From 8ce77e5d4fe003366c5d272c2c6b14abedcbcdb1 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 7 Jun 2024 14:53:21 +0200 Subject: [PATCH 01/10] Fix issue with MQC not displaying post-ar trimming FastQC results --- CHANGELOG.md | 14 +++++++++++++- assets/multiqc_config.yaml | 1 + 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 2da3a8c47..92739eeaf 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,18 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html). +## [2.5.2] - 2024-06-07 + +### `Added` + +### `Fixed` + +- [#1037](https://github.com/nf-core/eager/issues/1073) - Fixed post-adapterremoval trimmed FastQC results not being displayed in MultiQC (to @kieren-j-mitchell for reporting, fix by @jfy133 and @TCLamnidis) + +### `Dependencies` + +### `Deprecated` + ## [2.5.1] - 2024-02-21 ### `Added` @@ -11,7 +23,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. ### `Fixed` -- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample_name and suffixed with `.fasta` (i.e. `_.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) +- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample*name and suffixed with `.fasta` (i.e. `*.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) - [#1047](https://github.com/nf-core/eager/issues/1047) Changed the row some statistics were reported in the General Stats table. The File name collision fixed in 2.5.0 (see #1017) caused these statistics to be reported in the wrong row due to an added suffix. - [#1051](https://github.com/nf-core/eager/issues/1051) An error is now thrown if input BAM files end in `.unmapped.bam`, as this breaks the bam filtering process and empties the bam files in the process. (♥ Thanks to @PCQuilis for reporting.) diff --git a/assets/multiqc_config.yaml b/assets/multiqc_config.yaml index 8804ed9e1..f02837427 100644 --- a/assets/multiqc_config.yaml +++ b/assets/multiqc_config.yaml @@ -74,6 +74,7 @@ top_modules: path_filters: - "*.truncated_fastqc.zip" - "*.combined*_fastqc.zip" + - "*_postartrimmed_fastqc.zip" - "bowtie2": path_filters: - "*_bt2.log" From bda3bda9bc0b0962aae62d55ea0a10606f97faeb Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 7 Jun 2024 14:54:58 +0200 Subject: [PATCH 02/10] Update CHANGELOG.md --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 92739eeaf..4266082fc 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -23,7 +23,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. ### `Fixed` -- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample*name and suffixed with `.fasta` (i.e. `*.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) +- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample\name and suffixed with `.fasta` (i.e. `_.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) - [#1047](https://github.com/nf-core/eager/issues/1047) Changed the row some statistics were reported in the General Stats table. The File name collision fixed in 2.5.0 (see #1017) caused these statistics to be reported in the wrong row due to an added suffix. - [#1051](https://github.com/nf-core/eager/issues/1051) An error is now thrown if input BAM files end in `.unmapped.bam`, as this breaks the bam filtering process and empties the bam files in the process. (♥ Thanks to @PCQuilis for reporting.) From 9ba1f5bfc74265c9d48eb4a31672627f57bdb9f9 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 7 Jun 2024 15:38:19 +0200 Subject: [PATCH 03/10] Fix changelog autoformatting error --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 4266082fc..2bac6b856 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -23,7 +23,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. ### `Fixed` -- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample\name and suffixed with `.fasta` (i.e. `_.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) +- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample_name and suffixed with `.fasta` (i.e. `\_.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) - [#1047](https://github.com/nf-core/eager/issues/1047) Changed the row some statistics were reported in the General Stats table. The File name collision fixed in 2.5.0 (see #1017) caused these statistics to be reported in the wrong row due to an added suffix. - [#1051](https://github.com/nf-core/eager/issues/1051) An error is now thrown if input BAM files end in `.unmapped.bam`, as this breaks the bam filtering process and empties the bam files in the process. (♥ Thanks to @PCQuilis for reporting.) From 7c697bac4a98a0368293401ddaf643f1e9f2a9eb Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 7 Jun 2024 15:40:34 +0200 Subject: [PATCH 04/10] Update CHANGELOG.md --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 2bac6b856..d4a27c6c7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -23,7 +23,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. ### `Fixed` -- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample_name and suffixed with `.fasta` (i.e. `\_.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) +- [#1048](https://github.com/nf-core/eager/issues/1048) `--vcf2genome_outfile` parameter now gets prefixed by the sample_name and suffixed with `.fasta` (i.e. `_.fasta`). This ensures we avoid overwriting the output fasta of one sample with that of another when the option is provided. (♥ Thanks to @MeriamOs for reporting.) - [#1047](https://github.com/nf-core/eager/issues/1047) Changed the row some statistics were reported in the General Stats table. The File name collision fixed in 2.5.0 (see #1017) caused these statistics to be reported in the wrong row due to an added suffix. - [#1051](https://github.com/nf-core/eager/issues/1051) An error is now thrown if input BAM files end in `.unmapped.bam`, as this breaks the bam filtering process and empties the bam files in the process. (♥ Thanks to @PCQuilis for reporting.) From d1f39507332d03cfcc8d729a448c1e0198a2e81d Mon Sep 17 00:00:00 2001 From: Thiseas Christos Lamnidis Date: Wed, 26 Jun 2024 11:46:12 +0200 Subject: [PATCH 05/10] document lane merging output dir --- docs/output.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/output.md b/docs/output.md index 9ad6cb9ba..26115299d 100644 --- a/docs/output.md +++ b/docs/output.md @@ -680,6 +680,7 @@ Each module has it's own output directory which sit alongside the `MultiQC/` dir * When masking of the reference is requested prior to running pmdtools, an additional directory `reference_genome/masked_genome` will be found here, containing the masked reference. * `fastqc/`: this contains the original per-FASTQ FastQC reports that are summarised with MultiQC. These occur in both `html` (the report) and `.zip` format (raw data). The `after_clipping` folder contains the same but for after AdapterRemoval. * `adapterremoval/`: this contains the log files (ending with `.settings`) with raw trimming (and merging) statistics after AdapterRemoval. In the `output` sub-directory, are the output trimmed (and merged) `fastq` files. These you can use for downstream applications such as taxonomic binning for metagenomic studies. +* `lanemerging/`: this contains adapter-trimmed and merged (i.e. collapsed) FASTQ files that were merged across lanes, where applicable. These files are used for downstream applications such as taxonomic binning for metagenomic studies. * `post_ar_fastq_trimmed`: this contains `fastq` files that have been additionally trimmed after AdapterRemoval (if turned on). These reads are usually that had internal barcodes, or damage that needed to be removed before mapping. * `mapping/`: this contains a sub-directory corresponding to the mapping tool you used, inside of which will be the initial BAM files containing the reads that mapped to your reference genome with no modification (see below). You will also find a corresponding BAM index file (ending in `.csi` or `.bai`), and if running the `bowtie2` mapper: a log ending in `_bt2.log`. You can use these for downstream applications e.g. if you wish to use a different de-duplication tool not included in nf-core/eager (although please feel free to add a new module request on the Github repository's [issue page](https://github.com/nf-core/eager/issues)!). * `samtools/`: this contains two sub-directories. `stats/` contain the raw mapping statistics files (ending in `.stats`) from directly after mapping. `filter/` contains BAM files that have had a mapping quality filter applied (set by the `--bam_mapping_quality_threshold` flag) and a corresponding index file. Furthermore, if you selected `--bam_discard_unmapped`, you will find your separate file with only unmapped reads in the format you selected. Note unmapped read BAM files will _not_ have an index file. From eb785dd29461cb10099dda34ea76a5030eca90eb Mon Sep 17 00:00:00 2001 From: Thiseas Christos Lamnidis Date: Wed, 26 Jun 2024 11:53:18 +0200 Subject: [PATCH 06/10] Update Changelog --- CHANGELOG.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index d4a27c6c7..a529f87d8 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,9 +7,11 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. ### `Added` +- [#1079](https://github.com/nf-core/eager/issues/1079) - Added the `lanemerging` output directory in the output documentation (♥ to @TessaZei for reporting). + ### `Fixed` -- [#1037](https://github.com/nf-core/eager/issues/1073) - Fixed post-adapterremoval trimmed FastQC results not being displayed in MultiQC (to @kieren-j-mitchell for reporting, fix by @jfy133 and @TCLamnidis) +- [#1037](https://github.com/nf-core/eager/issues/1073) - Fixed post-adapterremoval trimmed FastQC results not being displayed in MultiQC (♥ to @kieren-j-mitchell for reporting, fix by @jfy133 and @TCLamnidis) ### `Dependencies` From 3aece14c2ed13a96df060d6bbe808df00c0d8745 Mon Sep 17 00:00:00 2001 From: "Thiseas C. Lamnidis" Date: Fri, 28 Jun 2024 10:29:07 +0200 Subject: [PATCH 07/10] Update docs/output.md Co-authored-by: James A. Fellows Yates --- docs/output.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/output.md b/docs/output.md index 26115299d..b17aa8253 100644 --- a/docs/output.md +++ b/docs/output.md @@ -680,7 +680,7 @@ Each module has it's own output directory which sit alongside the `MultiQC/` dir * When masking of the reference is requested prior to running pmdtools, an additional directory `reference_genome/masked_genome` will be found here, containing the masked reference. * `fastqc/`: this contains the original per-FASTQ FastQC reports that are summarised with MultiQC. These occur in both `html` (the report) and `.zip` format (raw data). The `after_clipping` folder contains the same but for after AdapterRemoval. * `adapterremoval/`: this contains the log files (ending with `.settings`) with raw trimming (and merging) statistics after AdapterRemoval. In the `output` sub-directory, are the output trimmed (and merged) `fastq` files. These you can use for downstream applications such as taxonomic binning for metagenomic studies. -* `lanemerging/`: this contains adapter-trimmed and merged (i.e. collapsed) FASTQ files that were merged across lanes, where applicable. These files are used for downstream applications such as taxonomic binning for metagenomic studies. +* `lanemerging/`: this contains adapter-trimmed and merged (i.e. collapsed) FASTQ files that were merged across lanes, where applicable. These files are the reads that go into mapping (when multiple lanes were specified for a library), and can be used for downstream applications such as taxonomic binning for metagenomic studies. * `post_ar_fastq_trimmed`: this contains `fastq` files that have been additionally trimmed after AdapterRemoval (if turned on). These reads are usually that had internal barcodes, or damage that needed to be removed before mapping. * `mapping/`: this contains a sub-directory corresponding to the mapping tool you used, inside of which will be the initial BAM files containing the reads that mapped to your reference genome with no modification (see below). You will also find a corresponding BAM index file (ending in `.csi` or `.bai`), and if running the `bowtie2` mapper: a log ending in `_bt2.log`. You can use these for downstream applications e.g. if you wish to use a different de-duplication tool not included in nf-core/eager (although please feel free to add a new module request on the Github repository's [issue page](https://github.com/nf-core/eager/issues)!). * `samtools/`: this contains two sub-directories. `stats/` contain the raw mapping statistics files (ending in `.stats`) from directly after mapping. `filter/` contains BAM files that have had a mapping quality filter applied (set by the `--bam_mapping_quality_threshold` flag) and a corresponding index file. Furthermore, if you selected `--bam_discard_unmapped`, you will find your separate file with only unmapped reads in the format you selected. Note unmapped read BAM files will _not_ have an index file. From 5739ae2a24f5d0d36dc982205802b0c8c17ad2dd Mon Sep 17 00:00:00 2001 From: "Thiseas C. Lamnidis" Date: Fri, 28 Jun 2024 10:30:30 +0200 Subject: [PATCH 08/10] Update CHANGELOG.md --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index a529f87d8..2319256f9 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,7 +7,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. ### `Added` -- [#1079](https://github.com/nf-core/eager/issues/1079) - Added the `lanemerging` output directory in the output documentation (♥ to @TessaZei for reporting). +- [#1079](https://github.com/nf-core/eager/issues/1079) - Added the `lanemerging` output directory in the output documentation (♥ to @TessaZei for reporting, fix by @TCLamnidis). ### `Fixed` From fb94810ef4519f771309736a6fd46b2345111066 Mon Sep 17 00:00:00 2001 From: Thiseas Christos Lamnidis Date: Fri, 28 Jun 2024 10:43:09 +0200 Subject: [PATCH 09/10] bump version to 2.5.2 --- .github/workflows/ci.yml | 4 ++-- Dockerfile | 4 ++-- environment.yml | 2 +- nextflow.config | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index e30b7d700..45e4f2186 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -37,13 +37,13 @@ jobs: - name: Build new docker image if: env.MATCHED_FILES - run: docker build --no-cache . -t nfcore/eager:2.5.1 + run: docker build --no-cache . -t nfcore/eager:2.5.2 - name: Pull docker image if: ${{ !env.MATCHED_FILES }} run: | docker pull nfcore/eager:dev - docker tag nfcore/eager:dev nfcore/eager:2.5.1 + docker tag nfcore/eager:dev nfcore/eager:2.5.2 - name: Install Nextflow env: diff --git a/Dockerfile b/Dockerfile index 01194d7b3..99b967439 100644 --- a/Dockerfile +++ b/Dockerfile @@ -7,7 +7,7 @@ COPY environment.yml / RUN conda env create --quiet -f /environment.yml && conda clean -a # Add conda installation dir to PATH (instead of doing 'conda activate') -ENV PATH /opt/conda/envs/nf-core-eager-2.5.1/bin:$PATH +ENV PATH /opt/conda/envs/nf-core-eager-2.5.2/bin:$PATH # Dump the details of the installed packages to a file for posterity -RUN conda env export --name nf-core-eager-2.5.1 > nf-core-eager-2.5.1.yml \ No newline at end of file +RUN conda env export --name nf-core-eager-2.5.2 > nf-core-eager-2.5.2.yml \ No newline at end of file diff --git a/environment.yml b/environment.yml index f9eb8f0b9..3f777f1d9 100644 --- a/environment.yml +++ b/environment.yml @@ -1,6 +1,6 @@ # You can use this file to create a conda environment for this pipeline: # conda env create -f environment.yml -name: nf-core-eager-2.5.1 +name: nf-core-eager-2.5.2 channels: - conda-forge - bioconda diff --git a/nextflow.config b/nextflow.config index 97308f807..2dddcaf30 100644 --- a/nextflow.config +++ b/nextflow.config @@ -289,7 +289,7 @@ params { // Container slug. Stable releases should specify release tag! // Developmental code should specify :dev -process.container = 'nfcore/eager:2.5.1' +process.container = 'nfcore/eager:2.5.2' // Load base.config by default for all pipelines includeConfig 'conf/base.config' @@ -419,7 +419,7 @@ manifest { description = 'A fully reproducible and state-of-the-art ancient DNA analysis pipeline' mainScript = 'main.nf' nextflowVersion = '>=20.07.1' - version = '2.5.1' + version = '2.5.2' } // Function to ensure that resource requirements don't go beyond From 81e45be2f5a18d98b34b437181973c5f8026f41c Mon Sep 17 00:00:00 2001 From: Thiseas Christos Lamnidis Date: Fri, 28 Jun 2024 10:46:58 +0200 Subject: [PATCH 10/10] update Changelog release date --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 2319256f9..4ae9c442b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html). -## [2.5.2] - 2024-06-07 +## [2.5.2] - 2024-06-28 ### `Added`