - display: "A combined profile of all samples aligned to a given database (as generated by `motus_merge`)." + display: "A combined profile of all samples aligned to a given database (as generated by motus_merge)." "**/taxpasta/*tsv": display: "Standardised taxon table containing multiple samples. The first column describes the taxonomy ID and the rest of the columns describe the read counts for each sample."