add ability to report class size in recovery plot

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -2,53 +2,53 @@ name: Bug report
 description: Report something that is broken or incorrect
 labels: bug
 body:
-- type: textarea
-  id: description
-  attributes:
-    label: Description of the bug
-    description: A clear and concise description of what the bug is.
-  validations:
-    required: true
-- type: textarea
-  id: command_used
-  attributes:
-    label: Command used and terminal output
-    description: Steps to reproduce the behaviour. Please paste the command you used
-      to launch the pipeline and the output from your terminal.
-    render: console
-    placeholder: '$ nextflow run ...
-
-
-      Some output where something broke
-
-      '
-- type: textarea
-  id: files
-  attributes:
-    label: Relevant files
-    description: 'Please drag and drop the relevant files here. Create a `.zip` archive
-      if the extension is not allowed.
-
-      Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
-      in the directory where you launched the pipeline)_ as well as custom Nextflow
-      configuration files.
-
-      '
-- type: textarea
-  id: system
-  attributes:
-    label: System information
-    description: '* Nextflow version _(eg. 23.04.0)_
-
-      * Hardware _(eg. HPC, Desktop, Cloud)_
-
-      * Executor _(eg. slurm, local, awsbatch)_
-
-      * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
-      or Apptainer)_
-
-      * OS _(eg. CentOS Linux, macOS, Linux Mint)_
-
-      * Version of jlab/refbasedassemblereval _(eg. 1.1, 1.5, 1.8.2)_
-
-      '
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: command_used
+    attributes:
+      label: Command used and terminal output
+      description: Steps to reproduce the behaviour. Please paste the command you used
+        to launch the pipeline and the output from your terminal.
+      render: console
+      placeholder: "$ nextflow run ...
+
+
+        Some output where something broke
+
+        "
+  - type: textarea
+    id: files
+    attributes:
+      label: Relevant files
+      description: "Please drag and drop the relevant files here. Create a `.zip` archive
+        if the extension is not allowed.
+
+        Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
+        in the directory where you launched the pipeline)_ as well as custom Nextflow
+        configuration files.
+
+        "
+  - type: textarea
+    id: system
+    attributes:
+      label: System information
+      description: "* Nextflow version _(eg. 23.04.0)_
+
+        * Hardware _(eg. HPC, Desktop, Cloud)_
+
+        * Executor _(eg. slurm, local, awsbatch)_
+
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
+        or Apptainer)_
+
+        * OS _(eg. CentOS Linux, macOS, Linux Mint)_
+
+        * Version of jlab/refbasedassemblereval _(eg. 1.1, 1.5, 1.8.2)_
+
+        "

.github/workflows/ci.yml

@@ -14,30 +14,3 @@ env:
 concurrency:
   group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}"
   cancel-in-progress: true
-
-jobs:
-  test:
-    name: Run pipeline with test data
-    # Only run on push if this is the nf-core dev branch (merged PRs)
-    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'jlab/refbasedassemblereval') }}"
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        NXF_VER:
-          - "23.04.0"
-          - "latest-everything"
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v3
-
-      - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
-        with:
-          version: "${{ matrix.NXF_VER }}"
-
-      - name: Run pipeline with test data
-        # TODO nf-core: You can customise CI pipeline run tests as required
-        # For example: adding multiple test runs with different parameters
-        # Remember that you can parallelise this by using strategy.matrix
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results

.github/workflows/linting.yml

@@ -66,43 +66,3 @@ jobs:
             Thanks again for your contribution!
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           allow-repeats: false
-
-  nf-core:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out pipeline code
-        uses: actions/checkout@v3
-
-      - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
-
-      - uses: actions/setup-python@v4
-        with:
-          python-version: "3.11"
-          architecture: "x64"
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install nf-core
-
-      - name: Run nf-core lint
-        env:
-          GITHUB_COMMENTS_URL: ${{ github.event.pull_request.comments_url }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          GITHUB_PR_COMMIT: ${{ github.event.pull_request.head.sha }}
-        run: nf-core -l lint_log.txt lint --dir ${GITHUB_WORKSPACE} --markdown lint_results.md
-
-      - name: Save PR number
-        if: ${{ always() }}
-        run: echo ${{ github.event.pull_request.number }} > PR_number.txt
-
-      - name: Upload linting log file artifact
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v3
-        with:
-          name: linting-logs
-          path: |
-            lint_log.txt
-            lint_results.md
-            PR_number.txt

.gitignore

@@ -26,4 +26,5 @@ plotting/*.csv*
 plotting/data_cache
 plotting/envs/
 plotting/envs_newtest/
-plotting/archive
+plotting/archive
+plotting/outdir/

.nf-core.yml

@@ -1,32 +1,32 @@
 lint:
   files_exist:
-  - CODE_OF_CONDUCT.md
-  - assets/nf-core-refbasedassemblereval_logo_light.png
-  - docs/images/nf-core-refbasedassemblereval_logo_light.png
-  - docs/images/nf-core-refbasedassemblereval_logo_dark.png
-  - .github/ISSUE_TEMPLATE/config.yml
-  - .github/workflows/awstest.yml
-  - .github/workflows/awsfulltest.yml
-  - conf/igenomes.config
-  - conf/igenomes.config
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-refbasedassemblereval_logo_light.png
+    - docs/images/nf-core-refbasedassemblereval_logo_light.png
+    - docs/images/nf-core-refbasedassemblereval_logo_dark.png
+    - .github/ISSUE_TEMPLATE/config.yml
+    - .github/workflows/awstest.yml
+    - .github/workflows/awsfulltest.yml
+    - conf/igenomes.config
+    - conf/igenomes.config
   files_unchanged:
-  - CODE_OF_CONDUCT.md
-  - assets/nf-core-refbasedassemblereval_logo_light.png
-  - docs/images/nf-core-refbasedassemblereval_logo_light.png
-  - docs/images/nf-core-refbasedassemblereval_logo_dark.png
-  - .github/ISSUE_TEMPLATE/bug_report.yml
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-refbasedassemblereval_logo_light.png
+    - docs/images/nf-core-refbasedassemblereval_logo_light.png
+    - docs/images/nf-core-refbasedassemblereval_logo_dark.png
+    - .github/ISSUE_TEMPLATE/bug_report.yml
   multiqc_config:
-  - report_comment
+    - report_comment
   nextflow_config:
-  - manifest.name
-  - manifest.homePage
-  - process.cpus
-  - process.memory
-  - process.time
-  - custom_config
+    - manifest.name
+    - manifest.homePage
+    - process.cpus
+    - process.memory
+    - process.time
+    - custom_config
 repository_type: pipeline
 template:
   prefix: jlab
   skip:
-  - igenomes
-  - nf_core_configs
+    - igenomes
+    - nf_core_configs

CITATIONS.md

@@ -13,51 +13,49 @@
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
   > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
-  >
+
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
-  >
+
 - [Bowtie2](https://link.springer.com/article/10.1186/s13040-014-0034-0)
 
-  > LANGDON, William B. Performance of genetic programming optimised Bowtie2 on genome comparison and analytic testing (GCAT) benchmarks.*BioData mining* , 2015, 8. Jg., Nr. 1, S. 1.
-  >
+  > LANGDON, William B. Performance of genetic programming optimised Bowtie2 on genome comparison and analytic testing (GCAT) benchmarks._BioData mining_ , 2015, 8. Jg., Nr. 1, S. 1.
+
 - [BEDTools](https://currentprotocols.onlinelibrary.wiley.com/doi/full/10.1002/0471250953.bi1112s47)
 
-  > QUINLAN, Aaron R. BEDTools: the Swiss‐army tool for genome feature analysis.  *Current protocols in bioinformatics* , 2014, 47. Jg., Nr. 1, S. 11.12. 1-11.12. 34.
-  >
+  > QUINLAN, Aaron R. BEDTools: the Swiss‐army tool for genome feature analysis. _Current protocols in bioinformatics_ , 2014, 47. Jg., Nr. 1, S. 11.12. 1-11.12. 34.
+
 - [Salmon](https://www.nature.com/articles/nmeth.4197)
 
-  > PATRO, Rob, et al. Salmon provides fast and bias-aware quantification of transcript expression.*Nature methods* , 2017, 14. Jg., Nr. 4, S. 417-419.
-  >
+  > PATRO, Rob, et al. Salmon provides fast and bias-aware quantification of transcript expression._Nature methods_ , 2017, 14. Jg., Nr. 4, S. 417-419.
+
 - [SeqKit](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0163962)
 
-  > SHEN, Wei, et al. SeqKit: a cross-platform and ultrafast toolkit for FASTA/Q file manipulation.  *PloS one* , 2016, 11. Jg., Nr. 10, S. e0163962.
-  >
+  > SHEN, Wei, et al. SeqKit: a cross-platform and ultrafast toolkit for FASTA/Q file manipulation. _PloS one_ , 2016, 11. Jg., Nr. 10, S. e0163962.
+
 - [Subread](https://academic.oup.com/nar/article/41/10/e108/1075719?login=true)
 
-  > LIAO, Yang; SMYTH, Gordon K.; SHI, Wei. The Subread aligner: fast, accurate and scalable read mapping by seed-and-vote.  *Nucleic acids research* , 2013, 41. Jg., Nr. 10, S. e108-e108.
-  >
+  > LIAO, Yang; SMYTH, Gordon K.; SHI, Wei. The Subread aligner: fast, accurate and scalable read mapping by seed-and-vote. _Nucleic acids research_ , 2013, 41. Jg., Nr. 10, S. e108-e108.
 
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)
 
   > Anaconda Software Distribution. Computer software. Vers. 2-2.4.0. Anaconda, Nov. 2016. Web.
-  >
+
 - [Bioconda](https://pubmed.ncbi.nlm.nih.gov/29967506/)
 
   > Grüning B, Dale R, Sjödin A, Chapman BA, Rowe J, Tomkins-Tinch CH, Valieris R, Köster J; Bioconda Team. Bioconda: sustainable and comprehensive software distribution for the life sciences. Nat Methods. 2018 Jul;15(7):475-476. doi: 10.1038/s41592-018-0046-7. PubMed PMID: 29967506.
-  >
+
 - [BioContainers](https://pubmed.ncbi.nlm.nih.gov/28379341/)
 
   > da Veiga Leprevost F, Grüning B, Aflitos SA, Röst HL, Uszkoreit J, Barsnes H, Vaudel M, Moreno P, Gatto L, Weber J, Bai M, Jimenez RC, Sachsenberg T, Pfeuffer J, Alvarez RV, Griss J, Nesvizhskii AI, Perez-Riverol Y. BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics. 2017 Aug 15;33(16):2580-2582. doi: 10.1093/bioinformatics/btx192. PubMed PMID: 28379341; PubMed Central PMCID: PMC5870671.
-  >
+
 - [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241)
 
   > Merkel, D. (2014). Docker: lightweight linux containers for consistent development and deployment. Linux Journal, 2014(239), 2. doi: 10.5555/2600239.2600241.
-  >
+
 - [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/)
 
   > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675.
-  >

README.md

@@ -17,13 +17,13 @@
 
 Recommended usage:
 
-* Create *in silico* datasets using [Marbel](https://anaconda.org/bioconda/marbel), name the output dirs: NAME_microbiome
-* Assemble the datasets
-* Run the pipeline
+- Create _in silico_ datasets using [Marbel](https://anaconda.org/bioconda/marbel), name the output dirs: NAME_microbiome
+- Assemble the datasets
+- Run the pipeline
 
 Fill the required parameters per run and adjust the example config files in `example/tool.config`, `example/dataset.config` and `example/resources.config`.
 
-For each dataset create a dataset.config with the data set name. For outdir parameter chose the same parent dir, if you want to visualise the datasets together, e.g., PATH/group/dataset1, PATH/group/dataset2. 
+For each dataset create a dataset.config with the data set name. For outdir parameter chose the same parent dir, if you want to visualise the datasets together, e.g., PATH/group/dataset1, PATH/group/dataset2.
 
 Run each dataset with:
 
@@ -35,7 +35,7 @@ nextflow run . \
    -c example/tool.config
 ```
 
-Afterwards there is multiple methods which can visualise the runs. A script which creates all orb files is provided: 
+Afterwards there is multiple methods which can visualise the runs. A script which creates all orb files is provided:
 `plotting/plot_orb_figures.py
 
 For the dependencies you can use:
@@ -52,7 +52,7 @@ python plotting/plot_orb_figures.py <fp_orb_basedir> <fp_marbel_basedir> <marbel
 
 `fp_orb_basedir`: Path of the results for orb.
 
-`fp_marbel_basedir`: Path to the *in silico* datasets. Datasets folders require _microbiome suffix.
+`fp_marbel_basedir`: Path to the _in silico_ datasets. Datasets folders require \_microbiome suffix.
 
 `marbel_sequence_file`: Path to the bio index file of the [Marbel repository](https://github.com/jlab/marbel): `src/marbel/data/deduplicated_pangenome_EDGAR_Microbiome_JLAB2.fas.bgz.bio_index`
 

assets/schema_input.json

@@ -18,7 +18,7 @@
                     "type": "string"
                 },
                 "errorMessage": "An array of assemblers for reads 1 must be provided"
-            },
+            }
         },
         "required": ["sample", "assemblers"]
     }

bin/calculate_calour_confusion.py

@@ -13,15 +13,15 @@
 
 row_prefix = "calour_"
 
-gene_summary = pd.read_csv(gene_summary_file, sep='\t')
-assembler_dge = pd.read_csv(assembler_dge_file, sep='\t')
+gene_summary = pd.read_csv(gene_summary_file, sep="\t")
+assembler_dge = pd.read_csv(assembler_dge_file, sep="\t")
 
 
 with open(map_file, "r") as file:
     contig_to_gene = json.load(file)
 
 assembler_dge["Name"] = assembler_dge["Name"].astype(str)
- 
+
 assembler_dge["original_cds"] = assembler_dge["Name"].map(contig_to_gene)
 
 assembler_dge["gene_name"] = assembler_dge["original_cds"].str.replace(r"_block\d+$", "", regex=True)
@@ -37,6 +37,13 @@
 
 cm = confusion_matrix(true_labels, pred_labels, labels=[0, 1])
 
-linear_cm = {f"{row_prefix}DE_TN": cm[0, 0], f"{row_prefix}DE_FP": cm[0, 1], f"{row_prefix}DE_FN": cm[1, 0], f"{row_prefix}DE_TP": cm[1, 1]}
+linear_cm = {
+    f"{row_prefix}DE_TN": cm[0, 0],
+    f"{row_prefix}DE_FP": cm[0, 1],
+    f"{row_prefix}DE_FN": cm[1, 0],
+    f"{row_prefix}DE_TP": cm[1, 1],
+}
 
-pd.DataFrame.from_dict(linear_cm, orient="index", columns=[prefix]).to_csv(f"{row_prefix}{prefix}_linear_cm.tsv", sep="\t")
+pd.DataFrame.from_dict(linear_cm, orient="index", columns=[prefix]).to_csv(
+    f"{row_prefix}{prefix}_linear_cm.tsv", sep="\t"
+)