diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index c1db0681..466a9098 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -6,10 +6,17 @@ name: CI # Triggers the workflow on push or pull request events on: [push, pull_request, workflow_dispatch] +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} + cancel-in-progress: true + # A workflow run is made up of one or more jobs that can run sequentially or in parallel -jobs: +jobs: # This workflow contains a single job called "build" build: + # avoid to run twice push and PR + if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name + # The type of runner that the job will run on runs-on: ubuntu-latest diff --git a/.github/workflows/mkdocs.yml b/.github/workflows/mkdocs.yml new file mode 100644 index 00000000..7a5cfd33 --- /dev/null +++ b/.github/workflows/mkdocs.yml @@ -0,0 +1,40 @@ +name: documentation +on: + push: + paths: + - 'docs/**' + - mkdocs.yml + pull_request: + branches: [main, master] + paths: + - 'docs/**' + - mkdocs.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} + cancel-in-progress: true + +permissions: + contents: write +jobs: + deploy: + # avoid to run twice push and PR + if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name + + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v3 + - uses: actions/setup-python@v4 + with: + python-version: 3.x + - uses: actions/cache@v2 + with: + key: ${{ github.ref }} + path: .cache + - run: pip install mkdocs-material + - run: pip install pymdown-extensions + - run: pip install mkdocs-minify-plugin + - run: pip install mkdocs-macros-plugin + - run: pip install mkdocs-embed-external-markdown + - run: pip install mkdocs-table-reader-plugin + - run: mkdocs gh-deploy --force diff --git a/.readthedocs.yml b/.readthedocs.yml deleted file mode 100644 index 2f24b7d6..00000000 --- a/.readthedocs.yml +++ /dev/null @@ -1,27 +0,0 @@ -# .readthedocs.yaml -# Read the Docs configuration file -# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details - -# Required -version: 2 - -# Set the OS, Python version and other tools you might need -build: - os: ubuntu-22.04 - tools: - python: "3.7" - -# Build documentation in the docs/ directory with Sphinx -sphinx: - configuration: docs/conf.py - -# Optionally build your docs in additional formats such as PDF -#formats: -# - pdf - -# Optional but recommended, declare the Python requirements required -# to build your documentation -# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html -python: - install: - - requirements: docs/requirements.txt \ No newline at end of file diff --git a/docs/README.md b/docs/README.md new file mode 100644 index 00000000..411d20e9 --- /dev/null +++ b/docs/README.md @@ -0,0 +1,52 @@ +### Mkdocs + +#### Welcome to MkDocs + +For full documentation visit [mkdocs.org](https://www.mkdocs.org). +For full documentation about the [material mkdocs theme](https://squidfunk.github.io/mkdocs-material/). + +#### Installation + +##### Manual + +As prerequisite you need python >=3.8 and pip. + +Install Mkdocs: + +`pip install mkdocs` + +For the theme: +`pip install mkdocs-material` + +For the extensions: +`pip install pymdown-extensions` + +For the plugins: +`pip install mkdocs-minify-plugin` +`pip install mkdocs-macros-plugin` +`pip install mkdocs-embed-external-markdown` + +##### Conda + +Clone the repository and move in it. +Then install all dependencies using conda and the `conda_env.yml` shipped with this repo: + +``` +conda env create -f conda_env.yml +``` + +Activate the environment and you are good: + +``` +conda activate education +``` + +#### Testing and building the website + + +* `mkdocs serve` - Start the live-reloading docs server, to test the site locally (http://127.0.0.1:8000/). +* `mkdocs gh-deploy` - Deploys the site on github pages. + +* `mkdocs build` - Build the documentation site. +* `mkdocs new [dir-name]` - Create a new project. +* `mkdocs -h` - Print help message and exit. diff --git a/docs/agat_for_you.md b/docs/agat_for_you.md index b27636dd..96e03cd6 100644 --- a/docs/agat_for_you.md +++ b/docs/agat_for_you.md @@ -12,15 +12,15 @@ task | tool -- | -- **check, fix, pad** missing information into sorted and standardised gff3 | `agat_convert_sp_gxf2gxf.pl` - * add missing parent features (e.g. gene and mRNA if only CDS/exon exists). - * add missing features (e.g. exon and UTR). - * add missing mandatory attributes (i.e. ID, Parent). - * fix identifiers to be uniq. - * fix feature locations. - * remove duplicated features. - * group related features (if spread in different places in the file). - * sort features (tabix optional). - * merge overlapping loci into one single locus (only if option activated). + * add missing parent features (e.g. gene and mRNA if only CDS/exon exists). + * add missing features (e.g. exon and UTR). + * add missing mandatory attributes (i.e. ID, Parent). + * fix identifiers to be uniq. + * fix feature locations. + * remove duplicated features. + * group related features (if spread in different places in the file). + * sort features (tabix optional). + * merge overlapping loci into one single locus (only if option activated). * Convert many formats @@ -61,5 +61,5 @@ make **function statistics** | `agat_sp_functional_statistics.pl` **specificity sensitivity** | `agat_sp_sensitivity_specificity.pl` **fusion / split** analysis between two annotations | `agat_sp_compare_two_annotations.pl` analyze differences between **BUSCO** results | `agat_sp_compare_two_BUSCOs.pl` -... and much more ...| ... see [here](https://agat.readthedocs.io/en/latest/) ... +... and much more ...| ... see [here](../tools/agat_convert_sp_gxf2gxf/) ... diff --git a/docs/agat_how_does_it_work.md b/docs/agat_how_does_it_work.md index 8da2e7f9..59e2e285 100644 --- a/docs/agat_how_does_it_work.md +++ b/docs/agat_how_does_it_work.md @@ -1,14 +1,14 @@ # How does AGAT work? -All tools taking GFF/GTF as input can be divided in two groups: \_sp\_ and \_sq\_. +All tools taking GFF/GTF as input can be divided in two groups: `_sp_` and `_sq_`. -* Tools with \_sp\_ prefix +* Tools with `_sp_` prefix \_sp\_ stands for SLURP. Those tools will charge the file in memory in a specific data structure. It has a memory cost but makes life smoother. Indeed, it allows to perform complicated tasks in a more time efficient way ( Any features can be accessed at any time by AGAT). Moreover, it allows to fix all potential errors in the limit of the possibilities given by the format itself. See the AGAT parser section for more information about it. -* with \_sq\_ prefix +* with `_sq_` prefix \_sq\_ stands for SEQUENTIAL. Those tools will read and process GFF/GTF files from the top to the bottom, line by line, performing tasks on the fly. This is memory efficient but the sanity check of the file is minimum. Those tools are not intended to perform complex tasks. @@ -41,10 +41,19 @@ $omniscient{level3}{tag_l3}{idZ} = @featureListL3 <= tag could be exon,cds,utr3 ### How does the AGAT parser work +The AGAT parser phylosophy will use several approach to understand the links/relationships betwen the featrures: + + * 1) Parse by Parent/child relationship or gene_id/transcript_id relationship. + * 2) ELSE Parse by a common tag (an attribute value shared by feature that must be grouped together. By default we are using locus_tag but can be set by parameter). + * 3) ELSE Parse sequentially (mean group features in a bucket, and the bucket change at each level2 feature, and bucket are join in a common tag at each new L1 feature). + To resume by priority of way to parse: **Parent/child or gene_id/transcript_id relationship > common attribute/tag > sequential.** + +![](img/agat_parsing_overview.jpg){ width=800px } + The parser may used only one or a mix of these approaches according of the peculiarity of the gtf/gff file you provide. - 1. Parsing approach 1: by Parent/child relationship + **1. Parsing approach 1: by Parent/child relationship** Example of Parent/ID relationship used by the GFF format: @@ -60,7 +69,7 @@ Example of gene_id/transcript_id relationship used by the GTF format: chr12 HAVANA exon 100 500 . + . gene_id "gene1"; transcript_id "transcript1"; exon_id=exon1; chr12 HAVANA CDS 100 500 . + 0 gene_id "gene1"; transcript_id "transcript1"; cds_id=cds-1; - 2. ELSE Parsing approach 2: by a common attribute/tag + **2. ELSE Parsing approach 2: by a common attribute/tag** a common attribute (or common tag) is an attribute value shared by feature that must be grouped together. AGAT uses default attributes (`gene_id` and `locus_tag`) displayed in the log but can be set by the user modifying the AGAT configuration file `agat_config.yaml`. You can modify the `agat_config.yaml` either running `agat config --expose` to access it (it will be copied in the current directory) and then modifying it manually; or running `agat config --expose --locus_tag attribute_name` that will copy the `agat_config.yaml` locally with the modification of the `locus_tag` parameter accordingly. @@ -72,7 +81,7 @@ Example of relationship made using a common tag (here locus_tag): chr12 HAVANA exon 100 500 . + . locus_tag="gene1";ID=exon1; chr12 HAVANA CDS 100 500 . + 0 locus_tag="gene1";ID=cds-1; - 3. ELSE Parsing approach 3: sequentially. + **3. ELSE Parsing approach 3: sequentially** Reading from top to the botom of the file, level3 features (e.g. exon, CDS, UTR) are attached to the last level2 feature (e.g. mRNA) met, and level2 feature are attached to the last L1 feature (e.g. gene) met. To see the list of features of each level see the feature_levels.yaml file (In the share folder in the github repo or using `agat levels --expose`). @@ -87,6 +96,7 @@ Example of relationship made sequentially: chr12 HAVANA exon 1000 5000 . + . ID="zzz" chr12 HAVANA CDS 1000 5000 . + 0 ID="www" +/!\\ Cases with only level3 features (i.e rast or some prokka files), sequential parsing may not work as expected if Parent/ID gene_id/transcript_id attributes are missing. Indeed all features will be the child of only one newly created Parent. To create a parent per feature or group of features, a common tag must be used to group them correctly (by default gene_id and locus_tag but you can set up the ones of your choice). See [Particular case](#particular-case). ### Particular case @@ -186,11 +196,11 @@ This will work well even if transcript isoforms exist. This will use the parsing In such case the sequential approach cannot be used (Indeed no level1 (e.g. gene) and no lelve2 (e.g. mrna) feature is present in the file). So the presence of parent/ID transcript_id/gene_id relationships and/or a proper common attribute is crucial. -1. Case with Parent/ID transcript_id/gene_id relationships. +##### 1. Case with Parent/ID transcript_id/gene_id relationships. If you have isoforms (for Eukaryote organism) in your files and the `common attribute` used is not set properly you can end up with isoforms having independent parent gene features. See below for more details. -1.1 +**1.1** Input (testB.gff): @@ -237,7 +247,7 @@ If you are lucky those attributes already exist. Here they are absent, you can u chr12 HAVANA CDS 700 900 . + 0 ID=cds-b;Parent=transcriptb;locus_id="gene2" -1.2. +**1.2** Here we have only level3 features, Parent/ID transcript_id/gene_id relationships present, default `common attributes` ( `locus_tag` or `gene_id`) is set for some features. @@ -272,9 +282,9 @@ Input testF.gff: The `common attributes` is used to attach isoforms to a common gene feature. As transcript4 has no common attribute, it will have its own parent features. -2. Case without Parent/ID transcript_id/gene_id relationships. Only `common attribute` approach to parse the file can be used. +##### 2. Case without Parent/ID transcript_id/gene_id relationships. Only `common attribute` approach to parse the file can be used. -2.1. +**2.1** Here we have only level3 features, no Parent/ID transcript_id/gene_id relationships, but a default `common attributes` ( `locus_tag` or `gene_id`) is present. @@ -347,7 +357,7 @@ As the default `common attribute` are absent (gene_id or locus_tag), you have to /!\\ In Eukaryote annotation containing isoforms it will not work properly. Indeed, it will result of isoforms merged in chimeric transcripts (It will be really unlucky to end up in such situation, because even a human cannot resolve such type of situation. There is no information about isoforms structure...). In Eukaryote cases (even for multi-exon CDS) with absence of isoforms, it will work correctly. -3. In the extreme case where you have only one type of feature, you may decide to use the ID as common attribute. +##### 3. In the extreme case where you have only one type of feature, you may decide to use the ID as common attribute. This is the same problem as seen previously. Here the worse case that can append: only level3 features, no Parent/ID transcript_id/gene_id relationships, and the default `common attributes` ( `locus_tag` and `gene_id`) are absent. Sequential approach will be used by AGAT but as there are only level3 features, all will be linked to only one parent. See below for more details. @@ -392,7 +402,7 @@ This case is fine for Prokaryote annotation. A) The annotation should not contain isoforms (Indeed, there is no existing information to decipher to which isoform a CDS will be part of. If isoforms are present, each one will be linked to its own gene feature). B) If there are multi-exon CDS, CDS parts must share the same ID (Indeed multi-exon CDS can share or not the same ID. Both way are allowed by the GFF format. If the CDS parts share the same ID, the CDS parts will be collected properly. If the CDS parts do not share the same ID, AGAT will slice it and create a gene/mRNA feature by CDS part!). -4. Case where you have only one type of feature, and some feature have Parent attributes and some other have common attributes. +##### 4. Case where you have only one type of feature, and some feature have Parent attributes and some other have common attributes. Input (testG.gff): diff --git a/docs/how_to_cite.md b/docs/how_to_cite.md index 691355f7..e14da16d 100644 --- a/docs/how_to_cite.md +++ b/docs/how_to_cite.md @@ -1,6 +1,6 @@ -## How to cite? +# How to cite? -This work has not been published yet(I will think about it). But if you wish to cite AGAT you can do it as follow (Adapt the version for the one you have used): +This work has not been published yet(I will think about it). But if you wish to cite AGAT you can do it as follow (Adapt the version for the one you have used): ``` Dainat J. AGAT: Another Gff Analysis Toolkit to handle annotations in any GTF/GFF format. diff --git a/docs/howto/how_to_aggregate_annotation.md b/docs/howto/how_to_aggregate_annotation.md new file mode 100644 index 00000000..49ba543f --- /dev/null +++ b/docs/howto/how_to_aggregate_annotation.md @@ -0,0 +1,7 @@ +# How to aggregate several annotations? + +There are two scripts in AGAT in order to aggregate annotations. They do not behave the same way. Find below some explanation on their behaviors. + +![](../img/aggregate_annotations.png "example") + + \ No newline at end of file diff --git a/docs/howto/how_to_extract_sequences.md b/docs/howto/how_to_extract_sequences.md new file mode 100644 index 00000000..cb9f22eb --- /dev/null +++ b/docs/howto/how_to_extract_sequences.md @@ -0,0 +1,7 @@ +# How to extract sequences? + +You can use the script agat_sp_extract_sequences.pl. Find below exmaples on how to use this script. + +![](../img/agat_sp_extract_sequences_2.png "gff_example") + +![](../img/agat_sp_extract_sequences_1.png "extraction_example") \ No newline at end of file diff --git a/docs/img/aggregate_annotations.png b/docs/img/aggregate_annotations.png new file mode 100644 index 00000000..e1f711ec Binary files /dev/null and b/docs/img/aggregate_annotations.png differ diff --git a/docs/img/aggregate_annotations.pptx b/docs/img/aggregate_annotations.pptx new file mode 100644 index 00000000..76e214e0 Binary files /dev/null and b/docs/img/aggregate_annotations.pptx differ diff --git a/docs/index.md b/docs/index.md new file mode 100644 index 00000000..a7ce8db2 --- /dev/null +++ b/docs/index.md @@ -0,0 +1,16 @@ +Welcome to AGAT's documentation! +================================ + +AGAT: Another GTF/GFF Analysis Toolkit +---------------------------------------- + +**A GFF/GTF toolkit allowing you to perform almost everything you might want to achieve ^^** + +The GTF/GFF formats are 9-column text formats used to describe and represent genomic features. +The formats have quite evolved since 1997, and despite well-defined specifications existing nowadays they have a great flexibility allowing holding wide variety of information. +This flexibility has a drawback aspect, there is an incredible amount of flavor of the formats: GFF / GFF1 / GFF2 / GFF2.5 / GFF3 / GTF / GTF2 / GTF2.1 / GTF2.2 / GTF2.5 / GTF3 + +It's often hard to understand and differentiate all GFF/GTF formats/flavors. Many tools using GTF/GFF formats fails due to specific expectations. +AGAT is a suite of tools able to deal with any GTF/GFF formats and perform most of the possible tasks you would need. + +![](img/wordcloud.png){ width=600px } \ No newline at end of file diff --git a/docs/index.rst b/docs/index.rst deleted file mode 100644 index 26677eb2..00000000 --- a/docs/index.rst +++ /dev/null @@ -1,133 +0,0 @@ -Welcome to AGAT's documentation! -================================ - -AGAT: Another GTF/GFF Analysis Toolkit ----------------------------------------- - -**A GFF/GTF toolkit allowing you to perform almost everything you might want to achieve ^^** - -The GTF/GFF formats are 9-column text formats used to describe and represent genomic features. -The formats have quite evolved since 1997, and despite well-defined specifications existing nowadays they have a great flexibility allowing holding wide variety of information. -This flexibility has a drawback aspect, there is an incredible amount of flavor of the formats: GFF / GFF1 / GFF2 / GFF2.5 / GFF3 / GTF / GTF2 / GTF2.1 / GTF2.2 / GTF2.5 / GTF3 - -It's often hard to understand and differentiate all GFF/GTF formats/flavors. Many tools using GTF/GFF formats fails due to specific expectations. -AGAT is a suite of tools able to deal with any GTF/GFF formats and perform most of the possible tasks you would need. - -.. figure:: img/wordcloud.png - - -Contents -======== - -.. toctree:: - :maxdepth: 2 - :caption: General - - agat_for_you.md - agat_how_does_it_work.md - troubleshooting.md - how_to_cite.md - why_agat.md - - -.. toctree:: - :maxdepth: 3 - :caption: Knowledge - - gxf.md - -.. toctree:: - :maxdepth: 2 - :caption: AGAT vs other tools - - topological-sorting-of-gff-features.md - gff_to_bed.md - gff_to_gtf.md - - -.. toctree:: - :maxdepth: 1 - :caption: List of tools - - tools/agat_convert_bed2gff.md - tools/agat_convert_embl2gff.md - tools/agat_convert_genscan2gff.md - tools/agat_convert_mfannot2gff.md - tools/agat_convert_minimap2_bam2gff.md - tools/agat_convert_sp_gff2bed.md - tools/agat_convert_sp_gff2gtf.md - tools/agat_convert_sp_gff2tsv.md - tools/agat_convert_sp_gff2zff.md - tools/agat_convert_sp_gxf2gxf.md - tools/agat_sp_Prokka_inferNameFromAttributes.md - tools/agat_sp_add_intergenic_regions.md - tools/agat_sp_add_introns.md - tools/agat_sp_add_splice_sites.md - tools/agat_sp_add_start_and_stop.md - tools/agat_sp_alignment_output_style.md - tools/agat_sp_clipN_seqExtremities_and_fixCoordinates.md - tools/agat_sp_compare_two_BUSCOs.md - tools/agat_sp_compare_two_annotations.md - tools/agat_sp_complement_annotations.md - tools/agat_sp_ensembl_output_style.md - tools/agat_sp_extract_attributes.md - tools/agat_sp_extract_sequences.md - tools/agat_sp_filter_by_ORF_size.md - tools/agat_sp_filter_by_locus_distance.md - tools/agat_sp_filter_by_mrnaBlastValue.md - tools/agat_sp_filter_feature_by_attribute_presence.md - tools/agat_sp_filter_feature_by_attribute_value.md - tools/agat_sp_filter_feature_from_keep_list.md - tools/agat_sp_filter_feature_from_kill_list.md - tools/agat_sp_filter_gene_by_intron_numbers.md - tools/agat_sp_filter_gene_by_length.md - tools/agat_sp_filter_incomplete_gene_coding_models.md - tools/agat_sp_filter_record_by_coordinates.md - tools/agat_sp_fix_cds_phases.md - tools/agat_sp_fix_features_locations_duplicated.md - tools/agat_sp_fix_fusion.md - tools/agat_sp_fix_longest_ORF.md - tools/agat_sp_fix_overlaping_genes.md - tools/agat_sp_fix_small_exon_from_extremities.md - tools/agat_sp_flag_premature_stop_codons.md - tools/agat_sp_flag_short_introns.md - tools/agat_sp_functional_statistics.md - tools/agat_sp_gxf_to_gff3.md - tools/agat_sp_keep_longest_isoform.md - tools/agat_sp_kraken_assess_liftover.md - tools/agat_sp_list_short_introns.md - tools/agat_sp_load_function_from_protein_align.md - tools/agat_sp_manage_IDs.md - tools/agat_sp_manage_UTRs.md - tools/agat_sp_manage_attributes.md - tools/agat_sp_manage_functional_annotation.md - tools/agat_sp_manage_introns.md - tools/agat_sp_merge_annotations.md - tools/agat_sp_move_attributes_within_records - tools/agat_sp_prokka_fix_fragmented_gene_annotations.md - tools/agat_sp_sensitivity_specificity.md - tools/agat_sp_separate_by_record_type.md - tools/agat_sp_split_by_level2_feature.md - tools/agat_sp_statistics.md - tools/agat_sp_to_tabulated.md - tools/agat_sp_webApollo_compliant.md - tools/agat_sq_add_attributes_from_tsv.md - tools/agat_sq_add_hash_tag.md - tools/agat_sq_add_locus_tag.md - tools/agat_sq_filter_feature_from_fasta.md - tools/agat_sq_list_attributes.md - tools/agat_sq_manage_IDs.md - tools/agat_sq_manage_attributes.md - tools/agat_sq_mask.md - tools/agat_sq_remove_redundant_entries.md - tools/agat_sq_repeats_analyzer.md - tools/agat_sq_reverse_complement.md - tools/agat_sq_rfam_analyzer.md - tools/agat_sq_split.md - tools/agat_sq_stat_basic.md - -Indices and tables -================== - -* :ref:`genindex` -* :ref:`search` diff --git a/docs/install.md b/docs/install.md new file mode 100644 index 00000000..f22ecb38 --- /dev/null +++ b/docs/install.md @@ -0,0 +1,159 @@ +# Installation + +## Using Docker + + +First you must have [Docker](https://docs.docker.com/get-docker/) installed and running. +Secondly have look at the availabe AGAT biocontainers at [quay.io](https://quay.io/repository/biocontainers/agat?tab=tags). + +Then: +``` +# get the chosen AGAT container version +docker pull quay.io/biocontainers/agat:0.8.0--pl5262hdfd78af_0 +# use an AGAT's tool e.g. agat_convert_sp_gxf2gxf.pl +docker run quay.io/biocontainers/agat:0.8.0--pl5262hdfd78af_0 agat_convert_sp_gxf2gxf.pl --help +``` + +## Using Singularity + +First you must have [Singularity](https://sylabs.io/guides/3.5/user-guide/quick_start.html) installed and running. +Secondly have look at the availabe AGAT biocontainers at [quay.io](https://quay.io/repository/biocontainers/agat?tab=tags). + +Then: +``` +# get the chosen AGAT container version +singularity pull docker://quay.io/biocontainers/agat:1.0.0--pl5321hdfd78af_0 +# run the container +singularity run agat_1.0.0--pl5321hdfd78af_0.sif +``` + +You are now in the container. You can use an AGAT's tool e.g. agat_convert_sp_gxf2gxf.pl doing +``` +agat_convert_sp_gxf2gxf.pl --help +``` + + +## Using Bioconda + +### Install AGAT + + ``` + conda install -c bioconda agat + ``` + +or in a fresh environment: + + ``` + conda create -c bioconda -n agat agat + ``` + +### Update AGAT + + ``` + conda update agat + ``` + +### Uninstall AGAT + ``` + conda uninstall agat + ``` + + +## Old school - Manually + +You will have to install all prerequisites and AGAT manually. + +### Install prerequisites + * R (optional) + You can install it by conda (`conda install r-base`), through [CRAN](https://cran.r-project.org) ([See here for a nice tutorial](https://www.datacamp.com/community/tutorials/installing-R-windows-mac-ubuntu)) or using your package management tool (e.g apt for Debian, Ubuntu, and related Linux distributions). R is optional and can be used to perform some plots. You will need to install the perl depency Statistics::R + + * Perl >= 5.8 + It should already be available on your computer. If you are unlucky [perl.org](https://www.perl.org/get.html) is the place to go. + + * Perl modules + They can be installed in different ways: + + * using cpan or cpanm + + ``` + cpanm install bioperl Clone Graph::Directed LWP::UserAgent Carp Sort::Naturally File::Share File::ShareDir::Install Moose YAML LWP::Protocol::https Term::ProgressBar + ``` + + * using conda + + * using the provided yaml file + + ``` + conda env create -f conda_environment_AGAT.yml + conda activate agat + ``` + + * manually + + ``` + conda install perl-bioperl perl-clone perl-graph perl-lwp-simple perl-carp perl-sort-naturally perl-file-share perl-file-sharedir-install perl-moose perl-yaml perl-lwp-protocol-https perl-term-progressbar + ``` + + * using your package management tool (e.g apt for Debian, Ubuntu, and related Linux distributions) + + ``` + apt install libbio-perl-perl libclone-perl libgraph-perl liblwp-useragent-determined-perl libstatistics-r-perl libcarp-clan-perl libsort-naturally-perl libfile-share-perl libfile-sharedir libfile-sharedir-install-perl libyaml-perl liblwp-protocol-https-perl libterm-progressbar-perl + ``` + + * Optional + Some scripts offer the possibility to perform plots. You will need R and Statistics::R which are not included by default. + + * R + You can install it by conda (`conda install r-base`), through [CRAN](https://cran.r-project.org) ([See here for a nice tutorial](https://www.datacamp.com/community/tutorials/installing-R-windows-mac-ubuntu)) or using your package management tool (e.g apt for Debian, Ubuntu, and related Linux distributions). + + * Statistics::R + You can install it through conda (`conda install perl-statistics-r`), using cpan/cpanm (`cpanm install Statistics::R`), or your package management tool (`apt install libstatistics-r-perl`) + + + +### Install AGAT + + ``` + git clone https://github.com/NBISweden/AGAT.git # Clone AGAT + cd AGAT # move into AGAT folder + perl Makefile.PL # Check all the dependencies* + make # Compile + make test # Test + make install # Install + ``` + +*If dependencies are missing you will be warn. Please refer to the [Install prerequisites](#install-prerequisites) section. + +**Remark**: On MS Windows, instead of make you'd probably have to use dmake or nmake depending the toolchain you have. + +### Update AGAT +From the folder where the repository is located. + + ``` + git pull # Update to last AGAT + perl Makefile.PL # Check all the dependencies* + make # Compile + make test # Test + make install # Install + ``` +*If dependencies are missing you will be warn. Please refer to the [Install prerequisites](#install-prerequisites) section. + +### Change to a specific version +From the folder where the repository is located. + + ``` + git pull # Update the code + git checkout v0.1 # use version v0.1 (See releases tab for a list of available versions) + perl Makefile.PL # Check all the dependencies* + make # Compile + make test # Test + make install # Install + ``` +*If dependencies are missing you will be warn. Please refer to the [Install prerequisites](#install-prerequisites) section. + +### Uninstall AGAT + + ``` + perl uninstall_AGAT + ``` + diff --git a/docs/tools/agat_convert_bed2gff.md b/docs/tools/agat_convert_bed2gff.md index bf93fa20..f2731ade 100644 --- a/docs/tools/agat_convert_bed2gff.md +++ b/docs/tools/agat_convert_bed2gff.md @@ -1,11 +1,11 @@ -# agat\_convert\_bed2gff.pl +# agat_convert_bed2gff.pl ## DESCRIPTION The script takes a bed file as input, and will translate it in gff format. The BED format is described [here](https://genome.ucsc.edu/FAQ/FAQformat.html##format1) -The script converts 0-based, half-open \[start-1, end) bed file to -1-based, closed \[start, end\] General Feature Format v3 (GFF3). +The script converts 0-based, half-open [start-1, end) bed file to +1-based, closed [start, end] General Feature Format v3 (GFF3). ## SYNOPSIS @@ -23,23 +23,23 @@ agat_convert_bed2gff.pl -h - **--source** The source informs about the tool used to produce the data and is stored in 2nd field of a gff file. - Example: Stringtie,Maker,Augustus,etc. \[default: data\] + Example: Stringtie,Maker,Augustus,etc. [default: data] -- **--primary\_tag** +- **--primary_tag** - The primary\_tag corresponds to the data type and is stored in 3rd field of a gff file. - Example: gene,mRNA,CDS,etc. \[default: gene\] + The primary_tag corresponds to the data type and is stored in 3rd field of a gff file. + Example: gene,mRNA,CDS,etc. [default: gene] -- **--inflate\_off** +- **--inflate_off** By default we inflate the block fields (blockCount, blockSizes, blockStarts) to create subfeatures - of the main feature (primary\_tag). The type of subfeature created is based on the - inflate\_type parameter. If you do not want this inflating behaviour you can deactivate it - by using the --inflate\_off option. + of the main feature (primary_tag). The type of subfeature created is based on the + inflate_type parameter. If you do not want this inflating behaviour you can deactivate it + by using the --inflate_off option. -- **--inflate\_type** +- **--inflate_type** - Feature type (3rd column in gff) created when inflate parameter activated \[default: exon\]. + Feature type (3rd column in gff) created when inflate parameter activated [default: exon]. - **--verbose** diff --git a/docs/tools/agat_convert_embl2gff.md b/docs/tools/agat_convert_embl2gff.md index 584f8b32..63991ea5 100644 --- a/docs/tools/agat_convert_embl2gff.md +++ b/docs/tools/agat_convert_embl2gff.md @@ -1,4 +1,4 @@ -# agat\_convert\_embl2gff.pl +# agat_convert_embl2gff.pl ## DESCRIPTION @@ -22,7 +22,7 @@ agat_converter_embl2gff.pl --embl infile.embl [ -o outfile ] This is an EMBL format dedicated for submission and contains particularity to deal with. This parameter is needed to get a proper sequence id in the GFF3 from an embl made with EMBLmyGFF3. -- **--primary\_tag**, **--pt**, **-t** +- **--primary_tag**, **--pt**, **-t** List of "primary tag". Useful to discard or keep specific features. Multiple tags must be coma-separated. diff --git a/docs/tools/agat_convert_genscan2gff.md b/docs/tools/agat_convert_genscan2gff.md index 9a1d9e0a..b0e95b90 100644 --- a/docs/tools/agat_convert_genscan2gff.md +++ b/docs/tools/agat_convert_genscan2gff.md @@ -1,10 +1,10 @@ -# agat\_convert\_genscan2gff.pl +# agat_convert_genscan2gff.pl ## DESCRIPTION The script takes a genscan file as input, and will translate it in gff format. -The genscan format is described here: http://genome.crg.es/courses/Bioinformatics2003\_genefinding/results/genscan.html -/!\\ vvv Known problem vvv /!\\ +The genscan format is described here: http://genome.crg.es/courses/Bioinformatics2003_genefinding/results/genscan.html +/! vvv Known problem vvv /! You must have submited only DNA sequence, wihtout any header!! Indeed the tool expects only DNA sequences and does not crash/warn if an header is submited along the sequence. @@ -12,7 +12,7 @@ e.g If you have an header ">seq" s-e-q are seen as the 3 first nucleotides of th Then all prediction location are shifted accordingly. (checked only on the online version http://argonaute.mit.edu/GENSCAN.html. I don't know if there is the same pronlem elsewhere.) -/!\\ ^^^ Known problem ^^^^ /!\\ +/! ^^^ Known problem ^^^^ /! ## SYNOPSIS @@ -30,12 +30,12 @@ agat_convert_genscan2gff.pl -h - **--source** The source informs about the tool used to produce the data and is stored in 2nd field of a gff file. - Example: Stringtie,Maker,Augustus,etc. \[default: data\] + Example: Stringtie,Maker,Augustus,etc. [default: data] -- **--primary\_tag** +- **--primary_tag** - The primary\_tag corresponf to the data type and is stored in 3rd field of a gff file. - Example: gene,mRNA,CDS,etc. \[default: gene\] + The primary_tag corresponf to the data type and is stored in 3rd field of a gff file. + Example: gene,mRNA,CDS,etc. [default: gene] - **--verbose** diff --git a/docs/tools/agat_convert_mfannot2gff.md b/docs/tools/agat_convert_mfannot2gff.md index a3c211f4..b9a1c336 100644 --- a/docs/tools/agat_convert_mfannot2gff.md +++ b/docs/tools/agat_convert_mfannot2gff.md @@ -1,4 +1,4 @@ -# agat\_convert\_mfannot2gff.pl +# agat_convert_mfannot2gff.pl ## DESCRIPTION diff --git a/docs/tools/agat_convert_minimap2_bam2gff.md b/docs/tools/agat_convert_minimap2_bam2gff.md index 46e2d388..f68f9efb 100644 --- a/docs/tools/agat_convert_minimap2_bam2gff.md +++ b/docs/tools/agat_convert_minimap2_bam2gff.md @@ -1,11 +1,11 @@ -# agat\_convert\_minimap2\_bam2gff.pl +# agat_convert_minimap2_bam2gff.pl ## DESCRIPTION The script converts output from minimap2 (bam or sam) into GFF file. To get bam from minimap2 use the following command: -minimap2 -ax splice:hq genome.fa Asecodes\_parviclava.nucest.fa | samtools sort -O BAM -o output.bam +minimap2 -ax splice:hq genome.fa Asecodes_parviclava.nucest.fa | samtools sort -O BAM -o output.bam To use bam with this script you will need samtools in your path. diff --git a/docs/tools/agat_convert_sp_gff2bed.md b/docs/tools/agat_convert_sp_gff2bed.md index a71cd62c..10552c7e 100644 --- a/docs/tools/agat_convert_sp_gff2bed.md +++ b/docs/tools/agat_convert_sp_gff2bed.md @@ -1,4 +1,4 @@ -# agat\_convert\_sp\_gff2bed.pl +# agat_convert_sp_gff2bed.pl ## DESCRIPTION diff --git a/docs/tools/agat_convert_sp_gff2gtf.md b/docs/tools/agat_convert_sp_gff2gtf.md index 7947acf1..1937115c 100644 --- a/docs/tools/agat_convert_sp_gff2gtf.md +++ b/docs/tools/agat_convert_sp_gff2gtf.md @@ -1,4 +1,4 @@ -# agat\_convert\_sp\_gff2gtf.pl +# agat_convert_sp_gff2gtf.pl ## DESCRIPTION @@ -6,16 +6,16 @@ The script aims to convert any GTF/GFF file into a proper GTF file. Full information about the format can be found here: [https://agat.readthedocs.io/en/latest/gxf.html](https://agat.readthedocs.io/en/latest/gxf.html) You can choose among 7 different GTF types (1, 2, 2.1, 2.2, 2.5, 3 or relax). Depending the version selected the script will filter out the features that are not accepted. -For GTF2.5 and 3, every level1 feature (e.g nc\_gene pseudogene) will be converted into +For GTF2.5 and 3, every level1 feature (e.g nc_gene pseudogene) will be converted into gene feature and every level2 feature (e.g mRNA ncRNA) will be converted into transcript feature. You can even produce a GFF-like GTF using the relax option. It allows to keep all original feature types (3rd column). No modification will occur e.g. mRNA to transcript. -To be fully GTF compliant all feature have a gene\_id and a transcript\_id attribute. -The gene\_id is unique identifier for the genomic source of the transcript, which is +To be fully GTF compliant all feature have a gene_id and a transcript_id attribute. +The gene_id is unique identifier for the genomic source of the transcript, which is used to group transcripts into genes. -The transcript\_id is a unique identifier for the predicted transcript, +The transcript_id is a unique identifier for the predicted transcript, which is used to group features into transcripts. ## SYNOPSIS @@ -31,22 +31,22 @@ agat_convert_sp_gff2gtf -h Input GFF file that will be read -- **--gtf\_version** +- **--gtf_version** version of the GTF output (1,2,2.1,2.2,2.5,3 or relax). Default 3. relax: all feature types are accepted. - 3: GTF3 (9 feature types accepted): gene, transcript, exon, CDS, Selenocysteine, start\_codon, stop\_codon, three\_prime\_utr and five\_prime\_utr + 3: GTF3 (9 feature types accepted): gene, transcript, exon, CDS, Selenocysteine, start_codon, stop_codon, three_prime_utr and five_prime_utr - 2.5: GTF2.5 (8 feature types accepted): gene, transcript, exon, CDS, UTR, start\_codon, stop\_codon, Selenocysteine + 2.5: GTF2.5 (8 feature types accepted): gene, transcript, exon, CDS, UTR, start_codon, stop_codon, Selenocysteine - 2.2: GTF2.2 (9 feature types accepted): CDS, start\_codon, stop\_codon, 5UTR, 3UTR, inter, inter\_CNS, intron\_CNS and exon + 2.2: GTF2.2 (9 feature types accepted): CDS, start_codon, stop_codon, 5UTR, 3UTR, inter, inter_CNS, intron_CNS and exon - 2.1: GTF2.1 (6 feature types accepted): CDS, start\_codon, stop\_codon, exon, 5UTR, 3UTR + 2.1: GTF2.1 (6 feature types accepted): CDS, start_codon, stop_codon, exon, 5UTR, 3UTR - 2: GTF2 (4 feature types accepted): CDS, start\_codon, stop\_codon, exon + 2: GTF2 (4 feature types accepted): CDS, start_codon, stop_codon, exon - 1: GTF1 (5 feature types accepted): CDS, start\_codon, stop\_codon, exon, intron + 1: GTF1 (5 feature types accepted): CDS, start_codon, stop_codon, exon, intron - **-o** , **--output** , **--out** , **--outfile** or **--gtf** diff --git a/docs/tools/agat_convert_sp_gff2tsv.md b/docs/tools/agat_convert_sp_gff2tsv.md index a44c76ce..d895d152 100644 --- a/docs/tools/agat_convert_sp_gff2tsv.md +++ b/docs/tools/agat_convert_sp_gff2tsv.md @@ -1,4 +1,4 @@ -# agat\_convert\_sp\_gff2tsv.pl +# agat_convert_sp_gff2tsv.pl ## DESCRIPTION diff --git a/docs/tools/agat_convert_sp_gff2zff.md b/docs/tools/agat_convert_sp_gff2zff.md index 0f8b0931..475435b8 100644 --- a/docs/tools/agat_convert_sp_gff2zff.md +++ b/docs/tools/agat_convert_sp_gff2zff.md @@ -1,4 +1,4 @@ -# agat\_convert\_sp\_gff2zff.pl +# agat_convert_sp_gff2zff.pl ## DESCRIPTION diff --git a/docs/tools/agat_convert_sp_gxf2gxf.md b/docs/tools/agat_convert_sp_gxf2gxf.md index 885baa23..32c702dc 100644 --- a/docs/tools/agat_convert_sp_gxf2gxf.md +++ b/docs/tools/agat_convert_sp_gxf2gxf.md @@ -1,4 +1,4 @@ -# agat\_convert\_sp\_gxf2gxf.pl +# agat_convert_sp_gxf2gxf.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_Prokka_inferNameFromAttributes.md b/docs/tools/agat_sp_Prokka_inferNameFromAttributes.md index 804cb5f1..8db9b674 100644 --- a/docs/tools/agat_sp_Prokka_inferNameFromAttributes.md +++ b/docs/tools/agat_sp_Prokka_inferNameFromAttributes.md @@ -1,4 +1,4 @@ -# agat\_sp\_Prokka\_inferNameFromAttributes.pl +# agat_sp_Prokka_inferNameFromAttributes.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_add_attribute_shortest_exon_size.md b/docs/tools/agat_sp_add_attribute_shortest_exon_size.md index 06bf344d..07c555e5 100644 --- a/docs/tools/agat_sp_add_attribute_shortest_exon_size.md +++ b/docs/tools/agat_sp_add_attribute_shortest_exon_size.md @@ -1,8 +1,8 @@ -# agat\_sp\_add\_attribute\_shortest\_exon\_size.pl +# agat_sp_add_attribute_shortest_exon_size.pl ## DESCRIPTION -The script add the attribute \ to each gene and rna, which will hold the size of the shortest exon in bp. +The script add the attribute to each gene and rna, which will hold the size of the shortest exon in bp. ## SYNOPSIS diff --git a/docs/tools/agat_sp_add_attribute_shortest_intron_size.md b/docs/tools/agat_sp_add_attribute_shortest_intron_size.md index 878c977b..58061dab 100644 --- a/docs/tools/agat_sp_add_attribute_shortest_intron_size.md +++ b/docs/tools/agat_sp_add_attribute_shortest_intron_size.md @@ -1,8 +1,8 @@ -# agat\_sp\_add\_attribute\_shortest\_intron\_size.pl +# agat_sp_add_attribute_shortest_intron_size.pl ## DESCRIPTION -The script add the attribute \ to each gene and rna, which will hold the size of the shortest intron in bp. +The script add the attribute to each gene and rna, which will hold the size of the shortest intron in bp. ## SYNOPSIS diff --git a/docs/tools/agat_sp_add_intergenic_regions.md b/docs/tools/agat_sp_add_intergenic_regions.md index 0f606d2b..23bd2efa 100644 --- a/docs/tools/agat_sp_add_intergenic_regions.md +++ b/docs/tools/agat_sp_add_intergenic_regions.md @@ -1,8 +1,8 @@ -# agat\_sp\_add\_intergenic\_regions.pl +# agat_sp_add_intergenic_regions.pl ## DESCRIPTION -The script aims to add intergenic features (intergenic\_region) to gtf/gff file. +The script aims to add intergenic features (intergenic_region) to gtf/gff file. The intergenic regions are deduced from gene features (feature type gene from the 3rd column). ## SYNOPSIS @@ -24,8 +24,8 @@ agat_sp_add_intergenic_regions.pl --help - **-c** or **--config** - String - Input agat config file. By default AGAT takes as input agat\_config.yaml file from the working directory if any, - otherwise it takes the orignal agat\_config.yaml shipped with AGAT. To get the agat\_config.yaml locally type: "agat config --expose". + String - Input agat config file. By default AGAT takes as input agat_config.yaml file from the working directory if any, + otherwise it takes the orignal agat_config.yaml shipped with AGAT. To get the agat_config.yaml locally type: "agat config --expose". The --config option gives yo the possibility to use your own AGAT config file (located elsewhere or named differently). - **-v** or **--verbose** diff --git a/docs/tools/agat_sp_add_introns.md b/docs/tools/agat_sp_add_introns.md index 41dbbb9d..a8297cb6 100644 --- a/docs/tools/agat_sp_add_introns.md +++ b/docs/tools/agat_sp_add_introns.md @@ -1,4 +1,4 @@ -# agat\_sp\_add\_introns.pl +# agat_sp_add_introns.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_add_splice_sites.md b/docs/tools/agat_sp_add_splice_sites.md index f2d9f798..05187f15 100644 --- a/docs/tools/agat_sp_add_splice_sites.md +++ b/docs/tools/agat_sp_add_splice_sites.md @@ -1,8 +1,8 @@ -# agat\_sp\_add\_splice\_sites.pl +# agat_sp_add_splice_sites.pl ## DESCRIPTION -The script aims to add splice sites features (five\_prime\_cis\_splice\_site and three\_prime\_cis\_splice\_site) to gtf/gff file. +The script aims to add splice sites features (five_prime_cis_splice_site and three_prime_cis_splice_site) to gtf/gff file. The splice sites are deduced from CDS features. ## SYNOPSIS @@ -24,8 +24,8 @@ agat_sp_add_splice_sites.pl --help - **-c** or **--config** - String - Input agat config file. By default AGAT takes as input agat\_config.yaml file from the working directory if any, - otherwise it takes the orignal agat\_config.yaml shipped with AGAT. To get the agat\_config.yaml locally type: "agat config --expose". + String - Input agat config file. By default AGAT takes as input agat_config.yaml file from the working directory if any, + otherwise it takes the orignal agat_config.yaml shipped with AGAT. To get the agat_config.yaml locally type: "agat config --expose". The --config option gives yo the possibility to use your own AGAT config file (located elsewhere or named differently). - **--help** or **-h** diff --git a/docs/tools/agat_sp_add_start_and_stop.md b/docs/tools/agat_sp_add_start_and_stop.md index f0bf5b39..40de0675 100644 --- a/docs/tools/agat_sp_add_start_and_stop.md +++ b/docs/tools/agat_sp_add_start_and_stop.md @@ -1,4 +1,4 @@ -# agat\_sp\_add\_start\_and\_stop.pl.pl +# agat_sp_add_start_and_stop.pl.pl ## DESCRIPTION @@ -25,7 +25,7 @@ agat_sp_add_start_and_stop.pl.pl --help - **--ct**, **--codon** or **--table** - Codon table to use. \[default 1\] + Codon table to use. [default 1] - **--out**, **--output** or **-o** diff --git a/docs/tools/agat_sp_alignment_output_style.md b/docs/tools/agat_sp_alignment_output_style.md index f3f6d554..ec80f0b4 100644 --- a/docs/tools/agat_sp_alignment_output_style.md +++ b/docs/tools/agat_sp_alignment_output_style.md @@ -1,9 +1,9 @@ -# agat\_sp\_alignment\_output\_style.pl +# agat_sp_alignment_output_style.pl ## DESCRIPTION The script takes a normal gtf/gff annotation format file and convert it -to gff3 alignment format. It means it add a structure of match / match\_part +to gff3 alignment format. It means it add a structure of match / match_part as relationship between the different features. ## SYNOPSIS @@ -22,7 +22,7 @@ agat_sp_alignment_output_style.pl --help - **-c** or **--ct** When the gff file provided is not correcly formated and features are linked - to each other by a comon tag (by default locus\_tag), this tag can be provided + to each other by a comon tag (by default locus_tag), this tag can be provided to parse the file correctly. - **-v** diff --git a/docs/tools/agat_sp_clipN_seqExtremities_and_fixCoordinates.md b/docs/tools/agat_sp_clipN_seqExtremities_and_fixCoordinates.md index c808a6a2..6abeea3e 100644 --- a/docs/tools/agat_sp_clipN_seqExtremities_and_fixCoordinates.md +++ b/docs/tools/agat_sp_clipN_seqExtremities_and_fixCoordinates.md @@ -1,4 +1,4 @@ -# agat\_sp\_clipN\_seqExtremities\_and\_fixCoordinates.pl +# agat_sp_clipN_seqExtremities_and_fixCoordinates.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_compare_two_BUSCOs.md b/docs/tools/agat_sp_compare_two_BUSCOs.md index f54bc04f..df37ab86 100644 --- a/docs/tools/agat_sp_compare_two_BUSCOs.md +++ b/docs/tools/agat_sp_compare_two_BUSCOs.md @@ -1,4 +1,4 @@ -# agat\_sp\_compare\_two\_BUSCOs.pl +# agat_sp_compare_two_BUSCOs.pl ## DESCRIPTION @@ -12,8 +12,8 @@ Where EOG090W00UK is the BUSCO name/label/group investigated, and complete2dupli By loading these gff tracks in a web browser and helped by other tracks (e.g the genome annotation/prediction) can help to understand why the BUSCO have been classified differently from run1 to run2. In other term it allows to catch potential problems in an annotation. -agat\_sp\_compare\_two\_BUSCOs.pl has been tested with results from BUSCO version 3 and 4. -/!\\ The tool expects a BUSCO run in genome mode as input folder 1 and a BUSCO run in proteins mode +agat_sp_compare_two_BUSCOs.pl has been tested with results from BUSCO version 3 and 4. +/! The tool expects a BUSCO run in genome mode as input folder 1 and a BUSCO run in proteins mode as input folder 2. You can also decide to provide twice (--f1 --f2) the same BUSCO run in genome mode, the tool will only extract the annotation of the complete,fragmented and duplicated annotated BUSCOs from the 1st run in gff. diff --git a/docs/tools/agat_sp_compare_two_annotations.md b/docs/tools/agat_sp_compare_two_annotations.md index d5a2f270..c990af48 100644 --- a/docs/tools/agat_sp_compare_two_annotations.md +++ b/docs/tools/agat_sp_compare_two_annotations.md @@ -1,4 +1,4 @@ -# agat\_sp\_compare\_two\_annotations.pl +# agat_sp_compare_two_annotations.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_complement_annotations.md b/docs/tools/agat_sp_complement_annotations.md index 5d2ccd6f..0b309d9c 100644 --- a/docs/tools/agat_sp_complement_annotations.md +++ b/docs/tools/agat_sp_complement_annotations.md @@ -1,4 +1,4 @@ -# agat\_sp\_complement\_annotations.pl +# agat_sp_complement_annotations.pl ## DESCRIPTION @@ -8,7 +8,7 @@ A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature with A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added. A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature with a CDS from the reference annotation will be added only if the CDSs don't overlap. A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added only if none of the l3 features overlap. -/!\\ It is sufficiant that only one isoform is overlapping to prevent the whole gene (l1 feature) from the addfile.gff to be added in the output. +/! It is sufficiant that only one isoform is overlapping to prevent the whole gene (l1 feature) from the addfile.gff to be added in the output. ## SYNOPSIS @@ -26,10 +26,10 @@ agat_sp_complement_annotations.pl --help - **--add** or **-a** Annotation(s) file you would like to use to complement the reference annotation. You can specify as much file you want like so: -a addfile1 -a addfile2 -a addfile3 - /!\\ The order you provide these files matter. Once the reference file has been complemented by file1, this new annotation becomes the new reference that will be complemented by file2 etc. - /!\\ The result with -a addfile1 -a addfile2 will differ to the result from -a addfile2 -a addfile1. So, be aware of what you want if you use several addfiles. + /! The order you provide these files matter. Once the reference file has been complemented by file1, this new annotation becomes the new reference that will be complemented by file2 etc. + /! The result with -a addfile1 -a addfile2 will differ to the result from -a addfile2 -a addfile1. So, be aware of what you want if you use several addfiles. -- **--size\_min** or **-s** +- **--size_min** or **-s** Option to keep the non-overlping gene only if the CDS size (in nucleotide) is over the minimum size defined. Default = 0 that means all of them are kept. diff --git a/docs/tools/agat_sp_ensembl_output_style.md b/docs/tools/agat_sp_ensembl_output_style.md index 1868a4c6..3bc94fe2 100644 --- a/docs/tools/agat_sp_ensembl_output_style.md +++ b/docs/tools/agat_sp_ensembl_output_style.md @@ -1,4 +1,4 @@ -# agat\_sp\_ensembl\_output\_style.pl +# agat_sp_ensembl_output_style.pl ## DESCRIPTION @@ -21,7 +21,7 @@ agat_sp_ensembl_output_style.pl --help - **-c** or **--ct** When the gff file provided is not correcly formated and features are linked - to each other by a comon tag (by default locus\_tag), this tag can be provided + to each other by a comon tag (by default locus_tag), this tag can be provided to parse the input file correctly. - **-v** diff --git a/docs/tools/agat_sp_extract_attributes.md b/docs/tools/agat_sp_extract_attributes.md index 33b0f6a2..43e2fd89 100644 --- a/docs/tools/agat_sp_extract_attributes.md +++ b/docs/tools/agat_sp_extract_attributes.md @@ -1,4 +1,4 @@ -# agat\_sp\_extract\_attributes.pl +# agat_sp_extract_attributes.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_extract_sequences.md b/docs/tools/agat_sp_extract_sequences.md index 45956e84..8c63eb73 100644 --- a/docs/tools/agat_sp_extract_sequences.md +++ b/docs/tools/agat_sp_extract_sequences.md @@ -1,4 +1,4 @@ -# agat\_sp\_extract\_sequences.pl +# agat_sp_extract_sequences.pl ## Briefly in pictures @@ -16,17 +16,17 @@ The result is written to the specified output file, or to STDOUT. Features spanning several locations (e.g. UTR, CDS), are extracted chunk by chunk and merged to create the biological feature. If you wish to extract each chunck independently, please refer to the --split parameter. To see the list of features that may span over several locations -within AGAT run: agat\_convert\_sp\_gxf2gxf.pl --expose -and then look at the file called features\_spread.json. +within AGAT run: agat_convert_sp_gxf2gxf.pl --expose +and then look at the file called features_spread.json. The headers are formated like that: -\>ID gene=gene\_ID name=NAME seq\_id=Chromosome\_ID type=cds 5'extra=VALUE +>ID gene=gene_ID name=NAME seq_id=Chromosome_ID type=cds 5'extra=VALUE The ID is the identifier of the feature (ID attribute in the 9th column. If missing it is created by AGAT) The gene value will be the ID of the level1 feature (the top feature of the record) The name value is optional and will be written only if the Name attribute exists in the gff. -The seq\_id value is the value from 1st column within the gff. +The seq_id value is the value from 1st column within the gff. The type value holds the information of the feature type extracted. 5'extra or 3'extra is optional, it holds the information of extra nucleotides removed or added when using the downstream and/or upstream parameter. @@ -71,7 +71,7 @@ agat_sp_extract_sequences.pl --help ## OPTIONS -- **--alternative\_start\_codon** or **--asc** +- **--alternative_start_codon** or **--asc** Bolean - When activated it can affect the translation of the start codon. Indeed alternative start codons exist, and are translated by the cells'machinery @@ -88,34 +88,34 @@ agat_sp_extract_sequences.pl --help then reverse complemented). It corresponds to extract the exons sequences, merge them, and reverse complement the sequence (--type exon --merge --revcomp). -- **--clean\_final\_stop** or **--cfs** +- **--clean_final_stop** or **--cfs** Boolean - The Clean Final Stop option allows removing the translation of the - final stop codons that is represented by the <\*> character. + final stop codons that is represented by the <*> character. This character can be disturbing for many programs (e.g interproscan) -- **--clean\_internal\_stop** or **--cis** +- **--clean_internal_stop** or **--cis** Boolean - The Clean Internal Stop option allows replacing the translation of the - stop codons present among the sequence that is represented by the <\*> character - by . Indeed the <\*> character can be disturbing for many programs + stop codons present among the sequence that is represented by the <*> character + by . Indeed the <*> character can be disturbing for many programs (e.g interproscan) - **--codon**, **--table** or **--ct** - Integer - Allow to choose the codon table for the translation. \[default 1\] + Integer - Allow to choose the codon table for the translation. [default 1] - **--do**, **-3**, **--three**, **-down** or **-downstream** Integer - It will take that number of nucleotide in more at the 3' extremity. - /!\\ You must activate the option "--full" if you with to extract only the most downstream part of certain feature (exon,cds,utr) + /! You must activate the option "--full" if you with to extract only the most downstream part of certain feature (exon,cds,utr) otherwise you will extract each downstream parts of the subfeatures (e.g many cds parts may be needed to shape a cds in its whole). - **--eo** Boolean - Called 'extremity only', this option will extract only the adjacent parts of a feature. This option has to be activated with -u and/or -p option. - /!\\ using -u and -p together builds a chimeric sequence which will be the concatenation of the left and right extremities of a feature. + /! using -u and -p together builds a chimeric sequence which will be the concatenation of the left and right extremities of a feature. - **-f** or **--fasta** @@ -129,7 +129,7 @@ agat_sp_extract_sequences.pl --help The use of that option with '--type exon' will extract the pre-mRNA sequence (i.e with introns). Use of that option on cds will give the pre-mRNA without the untraslated regions (UTRs). (To extract an mRNA as it is defined biologicaly you need to use the - \`-t exon\` option with the --merge option) + `-t exon` option with the --merge option) - **-g**, **--gff** or **-ref** @@ -178,12 +178,12 @@ agat_sp_extract_sequences.pl --help String - Output fasta file. If no output file is specified, the output will be written to STDOUT. -- **--plus\_strand\_only** +- **--plus_strand_only** Boolean - By default the extrated feature sequences from a minus strand is reverse complemented. Activating this option you will always get sequence from plus strand ( not reverse complemented). - You can get the opposite (minus strand only) by using --plus\_strand\_only --revcomp + You can get the opposite (minus strand only) by using --plus_strand_only --revcomp - **-p**, **--protein** or **--aa** @@ -191,7 +191,7 @@ agat_sp_extract_sequences.pl --help By default the codon table used is the 1 (Standard). See --table parameter for more options. -- **--remove\_orf\_offset** or **--roo** +- **--remove_orf_offset** or **--roo** Boolean - CDS can start with a phase different from 0 when a gene model is fragmented. When asking for protein translation this (start) offset is trimmed out automatically. @@ -201,7 +201,7 @@ agat_sp_extract_sequences.pl --help - **--revcomp** - Boolean - To reverse complement the extracted sequence \[default - False\]. + Boolean - To reverse complement the extracted sequence [default - False]. By default the extrated feature sequences from a minus strand is reverse complemented. Consequently, for minus strand features that option will extract the sequences from plus strand from left to right. @@ -218,19 +218,19 @@ agat_sp_extract_sequences.pl --help String - Define the feature you want to extract the sequence from. Default 'cds'. - Most common choice are: gene,mrna,exon,cds,trna,three\_prime\_utr,five\_prime\_utr. + Most common choice are: gene,mrna,exon,cds,trna,three_prime_utr,five_prime_utr. When you choose exon (or cds,utr,etc.), all the exons of a same parent feature are attached together before to extract the sequence. If you wish to extract each exon of an mRNA independently, see option --split. - /!\\ \`-t mRNA\` will extract the features labeled as "mRNA" and corresponds to the cdna\* + /! `-t mRNA` will extract the features labeled as "mRNA" and corresponds to the cdna* because it contains the introns if any. It does not actually extract the mRNAs as - it is defined biologicaly. To extract the mRNA as defined biologicaly you must use \`-t exon\`. - \*Not a real cdna because it is not reversed + it is defined biologicaly. To extract the mRNA as defined biologicaly you must use `-t exon`. + *Not a real cdna because it is not reversed - **--up**, **-5**, **--five** or **-upstream** Integer - It will take that number of nucleotide in more at the 5' extremity. - /!\\ You must activate the option "--full" if you wish to extract only the most + /! You must activate the option "--full" if you wish to extract only the most upstream part of certain features (exon,cds,utr) otherwise you will extract each upstream parts of the subfeatures (e.g many cds parts may be needed to shape a cds in its whole). diff --git a/docs/tools/agat_sp_filter_by_ORF_size.md b/docs/tools/agat_sp_filter_by_ORF_size.md index 3ca23ff9..2b67f5eb 100644 --- a/docs/tools/agat_sp_filter_by_ORF_size.md +++ b/docs/tools/agat_sp_filter_by_ORF_size.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_by\_ORF\_size.pl +# agat_sp_filter_by_ORF_size.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_filter_by_locus_distance.md b/docs/tools/agat_sp_filter_by_locus_distance.md index d64cc9d2..f9ca2bcd 100644 --- a/docs/tools/agat_sp_filter_by_locus_distance.md +++ b/docs/tools/agat_sp_filter_by_locus_distance.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_by\_locus\_distance.pl +# agat_sp_filter_by_locus_distance.pl ## DESCRIPTION @@ -26,9 +26,9 @@ agat_sp_filter_by_locus_distance.pl --help The minimum inter-loci distance to allow. No default (will not apply filter by default). -- **--add** or **--add\_flag** +- **--add** or **--add_flag** - Instead of filter the result into two output files, write only one and add the flag <low\_dist> in the gff.(tag = Lvalue or tag = Rvalue where L is left and R right and the value is the distance with accordingle the left or right locus) + Instead of filter the result into two output files, write only one and add the flag <low_dist> in the gff.(tag = Lvalue or tag = Rvalue where L is left and R right and the value is the distance with accordingle the left or right locus) - **-o** , **--output** , **--out** or **--outfile** diff --git a/docs/tools/agat_sp_filter_by_mrnaBlastValue.md b/docs/tools/agat_sp_filter_by_mrnaBlastValue.md index a4a8df92..917c1eb1 100644 --- a/docs/tools/agat_sp_filter_by_mrnaBlastValue.md +++ b/docs/tools/agat_sp_filter_by_mrnaBlastValue.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_by\_mrnaBlastValue.pl +# agat_sp_filter_by_mrnaBlastValue.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_filter_feature_by_attribute_presence.md b/docs/tools/agat_sp_filter_feature_by_attribute_presence.md index 83b0658c..9fd46d7f 100644 --- a/docs/tools/agat_sp_filter_feature_by_attribute_presence.md +++ b/docs/tools/agat_sp_filter_feature_by_attribute_presence.md @@ -1,11 +1,11 @@ -# agat\_sp\filter\_feature\_by\_attribute\_presence.pl +# agat_spfilter_feature_by_attribute_presence.pl ## DESCRIPTION The script aims to filter features according to attribute presence (9th column). If the attribute exists, the feature is discarded. Attribute are stored in the 9th column and have this shape: tag=value -/!\\ Removing a level1 or level2 feature will automatically remove all linked subfeatures, and +/! Removing a level1 or level2 feature will automatically remove all linked subfeatures, and removing all children of a feature will automatically remove this feature too. ## SYNOPSIS diff --git a/docs/tools/agat_sp_filter_feature_by_attribute_value.md b/docs/tools/agat_sp_filter_feature_by_attribute_value.md index b9fa6e50..ff5a182f 100644 --- a/docs/tools/agat_sp_filter_feature_by_attribute_value.md +++ b/docs/tools/agat_sp_filter_feature_by_attribute_value.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_feature\_by\_attribute\_value.pl +# agat_sp_filter_feature_by_attribute_value.pl ## DESCRIPTION @@ -8,9 +8,9 @@ The script aims to filter features according to attribute value (9th column). - If the attribute tag is missing (test cannot be applyed), the feature will be written into by default. If --na_aside parameter is activated then it will be written into _na.gff. Attribute are stored in the 9th column and have this shape: tag=value. -/!\\ Removing a level1 or level2 feature will automatically remove all linked subfeatures. -/!\\ Removing all children of a feature will automatically remove this feature too (excepted if --keep_parental is activated). -/!\\ If --keep_parental is not activated and --na_aside is activated, and all level3 features of a record are split between both _na.gff and _discarded.gff, then the parental level1 and level2 features are removed and will end up in the _na.gff file only. +/! Removing a level1 or level2 feature will automatically remove all linked subfeatures. +/! Removing all children of a feature will automatically remove this feature too (excepted if --keep_parental is activated). +/! If --keep_parental is not activated and --na_aside is activated, and all level3 features of a record are split between both _na.gff and _discarded.gff, then the parental level1 and level2 features are removed and will end up in the _na.gff file only. ## SYNOPSIS @@ -42,16 +42,16 @@ agat_sp_filter_feature_by_attribute_value.pl --help Value(s) to check in the attribute. Case sensitive. List of values must be coma separated. -- **--value\_insensitive** +- **--value_insensitive** Bolean. Deactivated by default. When activated the values provided by the --value parameter are handled case insensitive. -- **<--na\_aside** +- **<--na_aside** Bolean. Deactivated by default. By default if the attribute tag on which the filter is based is missing, the feature will be written into . When activated, such features will be written into a separate file called _na.gff. -- **<--keep\_parental>** +- **<--keep_parental>** Bolean. Deactivated by default. When activated even if all child features have been removed, the parental one will be kept. diff --git a/docs/tools/agat_sp_filter_feature_from_keep_list.md b/docs/tools/agat_sp_filter_feature_from_keep_list.md index 9070acbc..99e255dd 100644 --- a/docs/tools/agat_sp_filter_feature_from_keep_list.md +++ b/docs/tools/agat_sp_filter_feature_from_keep_list.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_feature\_from\_keep\_list.pl +# agat_sp_filter_feature_from_keep_list.pl ## DESCRIPTION @@ -30,7 +30,7 @@ agat_sp_filter_feature_from_keep_list.pl --help level3=CDS,exon,UTR,etc By default all feature are taking into account. fill the option by the value "all" will have the same behaviour. -- **--kl** or **--keep\_list** +- **--kl** or **--keep_list** Keep list. One value per line. diff --git a/docs/tools/agat_sp_filter_feature_from_kill_list.md b/docs/tools/agat_sp_filter_feature_from_kill_list.md index 794b4126..8c67c681 100644 --- a/docs/tools/agat_sp_filter_feature_from_kill_list.md +++ b/docs/tools/agat_sp_filter_feature_from_kill_list.md @@ -1,11 +1,11 @@ -# agat\_sp\_filter\_feature\_from\_kill\_list.pl +# agat_sp_filter_feature_from_kill_list.pl ## DESCRIPTION The script aims to remove features based on a kill list. The default behaviour is to look at the features's ID. If the feature has an ID (case insensitive) listed among the kill list it will be removed. -/!\\ Removing a level1 or level2 feature will automatically remove all linked subfeatures, and +/! Removing a level1 or level2 feature will automatically remove all linked subfeatures, and removing all children of a feature will automatically remove this feature too. ## SYNOPSIS @@ -30,7 +30,7 @@ agat_sp_filter_feature_from_kill_list.pl --help level3=CDS,exon,UTR,etc By default all feature are taking into account. fill the option by the value "all" will have the same behaviour. -- **--kl** or **--kill\_list** +- **--kl** or **--kill_list** Kill list. One value per line. diff --git a/docs/tools/agat_sp_filter_gene_by_intron_numbers.md b/docs/tools/agat_sp_filter_gene_by_intron_numbers.md index c4eee777..9b4b5377 100644 --- a/docs/tools/agat_sp_filter_gene_by_intron_numbers.md +++ b/docs/tools/agat_sp_filter_gene_by_intron_numbers.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_gene\_by\_intron\_numbers.pl +# agat_sp_filter_gene_by_intron_numbers.pl ## DESCRIPTION @@ -8,9 +8,9 @@ the other one with the remaining genes. Some examples: Select intronless genes: -agat\_sp\_filter\_gene\_by\_intron\_numbers.pl --gff infile.gff -o result.gff +agat_sp_filter_gene_by_intron_numbers.pl --gff infile.gff -o result.gff Select genes with more or equal 10 introns: -agat\_sp\_filter\_gene\_by\_intron\_numbers.pl --gff infile.gff --test ">=" --nb 10 \[ --output outfile \] +agat_sp_filter_gene_by_intron_numbers.pl --gff infile.gff --test ">=" --nb 10 [ --output outfile ] ## SYNOPSIS @@ -27,12 +27,12 @@ agat_sp_filter_gene_by_intron_numbers.pl --help - **-n**, **--nb** or **--number** - Integer - Number of introns \[Default 0\] + Integer - Number of introns [Default 0] - **-t** or **--test** Test to apply (>, <, =, >= or <=). If you use one of these two characters >, <, please do not forget to quote your parameter like that "<=". Else your terminal will complain. -\[Default "="\] +[Default "="] - **-o** or **--output** Output GFF file. If no output file is specified, the output will be diff --git a/docs/tools/agat_sp_filter_gene_by_length.md b/docs/tools/agat_sp_filter_gene_by_length.md index 4adc1fe6..a2742bf1 100644 --- a/docs/tools/agat_sp_filter_gene_by_length.md +++ b/docs/tools/agat_sp_filter_gene_by_length.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_gene\_by\_length.pl +# agat_sp_filter_gene_by_length.pl ## DESCRIPTION @@ -11,9 +11,9 @@ we apply the test on the longest one (the longest concatenated exon set). Some examples: Select L1 feature shorter than 1000bp: -agat\_sp\_filter\_gene\_by\_length.pl --gff infile.gff --size 1000 --test "<" -o result.gff +agat_sp_filter_gene_by_length.pl --gff infile.gff --size 1000 --test "<" -o result.gff Select genes longer than 200bp: -agat\_sp\_filter\_gene\_by\_length.pl --gff infile.gff --size 200 --test ">" -o result.gff +agat_sp_filter_gene_by_length.pl --gff infile.gff --size 200 --test ">" -o result.gff ## SYNOPSIS @@ -30,13 +30,13 @@ agat_sp_filter_gene_by_length.pl --help - **-s** or **--size** - Integer - Gene size in pb \[Default 100\] + Integer - Gene size in pb [Default 100] - **-t** or **--test** Test to apply (>, <, =, >= or <=). If you use one of these two characters >, <, please do not forget to quote your parameter like that "<=". Else your terminal will complain. - \[Default "="\] + [Default "="] - **-o** or **--output** diff --git a/docs/tools/agat_sp_filter_incomplete_gene_coding_models.md b/docs/tools/agat_sp_filter_incomplete_gene_coding_models.md index d82899cd..68e74728 100644 --- a/docs/tools/agat_sp_filter_incomplete_gene_coding_models.md +++ b/docs/tools/agat_sp_filter_incomplete_gene_coding_models.md @@ -1,10 +1,10 @@ -# agat\_sp\_filter\_incomplete\_gene\_coding\_models.pl +# agat_sp_filter_incomplete_gene_coding_models.pl ## DESCRIPTION The script aims to remove incomplete gene models. An incomplete gene coding model is a gene coding with start and/or stop codon missing in its cds. -You can modify the behavior using the skip\_start\_check or skip\_stop\_check options. +You can modify the behavior using the skip_start_check or skip_stop_check options. ## SYNOPSIS @@ -27,17 +27,17 @@ agat_sp_filter_incomplete_gene_coding_models.pl --help - **--ct** or **--table** or **--codon** This option allows specifying the codon table to use. - It expects an integer \[default 1\] + It expects an integer [default 1] -- **--ad** or **--add\_flag** +- **--ad** or **--add_flag** Instead of filter the result into two output files, write only one and add the flag <incomplete> in the gff.(tag = inclomplete, value = 1, 2, 3. 1=start missing; 2=stop missing; 3=both) -- **--skip\_start\_check** or **--sstartc** +- **--skip_start_check** or **--sstartc** Gene model must have a start codon. Activated by default. -- **--skip\_stop\_check** or **--sstopc** +- **--skip_stop_check** or **--sstopc** Gene model must have a stop codon. Activated by default. diff --git a/docs/tools/agat_sp_filter_record_by_coordinates.md b/docs/tools/agat_sp_filter_record_by_coordinates.md index 688ec134..fb7b63b5 100644 --- a/docs/tools/agat_sp_filter_record_by_coordinates.md +++ b/docs/tools/agat_sp_filter_record_by_coordinates.md @@ -1,4 +1,4 @@ -# agat\_sp\_filter\_record\_by\_coordinates.pl +# agat_sp_filter_record_by_coordinates.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_fix_cds_phases.md b/docs/tools/agat_sp_fix_cds_phases.md index 89c81a63..d57c8106 100644 --- a/docs/tools/agat_sp_fix_cds_phases.md +++ b/docs/tools/agat_sp_fix_cds_phases.md @@ -1,4 +1,4 @@ -# agat\_sp\_fix\_cds\_phases.pl +# agat_sp_fix_cds_phases.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_fix_features_locations_duplicated.md b/docs/tools/agat_sp_fix_features_locations_duplicated.md index e9729683..9d1c1af6 100644 --- a/docs/tools/agat_sp_fix_features_locations_duplicated.md +++ b/docs/tools/agat_sp_fix_features_locations_duplicated.md @@ -1,4 +1,4 @@ -# agat\_sp\_fix\_features\_locations\_duplicated.pl +# agat_sp_fix_features_locations_duplicated.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_fix_fusion.md b/docs/tools/agat_sp_fix_fusion.md index 2628dec4..f61f39ba 100644 --- a/docs/tools/agat_sp_fix_fusion.md +++ b/docs/tools/agat_sp_fix_fusion.md @@ -1,4 +1,4 @@ -# agat\_sp\_fix\_fusion.pl +# agat_sp_fix_fusion.pl ## DESCRIPTION @@ -25,7 +25,7 @@ agat_sp_fix_fusion.pl --help - **--ct**, **--codon** or **--table** - Codon table to use. \[default 1\] + Codon table to use. [default 1] - **-t** or **--threshold** diff --git a/docs/tools/agat_sp_fix_longest_ORF.md b/docs/tools/agat_sp_fix_longest_ORF.md index 78e06a28..d04f9144 100644 --- a/docs/tools/agat_sp_fix_longest_ORF.md +++ b/docs/tools/agat_sp_fix_longest_ORF.md @@ -1,4 +1,4 @@ -# agat\_sp\_fix\_longest\_ORF.pl +# agat_sp_fix_longest_ORF.pl ## DESCRIPTION @@ -31,7 +31,7 @@ agat_sp_fix_longest_ORF.pl --help - **--ct**, **--codon** or **--table** - Codon table to use. \[default 1\] + Codon table to use. [default 1] - **-m** or **--model** @@ -50,9 +50,9 @@ agat_sp_fix_longest_ORF.pl --help while we force here the prediction to have a start codon. A ORF wihtout start can be the fact of an incomplete or fragmented ORF: annotation tool didn't predict the start because: - \* the start region is NNNN - \* the start region is XXXX - \* correct nucleotides but prediction tool did not annotate this part (e.g incomplete evidence in evidence-based prediction) + * the start region is NNNN + * the start region is XXXX + * correct nucleotides but prediction tool did not annotate this part (e.g incomplete evidence in evidence-based prediction) Model6 = The ORF is same size but not correct frame (+1 or +2 bp gives a frame shift). diff --git a/docs/tools/agat_sp_fix_overlaping_genes.md b/docs/tools/agat_sp_fix_overlaping_genes.md index 0973262a..d07a7a5d 100644 --- a/docs/tools/agat_sp_fix_overlaping_genes.md +++ b/docs/tools/agat_sp_fix_overlaping_genes.md @@ -1,4 +1,4 @@ -# agat\_sp\_fix\_overlaping\_genes.pl +# agat_sp_fix_overlaping_genes.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_fix_small_exon_from_extremities.md b/docs/tools/agat_sp_fix_small_exon_from_extremities.md index bbd9b91f..a3efbd47 100644 --- a/docs/tools/agat_sp_fix_small_exon_from_extremities.md +++ b/docs/tools/agat_sp_fix_small_exon_from_extremities.md @@ -1,11 +1,11 @@ -# agat\_fix\_small\_exon\_from\_extremities.pl +# agat_fix_small_exon_from_extremities.pl ## DESCRIPTION The script aims to extend the small exons to make them longer. When submitting annotation to ENA they expect exon size of 15 nt minimum. Currently we extend only the exon from extremities, otherwise we risk to break the predicted ORF. -/!\\ When we extend an exon and the CDS has to be extended too (because is was a partial CDS), we exit; +/! When we extend an exon and the CDS has to be extended too (because is was a partial CDS), we exit; ## SYNOPSIS diff --git a/docs/tools/agat_sp_flag_premature_stop_codons.md b/docs/tools/agat_sp_flag_premature_stop_codons.md index e947cfa9..90450e6a 100644 --- a/docs/tools/agat_sp_flag_premature_stop_codons.md +++ b/docs/tools/agat_sp_flag_premature_stop_codons.md @@ -1,4 +1,4 @@ -# agat\_sp\_flag\_premature\_stop\_codons.pl +# agat_sp_flag_premature_stop_codons.pl ## DESCRIPTION @@ -26,7 +26,7 @@ agat_sp_flag_premature_stop_codons.pl --help - **--ct**, **--codon** or **--table** - Codon table to use. \[default 1\] + Codon table to use. [default 1] - **--out**, **--output** or **-o** diff --git a/docs/tools/agat_sp_flag_short_introns.md b/docs/tools/agat_sp_flag_short_introns.md index c38c8183..4f022b68 100644 --- a/docs/tools/agat_sp_flag_short_introns.md +++ b/docs/tools/agat_sp_flag_short_introns.md @@ -1,10 +1,10 @@ -# agat\_sp\_flag\_short\_introns.pl +# agat_sp_flag_short_introns.pl ## DESCRIPTION The script flags the short introns with the attribute <pseudo>. Is is usefull to avoid ERROR when submiting the data to EBI. -(Typical EBI error message: \*\*\*\*\*\*\*\*ERROR: Intron usually expected to be at least 10 nt long. Please check the accuracy) +(Typical EBI error message: ********ERROR: Intron usually expected to be at least 10 nt long. Please check the accuracy) ## SYNOPSIS @@ -19,7 +19,7 @@ agat_sp_flag_short_introns.pl --help Input GTF/GFF file. -- **--intron\_size** or **-i** +- **--intron_size** or **-i** Minimum intron size, default 10. All genes with an intron < of this size will be flagged with the pseudo attribute (the value will be the size of the smallest diff --git a/docs/tools/agat_sp_functional_statistics.md b/docs/tools/agat_sp_functional_statistics.md index 15a9864b..e5c76774 100644 --- a/docs/tools/agat_sp_functional_statistics.md +++ b/docs/tools/agat_sp_functional_statistics.md @@ -1,4 +1,4 @@ -# agat\_sp\_functional\_statistics.pl +# agat_sp_functional_statistics.pl ## DESCRIPTION @@ -24,7 +24,7 @@ agat_sp_functional_statistics.pl --help - **--output** or **-o** - Folder where will be written the results. \[Default output_functional_statistics\] + Folder where will be written the results. [Default output_functional_statistics] - **-c** or **--config** diff --git a/docs/tools/agat_sp_keep_longest_isoform.md b/docs/tools/agat_sp_keep_longest_isoform.md index a35c93aa..47b2c353 100644 --- a/docs/tools/agat_sp_keep_longest_isoform.md +++ b/docs/tools/agat_sp_keep_longest_isoform.md @@ -1,11 +1,11 @@ -# agat\_sp\_keep\_longest\_isoform.pl +# agat_sp_keep_longest_isoform.pl ## DESCRIPTION The script aims to filter isoforms when present. For a locus: -\- when all isoforms have CDS we keep the one with the longest CDS. -\- when some isoforms have CDS some others not, we keep the one with the longest CDS. -\- when none of the isoforms have CDS, we keep the one with the longest concatenated exons. +- when all isoforms have CDS we keep the one with the longest CDS. +- when some isoforms have CDS some others not, we keep the one with the longest CDS. +- when none of the isoforms have CDS, we keep the one with the longest concatenated exons. ## SYNOPSIS diff --git a/docs/tools/agat_sp_kraken_assess_liftover.md b/docs/tools/agat_sp_kraken_assess_liftover.md index 2896978f..60088019 100644 --- a/docs/tools/agat_sp_kraken_assess_liftover.md +++ b/docs/tools/agat_sp_kraken_assess_liftover.md @@ -1,17 +1,17 @@ -# agat\_sp\_kraken\_assess\_lift\_coverage.pl +# agat_sp_kraken_assess_lift_coverage.pl ## DESCRIPTION The script takes as input gtf produced by Kraken (lift-over tool). -It will analyse the kraken\_mapped attributes to calculate the mapped percentage of each mRNA. +It will analyse the kraken_mapped attributes to calculate the mapped percentage of each mRNA. According to a threshold (0 by default), gene with a mapping percentage over that value will be reported. -A plot nammed geneMapped\_plot.pdf is performed to visualize the result. -/!\\ The script handles chimeric files (i.e containg gene part mapped on the template genome and others on the de-novo one) -/!\\/!\\ If the file is complete (containing kraken\_mapped="TRUE" and kraken\_mapped="FALSE" attributes), +A plot nammed geneMapped_plot.pdf is performed to visualize the result. +/! The script handles chimeric files (i.e containg gene part mapped on the template genome and others on the de-novo one) +/!/! If the file is complete (containing kraken_mapped="TRUE" and kraken_mapped="FALSE" attributes), the script calcul the real percentage lentgh that has been mapped. -Else the calcul is only based on feature with kraken\_mapped="TRUE" attributes. +Else the calcul is only based on feature with kraken_mapped="TRUE" attributes. So in this case the result most of time will be 100%. -/!\\/!\\/!\\ We met rare cases where Kraken mapped a feature to several locations of the de-novo genome. +/!/!/! We met rare cases where Kraken mapped a feature to several locations of the de-novo genome. As result we could end up with mapping over > 100%. We report them as 100% mapped in the plot and a warning is raised to allow to check thoses cases. diff --git a/docs/tools/agat_sp_list_short_introns.md b/docs/tools/agat_sp_list_short_introns.md index 06a308b3..981ec10f 100644 --- a/docs/tools/agat_sp_list_short_introns.md +++ b/docs/tools/agat_sp_list_short_introns.md @@ -1,4 +1,4 @@ -# agat\_sp\_list\_short\_introns.pl +# agat_sp_list_short_introns.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_load_function_from_protein_align.md b/docs/tools/agat_sp_load_function_from_protein_align.md index c03479f8..baa11a65 100644 --- a/docs/tools/agat_sp_load_function_from_protein_align.md +++ b/docs/tools/agat_sp_load_function_from_protein_align.md @@ -1,4 +1,4 @@ -# agat\_sp\_load\_function\_from\_protein\_align.pl +# agat_sp_load_function_from_protein_align.pl ## DESCRIPTION @@ -38,7 +38,7 @@ agat_sp_load_function_from_protein_align.pl --help Rule to apply to lift function when a protein map properly. 1) replace => replace or add the product and Name attribute's values. 2) complete => add the product and Name attribute's values only if doesn't exist. - 3) add => add the lfp\_product and lfp\_name attributes with the corresponding values + 3) add => add the lfp_product and lfp_name attributes with the corresponding values - **--value**, **--threshold** or **-t** @@ -51,11 +51,11 @@ agat_sp_load_function_from_protein_align.pl --help - **--pe** Protein existence value. We will take the best overlap score protein according to the PE expected - 1\. Experimental evidence at protein level - 2\. Experimental evidence at transcript level - 3\. Protein inferred from homology - 4\. Protein predicted - 5\. Protein uncertain + 1. Experimental evidence at protein level + 2. Experimental evidence at transcript level + 3. Protein inferred from homology + 4. Protein predicted + 5. Protein uncertain - **--test** diff --git a/docs/tools/agat_sp_manage_IDs.md b/docs/tools/agat_sp_manage_IDs.md index 4ee24152..84bead87 100644 --- a/docs/tools/agat_sp_manage_IDs.md +++ b/docs/tools/agat_sp_manage_IDs.md @@ -1,11 +1,11 @@ -# agat\_sp\_manage\_IDs.pl +# agat_sp_manage_IDs.pl ## DESCRIPTION The script takes a gff3 file as input and will go through all feature to overwrite the value of the ID attribute. -By default the ID is built as follow: primary\_tag(i.e. 3rd column)-Number. -If you provide a specific prefix the ID is built as follow: $opt\_prefix.$letterCode.Number. +By default the ID is built as follow: primary_tag(i.e. 3rd column)-Number. +If you provide a specific prefix the ID is built as follow: $opt_prefix.$letterCode.Number. By default the numbering start at 1, but you can decide to change this value using the --nb option. The $letterCode is the first letter of the feature type (3rd colum). It is uniq for each feature type, i.e. when two feature types start with the same letter, the second one met will have the two first letter as $letterCode (and so one). @@ -30,15 +30,15 @@ agat_sp_manage_IDs.pl --help - **--ensembl** Boolean - For an ID Ensembl like (e.g PREFIXG00000000022). The ID is built as follow: - $opt\_prefix.$letterCode.0\*.Number where the number of 0 is adapted in order to have 11 digits. + $opt_prefix.$letterCode.0*.Number where the number of 0 is adapted in order to have 11 digits. - **--prefix** String - Add a specific prefix to the ID. By defaut if will be the feature type (3rd column). -- **--type\_dependent** +- **--type_dependent** - Boolean - Activate type\_dependent numbering. The number is depedendent of the feature type. + Boolean - Activate type_dependent numbering. The number is depedendent of the feature type. i.e instead of: NbV1Ch01 AUGUSTUS gene 97932 99714 0.06 - . ID=gene1 NbV1Ch01 AUGUSTUS mRNA 97932 99714 0.06 - . ID=mRNA2 diff --git a/docs/tools/agat_sp_manage_UTRs.md b/docs/tools/agat_sp_manage_UTRs.md index 1b0cfd29..3d6e4930 100644 --- a/docs/tools/agat_sp_manage_UTRs.md +++ b/docs/tools/agat_sp_manage_UTRs.md @@ -1,4 +1,4 @@ -# agat\_sp\_manage\_UTRs.pl +# agat_sp_manage_UTRs.pl ## DESCRIPTION @@ -24,11 +24,11 @@ agat_sp_manage_UTRs.pl --help Threshold of exon's number of the UTR. Over or equal to this threshold, the UTR will be discarded. Default value is 5. -- **-3**, **--three** or **--tree\_prime\_utr** +- **-3**, **--three** or **--tree_prime_utr** The threshold of the option <n> will be applied on the 3'UTR. -- **-5**, **--five** or **--five\_prime\_utr** +- **-5**, **--five** or **--five_prime_utr** The threshold of the option <n> will be applied on the 5'UTR. diff --git a/docs/tools/agat_sp_manage_attributes.md b/docs/tools/agat_sp_manage_attributes.md index bc4bf21b..a9286abf 100644 --- a/docs/tools/agat_sp_manage_attributes.md +++ b/docs/tools/agat_sp_manage_attributes.md @@ -1,4 +1,4 @@ -# agat\_sp\_manage\_attributes.pl +# agat_sp_manage_attributes.pl ## DESCRIPTION @@ -32,9 +32,9 @@ agat_sp_manage_attributes.pl --help - **--tag**, **--att** Attributes with the tag specified will be removed from the feature type specified by the option p (primary tag). List of tag must be coma separated. - /!\\\\ You must use "" if name contains spaces. + /! You must use "" if name contains spaces. Instead to remove an attribute, you can replace its Tag by a new Tag using this formulation tagName/newTagName. - To remove all attributes non mandatory (only ID and Parent are mandatory) you can use the option with <all\_attributes> parameter. + To remove all attributes non mandatory (only ID and Parent are mandatory) you can use the option with <all_attributes> parameter. - **--add** diff --git a/docs/tools/agat_sp_manage_functional_annotation.md b/docs/tools/agat_sp_manage_functional_annotation.md index a56ab45f..95e5cbad 100644 --- a/docs/tools/agat_sp_manage_functional_annotation.md +++ b/docs/tools/agat_sp_manage_functional_annotation.md @@ -1,14 +1,14 @@ -# agat\_sp\_manage\_functional\_annotation.pl +# agat_sp_manage_functional_annotation.pl ## DESCRIPTION The script take a gff3 file as input and blast and/or interpro output in order to attach functional annotation to corresponding features within the gff file. -\>The blast against Protein Database (outfmt 6) allows to fill the field/attribute +>The blast against Protein Database (outfmt 6) allows to fill the field/attribute NAME for gene and PRODUCT for mRNA. -\>The Interpro result (.tsv) file allows to fill the DBXREF field/attribute with +>The Interpro result (.tsv) file allows to fill the DBXREF field/attribute with pfam, tigr, interpro, GO, KEGG, etc... terms data. With the <id> option the script will change all the ID field by an Uniq ID @@ -107,7 +107,7 @@ agat_sp_manage_functional_annotation.pl --help String - The fasta file that has been used as DB for the blast. Gene names and products/descriptions will be fished from this file. -- **--be** or **--blast\_evalue** +- **--be** or **--blast_evalue** Float - Maximum e-value to keep the annotation from the blast file. By default 1e-6. @@ -116,11 +116,11 @@ agat_sp_manage_functional_annotation.pl --help Integer - The PE (protein existence) in the uniprot header indicates the type of evidence that supports the existence of the protein. You can decide until which protein existence level you want to consider to lift the finctional information. Default 5. - 1\. Experimental evidence at protein level - 2\. Experimental evidence at transcript level - 3\. Protein inferred from homology - 4\. Protein predicted - 5\. Protein uncertain + 1. Experimental evidence at protein level + 2. Experimental evidence at transcript level + 3. Protein inferred from homology + 4. Protein predicted + 5. Protein uncertain - **-i** or **--interpro** diff --git a/docs/tools/agat_sp_manage_introns.md b/docs/tools/agat_sp_manage_introns.md index 051346f9..d6767b88 100644 --- a/docs/tools/agat_sp_manage_introns.md +++ b/docs/tools/agat_sp_manage_introns.md @@ -1,4 +1,4 @@ -# agat\_sp\_manage\_introns.pl +# agat_sp_manage_introns.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_merge_annotations.md b/docs/tools/agat_sp_merge_annotations.md index c526a063..bbfcc095 100644 --- a/docs/tools/agat_sp_merge_annotations.md +++ b/docs/tools/agat_sp_merge_annotations.md @@ -1,4 +1,4 @@ -# agat\_sp\_merge\_annotations.pl +# agat_sp_merge_annotations.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_move_attributes_within_records.md b/docs/tools/agat_sp_move_attributes_within_records.md index 9d2bf63d..1aab5c34 100644 --- a/docs/tools/agat_sp_move_attributes_within_records.md +++ b/docs/tools/agat_sp_move_attributes_within_records.md @@ -1,4 +1,4 @@ -# agat\_sp\_move\_attributes\_within\_records.pl +# agat_sp_move_attributes_within_records.pl ## DESCRIPTION @@ -19,7 +19,7 @@ agat_sp_move_attributes_within_records.pl --help Input GFF3 file that will be read -- **--feature\_copy** or **--fc** +- **--feature_copy** or **--fc** primary tag (feature type) option to list from which feature we will copy the attributes, case insensitive. You can specified a feature (or a coma separated list) by giving its primary tag / feature type (column 3) value as: cds, Gene, MrNa, etc @@ -28,7 +28,7 @@ agat_sp_move_attributes_within_records.pl --help level3=CDS,exon,UTR,etc By default all level2 feature are used. -- **--feature\_paste** or **--fp** +- **--feature_paste** or **--fp** primary tag (feature type) option to list to which feature we will paste the attributes, case sensitive. You can specified a feature (or a coma separated list) by giving its primary tag / feature type (column 3) value as: cds, Gene, MrNa, etc @@ -41,8 +41,8 @@ agat_sp_move_attributes_within_records.pl --help Attribute that will be copied and pasted. Case sensitive. You can specified an attribute (or a coma separated list) by giving its attribute tag value (column9) as: Ontology, Dbxref, etc - Default: all\_attributes - /!\\ <all\_attributes> is a specific parameter meaning all the attributes will be use. + Default: all_attributes + /! <all_attributes> is a specific parameter meaning all the attributes will be use. - **-o** or **--output** @@ -55,8 +55,8 @@ agat_sp_move_attributes_within_records.pl --help - **-c** or **--config** - String - Input agat config file. By default AGAT takes as input agat\_config.yaml file from the working directory if any, - otherwise it takes the orignal agat\_config.yaml shipped with AGAT. To get the agat\_config.yaml locally type: "agat config --expose". + String - Input agat config file. By default AGAT takes as input agat_config.yaml file from the working directory if any, + otherwise it takes the orignal agat_config.yaml shipped with AGAT. To get the agat_config.yaml locally type: "agat config --expose". The --config option gives you the possibility to use your own AGAT config file (located elsewhere or named differently). - **-h** or **--help** diff --git a/docs/tools/agat_sp_prokka_fix_fragmented_gene_annotations.md b/docs/tools/agat_sp_prokka_fix_fragmented_gene_annotations.md index 04cbd2d4..93fff0b4 100644 --- a/docs/tools/agat_sp_prokka_fix_fragmented_gene_annotations.md +++ b/docs/tools/agat_sp_prokka_fix_fragmented_gene_annotations.md @@ -1,32 +1,32 @@ -# agat\_sp\_prokka\_fragmented\_gene\_annotations.pl +# agat_sp_prokka_fragmented_gene_annotations.pl ## DESCRIPTION The script aims to look at fragmented gene annotations (FRAGS) within prokka annotations. The FRAGS represent two (or more) ORFs that are in close proximity and are annotated -with homology to the same gene. In such cases, Prokka ads an \_n suffix to the gene ID. -For example, a splitted genX can then be found as genX\_1 and genX\_2 in the GFF. +with homology to the same gene. In such cases, Prokka ads an _n suffix to the gene ID. +For example, a splitted genX can then be found as genX_1 and genX_2 in the GFF. See here for a case: https://github.com/tseemann/prokka/issues/502 -\* The script will inform you how many case there is in your annotation. -\* If you think the FRAGS is due to a sequencing error (frameshift due to short indel), -using the --frags parameter will fix the FRAGS if genX\_1 and genX\_2 are not in the same frame. +* The script will inform you how many case there is in your annotation. +* If you think the FRAGS is due to a sequencing error (frameshift due to short indel), +using the --frags parameter will fix the FRAGS if genX_1 and genX_2 are not in the same frame. The gff and the fasta file will be modified. The gene are merged, an insertion of one or two N will be added in between the genes to fix the frameshift. -\* If you think the FRAGS is not due to a sequencing error, use the --pseudo parameter, -the gff will be fix (gene merged) and the agat\_pseudo attribute (the value is the position of the codon stop) +* If you think the FRAGS is not due to a sequencing error, use the --pseudo parameter, +the gff will be fix (gene merged) and the agat_pseudo attribute (the value is the position of the codon stop) will be added to the related features. -\* using --frags and --pseudo is similar to use only --frags, except when no frameshift -is found for a detected FRAGS (both gene are in the same frame), the agat\_pseudo +* using --frags and --pseudo is similar to use only --frags, except when no frameshift +is found for a detected FRAGS (both gene are in the same frame), the agat_pseudo attribute is also added to the related features. How the tool detecte the FRAGS? -\* Search for cases where contiguous genes have the same name (e.g. lpxA\_1 lpxA\_2). -\* If so we look at the size of the protein of each of those genes (lpxA\_1 AA=175 ; lpxA\_2 AA=116), +* Search for cases where contiguous genes have the same name (e.g. lpxA_1 lpxA_2). +* If so we look at the size of the protein of each of those genes (lpxA_1 AA=175 ; lpxA_2 AA=116), and compute the size when merged togeter (devoided of the overlap if any) => here 270 AA -\* Then we look at the size of the protein used to infer the name (lpxA\_1 inferred from Q9PIM1 = 263 AA ; lpxA\_2 inferred from P0A722 = 262 AA ) +* Then we look at the size of the protein used to infer the name (lpxA_1 inferred from Q9PIM1 = 263 AA ; lpxA_2 inferred from P0A722 = 262 AA ) and compute the average length of the reference protein: here 262AA. We add 20% to the length to be sure to include border cases => 282AA. -\* Compare the length of the merged proteins (262 AA) against the reference protein length (282). +* Compare the length of the merged proteins (262 AA) against the reference protein length (282). If the the expected protein length (282 AA) is longer we have a FRAGS. ## SYNOPSIS @@ -56,9 +56,9 @@ agat_sp_prokka_fragmented_gene_annotations.pl --help - **--pseudo** - Merge detected FRAGS and add the agat\_pseudo attribute (value will be the location of the first stop codon met). + Merge detected FRAGS and add the agat_pseudo attribute (value will be the location of the first stop codon met). -- **--hamap\_size** +- **--hamap_size** Some protein function are not infered by Uniprot but by Hamap. In such case the information is retrieved from the web. As hamap provide a family profile, the protein size if a range. @@ -69,9 +69,9 @@ agat_sp_prokka_fragmented_gene_annotations.pl --help - **--ct**, **--codon** or **--table** - Codon table to use. \[default 1\] + Codon table to use. [default 1] -- **--skip\_hamap** +- **--skip_hamap** For test purpose it could be useful to skip hamap, because it requires fetching information through internet. diff --git a/docs/tools/agat_sp_sensitivity_specificity.md b/docs/tools/agat_sp_sensitivity_specificity.md index 9b83a4d3..419d99cf 100644 --- a/docs/tools/agat_sp_sensitivity_specificity.md +++ b/docs/tools/agat_sp_sensitivity_specificity.md @@ -1,4 +1,4 @@ -# agat\_sp\_sensitivity\_specificity.pl +# agat_sp_sensitivity_specificity.pl ## DESCRIPTION diff --git a/docs/tools/agat_sp_separate_by_record_type.md b/docs/tools/agat_sp_separate_by_record_type.md index dc542528..fe3f48c0 100644 --- a/docs/tools/agat_sp_separate_by_record_type.md +++ b/docs/tools/agat_sp_separate_by_record_type.md @@ -1,4 +1,4 @@ -# agat\_sp\_separate\_by\_record\_type.pl +# agat_sp_separate_by_record_type.pl ## DESCRIPTION @@ -25,7 +25,7 @@ agat_sp_separate_by_record_type.pl --help - **-o** or **--output** - Output folder. If no output folder provided, the default name will be <split\_result>. + Output folder. If no output folder provided, the default name will be <split_result>. - **-c** or **--config** diff --git a/docs/tools/agat_sp_split_by_level2_feature.md b/docs/tools/agat_sp_split_by_level2_feature.md index 25c144e9..6a1f7572 100644 --- a/docs/tools/agat_sp_split_by_level2_feature.md +++ b/docs/tools/agat_sp_split_by_level2_feature.md @@ -1,4 +1,4 @@ -# agat\_sp\_split\_by\_level2\_feature.pl +# agat_sp_split_by_level2_feature.pl ## DESCRIPTION @@ -20,7 +20,7 @@ agat_sp_split_by_level2_feature.pl --help - **-o** or **--output** - Output folder. If no output folder provided, the default name will be <split\_result>. + Output folder. If no output folder provided, the default name will be <split_result>. - **-c** or **--config** diff --git a/docs/tools/agat_sp_statistics.md b/docs/tools/agat_sp_statistics.md index af01fe83..7f09c311 100644 --- a/docs/tools/agat_sp_statistics.md +++ b/docs/tools/agat_sp_statistics.md @@ -1,9 +1,9 @@ -# agat\_sp\_statistics.pl +# agat_sp_statistics.pl ## DESCRIPTION The script provides exhaustive statistics of a gft/gff file. -/!\\ If you have isoforms in your file, even if correct, some values calculated +/! If you have isoforms in your file, even if correct, some values calculated might sounds incoherent: e.g. total length mRNA can be superior than the genome size. Because all isoforms length is added... It is why by default we always compute the statistics twice when there are isoforms, once with the diff --git a/docs/tools/agat_sp_to_tabulated.md b/docs/tools/agat_sp_to_tabulated.md index a5eaa0b3..86aa3a34 100644 --- a/docs/tools/agat_sp_to_tabulated.md +++ b/docs/tools/agat_sp_to_tabulated.md @@ -1,4 +1,4 @@ -# agat\_sp\_to\_tabulated.pl +# agat_sp_to_tabulated.pl ## DESCRIPTION @@ -21,10 +21,10 @@ agat_sp_to_tabulated.pl --help - **-c** or **--ct** When the features doesn't have Parent/ID relationships, the parser will try to group - features using a common/shared attribute (i.e. a locus tag.). By default locus\_tag and gene\_id. + features using a common/shared attribute (i.e. a locus tag.). By default locus_tag and gene_id. You can provide another specific common/shared attribute using this option. -- **--ml** or **--merge\_loci** +- **--ml** or **--merge_loci** Merge loci parameter, default deactivated. You turn on the parameter if you want to merge loci into one locus when they overlap. (at CDS level for mRNA, at exon level for other level2 features. Strand has to be the same). Prokaryote can have overlaping loci so it should not use it for prokaryote annotation. diff --git a/docs/tools/agat_sp_webApollo_compliant.md b/docs/tools/agat_sp_webApollo_compliant.md index 0a63ca97..398a994e 100644 --- a/docs/tools/agat_sp_webApollo_compliant.md +++ b/docs/tools/agat_sp_webApollo_compliant.md @@ -1,4 +1,4 @@ -# agat\_sp\_webApollo\_compliant.pl +# agat_sp_webApollo_compliant.pl ## DESCRIPTION diff --git a/docs/tools/agat_sq_add_attributes_from_tsv.md b/docs/tools/agat_sq_add_attributes_from_tsv.md index 616f7927..9a608a60 100644 --- a/docs/tools/agat_sq_add_attributes_from_tsv.md +++ b/docs/tools/agat_sq_add_attributes_from_tsv.md @@ -1,4 +1,4 @@ -# agat\_sq\_add\_attributes\_from\_tsv.pl +# agat_sq_add_attributes_from_tsv.pl ## DESCRIPTION @@ -12,7 +12,7 @@ The other columns will be added as attribute in the GFF/GTF file. The header bec and the value is that defined for the corresponding feature line. (If the tag already exists, we append the value only if the value doesn't already exist). -\--- example --- +--- example --- - input.tsv: ``` @@ -33,7 +33,7 @@ chr1 irgsp gene 1000 2000 . + . ID=gene1;annot_type1=annot_x chr1 irgsp CDS 2983 3268 . + . ID=cds1;annot_type1=annot_y ``` -\--- example2 --- +--- example2 --- - input.tsv: ``` diff --git a/docs/tools/agat_sq_add_hash_tag.md b/docs/tools/agat_sq_add_hash_tag.md index 9f76ba24..a5446071 100644 --- a/docs/tools/agat_sq_add_hash_tag.md +++ b/docs/tools/agat_sq_add_hash_tag.md @@ -1,4 +1,4 @@ -# agat\_sq\_add\_hash\_tag.pl +# agat_sq_add_hash_tag.pl ## DESCRIPTION diff --git a/docs/tools/agat_sq_add_locus_tag.md b/docs/tools/agat_sq_add_locus_tag.md index 261db8c1..ffe7125d 100644 --- a/docs/tools/agat_sq_add_locus_tag.md +++ b/docs/tools/agat_sq_add_locus_tag.md @@ -1,4 +1,4 @@ -# agat\_sq\_add\_locus\_tag.pl +# agat_sq_add_locus_tag.pl ## DESCRIPTION @@ -25,7 +25,7 @@ agat_sq_add_locus_tag.pl --help - **--lo** or **--to** - Locus tag output, by defaut it will be called locus\_tag, but using this option you can specied the name of this attribute. + Locus tag output, by defaut it will be called locus_tag, but using this option you can specied the name of this attribute. - **--li** or **--ti** diff --git a/docs/tools/agat_sq_count_attributes.md b/docs/tools/agat_sq_count_attributes.md index 5685369a..b7843eba 100644 --- a/docs/tools/agat_sq_count_attributes.md +++ b/docs/tools/agat_sq_count_attributes.md @@ -1,4 +1,4 @@ -# agat\_sq\_count\_attributes.pl +# agat_sq_count_attributes.pl # DESCRIPTION diff --git a/docs/tools/agat_sq_filter_feature_from_fasta.md b/docs/tools/agat_sq_filter_feature_from_fasta.md index 7222fc0d..d760eaa3 100644 --- a/docs/tools/agat_sq_filter_feature_from_fasta.md +++ b/docs/tools/agat_sq_filter_feature_from_fasta.md @@ -1,4 +1,4 @@ -# agat\_sq\_filter\_feature\_from\_fasta.pl +# agat_sq_filter_feature_from_fasta.pl ## DESCRIPTION diff --git a/docs/tools/agat_sq_list_attributes.md b/docs/tools/agat_sq_list_attributes.md index 43fd372f..45aa5dd2 100644 --- a/docs/tools/agat_sq_list_attributes.md +++ b/docs/tools/agat_sq_list_attributes.md @@ -1,4 +1,4 @@ -# agat\_sq\_list\_attributes.pl +# agat_sq_list_attributes.pl ## DESCRIPTION diff --git a/docs/tools/agat_sq_manage_IDs.md b/docs/tools/agat_sq_manage_IDs.md index e86a5929..3bd52143 100644 --- a/docs/tools/agat_sq_manage_IDs.md +++ b/docs/tools/agat_sq_manage_IDs.md @@ -1,4 +1,4 @@ -# agat\_sq\_manage\_ID.pl +# agat_sq_manage_ID.pl ## DESCRIPTION diff --git a/docs/tools/agat_sq_manage_attributes.md b/docs/tools/agat_sq_manage_attributes.md index 18b7c2fa..d735df39 100644 --- a/docs/tools/agat_sq_manage_attributes.md +++ b/docs/tools/agat_sq_manage_attributes.md @@ -1,4 +1,4 @@ -# agat\_sp\_manage\_attributes.pl +# agat_sp_manage_attributes.pl ## DESCRIPTION @@ -32,9 +32,9 @@ agat_sq_manage_attributes.pl --help - **--tag**, **--att** Attributes with the tag specified will be removed from the feature type specified by the option p (primary tag). List of tag must be coma separated. - /!\\\\ You must use "" if name contains spaces. + /! You must use "" if name contains spaces. Instead to remove an attribute, you can replace its Tag by a new Tag using this formulation tagName/newTagName. - To remove all attributes non mandatory (only ID and Parent are mandatory) you can use the option with <all\_attributes> parameter. + To remove all attributes non mandatory (only ID and Parent are mandatory) you can use the option with <all_attributes> parameter. - **--add** @@ -59,7 +59,7 @@ agat_sq_manage_attributes.pl --help - **--strategy** - String. \[Default equal\]. Strategy to use when --value parameter is in use. Can be equal or match. + String. [Default equal]. Strategy to use when --value parameter is in use. Can be equal or match. Equal => the attribute value must be identical. Match => the attribute value must match - **-o** , **--output** , **--out** or **--outfile** diff --git a/docs/tools/agat_sq_mask.md b/docs/tools/agat_sq_mask.md index b6b03fbe..6b4a855f 100644 --- a/docs/tools/agat_sq_mask.md +++ b/docs/tools/agat_sq_mask.md @@ -1,4 +1,4 @@ -# agat\_sq\_mask.pl +# agat_sq_mask.pl ## DESCRIPTION diff --git a/docs/tools/agat_sq_remove_redundant_entries.md b/docs/tools/agat_sq_remove_redundant_entries.md index 0b2b95b6..9a16eeb5 100644 --- a/docs/tools/agat_sq_remove_redundant_entries.md +++ b/docs/tools/agat_sq_remove_redundant_entries.md @@ -1,8 +1,8 @@ -# agat\_sq\_remove\_redundant\_entries.pl +# agat_sq_remove_redundant_entries.pl ## DESCRIPTION -The script remove redundant entries: same seq\_id,primary\_tag,start,stop,ID,Parent. +The script remove redundant entries: same seq_id,primary_tag,start,stop,ID,Parent. If ID and Parent attribute is not present, we do no remove the feature. If one of them do not exists we use "" instead. diff --git a/docs/tools/agat_sq_repeats_analyzer.md b/docs/tools/agat_sq_repeats_analyzer.md index d3eacf73..d1f74888 100644 --- a/docs/tools/agat_sq_repeats_analyzer.md +++ b/docs/tools/agat_sq_repeats_analyzer.md @@ -1,9 +1,9 @@ -# agat\_sq\_repeats\_analyzer.pl +# agat_sq_repeats_analyzer.pl ## DESCRIPTION The script allows to generate a tabulated format report of repeats annotated -from a gff file containing repeats (feature type must be match or protein\_match). +from a gff file containing repeats (feature type must be match or protein_match). ## SYNOPSIS diff --git a/docs/tools/agat_sq_reverse_complement.md b/docs/tools/agat_sq_reverse_complement.md index 013df142..181b9f37 100644 --- a/docs/tools/agat_sq_reverse_complement.md +++ b/docs/tools/agat_sq_reverse_complement.md @@ -1,4 +1,4 @@ -# agat\_sq\_reverse\_complement.pl +# agat_sq_reverse_complement.pl ## DESCRIPTION diff --git a/docs/tools/agat_sq_rfam_analyzer.md b/docs/tools/agat_sq_rfam_analyzer.md index ac2a4e02..226de1a2 100644 --- a/docs/tools/agat_sq_rfam_analyzer.md +++ b/docs/tools/agat_sq_rfam_analyzer.md @@ -1,12 +1,12 @@ -# agat\_sq\_rfam\_analyzer.pl +# agat_sq_rfam_analyzer.pl ## DESCRIPTION The script allows to generate a tabulated format report of rfam-id annotated from a gff file -containing rfam results (type of the 3rd column must be ncRNA or nc\_RNA - not case sensitive. And the 9th column must contain the rfam-id attribute). +containing rfam results (type of the 3rd column must be ncRNA or nc_RNA - not case sensitive. And the 9th column must contain the rfam-id attribute). e.g: -ScG6Pog\_82 Rfam ncRNA 737595 737663 20.7 + 0 ID=RF00134\_ScG6Pog\_82\_737595;Name=RF00134\_ScG6Pog\_82\_737595;evalue=0.45;gc-content=0.28;model\_end=1;model\_start=1;rfam-acc=RF00134;rfam-id=snoZ196 -ScG6Pog\_82 Rfam ncRNA 305023 305103 20.8 + 0 ID=RF00227\_ScG6Pog\_82\_305023;Name=RF00227\_ScG6Pog\_82\_305023;evalue=0.35;gc-content=0.31;model\_end=1;model\_start=1;rfam-acc=RF00227;rfam-id=FIE3 +ScG6Pog_82 Rfam ncRNA 737595 737663 20.7 + 0 ID=RF00134_ScG6Pog_82_737595;Name=RF00134_ScG6Pog_82_737595;evalue=0.45;gc-content=0.28;model_end=1;model_start=1;rfam-acc=RF00134;rfam-id=snoZ196 +ScG6Pog_82 Rfam ncRNA 305023 305103 20.8 + 0 ID=RF00227_ScG6Pog_82_305023;Name=RF00227_ScG6Pog_82_305023;evalue=0.35;gc-content=0.31;model_end=1;model_start=1;rfam-acc=RF00227;rfam-id=FIE3 ## SYNOPSIS diff --git a/docs/tools/agat_sq_split.md b/docs/tools/agat_sq_split.md index e6b0e94c..4be22cb2 100644 --- a/docs/tools/agat_sq_split.md +++ b/docs/tools/agat_sq_split.md @@ -1,4 +1,4 @@ -# agat\_sq\_split.pl +# agat_sq_split.pl ## DESCRIPTION @@ -21,7 +21,7 @@ agat_sq_split.pl --help - **-i** or **--interval** Integer. Number of group of feature to include in each file. 1000 by default. -- **--ft** or **--feature\_type** +- **--ft** or **--feature_type** The top feature of the feature group. By default "gene". - **-o** or **--output** diff --git a/docs/tools/agat_sq_stat_basic.md b/docs/tools/agat_sq_stat_basic.md index 30b5a5af..29741157 100644 --- a/docs/tools/agat_sq_stat_basic.md +++ b/docs/tools/agat_sq_stat_basic.md @@ -1,4 +1,4 @@ -# agat\_sq\_stat\_basic.pl +# agat_sq_stat_basic.pl ## DESCRIPTION diff --git a/docs/troubleshooting.md b/docs/troubleshooting.md index 954c12ec..ea1c787c 100644 --- a/docs/troubleshooting.md +++ b/docs/troubleshooting.md @@ -10,12 +10,13 @@ agat levels --expose Then open the file with your favorite text editor. -Now choose which section you want to modify: -* `level1` (e.g. gene, match, region): +Now choose which section you want to modify: + + * `level1` (e.g. gene, match, region): For features that do not have parent -* `level2` (e.g. mrna, match_part, trna): + * `level2` (e.g. mrna, match_part, trna): For features that have one parent and the parent is a level 1 feature. -* `level3` (e.g. exon, intron, cds): + * `level3` (e.g. exon, intron, cds): For features that have one parent (the parent has also a parent) and no children For features that are discontinuous (i.e. when a single feature exists over multiple genomic locations like cds, utr) you must also fil the `spread` section. @@ -24,10 +25,11 @@ Then add the feature type information by adding a paired-value like this: ``` "bigRNA":"gene", ``` -Where `bigRNA`is the feature type and `gene` the parent feature type expected. -/!\\ For level1 feature type the second value can be: - * topfeature: feature does not expect children, and will be written first in the sequence - * standalone: feature does not expect children +Where `bigRNA`is the feature type and `gene` the parent feature type expected. +/!\\ For `level1` feature type the second value can be: + + * `topfeature`: feature does not expect children, and will be written first in the sequence + * `standalone`: feature does not expect children * other values do not have any meaning but a value is required, write whatever you want. ## AGAT throws features out, because child features are not provided diff --git a/docs/why_agat.md b/docs/why_agat.md index 592610e2..41ac9199 100644 --- a/docs/why_agat.md +++ b/docs/why_agat.md @@ -1,5 +1,4 @@ -Why AGAT? -============= +# Why AGAT? Providing support in genome annotation within [NBIS](https://nbis.se) the GTF/GFF format is the main format I handle. I receive from customers file in GTF/GFF format coming from a broad range of sources. Even sometimes files from mixed sources (concatenated in the same file), or manually edited. The problem is that often those files do not follow the official specifications or even if they do, they are not even be sure to be compatible we the inputs expected by the tools. diff --git a/mkdocs.yml b/mkdocs.yml new file mode 100644 index 00000000..1f96fa8d --- /dev/null +++ b/mkdocs.yml @@ -0,0 +1,197 @@ +# Project information +site_name: AGAT +site_author: Jacques Dainat +site_url: 'https://github.com/NBISweden/AGAT' +site_description: AGAT +site_dir: public # When you build your site, all of the files are written to the directory assigned to the site_dir configuration option (defaults to "site") +docs_dir: docs # The directory that holds the documentation source files (the MkDocs documentation) + +# Repository +repo_name: 'AGAT' +repo_url: 'https://github.com/NBISweden/AGAT' +edit_uri: edit/main/docs/ # Allow to replace edit/master/docs use by default + +# Configuration +theme: + name: material + logo: img/NBIS.png # logo top left page + search_index_only: true + include_search_page: true + features: + - announce.dismiss + - content.action.edit + - content.action.view + - content.code.annotate + - content.code.copy + # - content.tabs.link + - content.tooltips + - header.autohide + # - navigation.expand + - navigation.footer + - navigation.indexes + # - navigation.instant + # - navigation.prune + # - navigation.sections # collapse subsections + - navigation.tabs + # - navigation.tabs.sticky + - navigation.top + - navigation.tracking + - search.highlight + - search.share + - search.suggest + - toc.follow + - toc.integrate # remove table of content on the right side + palette: + - scheme: default + primary: indigo + accent: indigo + toggle: + icon: material/brightness-7 + name: Switch to dark mode + - scheme: slate + primary: indigo + accent: indigo + toggle: + icon: material/brightness-4 + name: Switch to light mode + +# Extensions +markdown_extensions: + - admonition + - pymdownx.details + - pymdownx.superfences + - pymdownx.tabbed + - pymdownx.snippets: + base_path: docs + - attr_list + - tables + - toc: + permalink: '#' + +# Plugins +plugins: + - search: + separator: '[\s\-,:!=\[\]()"`/]+|\.(?!\d)|&[lg]t;|(?!\b)(?=[A-Z][a-z])' + - minify: + minify_html: true + - macros + +# Customization +extra: +# homepage: # Page displayed when clicking the logo + history_buttons: false + # --- set whole scope variables --- + contact: jacques.dainat@gmail.com + institute: NBIS + unit: NBIS + color_table_header: "#333a99" + +# page tree +nav: + - AGAT Home: + - index.md + - install.md + - agat_for_you.md + - agat_how_does_it_work.md + - how_to_cite.md + - why_agat.md + - The GTF/GFF formats: + - gxf.md + - AGAT vs other tools: + - topological-sorting-of-gff-features.md + - gff_to_bed.md + - gff_to_gtf.md + - AGAT Tools: + - Slurp (sp prefix): + - tools/agat_convert_sp_gxf2gxf.md + - Convert: + - tools/agat_convert_bed2gff.md + - tools/agat_convert_embl2gff.md + - tools/agat_convert_genscan2gff.md + - tools/agat_convert_mfannot2gff.md + - tools/agat_convert_minimap2_bam2gff.md + - tools/agat_convert_sp_gff2bed.md + - tools/agat_convert_sp_gff2gtf.md + - tools/agat_convert_sp_gff2tsv.md + - tools/agat_convert_sp_gff2zff.md + - tools/agat_sp_to_tabulated.md + - tools/agat_sp_alignment_output_style.md + - Add: + - tools/agat_sp_add_intergenic_regions.md + - tools/agat_sp_add_introns.md + - tools/agat_sp_add_splice_sites.md + - tools/agat_sp_add_start_and_stop.md + - Aggregate: + - tools/agat_sp_complement_annotations.md + - tools/agat_sp_merge_annotations.md + - Compare: + - tools/agat_sp_compare_two_BUSCOs.md + - tools/agat_sp_compare_two_annotations.md + - tools/agat_sp_sensitivity_specificity.md + - Extract: + - tools/agat_sp_extract_attributes.md + - tools/agat_sp_extract_sequences.md + - Filter: + - tools/agat_sp_filter_by_ORF_size.md + - tools/agat_sp_filter_by_locus_distance.md + - tools/agat_sp_filter_by_mrnaBlastValue.md + - tools/agat_sp_filter_feature_by_attribute_presence.md + - tools/agat_sp_filter_feature_by_attribute_value.md + - tools/agat_sp_filter_feature_from_keep_list.md + - tools/agat_sp_filter_feature_from_kill_list.md + - tools/agat_sp_filter_gene_by_intron_numbers.md + - tools/agat_sp_filter_gene_by_length.md + - tools/agat_sp_filter_incomplete_gene_coding_models.md + - tools/agat_sp_filter_record_by_coordinates.md + - tools/agat_sp_keep_longest_isoform.md + - Flag: + - tools/agat_sp_flag_premature_stop_codons.md + - tools/agat_sp_flag_short_introns.md + - Fix: + - tools/agat_sp_fix_cds_phases.md + - tools/agat_sp_fix_features_locations_duplicated.md + - tools/agat_sp_fix_fusion.md + - tools/agat_sp_fix_longest_ORF.md + - tools/agat_sp_fix_overlaping_genes.md + - tools/agat_sp_fix_small_exon_from_extremities.md + - Manage: + - tools/agat_sp_manage_IDs.md + - tools/agat_sp_manage_UTRs.md + - tools/agat_sp_manage_attributes.md + - tools/agat_sp_manage_functional_annotation.md + - tools/agat_sp_manage_introns.md + - Statistics: + - tools/agat_sp_statistics.md + - tools/agat_sp_functional_statistics.md + - Other: + - tools/agat_sp_kraken_assess_liftover.md + - tools/agat_sp_list_short_introns.md + - tools/agat_sp_load_function_from_protein_align.md + - tools/agat_sp_move_attributes_within_records.md + - tools/agat_sp_prokka_fix_fragmented_gene_annotations.md + - tools/agat_sp_separate_by_record_type.md + - tools/agat_sp_split_by_level2_feature.md + - tools/agat_sp_clipN_seqExtremities_and_fixCoordinates.md + - tools/agat_sp_ensembl_output_style.md + - tools/agat_sp_Prokka_inferNameFromAttributes.md + - tools/agat_sp_webApollo_compliant.md + - Sequential (sq prefix): + - tools/agat_sq_add_attributes_from_tsv.md + - tools/agat_sq_add_hash_tag.md + - tools/agat_sq_add_locus_tag.md + - tools/agat_sq_filter_feature_from_fasta.md + - tools/agat_sq_list_attributes.md + - tools/agat_sq_manage_IDs.md + - tools/agat_sq_manage_attributes.md + - tools/agat_sq_mask.md + - tools/agat_sq_remove_redundant_entries.md + - tools/agat_sq_repeats_analyzer.md + - tools/agat_sq_reverse_complement.md + - tools/agat_sq_rfam_analyzer.md + - tools/agat_sq_split.md + - tools/agat_sq_stat_basic.md + - How to: + - howto/how_to_extract_sequences.md + - howto/how_to_aggregate_annotation.md + - Troubleshooting: + - troubleshooting.md \ No newline at end of file