Mercurial > repos > fubar > egapx_runner

annotate egapx_runner.xml @ 3:9b1c2fb3b218 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ncbi/egapx commit 69fafcdd687884c990c7f4027aa2982df66626e6
author fubar
date Sun, 04 Aug 2024 00:52:17 +0000
parents a3b158471bd3
children 6592ae57bb8b
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
1 <tool name="egapx_runner" id="egapx_runner" version="6.0.1" profile="22.05">
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
2 <!--Source in git at: https://github.com/fubar2/galaxy_tf_overlay-->
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
3 <!--Created by toolfactory@galaxy.org at 03/08/2024 10:40:32 using the Galaxy Tool Factory.-->
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
4 <description>Runs egapx</description>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
5 <requirements>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
6 <requirement version="3.12.3" type="package">python</requirement>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
7 <requirement version="24.04.4-0" type="package">nextflow</requirement>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
8 <requirement version="6.0.1" type="package">pyyaml</requirement>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
9 </requirements>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
10 <version_command><![CDATA[echo "6.0.1"]]></version_command>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
11 <command><![CDATA[mkdir -p ./egapx_config &&
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
12 #set econfigfile = $econfig + '.config'
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
13 cp '$__tool_directory__/ui/assets/config/executor/$econfigfile' ./egapx_config/ &&
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
14 python '$__tool_directory__/ui/egapx.py' '$yamlconfig' -e '$econfig' -o 'egapx_out']]></command>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
15 <inputs>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
16 <param name="yamlconfig" type="data" optional="false" label="egapx configuration yaml file to execute" help="" format="yaml,txt" multiple="false"/>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
17 <param name="econfig" type="select" label="Configuration" help="">
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
18 <option value="docker_minimal">docker minimal only works for the minimal dust mite sample using 6GB and 4 cores</option>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
19 <option value="singularity">singularity requires at least 128GB ram and 32 cores. 256GB and 64 cores recommendd</option>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
20 <option value="docker">docker requires at least 128GB ram and 32 cores. 256GB and 64 cores recommend</option>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
21 </param>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
22 </inputs>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
23 <outputs>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
24 <collection name="egapx_out" type="list" label="Outputs from egapx">
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
25 <discover_datasets pattern="__name_and_ext__" directory="egapx_out" visible="false"/>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
26 </collection>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
27 </outputs>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
28
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
29
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
30 <tests>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
31 <test>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
32 <output_collection name="egapx_out" count="8"/>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
33 <param name="yamlconfig" value="yamlconfig_sample"/>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
34 <param name="econfig" value="docker_minimal"/>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
35 </test>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
36 </tests>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
37
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
38
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
39
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
40 <help><![CDATA[
2
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
41 Galaxy tool wrapping the Eukaryotic Genome Annotation Pipeline (EGAPx)
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
42 =================================================================================================
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
43
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
44 **A very simple and crude way to run the EGAPx workflows inside Galaxy**
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
45
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
46 EGAPx requires huge resources to run with useful data. *128GB and 32 cores* are the minimum requirement; *256GB and 64 cores* are recommended.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
47
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
48 There is a special test minimal example that can be run in 6GB with 4 cores.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
49
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
50 In this implementation, the user can supply a yaml configuration file as initial proof of concept.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
51
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
52 Does not use computational resources as efficiently as converting the NF workflow components into Galaxy tools, but it is very simple to maintain until EGAPx becomes stable. It will also enable measurement of the actual loss of efficiency from the crude wrapping method.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
53
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
54
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
55 Sample yaml configurations
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
56 ===========================
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
57
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
58 YAML sample configurations can be uploaded into your Galaxy history from the `EGAPx github repository <https://github.com/ncbi/egapx/tree/main/examples/>`_.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
59 The simplest possible example is shown below - can be cut/paste into a history dataset in the upload tool.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
60
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
61
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
62 *./examples/input_D_farinae_small.yaml* is included in the examples linked above. RNA-seq data is provided as URI to the reads FASTA files.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
63 These FASTA files are a sampling of the reads from the complete SRA read files to expedite testing.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
64
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
65 ::
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
66
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
67 genome: https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/020/809/275/GCF_020809275.1_ASM2080927v1/GCF_020809275.1_ASM2080927v1_genomic.fna.gz
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
68 taxid: 6954
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
69 reads:
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
70 - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/data/Dermatophagoides_farinae_small/SRR8506572.1
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
71 - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/data/Dermatophagoides_farinae_small/SRR8506572.2
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
72 - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/data/Dermatophagoides_farinae_small/SRR9005248.1
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
73 - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/data/Dermatophagoides_farinae_small/SRR9005248.2
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
74
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
75
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
76
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
77 Purpose
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
78 ========
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
79
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
80 **This is not intended for production**
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
81
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
82 Just a proof of concept.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
83 It is possibly too inefficient to be useful although it may turn out not to be a problem if run on a dedicated workstation.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
84 At least the efficiency can now be more easily estimated.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
85
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
86 This tool is not recommended for public deployment because of the resource demands.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
87
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
88 EGAPx Overview
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
89 ===============
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
90
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
91 .. image:: $PATH_TO_IMAGES/Pipeline_sm_ncRNA_CAGE_80pct.png
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
92
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
93 **Warning:**
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
94 The current version is an alpha release with limited features and organism scope to collect initial feedback on execution. Outputs are not yet complete and not intended for production use. Please open a GitHub [Issue](https://github.com/ncbi/egapx/issues) if you encounter any problems with EGAPx. You can also write to cgr@nlm.nih.gov to give us your feedback or if you have any questions.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
95
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
96 EGAPx is the publicly accessible version of the updated NCBI [Eukaryotic Genome Annotation Pipeline](https://www.ncbi.nlm.nih.gov/genome/annotation_euk/process/).
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
97
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
98 EGAPx takes an assembly fasta file, a taxid of the organism, and RNA-seq data. Based on the taxid, EGAPx will pick protein sets and HMM models. The pipeline runs `miniprot` to align protein sequences, and `STAR` to align RNA-seq to the assembly. Protein alignments and RNA-seq read alignments are then passed to `Gnomon` for gene prediction. In the first step of `Gnomon`, the short alignments are chained together into putative gene models. In the second step, these predictions are further supplemented by _ab-initio_ predictions based on HMM models. The final annotation for the input assembly is produced as a `gff` file.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
99
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
100 **Security Notice:**
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
101
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
102 EGAPx has dependencies in and outside of its execution path that include several thousand files from the [NCBI C++ toolkit](https://www.ncbi.nlm.nih.gov/toolkit), and more than a million total lines of code. Static Application Security Testing has shown a small number of verified buffer overrun security vulnerabilities. Users should consult with their organizational security team on risk and if there is concern, consider mitigating options like running via VM or cloud instance.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
103
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
104
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
105 *To specify an array of NCBI SRA datasets in yaml*
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
106
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
107 ::
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
108
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
109 reads:
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
110 - SRR8506572
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
111 - SRR9005248
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
112
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
113
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
114 *To specify an SRA entrez query*
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
115
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
116 ::
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
117
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
118 reads: 'txid6954[Organism] AND biomol_transcript[properties] NOT SRS024887[Accession] AND (SRR8506572[Accession] OR SRR9005248[Accession] )'
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
119
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
120
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
121 **Note:** Both the above examples will have more RNA-seq data than the `input_D_farinae_small.yaml` example. To make sure the entrez query does not produce a large number of SRA runs, please run it first at the [NCBI SRA page](https://www.ncbi.nlm.nih.gov/sra). If there are too many SRA runs, then select a few of them and list it in the input yaml.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
122
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
123 Output
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
124 =======
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
125
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
126 EGAPx output will appear as a collection in the user history. The main annotation file is called *accept.gff*.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
127
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
128 ::
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
129
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
130 accept.gff
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
131 annot_builder_output
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
132 nextflow.log
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
133 run.report.html
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
134 run.timeline.html
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
135 run.trace.txt
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
136 run_params.yaml
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
137
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
138
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
139 The *nextflow.log* is the log file that captures all the process information and their work directories. ``run_params.yaml`` has all the parameters that were used in the EGAPx run. More information about the process time and resources can be found in the other run* files.
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
140
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
141 ## Intermediate files
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
142
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
143 In the log, each line denotes the process that completed in the workflow. The first column (_e.g._ `[96/621c4b]`) is the subdirectory where the intermediate output files and logs are found for the process in the same line, _i.e._, `egapx:miniprot:run_miniprot`. To see the intermediate files for that process, you can go to the work directory path that you had supplied and traverse to the subdirectory `96/621c4b`:
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
144
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
145 ::
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
146
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
147 $ aws s3 ls s3://temp_datapath/D_farinae/96/
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
148 PRE 06834b76c8d7ceb8c97d2ccf75cda4/
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
149 PRE 621c4ba4e6e87a4d869c696fe50034/
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
150 $ aws s3 ls s3://temp_datapath/D_farinae/96/621c4ba4e6e87a4d869c696fe50034/
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
151 PRE output/
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
152 2024-03-27 11:19:18 0
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
153 2024-03-27 11:19:28 6 .command.begin
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
154 2024-03-27 11:20:24 762 .command.err
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
155 2024-03-27 11:20:26 762 .command.log
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
156 2024-03-27 11:20:23 0 .command.out
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
157 2024-03-27 11:19:18 13103 .command.run
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
158 2024-03-27 11:19:18 129 .command.sh
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
159 2024-03-27 11:20:24 276 .command.trace
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
160 2024-03-27 11:20:25 1 .exitcode
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
161 $ aws s3 ls s3://temp_datapath/D_farinae/96/621c4ba4e6e87a4d869c696fe50034/output/
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
162 2024-03-27 11:20:24 17127134 aligns.paf
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
163
a3b158471bd3 planemo upload for repository https://github.com/ncbi/egapx commit 98875ef7eda9323fc9991970103954e9097d9e73
fubar
parents: 1
diff changeset
164
1
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
165 ]]></help>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
166 <citations>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
167 <citation type="doi">10.1093/bioinformatics/bts573</citation>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
168 </citations>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
169 </tool>
c8e1543546f8 planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4-dirty
fubar
parents:
diff changeset
170