annotate Marea/marea_cluster.xml @ 83:79a0d52a8e3d draft

Uploaded
author bimib
date Mon, 07 Jun 2021 14:11:43 +0000
parents 3f144565551f
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
42
b3f9e13bf15f Uploaded
bimib
parents: 41
diff changeset
1 <tool id="MaREA_cluester" name="Cluster Analysis" version="1.1.2">
29
9fcb0e8d6d47 Uploaded
bimib
parents: 28
diff changeset
2 <description></description>
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
3 <macros>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
4 <import>marea_macros.xml</import>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
5 </macros>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
6 <requirements>
83
79a0d52a8e3d Uploaded
bimib
parents: 76
diff changeset
7 <requirement type="package" version="0.25.3">pandas</requirement>
79a0d52a8e3d Uploaded
bimib
parents: 76
diff changeset
8 <requirement type="package" version="1.6.3">scipy</requirement>
79a0d52a8e3d Uploaded
bimib
parents: 76
diff changeset
9 <requirement type="package" version="0.24.2">scikit-learn</requirement>
79a0d52a8e3d Uploaded
bimib
parents: 76
diff changeset
10 <requirement type="package" version="3.4.2">matplotlib</requirement>
79a0d52a8e3d Uploaded
bimib
parents: 76
diff changeset
11 <requirement type="package" version="1.20.3">numpy</requirement>
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
12 </requirements>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
13 <command detect_errors="exit_code">
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
14 <![CDATA[
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
15 python $__tool_directory__/marea_cluster.py
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
16 --input $input
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
17 --tool_dir $__tool_directory__
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
18 --out_log $log
28
e6831924df01 small fixes (elbow plot and output managment)
bimib
parents: 27
diff changeset
19 --best_cluster $best_cluster
24
69ed2562e81e Uploaded
bimib
parents: 18
diff changeset
20 --cluster_type ${data.clust_type}
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
21 #if $data.clust_type == 'kmeans':
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
22 --k_min ${data.k_min}
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
23 --k_max ${data.k_max}
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
24 --elbow ${data.elbow}
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
25 --silhouette ${data.silhouette}
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
26 #end if
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
27 #if $data.clust_type == 'dbscan':
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
28 #if $data.dbscan_advanced.advanced == 'true'
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
29 --eps ${data.dbscan_advanced.eps}
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
30 --min_samples ${data.dbscan_advanced.min_samples}
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
31 #end if
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
32 #end if
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
33 #if $data.clust_type == 'hierarchy':
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
34 --k_min ${data.k_min}
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
35 --k_max ${data.k_max}
34
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
36 --silhouette ${data.silhouette}
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
37 #end if
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
38 ]]>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
39 </command>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
40 <inputs>
31
944e15aa970a Uploaded
bimib
parents: 29
diff changeset
41 <param name="input" argument="--input" type="data" format="tabular, csv, tsv" label="Input dataset" />
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
42
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
43 <conditional name="data">
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
44 <param name="clust_type" argument="--cluster_type" type="select" label="Choose clustering type:">
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
45 <option value="kmeans" selected="true">KMeans</option>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
46 <option value="dbscan">DBSCAN</option>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
47 <option value="hierarchy">Agglomerative Hierarchical</option>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
48 </param>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
49 <when value="kmeans">
31
944e15aa970a Uploaded
bimib
parents: 29
diff changeset
50 <param name="k_min" argument="--k_min" type="integer" min="2" max="20" value="2" label="Min number of clusters (k) to be tested" />
944e15aa970a Uploaded
bimib
parents: 29
diff changeset
51 <param name="k_max" argument="--k_max" type="integer" min="2" max="20" value="3" label="Max number of clusters (k) to be tested" />
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
52 <param name="elbow" argument="--elbow" type="boolean" value="true" label="Draw the elbow plot from k-min to k-max"/>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
53 <param name="silhouette" argument="--silhouette" type="boolean" value="true" label="Draw the Silhouette plot from k-min to k-max"/>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
54 </when>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
55 <when value="dbscan">
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
56 <conditional name="dbscan_advanced">
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
57 <param name="advanced" type="boolean" value="false" label="Want to use custom params for DBSCAN? (if not optimal values will be used)">
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
58 <option value="true">Yes</option>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
59 <option value="false">No</option>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
60 </param>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
61 <when value="false"></when>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
62 <when value="true">
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
63 <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" />
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
64 <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)"/>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
65
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
66 </when>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
67 </conditional>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
68 </when>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
69 <when value="hierarchy">
34
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
70 <param name="k_min" argument="--k_min" type="integer" min="2" max="20" value="2" label="Min number of clusters (k) to be tested" />
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
71 <param name="k_max" argument="--k_max" type="integer" min="3" max="20" value="3" label="Max number of clusters (k) to be tested" />
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
72 <param name="silhouette" argument="--silhouette" type="boolean" value="true" label="Draw the Silhouette plot from k-min to k-max"/>
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
73 </when>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
74 </conditional>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
75 </inputs>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
76
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
77 <outputs>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
78 <data format="txt" name="log" label="${tool.name} - Log" />
33
abf0bfe01c78 Uploaded
bimib
parents: 31
diff changeset
79 <data format="tabular" name="best_cluster" label="${tool.name} - best cluster assignment" />
28
e6831924df01 small fixes (elbow plot and output managment)
bimib
parents: 27
diff changeset
80 <collection name="results" type="list" label="${tool.name} - Plots and results">
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
81 <discover_datasets pattern="__name_and_ext__" directory="clustering"/>
33
abf0bfe01c78 Uploaded
bimib
parents: 31
diff changeset
82 <filter>data['clust_type'] == "kmeans" or data['clust_type'] == "hierarchy"</filter>
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
83 </collection>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
84 </outputs>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
85 <help>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
86 <![CDATA[
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
87
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
88 What it does
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
89 -------------
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
90
34
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
91 The tool performs cluster analysis of any dataset, according to most used algorithms: K-means, agglomerative
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
92 clustering and DBSCAN (Density Based Spatial Clustering of Applications with Noise).
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
93
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
94 Accepted files are:
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
95 - Tabular files in which rows indicate different variables and columns different observations. The first row reports the observations’ labels.
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
96
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
97
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
98 Example of input dataset:
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
99 -------------------------
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
100
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
101 +----------+----------+----------+
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
102 |TCGAA62670|TCGAA62671|TCGAA62672|
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
103 +==========+==========+==========+
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
104 | 0.523167 | 0.371355 | 0.925661 |
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
105 +----------+----------+----------+
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
106 | 0.568765 | 0.765567 | 0.456789 |
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
107 +----------+----------+----------+
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
108 | 0.876545 | 0.768933 | 0.987654 |
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
109 +----------+----------+----------+
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
110 | 0.456788 | 0.876543 | 0.876542 |
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
111 +----------+----------+----------+
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
112 | 0.876543 | 0.786543 | 0.897654 |
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
113 +----------+----------+----------+
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
114
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
115 .
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
116
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
117
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
118 Options:
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
119 --------
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
120
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
121 The following clustering types can be chosen:
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
122 - K-means. This option requires the number of clusters (k) to be set. Different values of k can be tested.
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
123 - Agglomerative clustering. Different values of k can be set, to cut the resulting dendrogram.
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
124 - DBSCAN. The DBSCAN method chooses the number of clusters based on parameters that define when a region is to be considered dense. Custom parameters may be used, namely the maximum distance between two samples for one to be considered as in the neighborhood of the other and the number of samples in a neighborhood for a point to be considered as a core point.
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
125
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
126 The tool generates:
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
127 - a tab-separated file: reporting the affiliation of each observation to a cluster. In case different numbers of clusters have been tested, the best cluster assignment is reported according to maximum average silhouette score. If desired, the elbow plot is generated, as well as silhouette plot for each k.
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
128 - a list of items, including: 1) the cluster assignment for each tested number of clusters 2) the dendrogram in case of agglomerative clustering 3) elbow and silhouete plots in case of k-means clustering.
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
129 - a log file (.txt).
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
130
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
131
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
132 .. class:: infomark
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
133
70
c22ba0547370 update links and pubblications.
bimib
parents: 42
diff changeset
134 **TIP**: This tool has been conceived to cluster gene expression data, by using the RAS scores computed by `Ras tool`_.
34
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
135
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
136 .. class:: infomark
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
137
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
138 **TIP**: If your data is not TAB delimited, use `Convert delimiters to TAB`_.
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
139
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
140 @REFERENCE@
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
141
70
c22ba0547370 update links and pubblications.
bimib
parents: 42
diff changeset
142 .. _Ras tool: http://bimib.disco.unimib.it:5555/?tool_id=toolshed.g2.bx.psu.edu%2Frepos%2Fbimib%2Fmarea%2FMaREA+RAS+Generator%2F1.0.6&version=1.0.6&__identifer=auulv6gbp76
c22ba0547370 update links and pubblications.
bimib
parents: 42
diff changeset
143 .. _Convert delimiters to TAB: http://bimib.disco.unimib.it:5555/?tool_id=Convert+characters1&version=1.0.0&__identifer=76g7trea4j6
34
1a97d1537623 Lot of bug fixes
bimib
parents: 33
diff changeset
144
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
145 ]]>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
146 </help>
76
3f144565551f Uploaded
bimib
parents: 75
diff changeset
147 <expand macro="citations" />
16
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
148 </tool>
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
149
c71ac0bb12de Uploaded
bimib
parents: 8
diff changeset
150