Merge pull request #476 from nf-core/bowtie2

Adds Bowtie2 to address

Author: jfy133

.github/workflows/ci.yml

@@ -98,6 +98,9 @@ jobs:
       - name: MAPPER_BWAMEM Test running with BWA Mem
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --mapper 'bwamem'
+      - name: MAPPER_BT2 Test running with BowTie2
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --mapper 'bowtie2' --bt2_alignmode 'local' --bt2_sensitivity 'sensitive' --bt2n 1 --bt2l 16 --bt2_trim5 1 --bt2_trim3 1
       - name: STRIP_FASTQ Run the basic pipeline with output unmapped reads as fastq
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --strip_input_fastq

.gitignore

@@ -7,3 +7,5 @@ tests/
 testing/
 *.pyc
 main_playground.nf
+.vscode
+*.code-workspace

CHANGELOG.md

@@ -23,6 +23,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 * Added ability for automated emails using `mailutils` to also send MultiQC reports
 * General documentation additions and cleaning, updated figures with CC-BY license
 * Added large 'fullsize' dataset test-profiles for ancient fish, human, and a draft pathogen contexts.
+* [#257](https://github.com/nf-core/eager/issues/257) Added the bowtie2 aligner as option for mapping, following Poullet and Orlando 2020 doi: [10.3389/fevo.2020.00105](https://doi.org/10.3389/fevo.2020.00105)
 
 ### `Fixed`
 

README.md

@@ -33,7 +33,7 @@ By default the pipeline currently performs the following:
 * Create reference genome indices for mapping (`bwa`, `samtools`, and `picard`)
 * Sequencing quality control (`FastQC`)
 * Sequencing adapter removal and for paired end data merging (`AdapterRemoval`)
-* Read mapping to reference using (`bwa aln`, `bwa mem` or `CircularMapper`)
+* Read mapping to reference using (`bwa aln`, `bwa mem`, `CircularMapper`, or `bowtie2`)
 * Post-mapping processing, statistics and conversion to bam (`samtools`)
 * Ancient DNA C-to-T damage pattern visualisation (`DamageProfiler`)
 * PCR duplicate removal (`DeDup` or `MarkDuplicates`)
@@ -66,7 +66,7 @@ Additional functionality contained by the pipeline currently includes:
 #### Biological Information
 
 * Mitochondrial to Nuclear read ratio calculation (`MtNucRatioCalculator`)
-* Statistical sex determination of human individuals (`SexDetErrmine`)
+* Statistical sex determination of human individuals (`Sex.DetERRmine`)
 
 #### Metagenomic Screening
 
@@ -178,8 +178,10 @@ If you've contributed and you're missing in here, please let us know and we will
   * Vågene, Å.J. et al., 2018. Salmonella enterica genomes from victims of a major sixteenth-century epidemic in Mexico. Nature ecology & evolution, 2(3), pp.520–528. Available at: [http://dx.doi.org/10.1038/s41559-017-0446-6](http://dx.doi.org/10.1038/s41559-017-0446-6).
   * Herbig, A. et al., 2016. MALT: Fast alignment and analysis of metagenomic DNA sequence data applied to the Tyrolean Iceman. bioRxiv, p.050559. Available at: [http://biorxiv.org/content/early/2016/04/27/050559](http://biorxiv.org/content/early/2016/04/27/050559).
 * **MaltExtract** Huebler, R. et al., 2019. HOPS: Automated detection and authentication of pathogen DNA in archaeological remains. bioRxiv, p.534198. Available at: [https://www.biorxiv.org/content/10.1101/534198v1?rss=1](https://www.biorxiv.org/content/10.1101/534198v1?rss=1). Download: [https://github.com/rhuebler/MaltExtract](https://github.com/rhuebler/MaltExtract)
-* **Kraken2**     Wood, D et al., 2019. Improved metagenomic analysis with Kraken 2. Genome Biology volume 20, Article number: 257. Available at: [https://doi.org/10.1186/s13059-019-1891-0](https://doi.org/10.1186/s13059-019-1891-0). Download: [https://ccb.jhu.edu/software/kraken2/](https://ccb.jhu.edu/software/kraken2/)
+* **Kraken2** Wood, D et al., 2019. Improved metagenomic analysis with Kraken 2. Genome Biology volume 20, Article number: 257. Available at: [https://doi.org/10.1186/s13059-019-1891-0](https://doi.org/10.1186/s13059-019-1891-0). Download: [https://ccb.jhu.edu/software/kraken2/](https://ccb.jhu.edu/software/kraken2/)
 * **endorS.py** Aida Andrades Valtueña (Unpublished). Download: [https://github.com/aidaanva/endorS.py](https://github.com/aidaanva/endorS.py)
+* **Bowtie2**  Langmead, B. and Salzberg, S. L. 2012 Fast gapped-read alignment with Bowtie 2. Nature methods, 9(4), p. 357–359. doi: [10.1038/nmeth.1923](https:/dx.doi.org/10.1038/nmeth.1923).
+* **sequenceTools** Stephan Schiffels (Unpublished). Download: [https://github.com/stschiff/sequenceTools](https://github.com/stschiff/sequenceTools)
 
 ## Data References
 

assets/multiqc_config.yaml

@@ -9,6 +9,7 @@ report_comment: >
 
 run_modules:
     - adapterRemoval
+    - bowtie2
     - custom_content
     - damageprofiler
     - dedup
@@ -56,6 +57,7 @@ extra_fn_clean_exts:
     - '.unifiedgenotyper'
     - '.trimmed_stats'
     - '_libmerged'
+    - '_bt2'
 
 
 top_modules:
@@ -68,8 +70,11 @@ top_modules:
     - 'fastqc':
        name: 'FastQC (post-AdapterRemoval)'
        path_filters:
-           - '*.truncated_fastqc.zip'
-           - '*.combined*_fastqc.zip'
+            - '*.truncated_fastqc.zip'
+            - '*.combined*_fastqc.zip'
+    - 'bowtie2':
+       path_filters:
+            - '*_bt2.log'
     - 'malt'
     - 'hops'
     - 'kraken'
@@ -117,6 +122,8 @@ table_columns_visible:
         percent_duplicates: False
         total_sequences: True
         percent_gc: True
+    bowtie2:
+        overall_alignment_rate: True
     MALT:
         Taxonomic assignment success: False
         Assig. Taxonomy: False
@@ -167,6 +174,8 @@ table_columns_placement:
         total_sequences: 400
         avg_sequence_length: 410
         percent_gc: 420
+    Bowtie 2 / HiSAT2:
+        overall_alignment_rate: 450
     MALT:
         Num. of queries: 430
         Total reads: 440
@@ -181,14 +190,14 @@ table_columns_placement:
     Samtools Flagstat (post-samtools filter):
         flagstat_total: 553
         mapped_passed: 554
+    custom_content:
+        endogenous_dna: 600
+        endogenous_dna_post: 610
     DeDup:
-        mapped_after_dedup: 600
-        clusterfactor: 610
+        mapped_after_dedup: 620
+        clusterfactor: 630
     Picard:
         PERCENT_DUPLICATION: 650
-    custom_content:
-        endogenous_dna: 680
-        endogenous_dna_post: 690
     DamageProfiler:
         5 Prime1: 700
         5 Prime2: 710

bin/scrape_software_versions.py

@@ -8,11 +8,12 @@
     'Nextflow': ['v_nextflow.txt', r"(\S+)"],
     'FastQC': ['v_fastqc.txt', r"FastQC v(\S+)"],
     'AdapterRemoval':['v_adapterremoval.txt', r"AdapterRemoval ver. (\S+)"],
-    'Picard MarkDuplicates': ['v_markduplicates.txt', r"([\d\.]+)-SNAPSHOT"],
+    'Picard MarkDuplicates': ['v_markduplicates.txt', r"(\S+)"],
     'Samtools': ['v_samtools.txt', r"samtools (\S+)"],
     'Preseq': ['v_preseq.txt', r"Version: (\S+)"],
     'MultiQC': ['v_multiqc.txt', r"multiqc, version (\S+)"],
-    'BWA': ['v_bwa.txt', r"Version: (\S+)"],
+    'BWA': ['v_bwa.txt', r"Version: (\S+)"], 
+    'Bowtie2': ['v_bowtie2.txt', r"bowtie2-([0-9]+\.[0-9]+\.[0-9]+) -fdebug"],
     'Qualimap': ['v_qualimap.txt', r"QualiMap v.(\S+)"],
     'GATK HaplotypeCaller': ['v_gatk.txt', r" v(\S+)"],
     #'GATK UnifiedGenotyper': ['v_gatk3_5.txt', r"version (\S+)"],
@@ -24,7 +25,7 @@
     'circulargenerator':['v_circulargenerator.txt',r"CircularGeneratorv(\S+)"],
     'DeDup':['v_dedup.txt',r"DeDup v(\S+)"],
     'freebayes':['v_freebayes.txt',r"v([0-9]\S+)"],
-    'Sequence Tools':['v_sequencetools.txt',r"v([0-9]\S+)"],
+    'sequenceTools':['v_sequencetools.txt',r"(\S+)"],
     'maltextract':['v_maltextract.txt', r"version(\S+)"],
     'malt':['v_malt.txt',r"version (\S+)"],
     'multivcfanalyzer':['v_multivcfanalyzer.txt', r"MultiVCFAnalyzer - (\S+)"],
@@ -43,6 +44,7 @@
 results['AdapterRemoval'] = '<span style="color:#999999;\">N/A</span>'
 results['fastP'] = '<span style="color:#999999;\">N/A</span>'
 results['BWA'] = '<span style="color:#999999;\">N/A</span>'
+results['Bowtie2'] = '<span style="color:#999999;\">N/A</span>'
 results['circulargenerator'] = '<span style="color:#999999;\">N/A</span>'
 results['Samtools'] = '<span style="color:#999999;\">N/A</span>'
 results['endorS.py'] = '<span style="color:#999999;\">N/A</span>'