Mercurial > repos > galaxytrakr > plasmidtrakr

annotate plasmidtrakr.xml @ 14:9a84b8511fc2 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
author galaxytrakr
date Thu, 30 Apr 2026 13:04:42 +0000
parents 6eaad34862cb
children 58006290e654
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
1 <tool id="plasmidtrakr" name="PlasmidTrakr" version="0.2.0">
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
2 <description>Screens assemblies against a Mash database and predicts isolate source using a trained machine learning model</description>
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
3
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
4 <requirements>
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
5 <requirement type="package" version="2.3">mash</requirement>
13
6eaad34862cb planemo upload commit 74ae4c98abbbea693de70e76434089d1d58ff87a
galaxytrakr
parents: 12
diff changeset
6 <requirement type="package" version="2.3.3">pandas</requirement>
6eaad34862cb planemo upload commit 74ae4c98abbbea693de70e76434089d1d58ff87a
galaxytrakr
parents: 12
diff changeset
7 <requirement type="package" version="1.6.1">scikit-learn</requirement>
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
8 </requirements>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
9
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
10 <command detect_errors="exit_code"><![CDATA[
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
11 ## 1. Symlink the Mash database from the tool data table
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
12 ln -s '$mash_database.fields.path' queries.msh &&
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
13
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
14 ## 2. Run Mash Screen internally
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
15 mash screen
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
16 -w
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
17 -i $threshold
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
18 queries.msh
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
19 '$assembly_input'
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
20 > mash_results.tabular
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
21 &&
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
22
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
23 ## 3. Run PlasmidTrakr prediction
9
c78b7a3494f9 planemo upload commit 117de6ae3eb1896dcb0044059b268136fc1b97ab
galaxytrakr
parents: 8
diff changeset
24 python $__tool_directory__/predict_source.py
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
25 -i mash_results.tabular
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
26 -b '$model_selection.fields.path'
10
cbc924a737db planemo upload commit 17291695ca68c131f51a65367eb52e9b4c405532
galaxytrakr
parents: 9
diff changeset
27 -t $threshold
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
28 -o '$prediction_output'
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
29 ]]></command>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
30
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
31 <inputs>
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
32 <param name="assembly_input" type="data" format="fasta,fasta.gz,fastq,fastq.gz" label="Genome Assembly / Reads" help="The FASTA/FASTQ file containing the isolate sequence."/>
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
33
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
34 <param name="mash_database" type="select" label="Select Mash Database" help="Choose the pre-computed Mash sketch database to screen against.">
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
35 <options from_data_table="mash_sketches">
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
36 <validator type="no_options" message="No Mash databases are configured. Please contact your Galaxy administrator." />
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
37 </options>
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
38 </param>
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
39
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
40 <param name="model_selection" type="select" label="Select Prediction Model" help="Choose which trained model to use for prediction.">
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
41 <options from_data_table="plasmidtrakr_models">
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
42 <validator type="no_options" message="No prediction models are configured. Please contact your Galaxy administrator." />
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
43 </options>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
44 </param>
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
45
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
46 <param name="threshold" type="float" value="0.95" min="0.0" max="1.0" label="Mash Identity Threshold" help="Filter plasmid hits below this identity. Must match the threshold used for model training."/>
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
47 </inputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
48
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
49 <outputs>
8
17b409c9320d planemo upload commit 8fe81cc450c2773ca4183b693341de07ff0337e9
galaxytrakr
parents: 7
diff changeset
50 <data name="prediction_output" format="tabular" label="Prediction for ${on_string}" />
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
51 </outputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
52
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
53 <help><![CDATA[
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
54 **What it does**
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
55
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
56 This tool performs a complete workflow in a single step: it screens a genome assembly or read set against a built-in plasmid database using **mash screen**, and then feeds those plasmid hits into a pre-trained **machine learning model** to predict the original source of the isolate.
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
57
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
58 **Workflow**
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
59 1. Provide your **genome assembly (FASTA)** or raw reads.
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
60 2. Select your **Mash database** from the server's configured list.
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
61 3. Select the desired prediction model.
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
62 4. Execute to screen and predict in one step.
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
63
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
64 **Output**
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
65 A tabular file containing the isolate ID, the predicted source, and a confidence score.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
66 ]]></help>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
67
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
68 <citations>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
69 <citation type="bibtex">
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
70 @misc{strain_2026_plasmidtrakr,
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
71 author = {Strain, Errol},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
72 title = {PlasmidTrakr: A tool for predicting isolate source from plasmid profiles},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
73 year = {2026},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
74 publisher = {GitHub},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
75 journal = {GitHub repository},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
76 howpublished = {\url{https://github.com/estrain/plasmidtrakr}}
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
77 }
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
78 </citation>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
79 </citations>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
80 </tool>