Mercurial > repos > ufz > checkv_end_to_end
diff end_to_end.xml @ 0:ace74c46b80f draft
planemo upload for repository https://github.com/Helmholtz-UFZ/ufz-galaxy-tools/blob/main/tools/checkv/ commit 625d1e8699c69e5ee3caef0cc5c883a9d9e6ac91
| author | ufz |
|---|---|
| date | Mon, 16 Sep 2024 09:54:01 +0000 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/end_to_end.xml Mon Sep 16 09:54:01 2024 +0000 @@ -0,0 +1,186 @@ +<tool id="checkv_end_to_end" name="CheckV end to end" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01" license="MIT"> + <description></description> + <macros> + <token name="@TOOL_VERSION@">1.0.3</token> + <token name="@VERSION_SUFFIX@">0</token> + </macros> + <xrefs> + <xref type="bio.tools">checkv</xref> + </xrefs> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">checkv</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ + checkv end_to_end + '$input' + output + -d '$reference.fields.path' + --remove_tmp + -t "\${GALAXY_SLOTS:-1}" + ]]></command> + <inputs> + <param name="input" type="data" format="fasta,fasta.gz,fasta.bz2" label="Input nucleotide sequences in FASTA format"/> + <param name="reference" type="select" label="CheckV reference data"> + <options from_data_table="checkv"> + <validator type="no_options" message="No reference data available. Contact your Galaxy admin"/> + </options> + </param> + <param name="optional_outputs" type="select" optional="true" multiple="true" label="Optional outputs"> + <option value="completeness">Overview of how completeness was estimated</option> + <option value="contamination"></option> + </param> + </inputs> + <outputs> + <data name="quality_summary" format="tabular" from_work_dir="output/quality_summary.tsv" label="${tool.name} on ${on_string}: Quality summary"/> + <data name="completeness" format="tabular" from_work_dir="output/completeness.tsv" label="${tool.name} on ${on_string}: Completeness"> + <filter>optional_outputs and "completeness" in optional_outputs</filter> + </data> + <data name="contamination" format="tabular" from_work_dir="output/contamination.tsv" label="${tool.name} on ${on_string}: Contamination"> + <filter>optional_outputs and "contamination" in optional_outputs</filter> + </data> + <data name="complete_genomes" format="tabular" from_work_dir="output/complete_genomes.tsv" label="${tool.name} on ${on_string}: Complete Genomes"/> + <data name="proviruses" format="fasta" from_work_dir="output/proviruses.fna" label="${tool.name} on ${on_string}: Proviruses"/> + <data name="viruses" format="fasta" from_work_dir="output/viruses.fna" label="${tool.name} on ${on_string}: Viruses"/> + </outputs> + <tests> + <!-- <test expect_num_outputs="4"> + <param name="input" value="test_sequences.fna"/> + <param name="reference" value="1.5"/> + <output name="quality_summary"> + <assert_contents> + <has_n_columns n="14"/> + <has_n_lines n="41"/> + </assert_contents> + </output> + <output name="complete_genomes"> + <assert_contents> + <has_n_columns n="11"/> + <has_n_lines n="6"/> + </assert_contents> + </output> + <output name="viruses"> + <assert_contents> + <has_line_matching expression="^>.*" n="39"/> + </assert_contents> + </output> + <output name="proviruses"> + <assert_contents> + <has_line_matching expression="^>.*" n="1"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="6"> + <param name="input" value="test_sequences.fna"/> + <param name="reference" value="1.5"/> + <param name="optional_outputs" value="completeness,contamination"/> + <output name="quality_summary"> + <assert_contents> + <has_n_columns n="14"/> + <has_n_lines n="41"/> + </assert_contents> + </output> + <output name="completeness"> + <assert_contents> + <has_n_columns n="15"/> + <has_n_lines n="41"/> + </assert_contents> + </output> + <output name="contamination"> + <assert_contents> + <has_n_columns n="14"/> + <has_n_lines n="41"/> + </assert_contents> + </output> + <output name="complete_genomes"> + <assert_contents> + <has_n_columns n="11"/> + <has_n_lines n="6"/> + </assert_contents> + </output> + <output name="viruses"> + <assert_contents> + <has_line_matching expression="^>.*" n="39"/> + </assert_contents> + </output> + <output name="proviruses"> + <assert_contents> + <has_line_matching expression="^>.*" n="1"/> + </assert_contents> + </output> + </test> --> + </tests> + <help><![CDATA[ + +.. class:: infomark + +**What it does** + +CheckV is a fully automated command-line pipeline for assessing the quality of single-contig viral genomes, including identification of host contamination for integrated proviruses, estimating completeness for genome fragments, and identification of closed genomes. + +There are 4 steps: + +1. Remove host contamination on proviruses + - Genes are first annotated as viral or microbial based on comparison to a custom database of HMMs + - CheckV scans over the contig (5' to 3') comparing gene annotations and GC content between a pair of adjacent gene windows + - This information is used to compute a score at each intergenic position and identify host-virus breakpoints + - Works best for contigs that are mostly viral + +2. Estimate genome completeness + + - Proteins are first compared to the CheckV genome database using AAI (average amino acid identity) + - After identifying the top hits, completeness is computed as a ratio between the contig length (or viral region length for proviruses) and the length of matched reference + - A confidence level is reported based on the strength of the alignment + - Generally, high- and medium-confidence estimates are quite accurate + - Less frequently, your viral genome may not have a close match to the CheckV database; in these cases CheckV estimates the completeness based on the viral HMMs identified on the contig + - Based on the HMMs found, CheckV returns the estimated range for genome completeness (e.g. 35% to 60% completeness), which represents the 90% confidence interval based on the distribution of lengths of reference genomes with the same viral HMMs + +3.: Predict closed genomes + + - Direct terminal repeats (DTRs) + - Repeated sequence of >20-bp at start/end of contig + - Most trusted signature in our experience + - May indicate circular genome or linear genome replicated from a circular template (i.e. concatamer) + - Proviruses + - Viral region with predicted host boundaries at 5' and 3' ends (see panel A) + - Note: CheckV will not detect proviruses if host regions have already been removed (e.g. using VIBRANT or VirSorter) + - Inverted terminal repeats (ITRs) + - Repeated sequence of >20-bp at start/end of contig (3' repeat is inverted) + - Least trusted signature + - For all the methods above, CheckV also checks whether the contig is approximately the correct sequence length based on estimated completeness; this is important because terminal repeats can represent artifacts of metagenomic assembly + +4. Summarize quality. + + - Based on the results of 1-3, CheckV generates a report file and assigns query contigs to one of five quality tiers (consistent with and expand upon the MIUViG quality tiers): + + - Complete + - High-quality (>90% completeness) + - Medium-quality (50-90% completeness) + - Low-quality (<50% completeness) + - Undetermined quality + + +Usage +..... + + +**Input** + +- Viral contigs in fasta (or gz, bz2 compressed fasta). +- CheckV reference data + +**Output** + +- Quality Summary: Tabular file showing integrated results from the three main modules and should be the main output referred to. +- Complete genomes: Tabular overview of putative complete genomes identified. +- Viruses: Virus sequences +- Proviruses: Provirus sequences + +Optional outputs: + +- Completeness: detailed overview of how completeness was estimated +- Contamination: detailed overview of how contamination was estimated + ]]></help> + <citations> + <citation type="doi">10.1038/s41587-020-00774-7</citation> + </citations> +</tool> \ No newline at end of file