annotate plasmidtrakr.xml @ 15:58006290e654 draft

planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
author galaxytrakr
date Thu, 30 Apr 2026 19:20:50 +0000
parents 9a84b8511fc2
children 706b2bbc64ed
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
15
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
1 <tool id="plasmidtrakr" name="PlasmidTrakr" version="0.2.1">
14
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[
15
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
11 ## 1. Create a sanitized variable for the input name (removes spaces/special chars for the shell)
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
12 #set $input_name = $assembly_input.element_identifier.replace(" ", "_")
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
13
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
14 ## 2. Symlink the Mash database
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
15 ln -s '$mash_database.fields.path' queries.msh &&
15
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
16
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
17 ## 3. Run Mash Screen
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
18 ## We redirect the output to a file named after the original input
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
19 mash screen
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
20 -w
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
21 -i $threshold
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
22 queries.msh
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
23 '$assembly_input'
15
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
24 > '${input_name}.tabular'
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
25 &&
15
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
26
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
27 ## 4. Run PlasmidTrakr prediction
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
28 ## We pass the newly named file to the python script
9
c78b7a3494f9 planemo upload commit 117de6ae3eb1896dcb0044059b268136fc1b97ab
galaxytrakr
parents: 8
diff changeset
29 python $__tool_directory__/predict_source.py
15
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
30 -i '${input_name}.tabular'
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
31 -b '$model_selection.fields.path'
10
cbc924a737db planemo upload commit 17291695ca68c131f51a65367eb52e9b4c405532
galaxytrakr
parents: 9
diff changeset
32 -t $threshold
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
33 -o '$prediction_output'
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
34 ]]></command>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
35
15
58006290e654 planemo upload commit 07e8ec488fa1fb8323b5e90bfc9842aa7337b950
galaxytrakr
parents: 14
diff changeset
36
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
37 <inputs>
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
38 <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
39
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
40 <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
41 <options from_data_table="mash_sketches">
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
42 <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
43 </options>
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
44 </param>
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
45
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
46 <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
47 <options from_data_table="plasmidtrakr_models">
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
48 <validator type="no_options" message="No prediction models are configured. Please contact your Galaxy administrator." />
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
49 </options>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
50 </param>
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
51
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
52 <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
53 </inputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
54
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
55 <outputs>
8
17b409c9320d planemo upload commit 8fe81cc450c2773ca4183b693341de07ff0337e9
galaxytrakr
parents: 7
diff changeset
56 <data name="prediction_output" format="tabular" label="Prediction for ${on_string}" />
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
57 </outputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
58
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
59 <help><![CDATA[
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
60 **What it does**
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
61
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
62 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
63
14
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
64 **Workflow**
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
65 1. Provide your **genome assembly (FASTA)** or raw reads.
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
66 2. Select your **Mash database** from the server's configured list.
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
67 3. Select the desired prediction model.
9a84b8511fc2 planemo upload commit 6681312523efb1b57807ea244c63f9cbb02c574e
galaxytrakr
parents: 13
diff changeset
68 4. Execute to screen and predict in one step.
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
69
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
70 **Output**
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
71 A tabular file containing the isolate ID, the predicted source, and a confidence score.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
72 ]]></help>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
73
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
74 <citations>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
75 <citation type="bibtex">
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
76 @misc{strain_2026_plasmidtrakr,
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
77 author = {Strain, Errol},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
78 title = {PlasmidTrakr: A tool for predicting isolate source from plasmid profiles},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
79 year = {2026},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
80 publisher = {GitHub},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
81 journal = {GitHub repository},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
82 howpublished = {\url{https://github.com/estrain/plasmidtrakr}}
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
83 }
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
84 </citation>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
85 </citations>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
86 </tool>