Merge pull request qbic-pipelines#213 from WackerO/smrna

Add smrnaseq functionality -->check the test in a follow-up PR
WackerO · Aug 7, 2023 · 58c57cf · 58c57cf
2 parents f2183ea + fccbb4c
commit 58c57cf
Show file tree

Hide file tree

Showing 33 changed files with 36,348 additions and 169 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -74,6 +74,7 @@ jobs:
             "test_contrast_list",
             "test_no_multiqc",
             "test_relevel",
+            "test_smrnaseq",
             "test_star_rsem",
             "test_star_salmon",
             "test_use_vst",

diff --git a/.prettierignore b/.prettierignore
@@ -6,6 +6,7 @@ work/
 data/
 results/
 .DS_Store
+testdata/
 testing/
 testing*
 *.pyc

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- [#213](https://github.com/qbic-pipelines/rnadeseq/pull/21) Added smrnaseq input support
 - [#212](https://github.com/qbic-pipelines/rnadeseq/pull/212) Added computational methods if no --software_versions
 - [#206](https://github.com/qbic-pipelines/rnadeseq/pull/206) Added logic to decide between rlog and vst, added tryCatch for heatmap saving because this only works unreliably
 - [#202](https://github.com/qbic-pipelines/rnadeseq/pull/202) Added background list to pathway analysis

diff --git a/assets/RNAseq_report.Rmd b/assets/RNAseq_report.Rmd
diff --git a/assets/references.bibtex b/assets/references.bibtex
@@ -1,95 +1,95 @@
 @article{ewels2016multiqc,
-    title={MultiQC: summarize analysis results for multiple tools and samples in a single report},
-    author={Ewels, Philip and Magnusson, M{\aa}ns and Lundin, Sverker and K{\"a}ller, Max},
-    journal={Bioinformatics},
-    volume={32},
-    number={19},
-    pages={3047--3048},
-    year={2016},
-    publisher={Oxford University Press}
+title={MultiQC: summarize analysis results for multiple tools and samples in a single report},
+author={Ewels, Philip and Magnusson, M{\aa}ns and Lundin, Sverker and K{\"a}ller, Max},
+journal={Bioinformatics},
+volume={32},
+number={19},
+pages={3047--3048},
+year={2016},
+publisher={Oxford University Press}
 }
 @article{kim2015hisat,
-    title={HISAT: a fast spliced aligner with low memory requirements},
-    author={Kim, Daehwan and Langmead, Ben and Salzberg, Steven L},
-    journal={Nature methods},
-    volume={12},
-    number={4},
-    pages={357},
-    year={2015},
-    publisher={Nature Publishing Group}
+title={HISAT: a fast spliced aligner with low memory requirements},
+author={Kim, Daehwan and Langmead, Ben and Salzberg, Steven L},
+journal={Nature methods},
+volume={12},
+number={4},
+pages={357},
+year={2015},
+publisher={Nature Publishing Group}
 }
 @article{wang2012rseqc,
-    title={RSeQC: quality control of RNA-seq experiments},
-    author={Wang, Liguo and Wang, Shengqin and Li, Wei},
-    journal={Bioinformatics},
-    volume={28},
-    number={16},
-    pages={2184--2185},
-    year={2012},
-    publisher={Oxford University Press}
+title={RSeQC: quality control of RNA-seq experiments},
+author={Wang, Liguo and Wang, Shengqin and Li, Wei},
+journal={Bioinformatics},
+volume={28},
+number={16},
+pages={2184--2185},
+year={2012},
+publisher={Oxford University Press}
 }
 @article{liao2014featurecounts,
-    title={featureCounts: an efficient general purpose program for assigning sequence reads to genomic features},
-    author={Liao, Yang and Smyth, Gordon K and Shi, Wei},
-    journal={Bioinformatics},
-    volume={30},
-    number={7},
-    pages={923--930},
-    year={2014}
+title={featureCounts: an efficient general purpose program for assigning sequence reads to genomic features},
+author={Liao, Yang and Smyth, Gordon K and Shi, Wei},
+journal={Bioinformatics},
+volume={30},
+number={7},
+pages={923--930},
+year={2014}
 }
 @article{love2014differential,
-    title={Differential analysis of count data--the DESeq2 package},
-    author={Love, Michael and Anders, Simon and Huber, Wolfgang},
-    journal={Genome Biol},
-    volume={15},
-    pages={550},
-    year={2014}
+title={Differential analysis of count data--the DESeq2 package},
+author={Love, Michael and Anders, Simon and Huber, Wolfgang},
+journal={Genome Biol},
+volume={15},
+pages={550},
+year={2014}
 }
 @article{Li2009,
-    author = {Li, Heng and Durbin, Richard},
-    title = {Fast and Accurate Short Read Alignment with Burrows--Wheeler Transform},
-    journal = {Bioinformatics},
-    issue_date = {July 2009},
-    volume = {25},
-    number = {14},
-    month = jul,
-    year = {2009},
-    issn = {1367-4803},
-    pages = {1754--1760},
-    numpages = {7},
-    url = {http://dx.doi.org/10.1093/bioinformatics/btp324},
-    doi = {10.1093/bioinformatics/btp324},
-    acmid = {1576130},
-    publisher = {Oxford University Press},
-    address = {Oxford, UK},
+author = {Li, Heng and Durbin, Richard},
+title = {Fast and Accurate Short Read Alignment with Burrows--Wheeler Transform},
+journal = {Bioinformatics},
+issue_date = {July 2009},
+volume = {25},
+number = {14},
+month = jul,
+year = {2009},
+issn = {1367-4803},
+pages = {1754--1760},
+numpages = {7},
+url = {http://dx.doi.org/10.1093/bioinformatics/btp324},
+doi = {10.1093/bioinformatics/btp324},
+acmid = {1576130},
+publisher = {Oxford University Press},
+address = {Oxford, UK},
 }
 @article{Lex2014,
-    doi = {10.1109/tvcg.2014.2346248},
-    url = {https://doi.org/10.1109/tvcg.2014.2346248},
-    year    = {2014},
-    month = {dec},
-    publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},
-    volume = {20},
-    number = {12},
-    pages = {1983--1992},
-    author = {Alexander Lex and Nils Gehlenborg and Hendrik Strobelt and Romain Vuillemot and Hanspeter Pfister},
-    title = {{UpSet}: Visualization of Intersecting Sets},
-    journal = {{IEEE} Transactions on Visualization and Computer Graphics}
+doi = {10.1109/tvcg.2014.2346248},
+url = {https://doi.org/10.1109/tvcg.2014.2346248},
+year    = {2014},
+month = {dec},
+publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},
+volume = {20},
+number = {12},
+pages = {1983--1992},
+author = {Alexander Lex and Nils Gehlenborg and Hendrik Strobelt and Romain Vuillemot and Hanspeter Pfister},
+title = {{UpSet}: Visualization of Intersecting Sets},
+journal = {{IEEE} Transactions on Visualization and Computer Graphics}
 }
 @article{Cingolani2012,
-    title={Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift},
-    author={Cingolani, P. and Patel, V.M. and Coon, M. and Nguyen, T. and Land, S.J. and Ruden, D.M. and Lu, X.},
-    journal={Frontiers in Genetics},
-    volume={3},
-    year={2012},
-    publisher={Frontiers Media SA}
+title={Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift},
+author={Cingolani, P. and Patel, V.M. and Coon, M. and Nguyen, T. and Land, S.J. and Ruden, D.M. and Lu, X.},
+journal={Frontiers in Genetics},
+volume={3},
+year={2012},
+publisher={Frontiers Media SA}
 }
 @article{Garrison2012,
-    title={Haplotype-based variant detection from short-read sequencing},
-    author={Garrison, E. and Marth, G.},
-    journal={arXiv:1207.3907},
-    publisher={[q-bio.GN]},
-    year={2012}
+title={Haplotype-based variant detection from short-read sequencing},
+author={Garrison, E. and Marth, G.},
+journal={arXiv:1207.3907},
+publisher={[q-bio.GN]},
+year={2012}
 }
 @article{Dobin2013,
 author = {Dobin, A. and Davis, C.A. and Schlesinger, F. and Drenkow, J. and Zaleski, C. and Jha, S. and Batut, P. and Chaisson, M. and Gingeras, T.R.},
@@ -168,51 +168,109 @@ title="dupRadar: a Bioconductor package for the assessment of PCR artifacts in R
 journal="BMC Bioinformatics",
 }
 @article{krueger2012trim,
-    title={Trim Galore: a wrapper tool around Cutadapt and FastQC to consistently apply quality and adapter trimming to FastQ files, with some extra functionality for MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries},
-    author={Krueger, F},
-    journal={URL http://www.bioinformatics.babraham.ac.uk/projects/trim\_galore/},
-    year={2012}
+title={Trim Galore: a wrapper tool around Cutadapt and FastQC to consistently apply quality and adapter trimming to FastQ files, with some extra functionality for MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries},
+author={Krueger, F},
+journal={URL http://www.bioinformatics.babraham.ac.uk/projects/trim\_galore/},
+year={2012}
 }
 @article{sayols2016dupradar,
-    title={dupRadar: a Bioconductor package for the assessment of PCR artifacts in RNA-Seq data},
-    author={Sayols, Sergi and Scherzinger, Denise and Klein, Holger},
-    journal={BMC bioinformatics},
-    volume={17},
-    number={1},
-    pages={428},
-    year={2016},
-    publisher={BioMed Central}
+title={dupRadar: a Bioconductor package for the assessment of PCR artifacts in RNA-Seq data},
+author={Sayols, Sergi and Scherzinger, Denise and Klein, Holger},
+journal={BMC bioinformatics},
+volume={17},
+number={1},
+pages={428},
+year={2016},
+publisher={BioMed Central}
 }
 @misc{andrews2010fastqc,
-    title={FastQC: a quality control tool for high throughput sequence data},
-    author={Andrews, Simon and others},
-    year={2010}
+title={FastQC: a quality control tool for high throughput sequence data},
+author={Andrews, Simon and others},
+year={2010}
 }
 @Book{ggplot,
-    author = {Hadley Wickham},
-    title = {ggplot2: Elegant Graphics for Data Analysis},
-    publisher = {Springer-Verlag New York},
-    year = {2016},
-    isbn = {978-3-319-24277-4},
-    url = {http://ggplot2.org},
+author = {Hadley Wickham},
+title = {ggplot2: Elegant Graphics for Data Analysis},
+publisher = {Springer-Verlag New York},
+year = {2016},
+isbn = {978-3-319-24277-4},
+url = {http://ggplot2.org},
 }
 @article{anders2012detecting,
-    title={Detecting differential usage of exons from RNA-seq data},
-    author={Anders, Simon and Reyes, Alejandro and Huber, Wolfgang},
-    journal={Genome research},
-    volume={22},
-    number={10},
-    pages={2008--2017},
-    year={2012},
-    publisher={Cold Spring Harbor Lab}
+title={Detecting differential usage of exons from RNA-seq data},
+author={Anders, Simon and Reyes, Alejandro and Huber, Wolfgang},
+journal={Genome research},
+volume={22},
+number={10},
+pages={2008--2017},
+year={2012},
+publisher={Cold Spring Harbor Lab}
 }
 @article{ewels2020nf,
-    title={The nf-core framework for community-curated bioinformatics pipelines},
-    author={Ewels, Philip A and Peltzer, Alexander and Fillinger, Sven and Patel, Harshil and Alneberg, Johannes and Wilm, Andreas and Garcia, Maxime Ulysse and Di Tommaso, Paolo and Nahnsen, Sven},
-    journal={Nature biotechnology},
-    volume={38},
-    number={3},
-    pages={276--278},
-    year={2020},
-    publisher={Nature Publishing Group}
+title={The nf-core framework for community-curated bioinformatics pipelines},
+author={Ewels, Philip A and Peltzer, Alexander and Fillinger, Sven and Patel, Harshil and Alneberg, Johannes and Wilm, Andreas and Garcia, Maxime Ulysse and Di Tommaso, Paolo and Nahnsen, Sven},
+journal={Nature biotechnology},
+volume={38},
+number={3},
+pages={276--278},
+year={2020},
+publisher={Nature Publishing Group}
+}
+@article{kang2018mirtrace,
+title={miRTrace reveals the organismal origins of microRNA sequencing data},
+author={Kang, Wenjing and Eldfjell, Yrin and Fromm, Bastian and Estivill, Xavier and Biryukova, Inna and Friedl{\"a}nder, Marc R},
+journal={Genome biology},
+volume={19},
+number={1},
+pages={1--15},
+year={2018},
+publisher={BioMed Central}
+}
+@article{langmead2009ultrafast,
+title={Ultrafast and memory-efficient alignment of short DNA sequences to the human genome},
+author={Langmead, Ben and Trapnell, Cole and Pop, Mihai and Salzberg, Steven L},
+journal={Genome biology},
+volume={10},
+number={3},
+pages={1--10},
+year={2009},
+publisher={BioMed Central}
+}
+@article{chen2018fastp,
+title={fastp: an ultra-fast all-in-one FASTQ preprocessor},
+author={Chen, Shifu and Zhou, Yanqing and Chen, Yaru and Gu, Jia},
+journal={Bioinformatics},
+volume={34},
+number={17},
+pages={i884--i890},
+year={2018},
+publisher={Oxford University Press}
+}
+@article{chen2023ultrafast,
+title={Ultrafast one-pass FASTQ data preprocessing, quality control, and deduplication using fastp},
+author={Chen, Shifu},
+journal={iMeta},
+pages={e107},
+year={2023},
+publisher={Wiley Online Library}
+}
+@article{li2009sequence,
+title={The sequence alignment/map format and SAMtools},
+author={Li, Heng and Handsaker, Bob and Wysoker, Alec and Fennell, Tim and Ruan, Jue and Homer, Nils and Marth, Gabor and Abecasis, Goncalo and Durbin, Richard and 1000 Genome Project Data Processing Subgroup},
+journal={bioinformatics},
+volume={25},
+number={16},
+pages={2078--2079},
+year={2009},
+publisher={Oxford University Press}
+}
+@article{li2011statistical,
+title={A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data},
+author={Li, Heng},
+journal={Bioinformatics},
+volume={27},
+number={21},
+pages={2987--2993},
+year={2011},
+publisher={Oxford University Press}
 }
diff --git a/conf/test_smrnaseq.config b/conf/test_smrnaseq.config
@@ -0,0 +1,32 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow config file for running tests
+ * -------------------------------------------------
+ * Defines bundled input files and everything required
+ * to run a fast and simple test. Use as follows:
+ *   nextflow run qbic-pipelines/rnadeseq -profile test_smrnaseq
+ */
+
+params {
+    config_profile_name = 'Test smrnaseq'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+    // Limit resources so that this can run on Travis
+    max_cpus = 2
+    max_memory = 6.GB
+    max_time = 48.h
+    // Input data
+    input = 'testdata/smrnaseq/samplesheet.tsv'
+    gene_counts = 'testdata/smrnaseq/counts'
+    model = 'testdata/smrnaseq/design.txt'
+    logFC_threshold = 1
+    project_summary = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/summary.tsv'
+    software_versions = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/software_versions_smrnaseq.yml'
+    genelist = 'testdata/smrnaseq/requested_genes.txt'
+    input_type = 'smrnaseq'
+    run_pathway_analysis = true
+    genome = 'GRCh37'
+    batch_effect = true
+    set_background = false // This is solely to get some enriched pathways so that the github tests also check the pathway analysis output
+    // species_library     = "org.Hs.eg.db"
+    // organism    = "hsapiens"
+}