diff --git a/faqs/galaxy/features_scratchbook.md b/faqs/galaxy/features_scratchbook.md index 216dfa4115d52a..0489ab285854c8 100644 --- a/faqs/galaxy/features_scratchbook.md +++ b/faqs/galaxy/features_scratchbook.md @@ -1,20 +1,20 @@ --- -title: Using the Scratchbook to view multiple datasets +title: Using the Window Manager to view multiple datasets area: features box_type: tip layout: faq contributors: [shiltemann,hexylena] --- -If you would like to view two or more datasets at once, you can use the **Scratchbook** feature in Galaxy: - 1. **Click** on the *Scratchbook* icon {% icon galaxy-scratchbook%} on the top menu bar. +If you would like to view two or more datasets at once, you can use the **Window Manager** feature in Galaxy: + 1. **Click** on the *Window Manager* icon {% icon galaxy-scratchbook%} on the top menu bar. - You should see a little checkmark on the icon now 2. **View** {% icon galaxy-eye %} a dataset by clicking on the eye icon {% icon galaxy-eye %} to view the output - You should see the output in a window overlayed over Galaxy - You can resize this window by dragging the bottom-right corner - 3. **Click** outside the file to exit the Scratchbook + 3. **Click** outside the file to exit the Window Manager 4. **View** {% icon galaxy-eye %} a second dataset from your history - You should now see a second window with the new dataset - This makes it easier to compare the two outputs 5. Repeat this for as many files as you would like to compare - 6. You can turn off the **Scratchbook** {% icon galaxy-scratchbook %} by clicking on the icon again + 6. You can turn off the **Window Manager** {% icon galaxy-scratchbook %} by clicking on the icon again diff --git a/learning-pathways/amr-gene-detection.md b/learning-pathways/amr-gene-detection.md index 99850e55508052..4fd06affc3c966 100644 --- a/learning-pathways/amr-gene-detection.md +++ b/learning-pathways/amr-gene-detection.md @@ -32,10 +32,8 @@ pathway: tutorials: - name: mrsa-illumina topic: assembly -# - name: mrsa-nanopore -# topic: assembly -# - name: hybrid-assembly -# topic: assembly + - name: mrsa-nanopore + topic: assembly - section: "Module: Genome annotation" description: | diff --git a/topics/assembly/tutorials/mrsa-nanopore/images/bandage_before_polishing.jpg b/topics/assembly/tutorials/mrsa-nanopore/images/bandage_before_polishing.jpg new file mode 100644 index 00000000000000..be9e31ccc6cc79 Binary files /dev/null and b/topics/assembly/tutorials/mrsa-nanopore/images/bandage_before_polishing.jpg differ diff --git a/topics/assembly/tutorials/mrsa-nanopore/images/fastqc.png b/topics/assembly/tutorials/mrsa-nanopore/images/fastqc.png new file mode 100644 index 00000000000000..c3cabe50a10004 Binary files /dev/null and b/topics/assembly/tutorials/mrsa-nanopore/images/fastqc.png differ diff --git a/topics/assembly/tutorials/mrsa-nanopore/images/nanoplot_after.png b/topics/assembly/tutorials/mrsa-nanopore/images/nanoplot_after.png new file mode 100644 index 00000000000000..0c70eba390fd60 Binary files /dev/null and b/topics/assembly/tutorials/mrsa-nanopore/images/nanoplot_after.png differ diff --git a/topics/assembly/tutorials/mrsa-nanopore/images/nanoplot_before.png b/topics/assembly/tutorials/mrsa-nanopore/images/nanoplot_before.png new file mode 100644 index 00000000000000..a9e4f55e0dbae5 Binary files /dev/null and b/topics/assembly/tutorials/mrsa-nanopore/images/nanoplot_before.png differ diff --git a/topics/assembly/tutorials/mrsa-nanopore/tutorial.bib b/topics/assembly/tutorials/mrsa-nanopore/tutorial.bib index e6b7a177c69a78..e621c9b94886a5 100644 --- a/topics/assembly/tutorials/mrsa-nanopore/tutorial.bib +++ b/topics/assembly/tutorials/mrsa-nanopore/tutorial.bib @@ -1,15 +1,26 @@ -@article{Hikichi_2019, - doi = {10.1128/mra.01212-19}, - url = {https://doi.org/10.1128%2Fmra.01212-19}, +@article{Alcock_2019, + doi = {10.1093/nar/gkz935}, + url = {https://doi.org/10.1093%2Fnar%2Fgkz935}, year = 2019, - month = {nov}, - publisher = {American Society for Microbiology}, - volume = {8}, - number = {47}, - author = {Miyako Hikichi and Miki Nagao and Kazunori Murase and Chihiro Aikawa and Takashi Nozawa and Akemi Yoshida and Taisei Kikuchi and Ichiro Nakagawa}, - editor = {Irene L. G. Newton}, - title = {Complete Genome Sequences of Eight Methicillin-Resistant Staphylococcus aureus Strains Isolated from Patients in Japan}, - journal = {Microbiology Resource Announcements} + month = {oct}, + publisher = {Oxford University Press ({OUP})}, + author = {Brian P Alcock and Amogelang R Raphenya and Tammy T Y Lau and Kara K Tsang and M{\'{e}}gane Bouchard and Arman Edalatmand and William Huynh and Anna-Lisa V Nguyen and Annie A Cheng and Sihan Liu and Sally Y Min and Anatoly Miroshnichenko and Hiu-Ki Tran and Rafik E Werfalli and Jalees A Nasir and Martins Oloni and David J Speicher and Alexandra Florescu and Bhavya Singh and Mateusz Faltyn and Anastasia Hernandez-Koutoucheva and Arjun N Sharma and Emily Bordeleau and Andrew C Pawlowski and Haley L Zubyk and Damion Dooley and Emma Griffiths and Finlay Maguire and Geoff L Winsor and Robert G Beiko and Fiona S L Brinkman and William W L Hsiao and Gary V Domselaar and Andrew G McArthur}, + title = {{CARD} 2020: antibiotic resistome surveillance with the comprehensive antibiotic resistance database}, + journal = {Nucleic Acids Research} +} + +@article{Carattoli2014, + doi = {10.1128/aac.02412-14}, + url = {https://doi.org/10.1128/aac.02412-14}, + year = {2014}, + month = apr, + publisher = {American Society for Microbiology}, + volume = {58}, + number = {7}, + pages = {3895--3903}, + author = {Alessandra Carattoli and Ea Zankari and Aurora Garc{\'{\i}}a-Fern{\'{a}}ndez and Mette Voldby Larsen and Ole Lund and Laura Villa and Frank M{\o}ller Aarestrup and Henrik Hasman}, + title = {In {SilicoDetection} and Typing of Plasmids using {PlasmidFinder} and Plasmid Multilocus Sequence Typing}, + journal = {Antimicrobial Agents and Chemotherapy} } @article{Gurevich2013, @@ -26,6 +37,157 @@ @article{Gurevich2013 journal = {Bioinformatics} } +@article{Hikichi_2019, + doi = {10.1128/mra.01212-19}, + url = {https://doi.org/10.1128%2Fmra.01212-19}, + year = 2019, + month = {nov}, + publisher = {American Society for Microbiology}, + volume = {8}, + number = {47}, + author = {Miyako Hikichi and Miki Nagao and Kazunori Murase and Chihiro Aikawa and Takashi Nozawa and Akemi Yoshida and Taisei Kikuchi and Ichiro Nakagawa}, + editor = {Irene L. G. Newton}, + title = {Complete Genome Sequences of Eight Methicillin-Resistant Staphylococcus aureus Strains Isolated from Patients in Japan}, + journal = {Microbiology Resource Announcements} +} + +@article{koren2017canu, + title={Canu: scalable and accurate long-read assembly via adaptive k-mer weighting and repeat separation}, + author={Koren, Sergey and Walenz, Brian P and Berlin, Konstantin and Miller, Jason R and Bergman, Nicholas H and Phillippy, Adam M}, + journal={Genome research}, + volume={27}, + number={5}, + pages={722--736}, + year={2017}, + publisher={Cold Spring Harbor Lab}, + doi={10.1101/gr.215087.116} +} + +@article{Li_2016, + author = {Li, Heng}, + journal = {Bioinformatics}, + number = {14}, + year = {2016}, + month = {3}, + pages = {2103--2110}, + publisher = {Oxford University Press (OUP)}, + title = {Minimap and miniasm: fast mapping and de novo assembly for noisy long sequences}, + volume = {32}, + doi={10.1093/bioinformatics/btw152} +} + +@article{Li_2009, + author = {Li, H. and Durbin, R.}, + journal = {Bioinformatics}, + number = {14}, + year = {2009}, + month = {5}, + pages = {1754--1760}, + publisher = {Oxford University Press (OUP)}, + title = {Fast and accurate short read alignment with {Burrows}-{Wheeler} transform}, + volume = {25}, + doi={10.1093/bioinformatics/btp324} +} + +@article{Li_2010, + author = {Li, Heng and Durbin, Richard}, + journal = {Bioinformatics}, + number = {5}, + year = {2010}, + month = {1}, + pages = {589--595}, + publisher = {Oxford University Press (OUP)}, + title = {Fast and accurate long-read alignment with {Burrows}--{Wheeler} transform}, + volume = {26}, + doi={10.1093/bioinformatics/btp698} +} + +@misc{Li2013Aligning, + author = {Li, Heng}, + year = {2013}, + title = {Aligning sequence reads, clone sequences and assembly contigs with {BWA}-{MEM}}, + howpublished = {http://arxiv.org/abs/1303.3997}, + doi={10.48550/arXiv.1303.3997} +} + +@article{lin2016assembly, + title={Assembly of long error-prone reads using de Bruijn graphs}, + author={Lin, Yu and Yuan, Jeffrey and Kolmogorov, Mikhail and Shen, Max W and Chaisson, Mark and Pevzner, Pavel A}, + journal={Proceedings of the National Academy of Sciences}, + volume={113}, + number={52}, + pages={E8396--E8405}, + year={2016}, + publisher={National Acad Sciences}, + doi={10.1073/pnas.1604560113} +} + + +@article{Lozano_2012, + doi = {10.1128/aem.00870-12}, + url = {https://doi.org/10.1128%2Faem.00870-12}, + year = 2012, + month = {jun}, + publisher = {American Society for Microbiology}, + volume = {78}, + number = {16}, + pages = {5948--5955}, + author = {Carmen Lozano and Lourdes Garc{\'{\i}}a-Migura and Carmen Aspiroz and Myriam Zarazaga and Carmen Torres and Frank M{\o}ller Aarestrup}, + title = {Expansion of a Plasmid Classification System for Gram-Positive Bacteria and Determination of the Diversity of Plasmids in Staphylococcus aureus Strains of Human, Animal, and Food Origins}, + journal = {Applied and Environmental Microbiology} +} + +@article{vaser2021time, + title={Time-and memory-efficient genome assembly with Raven}, + author={Vaser, Robert and {\v{S}}iki{\'c}, Mile}, + journal={Nature Computational Science}, + volume={1}, + number={5}, + pages={332--336}, + year={2021}, + publisher={Nature Publishing Group US New York}, + doi={10.1038/s43588-021-00073-4} +} + +@article{Vaser_2017, + author = {Vaser, Robert and Sovi{\' c}, Ivan and Nagarajan, Niranjan and {\v S}iki{\' c}, Mile}, + journal = {Genome Research}, + number = {5}, + year = {2017}, + month = {1}, + pages = {737--746}, + publisher = {Cold Spring Harbor Laboratory}, + title = {Fast and accurate de novo genome assembly from long uncorrected reads}, + volume = {27}, + doi={10.1101/gr.214270.116} +} + +@article{wick2015bandage, + title={Bandage: interactive visualization of de novo genome assemblies}, + author={Wick, Ryan R and Schultz, Mark B and Zobel, Justin and Holt, Kathryn E}, + journal={Bioinformatics}, + volume={31}, + number={20}, + pages={3350--3352}, + year={2015}, + publisher={Oxford University Press}, + doi={10.1093/bioinformatics/btv383} +} + +@article{Wick_2022, + author = {Wick, Ryan R. and Holt, Kathryn E.}, + journal = {PLOS Computational Biology}, + editor = {Schneidman-Duhovny, Dina}, + number = {1}, + year = {2022}, + month = {1}, + pages = {e1009802}, + publisher = {Public Library of Science (PLoS)}, + title = {Polypolish: Short-read polishing of long-read bacterial genome assemblies}, + volume = {18}, + doi={10.1371/journal.pcbi.1009802} +} + @article{Zankari2012, doi = {10.1093/jac/dks261}, url = {https://doi.org/10.1093/jac/dks261}, @@ -54,43 +216,9 @@ @article{Zankari2017 journal = {Journal of Antimicrobial Chemotherapy} } -@article{Carattoli2014, - doi = {10.1128/aac.02412-14}, - url = {https://doi.org/10.1128/aac.02412-14}, - year = {2014}, - month = apr, - publisher = {American Society for Microbiology}, - volume = {58}, - number = {7}, - pages = {3895--3903}, - author = {Alessandra Carattoli and Ea Zankari and Aurora Garc{\'{\i}}a-Fern{\'{a}}ndez and Mette Voldby Larsen and Ole Lund and Laura Villa and Frank M{\o}ller Aarestrup and Henrik Hasman}, - title = {In {SilicoDetection} and Typing of Plasmids using {PlasmidFinder} and Plasmid Multilocus Sequence Typing}, - journal = {Antimicrobial Agents and Chemotherapy} -} -@article{Lozano_2012, - doi = {10.1128/aem.00870-12}, - url = {https://doi.org/10.1128%2Faem.00870-12}, - year = 2012, - month = {jun}, - publisher = {American Society for Microbiology}, - volume = {78}, - number = {16}, - pages = {5948--5955}, - author = {Carmen Lozano and Lourdes Garc{\'{\i}}a-Migura and Carmen Aspiroz and Myriam Zarazaga and Carmen Torres and Frank M{\o}ller Aarestrup}, - title = {Expansion of a Plasmid Classification System for Gram-Positive Bacteria and Determination of the Diversity of Plasmids in Staphylococcus aureus Strains of Human, Animal, and Food Origins}, - journal = {Applied and Environmental Microbiology} -} -@article{Alcock_2019, - doi = {10.1093/nar/gkz935}, - url = {https://doi.org/10.1093%2Fnar%2Fgkz935}, - year = 2019, - month = {oct}, - publisher = {Oxford University Press ({OUP})}, - author = {Brian P Alcock and Amogelang R Raphenya and Tammy T Y Lau and Kara K Tsang and M{\'{e}}gane Bouchard and Arman Edalatmand and William Huynh and Anna-Lisa V Nguyen and Annie A Cheng and Sihan Liu and Sally Y Min and Anatoly Miroshnichenko and Hiu-Ki Tran and Rafik E Werfalli and Jalees A Nasir and Martins Oloni and David J Speicher and Alexandra Florescu and Bhavya Singh and Mateusz Faltyn and Anastasia Hernandez-Koutoucheva and Arjun N Sharma and Emily Bordeleau and Andrew C Pawlowski and Haley L Zubyk and Damion Dooley and Emma Griffiths and Finlay Maguire and Geoff L Winsor and Robert G Beiko and Fiona S L Brinkman and William W L Hsiao and Gary V Domselaar and Andrew G McArthur}, - title = {{CARD} 2020: antibiotic resistome surveillance with the comprehensive antibiotic resistance database}, - journal = {Nucleic Acids Research} -} \ No newline at end of file + + diff --git a/topics/assembly/tutorials/mrsa-nanopore/tutorial.md b/topics/assembly/tutorials/mrsa-nanopore/tutorial.md index f72578753f1ed1..6ff8353d95ee1c 100644 --- a/topics/assembly/tutorials/mrsa-nanopore/tutorial.md +++ b/topics/assembly/tutorials/mrsa-nanopore/tutorial.md @@ -1,22 +1,19 @@ --- layout: tutorial_hands_on -title: Genome Assembly of MRSA using Oxford Nanopore MinION Data +title: Genome Assembly of MRSA from Oxford Nanopore MinION data (and optionally Illumina data) zenodo_link: 'https://zenodo.org/record/10669812' questions: -- How to check the quality of the MinION data? -- How to perform an assembly with MinION data? -- What species do I have and what is its sequence type? -- Which resistance genes are on my genome? -- Where are the genes located on my genome? +- How to check the quality of the MinION data (together with Illumina data)? +- How to perform an assembly of a bacterial genome with MinION data? +- How to check the quality of an assembly? objectives: -- Assess your data on quality and quantity -- Assemble a genome -- Assess your assembly quality -- Assess presence of antimicrobial resistance genes -- Perform a species identification and MLST typing -- Search for resistance genes on the assembly -- Find a gene on your genome using Prokka + JBrowse +- Run tools to evaluate sequencing data on quality and quantity +- Process the output of quality control tools +- Improve the quality of sequencing data +- Run a tool to assemble a bacterial genome using short reads +- Run tools to assess the quality of an assembly +- Understand the outputs of tools to assess the quality of an assembly time_estimation: 2h key_points: - Nanopore produces fantastic assemblies but with low quality data @@ -27,10 +24,13 @@ tags: - amr - gmod - jbrowse1 +- microgalaxy +level: Introductory contributions: authorship: - bazante1 + - bebatut editing: - hexylena - bazante1 @@ -38,12 +38,13 @@ contributions: - miaomiaozhou88 funding: - avans-atgm + - abromics follow_up_training: - type: "internal" - topic_name: visualisation + topic_name: genome-annotation tutorials: - - jbrowse + - amr-gene-detection - type: "internal" topic_name: galaxy-interface tutorials: @@ -53,12 +54,18 @@ abbreviations: SVs: Structural Variations --- +Sequencing (determining of DNA/RNA nucleotide sequence) is used all over +the world for all kinds of analysis. The product of these sequencers are +reads, which are sequences of detected nucleotides. Depending on the +technique these have specific lengths (30-500bp) or using Oxford +Nanopore Technologies sequencing have much longer variable lengths. +{% snippet faqs/galaxy/sequencing_nanopore.md %} -In this training you're going to make an assembly of data produced by +In this training we will build an assembly of a bacterial genome, from data produced in "Complete Genome Sequences of Eight Methicillin-Resistant *Staphylococcus aureus* Strains Isolated from Patients in -Japan" from {% cite Hikichi_2019 %} which describes: +Japan" {% cite Hikichi_2019 %}: > Methicillin-resistant *Staphylococcus aureus* (MRSA) is a major pathogen > causing nosocomial infections, and the clinical manifestations of MRSA @@ -76,20 +83,26 @@ Japan" from {% cite Hikichi_2019 %} which describes: > {: .agenda} -# Background +# Galaxy and data preparation -Sequencing (determining of DNA/RNA nucleotide sequence) is used all over -the world for all kinds of analysis. The product of these sequencers are -reads, which are sequences of detected nucleotides. Depending on the -technique these have specific lengths (30-500bp) or using Oxford -Nanopore Technologies sequencing have much longer variable lengths. +Any analysis should get its own Galaxy history. So let's start by creating a new one and get the data into it. -{% snippet faqs/galaxy/sequencing_nanopore.md %} +> History creation +> +> 1. Create a new history for this analysis +> +> {% snippet faqs/galaxy/histories_create_new.md %} +> +> 2. Rename the history +> +> {% snippet faqs/galaxy/histories_rename.md %} +> +{: .hands_on} + +Now, we need to import the data: 1 FASTQ file containing the reads from the sequencer. > Data upload -> -> 1. Create a new history for this tutorial -> 2. {% tool [Import](upload1) %} the files from [Zenodo]({{ page.zenodo_link }}) or from the shared data library +> 1. {% tool [Import](upload1) %} the files from [Zenodo]({{ page.zenodo_link }}) or from the shared data library > > ``` > {{ page.zenodo_link }}/files/DRR187567.fastq.bz2 @@ -99,138 +112,216 @@ Nanopore Technologies sequencing have much longer variable lengths. > > {% snippet faqs/galaxy/datasets_import_from_data_library.md %} > -> 3. Convert the datatype of this output to uncompress it -> -> {% snippet faqs/galaxy/datasets_convert_datatype.md conversion="Convert compressed to uncompressed" %} -> -> 4. Rename the dataset to just the sequence run ID: `DRR187567` +> 2. Rename the dataset to keep only the sequence run ID (`DRR187567`) > > {% snippet faqs/galaxy/datasets_rename.md name="DRR187567" %} > -> 5. Tag the dataset `#unfiltered` +> 3. Tag the dataset `#unfiltered` > > {% snippet faqs/galaxy/datasets_add_tag.md %} > -> 6. **View** {% icon galaxy-eye %} the renamed file -> -> > -> > -> > 1. What are the 4 main features of each read in a fastq file. -> > 2. What is the name of your first read? -> > -> > > -> > > 1. The following: -> > > -> > > - A `@` followed by a name and sometimes information of the read -> > > - A nucleotide sequence -> > > - A `+` (optional followed by the name) -> > > - The quality score per base of nucleotide sequence (Each symbol -> > > represents a quality score, which will be explained later) -> > > -> > > 2. `DRR187567.1` -> > {: .solution} -> {: .question} +> 4. **View** {% icon galaxy-eye %} the renamed file +> +{: .hands_on} + +The dataset is a FASTQ file. + +> +> +> 1. What are the 4 main features of each read in a fastq file. +> 2. What is the name of your first read? +> +> > +> > 1. The following: +> > +> > - A `@` followed by a name and sometimes information of the read +> > - A nucleotide sequence +> > - A `+` (optional followed by the name) +> > - The quality score per base of nucleotide sequence (Each symbol +> > represents a quality score, which will be explained later) +> > +> > 2. `DRR187567.1` +> {: .solution} +{: .question} + +{% include _includes/cyoa-choices.html option1="Without Illumina MiSeq data" option2="With Illumina MiSeq data" default="Without Illumina MiSeq data" text="Do you have associated Illumina MiSeq data?" disambiguation="miseq"%} + +
+ +> Illumina Data upload +> 1. {% tool [Import](upload1) %} the files from [Zenodo]({{ page.zenodo_link }}) or from the shared data library +> +> ``` +> {{ page.zenodo_link }}/files/DRR187559_1.fastqsanger.bz2 +> {{ page.zenodo_link }}/files/DRR187559_2.fastqsanger.bz2 +> ``` +> +> {% snippet faqs/galaxy/datasets_import_via_link.md %} +> +> {% snippet faqs/galaxy/datasets_import_from_data_library.md %} +> +> 2. Rename the datasets to remove `.fastqsanger.bz2` and keep only the sequence run ID (`DRR187559_1` and `DRR187559_2`) +> +> {% snippet faqs/galaxy/datasets_rename.md name="DRR187567" %} +> {: .hands_on} +
+ # Quality Control -When assessing the fastq files all bases had their own quality (or Phred score) -represented by symbols. You can read more in our dedicated [Quality Control -Tutorial]({% link topics/sequence-analysis/tutorials/quality-control/tutorial.md %}). +During sequencing, errors are introduced, such as incorrect nucleotides being called. These are due to the technical limitations of each sequencing platform. Sequencing errors might bias the analysis and can lead to a misinterpretation of the data. **Sequence quality control is therefore an essential first step in any analysis.** + +When assessing the fastq files all bases had their own quality (or Phred score) represented by symbols. You can read more in our dedicated [Quality Control Tutorial]({% link topics/sequence-analysis/tutorials/quality-control/tutorial.md %}). + +To assess the quality by hand would be too much work. That's why tools like [NanoPlot](https://github.com/wdecoster/NanoPlot) or +[FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) are made, which will generate a summary and plots of the data statistics. NanoPlot is mainly used for long-read data, like ONT and PACBIO and FastQC for any read. -To assess the quality by hand would be too much work. That's why tools like -[NanoPlot](https://github.com/wdecoster/NanoPlot) or -[FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) are made, -which will generate a summary and plots of the data statistics. NanoPlot is -mainly used for long-read data, like ONT and PACBIO and FastQC for short read, -like Illumina and Sanger. +> Quality Control +> +> 1. {% tool [FastQC](toolshed.g2.bx.psu.edu/repos/devteam/fastqc/fastqc/0.74+galaxy0) %} with the following parameters: +> - {% icon param-files %} *"Short read data from your current history"*: `DRR187567` +> +> 2. Inspect the webpage output +> +{: .hands_on} -Depending on the analysis it could be possible that a certain quality or length -is needed. The reads can be filtered using the tool -[Filtlong](https://github.com/rrwick/Filtlong). In this training all reads -below 1000bp will be filtered. +FastQC combines quality statistics from all separate reads and combines them in plots. An important plot is the Per base sequence quality. -Before doing any assembly, the first questions you should ask about your input -reads include: +![FastQC plot showing reads that mostly stay in the read](./images/fastqc.png) -- What is the coverage of my genome? -- How good are my reads? -- Do I need to ask/perform for a new sequencing run? -- Is it suitable for the analysis I need to do? +
-> QC & Filtering +Here, we are going to trim the Illumina data using **fastp** ({% cite Chen2018 %}): + +- Trim the start and end of the reads if those fall below a quality score of 20 +- Filter for reads to keep only reads with at least 30 bases: Anything shorter will complicate the assembly + +> Quality improvement of the Illumina reads +> +> 1. {% tool [fastp](toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/0.23.2+galaxy0) %} with the following parameters: +> - *"Single-end or paired reads"*: `Paired` +> - {% icon param-file %} *"Input 1"*: `DRR187559_1` +> - {% icon param-file %} *"Input 2"*: `DRR187559_2` +> - In *"Filter Options"*: +> - In *"Length filtering Options"*: +> - *Length required*: `30` +> - In *"Read Modification Options"*: +> - In *"Per read cuitting by quality options"*: +> - *Cut by quality in front (5')*: `Yes` +> - *Cut by quality in front (3')*: `Yes` +> - *Cutting window size*: `4` +> - *Cutting mean quality*: `20` +> - In *"Output Options"*: +> - *"Output JSON report"*: `Yes` > -> 1. {% tool [filtlong](toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.0) %} with the following parameters: -> - {% icon param-file %} *"Input FASTQ"*: `DRR187567` (output of **Convert compressed file to uncompressed.** {% icon tool %}) +{: .hands_on} + +
+ +Depending on the analysis it could be possible that a certain quality or length is needed. The reads can be filtered using the [Filtlong](https://github.com/rrwick/Filtlong) tool. In this training all reads below 1000bp will be filtered. + +
+ +When Illumina reads are available, we can use them **if they are good Illumina reads (high depth and complete coverage)** as external reference. In this case, Filtlong ignores the Phred quality scores and instead judges read quality using k-mer matches to the reference (a more accurate gauge of quality). + +
+ +> Filtering +> 1. {% tool [filtlong](toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.1+galaxy0) %} with the following parameters: +> - {% icon param-file %} *"Input FASTQ"*: `DRR187567` > - In *"Output thresholds"*: > - *"Min. length"*: `1000` > +>
+> - In *"External references"*: +> - {% icon param-file %} *"Reference Illumina read"*: **fastp** `Read 1 output` +> - {% icon param-file %} *"Reference Illumina read"*: **fastp** `Read 2 output` +>
+> > 2. Rename the dataset to `DRR187567-filtered` > > {% snippet faqs/galaxy/datasets_rename.md name="DRR187567-filtered" %} > -> 3. Tag the dataset `#filtered` +{: .hands_on} + +The output can be evaluated using **NanoPlot** for plotting long read sequencing data and alignments + +> Filtering +> 1. Convert the datatype of `DRR187567` to uncompress it > -> {% snippet faqs/galaxy/datasets_add_tag.md %} +> {% snippet faqs/galaxy/datasets_convert_datatype.md conversion="Convert compressed to uncompressed" %} > -> 3. {% tool [Nanoplot](toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.28.2+galaxy1) %} with the following parameters: +> 2. {% tool [NanoPlot](toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.41.0+galaxy0) %} with the following parameters: > - *"Select multifile mode"*: `batch` > - *"Type of the file(s) to work on"*: `fastq` -> - {% icon param-files %} *"files"*: **both** `DRR187567` and `DRR187567-filtered` +> - {% icon param-files %} *"files"*: **both** `DRR187567 uncompressed` and `DRR187567-filtered` > - In *"Options for customizing the plots created"*: > - *"Show the N50 mark in the read length histogram."*: `Yes` > {: .hands_on} -In principle we just ran the NanoPlot 2 times. For this reason, we have two -reports we want to view and compare! +We ran the **NanoPlot** two times: one for the raw reads (`DRR187567`) and one for the reads after filtering (`DRR187567-filtered`). -Comparing different output files is easier if we can view more than one dataset -simultaneously. The Scratchbook function allows us to build up a collection of -datasets that will be shown on the screen together. +For each run, **NanoPlot** generates 5 outputs: -{% snippet faqs/galaxy/features_scratchbook.md %} +- 2 plots: + - Histogram Read Length + - Histogram Read Length after log transformation -Open both NanoPlot HTML Reports and check the **General summary** section of each to compare the results: + ![before filtering, showing a large mostly gaussian curve](./images/nanoplot_before.png "Before filtering") + + ![after filtering, same curve as before but everything below 1000bp is gone](./images/nanoplot_after.png "After filtering") -General summary | Not Filtered | Filtered (Filtlong) | Change (%) -------------------- | -------------- | ------------------- | ---------- -Mean read length | 6,813.0 | 8,721.1 | 28.0% -Mean read quality | 9 | 9 | 0.0% -Median read length | 3,400.0 | 5,451.0 | 60.3% -Median read quality | 8.9 | 9.0 | -1.1% -Number of reads | 91,288.0 | 69,906.0 | -23.4% -Read length N50 | 14,810.0 | 15,102.0 | 2.0% -Total bases | 621,945,741.0 | 609,657,642.0 | -2.0% -Before | After ------- | ---- -![before filtering, showing a large mostly gaussian curve](../../images/mrsa/before.png) | ![after filtering, same curve as before but everything below 1000bp is gone](../../images/mrsa/after.png) +- 2 tabular files with statistics: one general and one after filtering. -> -> -> 1. What is the increase of your median read length? -> 2. What is the decrease in total bases? -> 3. What is coverage? -> 4. What would be the coverage before and after trimming, based on a genome size of 2.9 Mbp? -> -> > -> > 1. 3,400.0 to 5,451.0, a 60.3% increase -> > 2. -2.0% decrease, not a very significant decrease so our data was quite good to start with and didn't have many short reads which were removed. -> > 3. Coverage is a measure of, on average, how many reads 'cover' a single base in the genome. If you divide the total reads, by the genome size, you will get a number how many times your genomes could theoretically be ‘covered’ by reads. -> > 4. Before $$ \frac{621,945,741}{2,900,000} = 214.4$$ and after $$ \frac{609,657,642}{2,900,000} = 210.2$$. This is *not* a very big decrease in coverage, so no cause for concern. Generally in sequencing experiments you have some minimum coverage you expect to see based on how much of your sample you sequenced. If it falls below that threshold it might be cause for concern. -> > -> > Additionally many people do not do any filtering or QC steps with their NanoPore data, it is expected that the quality is low, and often the focus is on assembling large {SVs} rather than having high quality reads and base-level variation analyses. -> {: .solution} -{: .question} + The second one is empty because we did not used **NanoPlot** filtering options. + +- A HTML report summarizing above information + + We can compare the two generated reports. Galaxy allows to view several datasets side-by-side using the Window Manager function + + > Inspect NanoPlot reports + > + > 1. Enable Window Manager + > + > {% snippet faqs/galaxy/features_scratchbook.md %} + > + > 2. Open both NanoPlot HTML Reports + > 3. Check the **Summary statistics** section of each to compare the results + > + {: .hands_on} + + Summary statistics | Not Filtered | Filtered (Filtlong) | Change (%) + ------------------- | -------------- | ------------------- | ---------- + Number of reads | 91,288 | 69,906 | -23.4% + Number of bases | 621,945,741.0 | 609,657,642.0 | -2.0% + Median read length | 3,400.0 | 5,451.0 | 60.3% + Mean read length | 6,813.0 | 8,721.1 | 28.0% + Read length N50 | 14,810.0 | 15,102.0 | 2.0% + Mean read quality | 9 | 9 | 0.0% + Median read quality | 8.9 | 9.0 | 1.1% + + > + > + > 1. What is the increase of your median read length? + > 2. What is the decrease in the number of bases? + > 3. What is coverage? + > 4. What would be the coverage before and after trimming, based on a genome size of 2.9 Mbp? + > + > > + > > 1. 3,400 bp to 5,451 bp, a 60.3% increase + > > 2. A -2.0% decrease is not a very significant decrease. Our data was quite good to start with and didn't have many short reads which were removed (23.4%) + > > 3. The coverage is a measure of how many reads 'cover' on average a single base in the genome. If you divide the total reads by the genome size, you will get a number how many times your genomes could theoretically be "covered" by reads. + > > 4. Before $$ \frac{621,945,741}{2,900,000} = 214.4$$ and after $$ \frac{609,657,642}{2,900,000} = 210.2$$. This is *not* a very big decrease in coverage, so no cause for concern. Generally in sequencing experiments you have some minimum coverage you expect to see based on how much of your sample you sequenced. If it falls below that threshold it might be cause for concern. + > > + > {: .solution} + {: .question} -While there is currently no community consensus over -the best trimming or filtering practices with long read data, there are still -some steps that can be beneficial to do for the assembly process. -{% tool [Porechop](toolshed.g2.bx.psu.edu/repos/iuc/porechop/porechop/0.2.3) %} -is a commonly used tool for removing adapter sequences, and we used -{% tool [filtlong](toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.0) %} -for removing shorter reads which might make the assembly process more difficult. +While there is currently no community consensus over the best trimming or filtering practices with long read data, there are still some steps that can be beneficial to do for the assembly process. {% tool [Porechop](toolshed.g2.bx.psu.edu/repos/iuc/porechop/porechop/0.2.3) %} is a commonly used tool for removing adapter sequences, and we used {% tool [filtlong](toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.0) %} for removing shorter reads which might make the assembly process more difficult. + +Many people do not do any trimming of their NanoPore data based on the quality as it is expected that the quality is low, and often the focus is on assembling large {SVs} rather than having high quality reads and base-level variation analyses. # Assembly @@ -238,296 +329,181 @@ When the quality of the reads is determined and the data is filtered (like we did with filtlong) and/or trimmed (like is more often done with short read data) an assembly can be made. -There are many tools that create assembly for long-read data, but in this -tutorial [Flye](https://github.com/fenderglass/Flye) will be used. Flye is a de -novo assembler for single molecule sequencing reads. It can be used from -bacteria to human assemblies. The Flye assembly is based on finding overlapping -reads with variable length with high error tolerance. Flye will output the -assembly in a .fasta file, which looks like a .fastq file without the 3rd and -4th line for the "+" sign and the quality score. +There are many tools that create assembly for long-read data, e.g. Canu ({% cite koren2017canu %}), Raven ({% cite vaser2021time %}), Miniasm ({% cite Li_2016 %}). In this tutorial, we use [**Flye**](https://github.com/fenderglass/Flye) ({% cite lin2016assembly %}). **Flye** is a de +novo assembler for single molecule sequencing reads. It can be used from bacteria to human assemblies. The Flye assembly is based on finding overlapping reads with variable length with high error tolerance. {% snippet faqs/galaxy/analysis_results_may_vary.md %} > Assembly using Flye > -> 1. {% tool [Flye assembly](toolshed.g2.bx.psu.edu/repos/bgruening/flye/flye/2.6) %} with the following parameters: +> 1. {% tool [Flye assembly](toolshed.g2.bx.psu.edu/repos/bgruening/flye/flye/2.9.1+galaxy0) %} with the following parameters: > - {% icon param-file %} *"Input reads"*: `DRR187567-filtered` (output of **filtlong** {% icon tool %}) -> - *"estimated genome size (for example, 5m or 2.6g)"*: `2.8m` or `2800000` (average genome size of MRSA) -> -> 2. View {% icon galaxy-eye %} the `assembly_info` output and check the *General summary* table in the assembly info file, and compare the results. -> -> #seq_name | length | cov. | circ. | repeat | mult. | graph_path -> --------- | ------ | ---- | ----- | ------ | ----- | ---------- -> contig_1 | 60303 | 1504 | + | + | 6 | 1 -> contig_2 | 2927029 | 181 | + | - | 1 | 2 -> -> *NOTE: The results can differ from this example, because Flye can differ a bit per assembly* -> -> 3. {% tool [Bandage Image](toolshed.g2.bx.psu.edu/repos/iuc/bandage/bandage_image/0.8.1+galaxy2) %} with the following parameters: +> - *"Mode"*: `Nanopore corrected (--nano-corr)` +> - *"Reduced contig assembly coverage"*: `Disable reduced coverage for initial disjointing assembly` > -> - {% icon param-file %} *"Graphical Fragment Assembly"*: `Flye assembly on data .. (Graphical Fragment Assembly)` -> -> 4. View {% icon galaxy-eye %} the assembly graph image -> -> ![Bandage output showing two contigs, one big, one tiny](../../images/mrsa/bandage.png) {: .hands_on} -> -> -> 1. How many contigs do you have? -> 2. What is the coverage of your longest contig? -> 3. What is the length of your longest contig? -> 4. Does this feel like potentially a MRSA genome? -> -> > -> > While results may vary due to randomness in the assembly process, in our case we had: -> > -> > 1. 2 -> > 2. 181 -> > 2. 2.9mb -> > 3. Yes, you've got one 2.9Mb genome which is approximately the size of a MRSA genome, and one small potential plasmid genome. -> {: .solution} -{: .question} +**Flye** generates 4 outputs: -## QC +- A FASTA file called `consensus` with contigs, i.e. the contiguous sequences made by combining separate reads in the assembly, and possibly scaffolds built by **Flye** -[Quast](http://quast.bioinf.spbau.ru/) ({% cite Gurevich2013 %}) -is a tool providing quality metrics for assemblies, and can also be used -to compare multiple assemblies. The tool can also take an optional -reference file as input, and will provide complementary metrics. QUAST -stands for QUality ASsessment Tool. With later updates gene annotation -also possible with QUAST. + > + > + > How many contigs are there? + > > + > > + > > There are 2 sequences in the `consensus` dataset + > {: .solution} + {: .question} -> Quality Control of assembly using Quast -> -> 1. {% tool [Quast](toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.0.2+galaxy1) %} with the following parameters: -> - *"Use customized names for the input files?"*: `No, use dataset names` -> - {% icon param-file %} *"Contigs/scaffolds file"*: `consensus` (output of **Flye assembly** {% icon tool %}) -> -> 2. View {% icon galaxy-eye %} the HTML report from QUAST -> -> The Quast tool outputs assembly metrics as an html file with metrics and -> graphs. The image below looks exceptionally boring. This is a good -> thing, because each corner means one contig. A contig is the contiguous -> sequence made by combining all separate reads in the assembly -> -> ![Image showing the HTML output of quast including a table over conting information and a cumulative length graph with the contigs.](../../images/mrsa/quast.png) -> -{: .hands_on} +- 2 assembly graph files: `assembly graph` and `graphical fragment assembly` -One can see that there are two contigs. The largest contig is 2,927,008 -bp (for comparison [MRSA Isolate HC1335 -Strain](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5174738/) genome -length was 2,976,370 bp) and the smallest is 2,987,958 (total length) - -2,927,008 (length of the largest) = 60,950 bp. sequencing. The length of -the largest contig can mean that it is the total chromosomal DNA of the *S. aureus*. + We can visualize the assembly graph using the `graphical fragment assembly` with **Bandage** ({% cite wick2015bandage %}), a package for exploring assembly graphs through summary reports and visualizations of their contents. -> -> -> 1. What is you GC content? -> -> > -> > -> > 1. The GC content for our assembly was 32.73% (for comparison [MRSA Isolate HC1335 Strain](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5174738/) GC% is 32.89%). This means the length and GC% of the assembly could be good! -> > -> {: .solution} -{: .question} + > Assembly inspection + > 1. {% tool [Bandage Image](toolshed.g2.bx.psu.edu/repos/iuc/bandage/bandage_image/2022.09+galaxy4) %} with the following parameters: + > - {% icon param-file %} *"Graphical Fragment Assembly"*: `graphical fragment assembly` (output of **Flye**) + > + {: .hands_on} -# Identification of AMR Genes + ![Bandage output showing 2 contigs](./images/bandage_before_polishing.jpg) -Because we are working with a MRSA we are curious to see which resistance genes are located on the genome or on the plasmid. To determine whether the contigs contain antimicrobial resistance (AMR) genes [staramr](https://github.com/phac-nml/staramr) can be used **Staramr** scans bacterial genome contigs against both the **ResFinder** ({% cite Zankari2012 %}), **PointFinder** ({% cite Zankari2017 %}), and **PlasmidFinder** ({% cite Carattoli2014 %}) databases (used by the ResFinder webservice) and compiles a summary report of detected antimicrobial resistance genes. +- A table `assembly info` with assembly information -> Run staramr -> -> 1. {% tool [staramr](toolshed.g2.bx.psu.edu/repos/nml/staramr/staramr_search/0.7.1+galaxy2) %} with the following parameters: -> - {% icon param-file %} *"genomes"*: `consensus` (output of **Flye assembly** {% icon tool %}) -> -> There are 7 different output files produced by **staramr** tool: -> -> File | Contents -> --------------------- | --- -> summary.tsv | A summary of all detected AMR genes/mutations in each genome, one genome per line. -> detailed_summary.tsv | A detailed summary of all detected AMR genes/mutations of each genome, one line per feature and multiple lines per genome. -> resfinder.tsv | A tabular file of each AMR gene and additional BLAST information from the **ResFinder** database, one gene per line. -> Plasmidfinder.tsv | A tabular file of each plastid sequences with additional BLAST information from the **PlasmidFinder** database, one sequence per line. -> settings.txt | The command-line, database versions, and other settings used to run staramr. -> mlst.tsv | A tabular file of the found loci per genome with its specified MLST scheme. -> results.xlsx | An Excel spreadsheet containing the previous 4 files as separate worksheets. -> -> 2. View {% icon galaxy-eye %} the detailed_summary.tsv file -> - In this example the ST-typing could not be obtained. Multi-locus sequence type (MLST) is based on specific locus/alleles, which is sometimes hard to determine with error rich sequence data (like NanoPore). -> - For the plasmid and resistance results the identity, overlap, length and the location on the contig can be found here. -> - Multiple rep sequences are located on the second contig. (See "plasmid typing for gram-positive bacteria" {% cite Lozano_2012 %} for more information) -> - Multiple resistance genes can be found on both contig 1 and contig 2. -> - In the last column there are "Accession" numbers. These are references to NCBI, and you can search for these numbers there. E.g. [M13771](https://www.ncbi.nlm.nih.gov/nuccore/M13771) -> -{: .hands_on} + It should be something similar but probably sligtly different because Flye can differ a bit per assembly: + + #seq_name | length | cov. | circ. | repeat | mult. | alt_group | graph_path + --------- | ------ | ---- | ----- | ------ | ----- | --------- | ---------- + contig_1 | 2927029 | 183 | Y | N | 2 | * | 1 + contig_2 | 60115 | 379 | Y | Y | 2 | * | 2 + > + > 1. What is the coverage of your longest contig? + > 2. What is the length of your longest contig? + > 3. Could this contig potentially be a MRSA genome? + > + > > + > > While results may vary due to randomness in the assembly process, in our case we had: + > > 1. 183 + > > 2. 2.9Mb + > > 3. 2.9Mb is approximately the size of a MRSA genome. So contig 1 could be the genome. Contig 2 could be one small potential plasmid genome. + > {: .solution} + {: .question} -## CARD database +## Assembly Evaluation -To get more information about these antibiotic resistant genes, you can check the [CARD database](https://card.mcmaster.ca) (**C**omprehensive **A**ntibiotic **R**esistance **D**atabase) ({% cite Jia2016 %}) +To evaluate the assembly, we use also [Quast](http://quast.bioinf.spbau.ru/) ({% cite Gurevich2013 %}) (QUality ASsessment Tool), a tool providing quality metrics for assemblies. This tool can be used to compare multiple assemblies, can take an optional reference file as input to provide complementary metrics, etc -![Screenshot of mecA sequence in CARD database with lots of metadata](../../images/mrsa/card.png "Screenshot of the CARD database interface. CARD gives information about the antibiotic resistance genes, as well as links to relevant publications.") +> Quality Control of assembly using Quast +> +> 1. {% tool [Quast](toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.2.0+galaxy1) %} with the following parameters: +> - *Assembly mode?*: `Co-assembly` +> - *"Use customized names for the input files?"*: `No, use dataset names` +> - {% icon param-file %} *"Contigs/scaffolds file"*: `consensus` output of **Flye** +> +{: .hands_on} -CARD can be very helpful to check all the resistance genes and check if -it is logical to find the resistance gene in a specific bacteria. +QUAST outputs assembly metrics as an HTML file with metrics and graphs. > > -> 1. To what family does [mecA](https://card.mcmaster.ca/ontology/36911) belong? -> 2. Do you expect to find this gene in this MRSA strain and why? -> 3. Is the accession number of the entry related to the accession reported by staramr? +> 1. How many contigs is there? +> 2. How long is the largest contig? +> 3. What is the total length of all contigs? +> 4. What is you GC content? +> 5. How does it compare to results for KUN1163 in [Table 1](https://journals.asm.org/doi/10.1128/mra.01212-19#tab1) in {% cite Hikichi_2019 %}? > > > > > -> > 1. [Methicillin resistant PBP2](https://card.mcmaster.ca/ontology/37589) -> > 2. The strain we use is a Methicillin(multi) resistant Staphylococcus aureus. As `mecA` has a perfect resistome mach with *S. aureus*, and the AMR Gene Family is methicillin resistant PBP2, we expect to see mecA in MRSA. -> > 3. No, these are completely unrelated. Unfortunately this is a **very** common issue in bioinformatics. Everyone builds their own numbering system for entries in their database (usually calling them 'accessions'), and then someone else needs to build a service to link these databases. +> > 1. 2 contigs +> > 2. The largest contig is 2,907,099 bp. +> > 3. 2,967,214 (*Total length (>= 0 bp)*). +> > 4. The GC content for our assembly is 32.91%. +> > 5. KUN1163 has a genome size of 2,914,567 bp (not far from the length of the largest contig), with a GC content of 32.91% (as in our assembly) > > > {: .solution} {: .question} -## Gene annotation using Prokka - -[Prokka](https://github.com/tseemann/prokka/blob/master/README.md) is a -tool software tool to rapidly annotate bacterial, archaeal and viral -genomes. Prokka will be used on your own made genome (assembly). Prokka -will try to annotate the bacteria based on related species and starting -codons can be chosen or default of the species can be used. - -[JBrowse](https://jbrowse.org/docs/tutorial.html) is used to visualize -your genome file and merge multiple outputs.\ -In this case you will use your assembly as your reference and the output -from prokka as an information track. - - -> Annotating the Genome -> -> 1. {% tool [Prokka](toolshed.g2.bx.psu.edu/repos/crs4/prokka/prokka/1.14.5+galaxy0) %} with the following parameters: -> - {% icon param-file %} *"Contigs to annotate"*: `consensus` (output of **Flye assembly** {% icon tool %}) -> - *"Genus name (--genus)"*: `staphylococcus ` -> - *"Species name (--species)"*: `aureus` -> - *"Kingdom (--kingdom)"*: `Bacteria` -> - *"Additional outputs"*: Select only the "Annotation in GFF3 format containing both sequences and annotations" -> -> 2. {% tool [Select lines that match an expression](Grep1) %} with the following parameters: -> - {% icon param-file %} *"Select lines from"*: `staramr on data .. detailed_summary.tsv` -> - *"that"*: Matching -> - *"the pattern"*: `[0-9]+\.[0-9]+\t` -> -> This will select lines with a decimal value (###.##) followed by a tab character, the column separator in Galaxy. As a result, any lines without an identity value will be filtered out. -> -> 3. {% tool [Table to GFF3](toolshed.g2.bx.psu.edu/repos/iuc/tbl2gff3/tbl2gff3/1.2) %} -> - {% icon param-file %} *"Table"*: the output of the above **Select lines** {% icon tool %} step. -> - *"Record ID column or value"*: `8` -> - *"Feature start column or value"*: `9` -> - *"Feature end column or value"*: `10` -> - *"Feature score column or value"*: `5` -> - *"Feature source column or value"*: `3` -> - {% icon param-repeat %} *"Insert Qualifiers"* -> - *"Name"*: `Name` -> - *"Qualifier value column or raw text"*: `2` -> - {% icon param-repeat %} *"Insert Qualifiers"* -> - *"Name"*: `phenotype` -> - *"Qualifier value column or raw text"*: `4` -> - {% icon param-repeat %} *"Insert Qualifiers"* -> - *"Name"*: `accession` -> - *"Qualifier value column or raw text"*: `11` -> -> 4. {% tool [Map with minimap2](toolshed.g2.bx.psu.edu/repos/iuc/minimap2/minimap2/2.17+galaxy2) %} with the following parameters: -> - *"Will you select a reference genome from your history or use a built-in index?"*: `Use a genome from the history and build index` -> - {% icon param-file %} *"Use the following dataset as the reference sequence"*: `consensus` (output of **Flye assembly** {% icon tool %}) -> - *"Single or Paired-end reads"*: `Single` -> - *"Select fastq dataset"*: `DRR187567-filtered` -> - *"Select a profile of preset options"*: `Oxford Nanopore read to reference mapping. Slightly more sensitive for Oxford Nanopore to reference mapping (-k15). For PacBio reads, HPC minimizers consistently leads to faster performance and more sensitive results in comparison to normal minimizers. For Oxford Nanopore data, normal minimizers are better, though not much. The effectiveness of HPC is determined by the sequencing error mode. (map-ont)` -> -> 5. {% tool [JBrowse](toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.9+galaxy0) %} with the following parameters: -> - *"Reference genome to display"*: `Use a genome from history` -> - {% icon param-file %} *"Select the reference genome"*: `consensus` (output of **Flye assembly** {% icon tool %}) -> - *"Genetic Code"*: `11. The Bacterial, Archaeal and Plant Plastid Code` -> - In *"Track Group"*: -> - {% icon param-repeat %} *"Insert Track Group"* -> - *"Track Category"*: `Prokka` -> - In *"Annotation Track"*: -> - {% icon param-repeat %} *"Insert Annotation Track"* -> - *"Track Type"*: `GFF/GFF3/BED Features` -> - {% icon param-file %} *"GFF/GFF3/BED Track Data"*: `out_gff` (output of **Prokka** {% icon tool %}) -> - *"JBrowse Track Type [Advanced]"*: `Neat Canvas Features` -> - *"Track Visibility"*: `On for new users` -> - {% icon param-repeat %} *"Insert Track Group"* -> - *"Track Category"*: `AMR` -> - In *"Annotation Track"*: -> - {% icon param-repeat %} *"Insert Annotation Track"* -> - *"Track Type"*: `GFF/GFF3/BED Features` -> - {% icon param-file %} *"GFF/GFF3/BED Track Data"*: `Table to GFF3 on ...`, the output of the table to gff3 step -> - *"JBrowse Track Type [Advanced]"*: `Neat Canvas Features` -> - *"Track Visibility"*: `On for new users` -> - {% icon param-repeat %} *"Insert Track Group"* -> - *"Track Category"*: `Sequencing` -> - In *"Annotation Track"*: -> - {% icon param-repeat %} *"Insert Annotation Track"* -> - *"Track Type"*: `BAM Pileups` -> - {% icon param-file %} *"BAM Track Data"*: Minimap2's output -> - *"Autogenerate SNP Track"*: `Yes` -> -> 3. View the output of JBrowse -> -{: .hands_on} - -If it takes too long to build the JBrowse instance, you can view an embedded one here. (**Warning**: feature name search will not work.) - -{% snippet topics/visualisation/faqs/visualizations_jbrowse.html datadir="data" tracks="DNA,d6de62f94b0de381be4ee8f27dd61ab9_0,81dca2c0e6930aa541a1a88927ed51dd_0" %} +
-A useful option is the "search features" option +## Assembly Polishing -1. Under the **View** menu click on the **Search Features** option +We can now polish the assembly using both the short reads and/or long reads. This process aligns the reads to the assembly contigs, and makes corrections to the contigs where warranted. - ![Screenshot of jbrowse top menu with search features button](../../images/mrsa/search-features.png) +Several tools exist for polishing, e.g. Racon ({% cite Vaser_2017 %}). Here we will use **Polypolish** ({% cite Wick_2022 %}), a tool for polishing genome assemblies with short reads. - Now we are going to search for the aac(6')-aph(2'') gene (the resistance gene we found with the staramr (resfinder) results) +**Polypolish** needs as input the assembly but also SAM/BAM files where each read has been aligned to *all* possible locations (not just a single best location). Errors in repeats will be covered by short-read alignments, and **Polypolish** can therefore fix those errors. -2. Type in the search bar: aac(6')-aph(2'') +To get the SAM/BAM files, we need to map the short reads on the assembly. We will use **BWA-MEM** ({% cite Li_2009 %}, {% cite Li_2010 %}, {% cite Li2013Aligning %}). - You won't find any results, because the names can be different for different database. +We need to set up **BWA-MEM** so it aligns each read to all possible locations, not just the best location. This option does not work with paired-end alignment. We will then need to align forward and reverse read files separately, instead of aligning both read files with a single BWA-MEM run as usually recommended. -3. Now only type: `aac` and you'll find multiple results. - - ![Screenshot of search table showing multiple results](../../images/mrsa/search-results.png) - - -4. Now go back to the staramr (resfinder) results and check the starting position of the aac(6')-aph(2'') genes match the prokka results. - -5. You can also use the location from the resfinder results by typing - your coordinates, and you also can highlight specific - parts. - - For example if an aac(6')-aph(2'') region was found on contig_2 with start 39209 and end 37755, you could write `contig_2:39209..37755` in the search box to go directly to that region. +> Align short-reads on assembly +> 1. Change the datatype of both FASTQ outputs of **fastp** to `fastqsanger.gz` +> +> {% snippet faqs/galaxy/datasets_change_datatype.md datatype="fastqsanger.gz" %} +> +> 2. {% tool [BWA-MEM2](toolshed.g2.bx.psu.edu/repos/iuc/bwa_mem2/bwa_mem2/2.2.1+galaxy1) %} with the following parameters: +> - *"Will you select a reference genome from your history or use a built-in index?"*: `Use a genome from history and build index` +> - {% icon param-file %} *"Use the following dataset as the reference sequence"*: `consensus` output of **Flye** +> - *"Single or Paired-end reads"*: `Single` +> - {% icon param-files %} *"Select fastq dataset"*: both outputs of **fastp** +> - *"Set read groups information?"*: `Do not set` +> - *"Select analysis mode"*: `5.Full list of options` +> - *"Set algorithmic options?"*: `Do not set` +> - *"Set scoring options?"*: `Do not set` +> - *"Set input/output options"*: `Set` +> - *"Output all alignments for single-ends or unpaired paired-ends"*: `Yes` +> - *"BAM sorting mode"*: `Not sorted (sorted as input)` +> +{: .hands_on} - ![entering a location directly in jbrowse](../../images/mrsa/enter-loc.png) +We can now run **Polypolish**. -6. After browsing to the region, under **view** press **Set highlight** and use the current region +> Polish assembly +> +> 1. {% tool [Polypolish](toolshed.g2.bx.psu.edu/repos/iuc/polypolish/polypolish/0.5.0+galaxy2) %} with the following parameters: +> - In *"Input sequences"*: +> - {% icon param-file %} *"Select a draft genome for polishing"*: `consensus` output of **Flye** +> - *"Select aligned data to polish"*: `Paired SAM/BAM files` +> - {% icon param-file %} *"Select forward SAM/BAM file"*: output of **BWA-MEM2** on the `Read 1` output of **fastp** +> - {% icon param-file %} *"Select reverse SAM/BAM file"*: output of **BWA-MEM2** on the `Read 2` output of **fastp** +> +{: .hands_on} - Now you can easily see that the aac(6')-aph(2'') gene in - resfinder is much bigger than the genes found by prokka. +To check the impact of the polishing, let's run **QUAST** on both **Flye** and **Polypolish** outputs. - ![highlighted region covering multiple genes in jbrowse](../../images/mrsa/highlight.png) +> Quality Control of polished assembly +> +> 1. {% tool [Quast](toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.2.0+galaxy1) %} with the following parameters: +> - *Assembly mode?*: `Co-assembly` +> - *"Use customized names for the input files?"*: `No, use dataset names` +> - {% icon param-files %} *"Contigs/scaffolds file"*: `consensus` output of **Flye** and output of **Polypolish** +> +{: .hands_on} - So always know what you're searching for and specify which tools - were used with which databases! +The HTML report generated by **QUAST** gives metrics for both assembly side-by-side -In this tutorial Jbrowse was only used for showing the locations of your -found genes, but it can be used with many more inputs. +Statistics | **Flye** output | **Polypolish** output +--- | --- | --- +Number of contigs | 2 | 2 +Largest contig | 2,907,099 | 2,915,230 +Total length (>= 0 bp) | 2,967,214 | 2,975,666 +GC (%) | 32.91 | 32.84 > > -> 1. Did the location of the aac(6')-aph(2'') regions in staramr correspond with any of the found genes in the prokka/jbrowse output? +> Is the assembly after polishing better than before given the results for KUN1163 in [Table 1](https://journals.asm.org/doi/10.1128/mra.01212-19#tab1) in {% cite Hikichi_2019 %}? > > > -> > 1. Yes, multiple aacA-aphD genes are found within the staramr annotated aac(6')-aph(2'') region +> > +> > The largest contig after polishing has a length of 2,915,230 bp, which closr to the expected 2,914,567 bp. But the GC content (32.84% after polishing) is slightly worst given the expected 32.91% also found in the assembly before polishing. +> > > {: .solution} {: .question} +
# Conclusion +In this tutorial, we prepared long reads (using short reads if we had some) assembled them, inspect the produced assembly for its quality, and polished it (if short reads where provided). The assembly, even if uncomplete, is reasonable good to be used in downstream analysis, like [AMR gene detection]({% link topics/genome-annotation/tutorials/amr-gene-detection/tutorial.md %}) \ No newline at end of file diff --git a/topics/assembly/tutorials/mrsa-nanopore/workflows/main-workflow-tests.yml b/topics/assembly/tutorials/mrsa-nanopore/workflows/main-workflow-tests.yml new file mode 100644 index 00000000000000..979363a8346c24 --- /dev/null +++ b/topics/assembly/tutorials/mrsa-nanopore/workflows/main-workflow-tests.yml @@ -0,0 +1,46 @@ +- doc: Test outline for Genome-Assembly-of-MRSA-using-Oxford-Nanopore-MinION-(and-Illumina-data-if-available) + job: + Illumina reverse raw reads: + class: File + location: https://zenodo.org/record/10669812/files/DRR187567.fastq.bz2 + filetype: fastqsanger.bz2 + Illumina forward raw reads: + class: File + location: https://zenodo.org/record/10669812/files/DRR187559_1.fastqsanger.bz2 + filetype: fastqsanger.bz2 + Nanopore raw reads: + class: File + location: https://zenodo.org/record/10669812/files/DRR187559_2.fastqsanger.bz2 + filetype: fastqsanger.bz2 + outputs: + nanoplot_before_filtering: + asserts: + has_text: + text: "number_of_reads" + has_text: + text: "91288" + has_n_lines: + n: 24 + nanoplot_after_filtering: + asserts: + has_text: + text: "number_of_reads" + has_n_lines: + n: 24 + flye_assembly_info: + asserts: + has_text: + text: "contig_1" + has_n_lines: + n: 2 + quast_report_before_polishing: + asserts: + has_text: + text: "Flye" + + quast_report_after_polishing: + asserts: + has_text: + text: "Flye" + has_text: + text: "Polypolish" \ No newline at end of file diff --git a/topics/assembly/tutorials/mrsa-nanopore/workflows/main-workflow.ga b/topics/assembly/tutorials/mrsa-nanopore/workflows/main-workflow.ga new file mode 100644 index 00000000000000..a1242ea70f250c --- /dev/null +++ b/topics/assembly/tutorials/mrsa-nanopore/workflows/main-workflow.ga @@ -0,0 +1,755 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "Genome Assembly of MRSA from Oxford Nanopore MinION data (and optionally Illumina data)", + "creator": [ + { + "class": "Person", + "identifier": "https://orcid.org/0000-0003-2255-1631", + "name": "Bazante Sanders" + }, + { + "class": "Person", + "identifier": "https://orcid.org/0000-0001-9852-1987", + "name": "B\u00e9r\u00e9nice Batut" + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "Genome Assembly of MRSA using Oxford Nanopore MinION (and Illumina data if available)", + "steps": { + "0": { + "annotation": "Nanopore raw reads", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Nanopore raw reads", + "name": "Nanopore raw reads" + } + ], + "label": "Nanopore raw reads", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 65.66800632871802, + "top": 217.27323322511424 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "cd4fd302-af94-4771-9b80-7c7acb6619d4", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "Illumina forward raw reads", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Illumina forward raw reads", + "name": "Illumina forward raw reads" + } + ], + "label": "Illumina forward raw reads", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 0, + "top": 479 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "b3fe89da-544c-4066-abcb-b33d4f005796", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "Illumina reverse raw reads", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Illumina reverse raw reads", + "name": "Illumina reverse raw reads" + } + ], + "label": "Illumina reverse raw reads", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 0, + "top": 602 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "16545abc-0513-4a32-9ea5-4a168875a854", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "CONVERTER_bz2_to_uncompressed", + "errors": null, + "id": 3, + "input_connections": { + "input1": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Convert compressed file to uncompressed.", + "outputs": [ + { + "name": "output1", + "type": "auto" + } + ], + "position": { + "left": 352.64512461709074, + "top": 252.6654375258992 + }, + "post_job_actions": { + "ChangeDatatypeActionoutput1": { + "action_arguments": { + "newtype": "fastqsanger" + }, + "action_type": "ChangeDatatypeAction", + "output_name": "output1" + } + }, + "tool_id": "CONVERTER_bz2_to_uncompressed", + "tool_state": "{\"__input_ext\": \"input\", \"__target_datatype__\": \"fastqsanger\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"input1\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.1", + "type": "tool", + "uuid": "6b12fdbd-8285-4641-9f6e-fea33cd1d96d", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/fastqc/fastqc/0.74+galaxy0", + "errors": null, + "id": 4, + "input_connections": { + "input_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "FastQC", + "outputs": [ + { + "name": "html_file", + "type": "html" + }, + { + "name": "text_file", + "type": "txt" + } + ], + "position": { + "left": 570.0128283788754, + "top": 0 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/fastqc/fastqc/0.74+galaxy0", + "tool_shed_repository": { + "changeset_revision": "5ec9f6bceaee", + "name": "fastqc", + "owner": "devteam", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"fastqsanger.bz2\", \"adapters\": null, \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"contaminants\": null, \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"kmers\": \"7\", \"limits\": null, \"min_length\": null, \"nogroup\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.74+galaxy0", + "type": "tool", + "uuid": "01722ab1-6bd2-40f3-ab62-5d8aa4848fb3", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/0.23.2+galaxy0", + "errors": null, + "id": 5, + "input_connections": { + "single_paired|in1": { + "id": 1, + "output_name": "output" + }, + "single_paired|in2": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "fastp", + "outputs": [ + { + "name": "out1", + "type": "input" + }, + { + "name": "out2", + "type": "input" + }, + { + "name": "report_html", + "type": "html" + }, + { + "name": "report_json", + "type": "json" + } + ], + "position": { + "left": 223.01666259765625, + "top": 797 + }, + "post_job_actions": { + "ChangeDatatypeActionout1": { + "action_arguments": { + "newtype": "fastqsanger.gz" + }, + "action_type": "ChangeDatatypeAction", + "output_name": "out1" + }, + "ChangeDatatypeActionout2": { + "action_arguments": { + "newtype": "fastqsanger.gz" + }, + "action_type": "ChangeDatatypeAction", + "output_name": "out2" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/0.23.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "65b93b623c77", + "name": "fastp", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"auto\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"filter_options\": {\"quality_filtering_options\": {\"disable_quality_filtering\": false, \"qualified_quality_phred\": \"30\", \"unqualified_percent_limit\": null, \"n_base_limit\": null}, \"length_filtering_options\": {\"disable_length_filtering\": false, \"length_required\": null, \"length_limit\": null}, \"low_complexity_filter\": {\"enable_low_complexity_filter\": false, \"complexity_threshold\": null}}, \"output_options\": {\"report_html\": true, \"report_json\": true}, \"overrepresented_sequence_analysis\": {\"overrepresentation_analysis\": false, \"overrepresentation_sampling\": null}, \"read_mod_options\": {\"polyg_tail_trimming\": {\"trimming_select\": \"\", \"__current_case__\": 1, \"poly_g_min_len\": null}, \"polyx_tail_trimming\": {\"polyx_trimming_select\": \"\", \"__current_case__\": 1}, \"umi_processing\": {\"umi\": false, \"umi_loc\": null, \"umi_len\": null, \"umi_prefix\": null}, \"cutting_by_quality_options\": {\"cut_by_quality5\": true, \"cut_by_quality3\": true, \"cut_window_size\": \"4\", \"cut_mean_quality\": \"20\"}, \"base_correction_options\": {\"correction\": false}}, \"single_paired\": {\"single_paired_selector\": \"paired\", \"__current_case__\": 1, \"in1\": {\"__class__\": \"ConnectedValue\"}, \"in2\": {\"__class__\": \"ConnectedValue\"}, \"adapter_trimming_options\": {\"disable_adapter_trimming\": false, \"adapter_sequence1\": null, \"adapter_sequence2\": null}, \"global_trimming_options\": {\"trim_front1\": null, \"trim_tail1\": null, \"trim_front2\": null, \"trim_tail2\": null}}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.23.2+galaxy0", + "type": "tool", + "uuid": "ac85f962-516c-4ff7-a8c3-98ea92f09d1f", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.41.0+galaxy0", + "errors": null, + "id": 6, + "input_connections": { + "mode|reads|files": { + "id": 3, + "output_name": "output1" + } + }, + "inputs": [], + "label": null, + "name": "NanoPlot", + "outputs": [ + { + "name": "output_html", + "type": "html" + }, + { + "name": "nanostats", + "type": "tabular" + }, + { + "name": "nanostats_post_filtering", + "type": "tabular" + }, + { + "name": "read_length", + "type": "png" + }, + { + "name": "log_read_length", + "type": "png" + } + ], + "position": { + "left": 598.8807084399002, + "top": 268.83097889129806 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.41.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "0f1c34698076", + "name": "nanoplot", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"customization\": {\"color\": null, \"plots\": null, \"N50\": true}, \"filter\": {\"maxlength\": null, \"minlength\": null, \"drop_outliers\": false, \"downsample\": null, \"loglength\": false, \"percentqual\": false, \"alength\": false, \"minqual\": null, \"runtime_until\": null, \"readtype\": null, \"barcoded\": false, \"no_supplementary\": false}, \"mode\": {\"choice\": \"batch\", \"__current_case__\": 0, \"reads\": {\"type\": \"fastq\", \"__current_case__\": 0, \"files\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.41.0+galaxy0", + "type": "tool", + "uuid": "ad46f297-04f2-4959-aa09-db88cd91cc27", + "when": null, + "workflow_outputs": [ + { + "label": "nanoplot_before_filtering", + "output_name": "nanostats", + "uuid": "a97e6f33-8182-4a33-86dd-6cfbb83a842d" + } + ] + }, + "7": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.1+galaxy0", + "errors": null, + "id": 7, + "input_connections": { + "external_references|illumina_1": { + "id": 5, + "output_name": "out1" + }, + "external_references|illumina_2": { + "id": 5, + "output_name": "out2" + }, + "input_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "filtlong", + "outputs": [ + { + "name": "outfile", + "type": "fastqsanger" + } + ], + "position": { + "left": 570.0128323555666, + "top": 593 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.1+galaxy0", + "tool_shed_repository": { + "changeset_revision": "1f296803dfa3", + "name": "filtlong", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"external_references\": {\"assembly\": null, \"illumina_1\": {\"__class__\": \"ConnectedValue\"}, \"illumina_2\": {\"__class__\": \"ConnectedValue\"}}, \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"other\": {\"window_size\": \"250\"}, \"output_thresholds\": {\"target_bases\": null, \"keep_percent\": null, \"max_length\": null, \"min_length\": \"1000\", \"min_mean_q\": null, \"min_window_q\": null}, \"read_manipulation\": {\"trim\": false, \"split\": null}, \"score_weights\": {\"length_weight\": \"1.0\", \"mean_q_weight\": \"1.0\", \"window_q_weight\": \"1.0\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.2.1+galaxy0", + "type": "tool", + "uuid": "3c61c7b3-84c1-43d4-b106-9fb2e5c37d12", + "when": null, + "workflow_outputs": [] + }, + "8": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/flye/flye/2.9.1+galaxy0", + "errors": null, + "id": 8, + "input_connections": { + "inputs": { + "id": 7, + "output_name": "outfile" + } + }, + "inputs": [], + "label": null, + "name": "Flye", + "outputs": [ + { + "name": "consensus", + "type": "fasta" + }, + { + "name": "assembly_graph", + "type": "graph_dot" + }, + { + "name": "assembly_gfa", + "type": "txt" + }, + { + "name": "assembly_info", + "type": "tabular" + } + ], + "position": { + "left": 850.0098909589506, + "top": 593 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/flye/flye/2.9.1+galaxy0", + "tool_shed_repository": { + "changeset_revision": "cb8dfd28c16f", + "name": "flye", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"asm\": {\"asm_select\": \"false\", \"__current_case__\": 1}, \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"generate_log\": false, \"inputs\": {\"__class__\": \"ConnectedValue\"}, \"iterations\": \"1\", \"keep_haplotypes\": false, \"meta\": false, \"min_overlap\": null, \"mode_conditional\": {\"mode\": \"--nano-corr\", \"__current_case__\": 1}, \"no_alt_contigs\": false, \"scaffold\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.9.1+galaxy0", + "type": "tool", + "uuid": "8cf7ff30-4007-49cb-a959-e25c337f05be", + "when": null, + "workflow_outputs": [ + { + "label": "flye_assembly_info", + "output_name": "assembly_info", + "uuid": "f12e718f-1bd5-490d-bd41-f0747aaa41a6" + } + ] + }, + "9": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.41.0+galaxy0", + "errors": null, + "id": 9, + "input_connections": { + "mode|reads|files": { + "id": 7, + "output_name": "outfile" + } + }, + "inputs": [], + "label": null, + "name": "NanoPlot", + "outputs": [ + { + "name": "output_html", + "type": "html" + }, + { + "name": "nanostats", + "type": "tabular" + }, + { + "name": "nanostats_post_filtering", + "type": "tabular" + }, + { + "name": "read_length", + "type": "png" + }, + { + "name": "log_read_length", + "type": "png" + } + ], + "position": { + "left": 850.0098909589506, + "top": 859 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.41.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "0f1c34698076", + "name": "nanoplot", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"customization\": {\"color\": null, \"plots\": null, \"N50\": true}, \"filter\": {\"maxlength\": null, \"minlength\": null, \"drop_outliers\": false, \"downsample\": null, \"loglength\": false, \"percentqual\": false, \"alength\": false, \"minqual\": null, \"runtime_until\": null, \"readtype\": null, \"barcoded\": false, \"no_supplementary\": false}, \"mode\": {\"choice\": \"batch\", \"__current_case__\": 0, \"reads\": {\"type\": \"fastq\", \"__current_case__\": 0, \"files\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.41.0+galaxy0", + "type": "tool", + "uuid": "467fca53-715f-4717-ab4c-c4410d321086", + "when": null, + "workflow_outputs": [ + { + "label": "nanoplot_after_filtering", + "output_name": "nanostats", + "uuid": "89524090-f590-434d-89e2-66f0b1a23c7c" + } + ] + }, + "10": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bandage/bandage_image/2022.09+galaxy4", + "errors": null, + "id": 10, + "input_connections": { + "input_file": { + "id": 8, + "output_name": "assembly_gfa" + } + }, + "inputs": [], + "label": null, + "name": "Bandage Image", + "outputs": [ + { + "name": "outfile", + "type": "jpg" + } + ], + "position": { + "left": 1140.0069535390257, + "top": 346 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bandage/bandage_image/2022.09+galaxy4", + "tool_shed_repository": { + "changeset_revision": "ddddce450736", + "name": "bandage", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"fontsize\": null, \"height\": \"1000\", \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"lengths\": false, \"names\": false, \"nodewidth\": null, \"output_format\": \"jpg\", \"width\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2022.09+galaxy4", + "type": "tool", + "uuid": "beb931b3-0784-4abc-bbed-fad4ad60645a", + "when": null, + "workflow_outputs": [] + }, + "11": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bwa_mem2/bwa_mem2/2.2.1+galaxy1", + "errors": null, + "id": 11, + "input_connections": { + "fastq_input|fastq_input1": { + "id": 5, + "output_name": "out2" + }, + "reference_source|ref_file": { + "id": 8, + "output_name": "consensus" + } + }, + "inputs": [], + "label": null, + "name": "BWA-MEM2", + "outputs": [ + { + "name": "bam_output", + "type": "bam" + } + ], + "position": { + "left": 1140.0069535390257, + "top": 520 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bwa_mem2/bwa_mem2/2.2.1+galaxy1", + "tool_shed_repository": { + "changeset_revision": "bfaa0d22c2e4", + "name": "bwa_mem2", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"analysis_type\": {\"analysis_type_selector\": \"full\", \"__current_case__\": 4, \"algorithmic_options\": {\"algorithmic_options_selector\": \"do_not_set\", \"__current_case__\": 1}, \"scoring_options\": {\"scoring_options_selector\": \"do_not_set\", \"__current_case__\": 1}, \"io_options\": {\"io_options_selector\": \"set\", \"__current_case__\": 0, \"five\": false, \"q\": false, \"T\": \"30\", \"h\": \"5\", \"a\": true, \"C\": false, \"V\": false, \"Y\": false, \"M\": false, \"K\": null}}, \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"fastq_input\": {\"fastq_input_selector\": \"single\", \"__current_case__\": 1, \"fastq_input1\": {\"__class__\": \"ConnectedValue\"}}, \"output_sort\": \"unsorted\", \"reference_source\": {\"reference_source_selector\": \"history\", \"__current_case__\": 1, \"ref_file\": {\"__class__\": \"ConnectedValue\"}}, \"rg\": {\"rg_selector\": \"do_not_set\", \"__current_case__\": 3}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.2.1+galaxy1", + "type": "tool", + "uuid": "495536ef-3085-46d7-bd81-f88a8a685069", + "when": null, + "workflow_outputs": [] + }, + "12": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.2.0+galaxy1", + "errors": null, + "id": 12, + "input_connections": { + "mode|in|inputs": { + "id": 8, + "output_name": "consensus" + } + }, + "inputs": [], + "label": null, + "name": "Quast", + "outputs": [ + { + "name": "report_html", + "type": "html" + } + ], + "position": { + "left": 1140.0069535390257, + "top": 767 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.2.0+galaxy1", + "tool_shed_repository": { + "changeset_revision": "72472698a2df", + "name": "quast", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"advanced\": {\"contig_thresholds\": \"0,1000\", \"strict_NA\": false, \"extensive_mis_size\": \"1000\", \"scaffold_gap_max_size\": \"1000\", \"unaligned_part_size\": \"500\", \"skip_unaligned_mis_contigs\": true, \"fragmented_max_indent\": null, \"report_all_metrics\": false, \"x_for_Nx\": \"90\"}, \"alignments\": {\"use_all_alignments\": false, \"min_alignment\": \"65\", \"ambiguity_usage\": \"one\", \"ambiguity_score\": \"0.99\", \"fragmented\": false, \"upper_bound_assembly\": false, \"upper_bound_min_con\": null, \"local_mis_size\": \"200\"}, \"assembly\": {\"type\": \"genome\", \"__current_case__\": 0, \"ref\": {\"use_ref\": \"false\", \"__current_case__\": 1, \"est_ref_size\": null}, \"orga_type\": \"\", \"min_identity\": \"95.0\"}, \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"genes\": {\"gene_finding\": {\"tool\": \"none\", \"__current_case__\": 0}, \"rna_finding\": false, \"conserved_genes_finding\": false}, \"large\": false, \"min_contig\": \"500\", \"mode\": {\"mode\": \"co\", \"__current_case__\": 1, \"in\": {\"custom\": \"false\", \"__current_case__\": 1, \"inputs\": {\"__class__\": \"ConnectedValue\"}}, \"reads\": {\"reads_option\": \"disabled\", \"__current_case__\": 0}}, \"output_files\": \"html\", \"split_scaffolds\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "5.2.0+galaxy1", + "type": "tool", + "uuid": "6949cf20-419e-4cee-86fa-3b08ab60cb9f", + "when": null, + "workflow_outputs": [ + { + "label": "quast_report_before_polishing", + "output_name": "report_html", + "uuid": "dabfb8fd-8791-4959-a9dc-9b3c1e57a69c" + } + ] + }, + "13": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bwa_mem2/bwa_mem2/2.2.1+galaxy1", + "errors": null, + "id": 13, + "input_connections": { + "fastq_input|fastq_input1": { + "id": 5, + "output_name": "out1" + }, + "reference_source|ref_file": { + "id": 8, + "output_name": "consensus" + } + }, + "inputs": [], + "label": null, + "name": "BWA-MEM2", + "outputs": [ + { + "name": "bam_output", + "type": "bam" + } + ], + "position": { + "left": 1140.0069535390257, + "top": 995 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bwa_mem2/bwa_mem2/2.2.1+galaxy1", + "tool_shed_repository": { + "changeset_revision": "bfaa0d22c2e4", + "name": "bwa_mem2", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"analysis_type\": {\"analysis_type_selector\": \"full\", \"__current_case__\": 4, \"algorithmic_options\": {\"algorithmic_options_selector\": \"do_not_set\", \"__current_case__\": 1}, \"scoring_options\": {\"scoring_options_selector\": \"do_not_set\", \"__current_case__\": 1}, \"io_options\": {\"io_options_selector\": \"set\", \"__current_case__\": 0, \"five\": false, \"q\": false, \"T\": \"30\", \"h\": \"5\", \"a\": true, \"C\": false, \"V\": false, \"Y\": false, \"M\": false, \"K\": null}}, \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"fastq_input\": {\"fastq_input_selector\": \"single\", \"__current_case__\": 1, \"fastq_input1\": {\"__class__\": \"ConnectedValue\"}}, \"output_sort\": \"unsorted\", \"reference_source\": {\"reference_source_selector\": \"history\", \"__current_case__\": 1, \"ref_file\": {\"__class__\": \"ConnectedValue\"}}, \"rg\": {\"rg_selector\": \"do_not_set\", \"__current_case__\": 3}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.2.1+galaxy1", + "type": "tool", + "uuid": "bac09855-3519-4cb8-9f1e-29003e31aca8", + "when": null, + "workflow_outputs": [] + }, + "14": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/polypolish/polypolish/0.5.0+galaxy2", + "errors": null, + "id": 14, + "input_connections": { + "input|fasta_file": { + "id": 8, + "output_name": "consensus" + }, + "input|sam_data_type|R1_sam": { + "id": 13, + "output_name": "bam_output" + }, + "input|sam_data_type|R2_sam": { + "id": 11, + "output_name": "bam_output" + } + }, + "inputs": [], + "label": null, + "name": "Polypolish", + "outputs": [ + { + "name": "polished_fasta", + "type": "fasta" + } + ], + "position": { + "left": 1420.004016119101, + "top": 649 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/polypolish/polypolish/0.5.0+galaxy2", + "tool_shed_repository": { + "changeset_revision": "f355085dd2aa", + "name": "polypolish", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"input\": {\"fasta_file\": {\"__class__\": \"ConnectedValue\"}, \"sam_data_type\": {\"sam_selector\": \"paired\", \"__current_case__\": 1, \"R1_sam\": {\"__class__\": \"ConnectedValue\"}, \"R2_sam\": {\"__class__\": \"ConnectedValue\"}, \"insert_filter\": {\"filter_select\": \"filter\", \"__current_case__\": 0, \"low\": \"0.1\", \"high\": \"99.9\"}}}, \"options\": {\"min_depth\": \"5\", \"fraction_invalid\": \"0.2\", \"max_errors\": \"10\", \"fraction_valid\": \"0.5\", \"keep_logfile\": false, \"debug\": false}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.5.0+galaxy2", + "type": "tool", + "uuid": "027af3cc-f05c-4b59-a317-1f0390d3c4ad", + "when": null, + "workflow_outputs": [] + }, + "15": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.2.0+galaxy1", + "errors": null, + "id": 15, + "input_connections": { + "mode|in|inputs": [ + { + "id": 14, + "output_name": "polished_fasta" + }, + { + "id": 8, + "output_name": "consensus" + } + ] + }, + "inputs": [], + "label": null, + "name": "Quast", + "outputs": [ + { + "name": "report_html", + "type": "html" + } + ], + "position": { + "left": 1700.001078699176, + "top": 853 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.2.0+galaxy1", + "tool_shed_repository": { + "changeset_revision": "72472698a2df", + "name": "quast", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"advanced\": {\"contig_thresholds\": \"0,1000\", \"strict_NA\": false, \"extensive_mis_size\": \"1000\", \"scaffold_gap_max_size\": \"1000\", \"unaligned_part_size\": \"500\", \"skip_unaligned_mis_contigs\": true, \"fragmented_max_indent\": null, \"report_all_metrics\": false, \"x_for_Nx\": \"90\"}, \"alignments\": {\"use_all_alignments\": false, \"min_alignment\": \"65\", \"ambiguity_usage\": \"one\", \"ambiguity_score\": \"0.99\", \"fragmented\": false, \"upper_bound_assembly\": false, \"upper_bound_min_con\": null, \"local_mis_size\": \"200\"}, \"assembly\": {\"type\": \"genome\", \"__current_case__\": 0, \"ref\": {\"use_ref\": \"false\", \"__current_case__\": 1, \"est_ref_size\": null}, \"orga_type\": \"\", \"min_identity\": \"95.0\"}, \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"genes\": {\"gene_finding\": {\"tool\": \"none\", \"__current_case__\": 0}, \"rna_finding\": false, \"conserved_genes_finding\": false}, \"large\": false, \"min_contig\": \"500\", \"mode\": {\"mode\": \"co\", \"__current_case__\": 1, \"in\": {\"custom\": \"false\", \"__current_case__\": 1, \"inputs\": {\"__class__\": \"ConnectedValue\"}}, \"reads\": {\"reads_option\": \"disabled\", \"__current_case__\": 0}}, \"output_files\": \"html\", \"split_scaffolds\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "5.2.0+galaxy1", + "type": "tool", + "uuid": "866187e0-dd7c-40d5-b121-a8ef4a281c80", + "when": null, + "workflow_outputs": [ + { + "label": "quast_report_after_polishing", + "output_name": "report_html", + "uuid": "4e465b51-68bf-4203-9a7c-897f46c70277" + } + ] + } + }, + "tags": [ + "Assembly" + ], + "uuid": "20037c4e-dc50-4a04-a788-4dab0b198f7c", + "version": 8 +} \ No newline at end of file diff --git a/topics/assembly/tutorials/mrsa-nanopore/workflows/main_workflow.ga b/topics/assembly/tutorials/mrsa-nanopore/workflows/main_workflow.ga deleted file mode 100644 index 41433df87e90c6..00000000000000 --- a/topics/assembly/tutorials/mrsa-nanopore/workflows/main_workflow.ga +++ /dev/null @@ -1,882 +0,0 @@ -{ - "a_galaxy_workflow": "true", - "annotation": "Genome Assembly of MRSA using Oxford Nanopore MinION Data", - "creator": [ - { - "class": "Organization", - "name": "Avans Hogeschool", - "url": "https://www.avans.nl" - }, - { - "class": "Person", - "identifier": "0000-0001-9760-8992", - "jobTitle": "Docent HBO", - "name": "Helena Rasche", - "url": "https://github.com/hexylena" - }, - { - "class": "Person", - "identifier": "", - "name": "Miaomiao Zhou" - } - ], - "format-version": "0.1", - "license": "AGPL-3.0-or-later", - "name": "Genome Assembly of MRSA using Oxford Nanopore MinION Data (imported from uploaded file)", - "steps": { - "0": { - "annotation": "The data must be compressed for this pipeline to execute.", - "content_id": null, - "errors": null, - "id": 0, - "input_connections": {}, - "inputs": [ - { - "description": "The data must be compressed for this pipeline to execute.", - "name": "Nanopore fastq.bz2" - } - ], - "label": "Nanopore fastq.bz2", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 338.4499969482422, - "height": 81.94999694824219, - "left": 366, - "right": 566, - "top": 256.5, - "width": 200, - "x": 366, - "y": 256.5 - }, - "tool_id": null, - "tool_state": "{\"optional\": false}", - "tool_version": null, - "type": "data_input", - "uuid": "cb47330a-cb61-4c99-9487-61978f540930", - "workflow_outputs": [] - }, - "1": { - "annotation": "", - "content_id": "CONVERTER_bz2_to_uncompressed", - "errors": null, - "id": 1, - "input_connections": { - "input1": { - "id": 0, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Convert compressed file to uncompressed.", - "outputs": [ - { - "name": "output1", - "type": "auto" - } - ], - "position": { - "bottom": 358.1666717529297, - "height": 133.6666717529297, - "left": 612.13330078125, - "right": 812.13330078125, - "top": 224.5, - "width": 200, - "x": 612.13330078125, - "y": 224.5 - }, - "post_job_actions": { - "HideDatasetActionoutput1": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "output1" - } - }, - "tool_id": "CONVERTER_bz2_to_uncompressed", - "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"input1\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.1", - "type": "tool", - "uuid": "706c8976-8d2a-4743-ac4b-6557c2f4c46d", - "workflow_outputs": [] - }, - "2": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.0", - "errors": null, - "id": 2, - "input_connections": { - "input_file": { - "id": 1, - "output_name": "output1" - } - }, - "inputs": [], - "label": null, - "name": "filtlong", - "outputs": [ - { - "name": "outfile", - "type": "fastqsanger" - } - ], - "position": { - "bottom": 340.3666687011719, - "height": 224.86666870117188, - "left": 866.2666625976562, - "right": 1066.2666625976562, - "top": 115.5, - "width": 200, - "x": 866.2666625976562, - "y": 115.5 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/filtlong/filtlong/0.2.0", - "tool_shed_repository": { - "changeset_revision": "8880fb74ef56", - "name": "filtlong", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"fastqsanger\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"external_references\": {\"assembly\": null, \"illumina_1\": null, \"illumina_2\": null}, \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"other\": {\"window_size\": \"250\"}, \"output_thresholds\": {\"target_bases\": null, \"keep_percent\": null, \"min_length\": \"1000\", \"min_mean_q\": null, \"min_window_q\": null}, \"read_manipulation\": {\"trim\": \"false\", \"split\": null}, \"score_weights\": {\"length_weight\": \"1.0\", \"mean_q_weight\": \"1.0\", \"window_q_weight\": \"1.0\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.2.0", - "type": "tool", - "uuid": "33b0f002-a454-4328-a4fd-a1d97496af2e", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile", - "uuid": "4faed3a5-a85c-4f23-9d8c-8490784679ae" - } - ] - }, - "3": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.28.2+galaxy1", - "errors": null, - "id": 3, - "input_connections": { - "mode|reads|files": { - "id": 1, - "output_name": "output1" - } - }, - "inputs": [], - "label": null, - "name": "NanoPlot", - "outputs": [ - { - "name": "output_html", - "type": "html" - }, - { - "name": "nanostats", - "type": "txt" - }, - { - "name": "nanostats_post_filtering", - "type": "txt" - }, - { - "name": "read_length", - "type": "png" - }, - { - "name": "log_read_length", - "type": "png" - } - ], - "position": { - "bottom": 794.9666748046875, - "height": 418.4666748046875, - "left": 863.2666625976562, - "right": 1063.2666625976562, - "top": 376.5, - "width": 200, - "x": 863.2666625976562, - "y": 376.5 - }, - "post_job_actions": { - "HideDatasetActionlog_read_length": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "log_read_length" - }, - "HideDatasetActionnanostats": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "nanostats" - }, - "HideDatasetActionnanostats_post_filtering": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "nanostats_post_filtering" - }, - "HideDatasetActionread_length": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "read_length" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.28.2+galaxy1", - "tool_shed_repository": { - "changeset_revision": "edbb6c5028f5", - "name": "nanoplot", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"fastqsanger\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"customization\": {\"color\": null, \"format\": \"png\", \"plots\": null, \"N50\": \"true\"}, \"filter\": {\"maxlength\": null, \"minlength\": null, \"drop_outliers\": \"false\", \"downsample\": null, \"loglength\": \"false\", \"percentqual\": \"false\", \"alength\": \"false\", \"minqual\": null, \"readtype\": null, \"barcoded\": \"false\"}, \"mode\": {\"choice\": \"batch\", \"__current_case__\": 0, \"reads\": {\"type\": \"fastq\", \"__current_case__\": 0, \"files\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.28.2+galaxy1", - "type": "tool", - "uuid": "1f0003c4-efd5-4117-87e1-b86b5d915669", - "workflow_outputs": [ - { - "label": null, - "output_name": "output_html", - "uuid": "0ca8050e-5f61-4170-b1ef-6a0f84cfd420" - } - ] - }, - "4": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.28.2+galaxy1", - "errors": null, - "id": 4, - "input_connections": { - "mode|reads|files": { - "id": 2, - "output_name": "outfile" - } - }, - "inputs": [], - "label": null, - "name": "NanoPlot", - "outputs": [ - { - "name": "output_html", - "type": "html" - }, - { - "name": "nanostats", - "type": "txt" - }, - { - "name": "nanostats_post_filtering", - "type": "txt" - }, - { - "name": "read_length", - "type": "png" - }, - { - "name": "log_read_length", - "type": "png" - } - ], - "position": { - "bottom": 592.9666748046875, - "height": 418.4666748046875, - "left": 1143.4000244140625, - "right": 1343.4000244140625, - "top": 174.5, - "width": 200, - "x": 1143.4000244140625, - "y": 174.5 - }, - "post_job_actions": { - "HideDatasetActionlog_read_length": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "log_read_length" - }, - "HideDatasetActionnanostats": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "nanostats" - }, - "HideDatasetActionnanostats_post_filtering": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "nanostats_post_filtering" - }, - "HideDatasetActionread_length": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "read_length" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/nanoplot/nanoplot/1.28.2+galaxy1", - "tool_shed_repository": { - "changeset_revision": "edbb6c5028f5", - "name": "nanoplot", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"fastqsanger\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"customization\": {\"color\": null, \"format\": \"png\", \"plots\": null, \"N50\": \"true\"}, \"filter\": {\"maxlength\": null, \"minlength\": null, \"drop_outliers\": \"false\", \"downsample\": null, \"loglength\": \"false\", \"percentqual\": \"false\", \"alength\": \"false\", \"minqual\": null, \"readtype\": null, \"barcoded\": \"false\"}, \"mode\": {\"choice\": \"batch\", \"__current_case__\": 0, \"reads\": {\"type\": \"fastq\", \"__current_case__\": 0, \"files\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.28.2+galaxy1", - "type": "tool", - "uuid": "b7aa6d6b-b079-4702-82da-db746702b024", - "workflow_outputs": [ - { - "label": null, - "output_name": "output_html", - "uuid": "0f119f46-17d5-4035-bf11-5b1128ae8ac8" - } - ] - }, - "5": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/flye/flye/2.6", - "errors": null, - "id": 5, - "input_connections": { - "inputs": { - "id": 2, - "output_name": "outfile" - } - }, - "inputs": [], - "label": null, - "name": "Flye assembly", - "outputs": [ - { - "name": "consensus", - "type": "fasta" - }, - { - "name": "assembly_graph", - "type": "graph_dot" - }, - { - "name": "assembly_gfa", - "type": "txt" - }, - { - "name": "assembly_info", - "type": "tabular" - }, - { - "name": "flye_log", - "type": "txt" - } - ], - "position": { - "bottom": 1072.3666687011719, - "height": 438.8666687011719, - "left": 1143.4000244140625, - "right": 1343.4000244140625, - "top": 633.5, - "width": 200, - "x": 1143.4000244140625, - "y": 633.5 - }, - "post_job_actions": { - "HideDatasetActionassembly_gfa": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "assembly_gfa" - }, - "HideDatasetActionassembly_graph": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "assembly_graph" - }, - "HideDatasetActionassembly_info": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "assembly_info" - }, - "HideDatasetActionflye_log": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "flye_log" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/flye/flye/2.6", - "tool_shed_repository": { - "changeset_revision": "3ee0ef312022", - "name": "flye", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"fastqsanger\", \"asm\": null, \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"g\": \"2.8m\", \"i\": \"1\", \"inputs\": {\"__class__\": \"ConnectedValue\"}, \"m\": null, \"meta\": \"false\", \"mode\": \"--nano-raw\", \"no_trestle\": \"false\", \"plasmids\": \"false\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "2.6", - "type": "tool", - "uuid": "b51ee84f-4159-4cc4-8c55-ea439becc4af", - "workflow_outputs": [ - { - "label": null, - "output_name": "consensus", - "uuid": "a703dc4f-dab4-47f4-9934-37d7986f1f83" - } - ] - }, - "6": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bandage/bandage_image/0.8.1+galaxy2", - "errors": null, - "id": 6, - "input_connections": { - "input_file": { - "id": 5, - "output_name": "assembly_gfa" - } - }, - "inputs": [], - "label": null, - "name": "Bandage Image", - "outputs": [ - { - "name": "outfile", - "type": "jpg" - } - ], - "position": { - "bottom": 560.9666595458984, - "height": 174.46665954589844, - "left": 1430.5333251953125, - "right": 1630.5333251953125, - "top": 386.5, - "width": 200, - "x": 1430.5333251953125, - "y": 386.5 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bandage/bandage_image/0.8.1+galaxy2", - "tool_shed_repository": { - "changeset_revision": "b2860df42e16", - "name": "bandage", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"height\": \"1000\", \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"lengths\": \"false\", \"names\": \"false\", \"output_format\": \"jpg\", \"width\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.8.1+galaxy2", - "type": "tool", - "uuid": "067da871-ab29-4a9b-8c68-90d139aede65", - "workflow_outputs": [ - { - "label": "Bandage Image on input dataset(s): Assembly Graph Image", - "output_name": "outfile", - "uuid": "799bd26b-b2da-45d4-9a79-8a880d608307" - } - ] - }, - "7": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.0.2+galaxy1", - "errors": null, - "id": 7, - "input_connections": { - "in|inputs": { - "id": 5, - "output_name": "consensus" - } - }, - "inputs": [], - "label": null, - "name": "Quast", - "outputs": [ - { - "name": "quast_tabular", - "type": "tabular" - }, - { - "name": "report_html", - "type": "html" - }, - { - "name": "report_pdf", - "type": "pdf" - }, - { - "name": "log", - "type": "txt" - } - ], - "position": { - "bottom": 907.9666748046875, - "height": 306.4666748046875, - "left": 1430.5333251953125, - "right": 1630.5333251953125, - "top": 601.5, - "width": 200, - "x": 1430.5333251953125, - "y": 601.5 - }, - "post_job_actions": { - "HideDatasetActionlog": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "log" - }, - "HideDatasetActionreport_pdf": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "report_pdf" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.0.2+galaxy1", - "tool_shed_repository": { - "changeset_revision": "ebb0dcdb621a", - "name": "quast", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"input\", \"al\": {\"use_all_alignments\": \"false\", \"min_alignment\": \"65\", \"min_identity\": \"95.0\", \"ambiguity_usage\": \"one\", \"ambiguity_score\": \"0.99\", \"fragmented\": \"false\", \"fragmented_max_indent\": \"50\", \"upper_bound_assembly\": \"false\", \"upper_bound_min_con\": \"2\"}, \"assembly\": {\"type\": \"genome\", \"__current_case__\": 0, \"ref\": {\"use_ref\": \"false\", \"__current_case__\": 1, \"est_ref_size\": null}, \"orga_type\": \"\"}, \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"circos\": \"false\", \"contig_thresholds\": \"0,1000\", \"extensive_mis_size\": \"1000\", \"genes\": {\"gene_finding\": {\"tool\": \"none\", \"__current_case__\": 0}, \"rna_finding\": \"false\", \"conserved_genes_finding\": \"false\"}, \"in\": {\"custom\": \"false\", \"__current_case__\": 1, \"inputs\": {\"__class__\": \"ConnectedValue\"}}, \"k_mer\": {\"k_mer_stats\": \"\", \"__current_case__\": 1}, \"large\": \"false\", \"min_contig\": \"500\", \"scaffold_gap_max_size\": \"1000\", \"skip_unaligned_mis_contigs\": \"true\", \"split_scaffolds\": \"false\", \"strict_NA\": \"false\", \"unaligned_part_size\": \"500\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "5.0.2+galaxy1", - "type": "tool", - "uuid": "f4d7a10d-93b8-4bf9-a853-7a37089587da", - "workflow_outputs": [ - { - "label": null, - "output_name": "quast_tabular", - "uuid": "9ed01007-5e81-4c42-a1d5-bbac2503c096" - }, - { - "label": null, - "output_name": "report_html", - "uuid": "0dac7c81-8e68-4ee1-8ba5-3ab7f4205de9" - } - ] - }, - "8": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/nml/staramr/staramr_search/0.7.1+galaxy2", - "errors": null, - "id": 8, - "input_connections": { - "genomes": { - "id": 5, - "output_name": "consensus" - } - }, - "inputs": [], - "label": null, - "name": "staramr", - "outputs": [ - { - "name": "blast_hits", - "type": "input" - }, - { - "name": "mlst", - "type": "tabular" - }, - { - "name": "summary", - "type": "tabular" - }, - { - "name": "detailed_summary", - "type": "tabular" - }, - { - "name": "resfinder", - "type": "tabular" - }, - { - "name": "plasmidfinder", - "type": "tabular" - }, - { - "name": "settings", - "type": "txt" - }, - { - "name": "excel", - "type": "xlsx" - } - ], - "position": { - "bottom": 1604.7666625976562, - "height": 591.2666625976562, - "left": 1427.5333251953125, - "right": 1627.5333251953125, - "top": 1013.5, - "width": 200, - "x": 1427.5333251953125, - "y": 1013.5 - }, - "post_job_actions": { - "HideDatasetActionblast_hits": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "blast_hits" - }, - "HideDatasetActionexcel": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "excel" - }, - "HideDatasetActionmlst": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "mlst" - }, - "HideDatasetActionplasmidfinder": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "plasmidfinder" - }, - "HideDatasetActionresfinder": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "resfinder" - }, - "HideDatasetActionsettings": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "settings" - }, - "HideDatasetActionsummary": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "summary" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/staramr/staramr_search/0.7.1+galaxy2", - "tool_shed_repository": { - "changeset_revision": "2fd4d4c9c5c2", - "name": "staramr", - "owner": "nml", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"fasta\", \"advanced\": {\"pid_threshold\": \"98.0\", \"plength_resfinder\": \"60.0\", \"plength_pointfinder\": \"95.0\", \"plength_plasmidfinder\": \"60.0\", \"genome_size_lower_bound\": \"4000000\", \"genome_size_upper_bound\": \"6000000\", \"minimum_N50_value\": \"10000\", \"minimum_contig_length\": \"300\", \"unacceptable_number_contigs\": \"1000\", \"report_all_blast\": \"false\", \"exclude_negatives\": \"false\", \"exclude_resistance_phenotypes\": \"false\", \"mlst_scheme\": \"auto\", \"exclude_genes\": {\"exclude_genes_condition\": \"default\", \"__current_case__\": 0}, \"plasmidfinder_type\": \"include_all\"}, \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"genomes\": {\"__class__\": \"ConnectedValue\"}, \"use_pointfinder\": \"disabled\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.7.1+galaxy2", - "type": "tool", - "uuid": "7fbcaff0-caa0-45ac-89e1-65c6fba56af8", - "workflow_outputs": [ - { - "label": null, - "output_name": "detailed_summary", - "uuid": "662c45d6-fe22-466f-9ea5-d2a35b03d13f" - } - ] - }, - "9": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/crs4/prokka/prokka/1.14.5+galaxy0", - "errors": null, - "id": 9, - "input_connections": { - "input": { - "id": 5, - "output_name": "consensus" - } - }, - "inputs": [], - "label": null, - "name": "Prokka", - "outputs": [ - { - "name": "out_gff", - "type": "gff" - }, - { - "name": "out_txt", - "type": "txt" - }, - { - "name": "out_log", - "type": "txt" - } - ], - "position": { - "bottom": 1235.566650390625, - "height": 286.066650390625, - "left": 1707.6666259765625, - "right": 1907.6666259765625, - "top": 949.5, - "width": 200, - "x": 1707.6666259765625, - "y": 949.5 - }, - "post_job_actions": { - "HideDatasetActionout_gff": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "out_gff" - }, - "HideDatasetActionout_log": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "out_log" - }, - "HideDatasetActionout_txt": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "out_txt" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/crs4/prokka/prokka/1.14.5+galaxy0", - "tool_shed_repository": { - "changeset_revision": "111884f0d912", - "name": "prokka", - "owner": "crs4", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"fasta\", \"centre\": \"\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"compliant\": {\"compliant_select\": \"no\", \"__current_case__\": 0, \"addgenes\": \"false\", \"mincontig\": \"200\"}, \"evalue\": \"1e-06\", \"fast\": \"false\", \"genus\": \"staphylococcus \", \"gffver\": \"3\", \"increment\": \"1\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"kingdom\": {\"kingdom_select\": \"Bacteria\", \"__current_case__\": 1, \"gcode\": \"11\"}, \"locustag\": \"\", \"metagenome\": \"false\", \"norrna\": \"false\", \"notrna\": \"false\", \"outputs\": [\"gff\", \"txt\"], \"plasmid\": \"\", \"proteins\": null, \"rfam\": \"false\", \"species\": \"aureus\", \"strain\": \"\", \"usegenus\": \"false\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.14.5+galaxy0", - "type": "tool", - "uuid": "e19b465b-ba5d-47d4-82f0-fc9c61116fc4", - "workflow_outputs": [] - }, - "10": { - "annotation": "", - "content_id": "Grep1", - "errors": null, - "id": 10, - "input_connections": { - "input": { - "id": 8, - "output_name": "detailed_summary" - } - }, - "inputs": [], - "label": null, - "name": "Select", - "outputs": [ - { - "name": "out_file1", - "type": "input" - } - ], - "position": { - "bottom": 1368.3666687011719, - "height": 92.86666870117188, - "left": 1707.6666259765625, - "right": 1907.6666259765625, - "top": 1275.5, - "width": 200, - "x": 1707.6666259765625, - "y": 1275.5 - }, - "post_job_actions": {}, - "tool_id": "Grep1", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"invert\": \"\", \"keep_header\": \"false\", \"pattern\": \"[0-9]+\\\\.[0-9]+\\\\t\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.3", - "type": "tool", - "uuid": "bbfd736f-bfe6-46bf-a9ce-1f9a5ec94b4a", - "workflow_outputs": [ - { - "label": null, - "output_name": "out_file1", - "uuid": "36b863c6-4092-4df3-ba8f-f7710fa7ed5c" - } - ] - }, - "11": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/tbl2gff3/tbl2gff3/1.1", - "errors": null, - "id": 11, - "input_connections": { - "table": { - "id": 10, - "output_name": "out_file1" - } - }, - "inputs": [], - "label": null, - "name": "Table to GFF3", - "outputs": [ - { - "name": "output", - "type": "gff3" - } - ], - "position": { - "bottom": 1378.7666625976562, - "height": 113.26666259765625, - "left": 1984.800048828125, - "right": 2184.800048828125, - "top": 1265.5, - "width": 200, - "x": 1984.800048828125, - "y": 1265.5 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/tbl2gff3/tbl2gff3/1.1", - "tool_shed_repository": { - "changeset_revision": "965674d88d34", - "name": "tbl2gff3", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"attributes\": [{\"__index__\": 0, \"key\": \"Name\", \"val\": \"2\"}, {\"__index__\": 1, \"key\": \"phenotype\", \"val\": \"4\"}], \"begin\": \"9\", \"end\": \"10\", \"rid\": \"8\", \"score\": \"5\", \"source\": \"3\", \"strand\": {\"strand_select\": \"none\", \"__current_case__\": 0}, \"table\": {\"__class__\": \"ConnectedValue\"}, \"type\": \"sequence_feature\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.1", - "type": "tool", - "uuid": "24213183-119f-4f54-a86f-dba8776357dd", - "workflow_outputs": [ - { - "label": null, - "output_name": "output", - "uuid": "e986b669-b28f-4679-b93b-5bac93773a46" - } - ] - }, - "12": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.9+galaxy0", - "errors": null, - "id": 12, - "input_connections": { - "reference_genome|genome": { - "id": 5, - "output_name": "consensus" - }, - "track_groups_0|data_tracks_0|data_format|annotation": { - "id": 9, - "output_name": "out_gff" - }, - "track_groups_1|data_tracks_0|data_format|annotation": { - "id": 11, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "JBrowse", - "outputs": [ - { - "name": "output", - "type": "html" - } - ], - "position": { - "bottom": 1260.566650390625, - "height": 276.066650390625, - "left": 2261.933349609375, - "right": 2461.933349609375, - "top": 984.5, - "width": 200, - "x": 2261.933349609375, - "y": 984.5 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.9+galaxy0", - "tool_shed_repository": { - "changeset_revision": "17359b808b01", - "name": "jbrowse", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"action\": {\"action_select\": \"create\", \"__current_case__\": 0}, \"gencode\": \"11\", \"jbgen\": {\"defaultLocation\": \"\", \"trackPadding\": \"20\", \"shareLink\": \"true\", \"aboutDescription\": \"\", \"show_tracklist\": \"true\", \"show_nav\": \"true\", \"show_overview\": \"true\", \"show_menu\": \"true\", \"hideGenomeOptions\": \"false\"}, \"plugins\": {\"BlastView\": \"true\", \"ComboTrackSelector\": \"false\", \"GCContent\": \"false\"}, \"reference_genome\": {\"genome_type_select\": \"history\", \"__current_case__\": 1, \"genome\": {\"__class__\": \"ConnectedValue\"}}, \"standalone\": \"minimal\", \"track_groups\": [{\"__index__\": 0, \"category\": \"Prokka\", \"data_tracks\": [{\"__index__\": 0, \"data_format\": {\"data_format_select\": \"gene_calls\", \"__current_case__\": 2, \"annotation\": {\"__class__\": \"ConnectedValue\"}, \"match_part\": {\"match_part_select\": \"false\", \"__current_case__\": 1}, \"index\": \"true\", \"track_config\": {\"track_class\": \"NeatHTMLFeatures/View/Track/NeatFeatures\", \"__current_case__\": 3, \"html_options\": {\"topLevelFeatures\": null}}, \"jbstyle\": {\"style_classname\": \"feature\", \"style_label\": \"product,name,id\", \"style_description\": \"note,description\", \"style_height\": \"10px\", \"max_height\": \"600\"}, \"jbcolor_scale\": {\"color_score\": {\"color_score_select\": \"none\", \"__current_case__\": 0, \"color\": {\"color_select\": \"automatic\", \"__current_case__\": 0}}}, \"jb_custom_config\": {\"option\": []}, \"jbmenu\": {\"track_menu\": []}, \"track_visibility\": \"default_on\", \"override_apollo_plugins\": \"False\", \"override_apollo_drag\": \"False\"}}]}, {\"__index__\": 1, \"category\": \"AMR\", \"data_tracks\": [{\"__index__\": 0, \"data_format\": {\"data_format_select\": \"gene_calls\", \"__current_case__\": 2, \"annotation\": {\"__class__\": \"ConnectedValue\"}, \"match_part\": {\"match_part_select\": \"false\", \"__current_case__\": 1}, \"index\": \"false\", \"track_config\": {\"track_class\": \"NeatHTMLFeatures/View/Track/NeatFeatures\", \"__current_case__\": 3, \"html_options\": {\"topLevelFeatures\": null}}, \"jbstyle\": {\"style_classname\": \"feature\", \"style_label\": \"product,name,id\", \"style_description\": \"note,description\", \"style_height\": \"10px\", \"max_height\": \"600\"}, \"jbcolor_scale\": {\"color_score\": {\"color_score_select\": \"score\", \"__current_case__\": 1, \"score_scaling\": \"linear\", \"score_scales\": {\"scale_select\": \"automatic\", \"__current_case__\": 0}, \"color_scheme\": {\"score_scheme\": \"opacity\", \"__current_case__\": 0, \"color\": {\"color_select\": \"automatic\", \"__current_case__\": 0}}}}, \"jb_custom_config\": {\"option\": []}, \"jbmenu\": {\"track_menu\": []}, \"track_visibility\": \"default_on\", \"override_apollo_plugins\": \"False\", \"override_apollo_drag\": \"False\"}}]}], \"uglyTestingHack\": \"\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.16.9+galaxy0", - "type": "tool", - "uuid": "f6a40d12-ad64-4756-964e-16e0c5bcc04c", - "workflow_outputs": [ - { - "label": null, - "output_name": "output", - "uuid": "1d0adf59-23e3-420f-8992-f27451496d3c" - } - ] - } - }, - "tags": [ - "assembly" - ], - "uuid": "ee3322f4-c48c-480a-8eea-d8f6fd515d21", - "version": 3 -} \ No newline at end of file