Mercurial > repos > bimib > marea

comparison Marea/marea_cluster.xml @ 16:c71ac0bb12de draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bimib
date Tue, 01 Oct 2019 06:05:13 -0400
parents 68a5f2db55b9
children 640f303d0cec
comparison
equal deleted inserted replaced
15:d0e7f14b773f 16:c71ac0bb12de
1 <tool id="MaREA_cluester" name="MaREA cluster analysis" version="1.0.0"> 1 <tool id="MaREA_cluester" name="MaREA cluster analysis" version="1.0.1">
2 <description>of Reaction Activity Scores</description> 2 <description>of Reaction Activity Scores - 1.0.1</description>
3 <macros> 3 <macros>
4 <import>marea_macros.xml</import> 4 <import>marea_macros.xml</import>
5 </macros> 5 </macros>
6 <requirements> 6 <requirements>
7 <requirement type="package" version="0.23.0">pandas</requirement> 7 <requirement type="package" version="0.23.0">pandas</requirement>
8 <requirement type="package" version="1.1.0">scipy</requirement> 8 <requirement type="package" version="1.1.0">scipy</requirement>
9 <requirement type="package" version="0.10.1">cobra</requirement> 9 <requirement type="package" version="0.10.1">cobra</requirement>
10 <requirement type="package" version="0.19.1">scikit-learn</requirement> 10 <requirement type="package" version="0.21.3">scikit-learn</requirement>
11 <requirement type="package" version="2.2.2">matplotlib</requirement> 11 <requirement type="package" version="2.2.2">matplotlib</requirement>
12 <requirement type="package" version="1.17">numpy</requirement>
12 </requirements> 13 </requirements>
13 <command detect_errors="exit_code"> 14 <command detect_errors="exit_code">
14 <![CDATA[ 15 <![CDATA[
15 python $__tool_directory__/marea_cluster.py 16 python $__tool_directory__/marea_cluster.py
16 --rules_selector $cond_rule.rules_selector 17 --input $input
17 #if $cond_rule.rules_selector == 'Custom':
18 --custom ${cond_rule.Custom_rules}
19 #end if
20 --cond_hier $cond_hier.hier
21 #if $cond_hier.hier == 'yes':
22 --linkage ${cond_hier.linkage}
23 --dendro $dendrogram
24 #end if
25 --k_max $k_max
26 --k_min $k_min
27 --data $input
28 --name $name
29 --none $None
30 --tool_dir $__tool_directory__ 18 --tool_dir $__tool_directory__
31 --out_log $log 19 --out_log $log
32 --elbow $elbow 20 #if $data.clust_type == 'kmeans':
21 --k_min ${data.k_min}
22 --k_max ${data.k_max}
23 --elbow ${data.elbow}
24 --silhouette ${data.silhouette}
25 #end if
26 #if $data.clust_type == 'dbscan':
27 #if $data.dbscan_advanced.advanced == 'true'
28 --eps ${data.dbscan_advanced.eps}
29 --min_samples ${data.dbscan_advanced.min_samples}
30 #end if
31 #end if
32 #if $data.clust_type == 'hierarchy':
33 --k_min ${data.k_min}
34 --k_max ${data.k_max}
35 #end if
33 ]]> 36 ]]>
34 </command> 37 </command>
35 <inputs> 38 <inputs>
36 <conditional name="cond_rule"> 39 <param name="input" argument="--input" type="data" format="tabular, csv, tsv" label="RNAseq of all samples" />
37 <expand macro="options"/> 40
38 <when value="Custom"> 41 <conditional name="data">
39 <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules" /> 42 <param name="clust_type" argument="--cluster_type" type="select" label="Choose clustering type:">
40 </when> 43 <option value="kmeans" selected="true">KMeans</option>
41 <when value="HMRcore"> 44 <option value="dbscan">DBSCAN</option>
42 </when> 45 <option value="hierarchy">Agglomerative Hierarchical</option>
43 <when value="Recon"> 46 </param>
44 </when> 47 <when value="kmeans">
45 </conditional> 48 <param name="k_min" argument="--k_min" type="integer" min="2" max="99" value="3" label="Min number of clusters (k) to be tested" />
46 <param name="input" argument="--data" type="data" format="tabular, csv, tsv" label="RNAseq of all samples" /> 49 <param name="k_max" argument="--k_max" type="integer" min="3" max="99" value="5" label="Max number of clusters (k) to be tested" />
47 <param name="name" argument="--name" type="text" label="Output name prefix" value="dataset" /> 50 <param name="elbow" argument="--elbow" type="boolean" value="true" label="Draw the elbow plot from k-min to k-max"/>
48 <param name="k_min" argument="--k_min" type="integer" size="20" value="3" min="2" max="30" label="Min number of clusters (k) to be tested (k-means)"/> 51 <param name="silhouette" argument="--silhouette" type="boolean" value="true" label="Draw the Silhouette plot from k-min to k-max"/>
49 <param name="k_max" argument="--k_max" type="integer" size="20" value="3" min="2" max="30" label="Max number of clusters (k) to be tested (k-means)"/> 52 </when>
50 <param name="None" argument="--none" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" help="If NO is selected, (A and NaN) is solved as (NaN)" /> 53 <when value="dbscan">
51 <conditional name="cond_hier"> 54 <conditional name="dbscan_advanced">
52 <param name="hier" argument="--cond_hier" type="select" label="Produce dendrogram (hierarchical clustering):"> 55 <param name="advanced" type="boolean" value="false" label="Want to use custom params for DBSCAN? (if not optimal values will be used)">
53 <option value="no" selected="true">no</option> 56 <option value="true">Yes</option>
54 <option value="yes">yes</option> 57 <option value="false">No</option>
55 </param> 58 </param>
56 <when value="yes"> 59 <when value="false"></when>
57 <param name="linkage" argument="--linkage" type="select" label="Linkage type:"> 60 <when value="true">
58 <option value="single" selected="true">Single: minimum distance between all observations of two sets</option> 61 <param name="eps" argument="--eps" type="float" value="0.5" label="Epsilon - The maximum distance between two samples for one to be considered as in the neighborhood of the other" />
59 <option value="complete">Complete: maximum distance between all observations of two sets</option> 62 <param name="min_samples" argument="min_samples" type="integer" value="5" label="Min samples - The number of samples in a neighborhood for a point to be considered as a core point (this includes the point itself)"/>
60 <option value="average">Average: average distance between all observations of two sets</option> 63
61 </param> 64 </when>
62 </when> 65 </conditional>
63 <when value="no"> 66 </when>
64 </when> 67 <when value="hierarchy">
65 </conditional> 68 <param name="k_min" argument="--k_min" type="integer" min="2" max="99" value="3" label="Min number of clusters (k) to be tested" />
69 <param name="k_max" argument="--k_max" type="integer" min="3" max="99" value="5" label="Max number of clusters (k) to be tested" />
70 </when>
71 </conditional>
66 </inputs> 72 </inputs>
67 73
68 <outputs> 74 <outputs>
69 <data format="txt" name="log" label="Log" /> 75 <data format="txt" name="log" label="${tool.name} - Log" />
70 <data format="pdf" name="dendrogram" label="$name dendrogram"> 76 <collection name="results" type="list" label="${tool.name} - Results">
71 <filter>cond_hier['hier'] == 'yes'</filter> 77 <discover_datasets pattern="__name_and_ext__" directory="clustering"/>
72 </data>
73 <data format="pdf" name="elbow" label="$name elbow evaluation method" />
74 <collection name="cluster_out" type="list" label="Clusters $k_min - $k_max">
75 <discover_datasets pattern="__name_and_ext__" directory="cluster_out" />
76 </collection> 78 </collection>
77 </outputs> 79 </outputs>
78 <tests>
79 <test>
80 <param name="k_min" value="4"/>
81 <output name="log" file="log.txt"/>
82 </test>
83 </tests>
84 <help> 80 <help>
85 <![CDATA[ 81 <![CDATA[
86 82
87 What it does 83 What it does
88 ------------- 84 -------------
89
90 This tool performs cluster analysis of RNA-seq dataset(s) based of Graudenzi et al."`MaREA`_: Metabolic feature extraction, enrichment and visualization of RNAseq data" bioRxiv (2018): 248724.
91
92 Accepted files are:
93 1) For "Recon 2.2 rules" or "HMRcore rules" options: RNA-seq dataset. The user can specify a label of output prefix (as e.g. "K=3 *dataset*" and "K=4 *MyDataset*");
94 2) For "Custom rules" option: custom rules dataset, custom map (.svg) and RNA-seq dataset. The user can specify a label of output prefix (as e.g. "K=3 *dataset*" and "K=4 *MyDataset*").
95
96 Optional files:
97 - custom GPR (Gene-Protein-Reaction) rules. Two accepted formats:
98
99 * (Cobra Toolbox and CobraPy compliant) xml of metabolic model;
100 * .csv file specifyig for each reaction ID (column 1) the corresponding GPR rule (column 2).
101 - custom svg map. Graphical elements must have the same IDs of reactions. See HmrCore svg map for an example.
102
103 The tool generates:
104 1) Clusters n1 - n2 (n1 and n2 refer to min and max number of clusters): class-files (as many files as the chosen different number of clusters k to be tested) specifying the class/condition each sample belongs to;
105 2) Log: a log file (.txt);
106 3) *dataset* elbow evaluation method: diagram (.pdf) of elbow evaluation method;
107 4) *dataset* dendrogram (optional): dendrogram (.pdf) if the user chooses to produce a dendrogram (hierachical clustering).
108
109 RNA-seq datasets format: tab-separated text files, reporting the expression level (e.g., TPM, RPKM, ...) of each gene (row) for a given sample (column). Header: sample ID.
110
111
112 Example input
113 -------------
114
115 **RNA-seq dataset**:
116
117 @DATASET_EXEMPLE1@
118
119 **Custom Rules Dataset**:
120
121 @CUSTOM_RULES_EXEMPLE@
122
123 **Custom Map**:
124
125 *see the generated HMRcore .svg map for example*
126
127
128
129 .. class:: infomark
130
131 **TIP**: If your data is not TAB delimited, use `Convert delimiters to TAB`_.
132
133 .. class:: warningmark
134
135 If dendrogram it's too populated, each path and label can be not clear.
136
137 @REFERENCE@
138
139 .. _MaREA: https://www.biorxiv.org/content/early/2018/01/16/248724
140 .. _Convert delimiters to TAB: https://usegalaxy.org/?tool_id=Convert+characters1&version=1.0.0&__identifer=6t22teyofhj
141 85
142 86
143 ]]> 87 ]]>
144 </help> 88 </help>
145 <expand macro="citations" /> 89 <expand macro="citations" />