annotate plasmidtrakr.xml @ 3:6c88e978d6ad draft

planemo upload commit 60769393d9dfffc10194637c7bb275835ee6092d
author galaxytrakr
date Wed, 29 Apr 2026 17:13:17 +0000
parents fe9ff3859d68
children 210866cf0df9
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
fe9ff3859d68 planemo upload commit 3e1ba2085173abf4b891e9d715399bbbece65bba
galaxytrakr
parents: 0
diff changeset
1 <tool id="plasmidtrakr" name="Predict Isolate Source" version="0.1.1">
0
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
2 <description>Predicts isolate source from plasmid profiles using a trained machine learning model</description>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
3
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
4 <requirements>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
5 <requirement type="package" version="1.5.3">pandas</requirement>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
6 <requirement type="package" version="1.2.2">scikit-learn</requirement>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
7 </requirements>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
8
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
9 <!-- FIXED: Added $ before __tool_directory__ -->
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
10 <version_command>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
11 python '$__tool_directory__/predict_source.py' --version
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
12 </version_command>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
13
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
14 <!-- FIXED: Added $ before __tool_directory__ -->
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
15 <command detect_errors="exit_code"><![CDATA[
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
16 python '$__tool_directory__/predict_source.py'
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
17 -i '$mash_input'
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
18 -b '$model_selection.path'
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
19 -t '$threshold'
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
20 -o '$prediction_output'
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
21 ]]></command>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
22
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
23 <inputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
24 <param name="mash_input" type="data" format="tabular" label="Mash Screen Output" help="The tabular output file from the Galaxy 'mash screen' tool."/>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
25
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
26 <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
27 <options from_data_table="plasmidtrakr_models">
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
28 <validator type="no_options" message="No prediction models are configured. Please contact your Galaxy administrator." />
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
29 </options>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
30 </param>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
31
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
32 <param name="threshold" type="float" value="0.95" label="Mash Identity Threshold" help="Filter plasmid hits below this identity. Must match the threshold used for model training."/>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
33 </inputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
34
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
35 <outputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
36 <data name="prediction_output" format="tabular" label="Prediction for ${on_string} using ${model_selection.name}" />
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
37 </outputs>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
38
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
39 <!-- FIXED: Cleaned up Markdown formatting in the help block (removed backslashes) -->
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
40 <help><![CDATA[
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
41 **What it does**
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
42
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
43 This tool takes the list of plasmid hits from the Galaxy **mash screen** tool and uses a pre-trained **machine learning model** to predict the original source of the isolate.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
44
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
45 **Workflow for Genome Assemblies**
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
46
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
47 1. Go to the **mash screen** tool in Galaxy.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
48 2. In the **"Single or Paired-end reads"** dropdown, select **"Single"**.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
49 3. For the **"Select fastq dataset"** input, provide your **genome assembly FASTA file**.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
50 4. Run the `mash screen` job against the appropriate plasmid database.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
51 5. Use the tabular output from that job as the input for **this prediction tool**.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
52 6. Select the desired prediction model from the dropdown menu.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
53 7. Execute to get your prediction.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
54
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
55 **Output**
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
56
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
57 A tabular file containing the isolate ID, the predicted source, and a confidence score.
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
58 ]]></help>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
59
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
60 <citations>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
61 <citation type="bibtex">
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
62 @misc{strain_2026_plasmidtrakr,
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
63 author = {Strain, Errol},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
64 title = {PlasmidTrakr: A tool for predicting isolate source from plasmid profiles},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
65 year = {2026},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
66 publisher = {GitHub},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
67 journal = {GitHub repository},
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
68 howpublished = {\url{https://github.com/estrain/plasmidtrakr}}
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
69 }
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
70 </citation>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
71 </citations>
f25631df0e9f planemo upload commit 25e4c800a5358b8615dac18ea5e908e31c534020
galaxytrakr
parents:
diff changeset
72 </tool>