Mercurial > repos > ebi-gxa > scanpy_integrate_harmony
comparison scanpy-integrate-harmony.xml @ 0:8b3a52fbb482 draft
"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 62f47287c7e8449c59a1f1f454852ddc669b1b1e-dirty"
author | ebi-gxa |
---|---|
date | Mon, 07 Sep 2020 13:10:56 +0000 |
parents | |
children | f1298838e93b |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:8b3a52fbb482 |
---|---|
1 <?xml version="1.0" encoding="utf-8"?> | |
2 <tool id="scanpy_integrate_harmony" name="Scanpy Harmony" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@"> | |
3 <description>adjust principal components for variables that might introduce batch effect</description> | |
4 <macros> | |
5 <import>scanpy_macros2.xml</import> | |
6 </macros> | |
7 <expand macro="requirements"/> | |
8 <command detect_errors="exit_code"><![CDATA[ | |
9 #if $batch_key | |
10 ln -s '${input_obj_file}' input.h5 && | |
11 PYTHONIOENCODING=utf-8 scanpy-integrate harmony | |
12 --batch-key '${batch_key}' | |
13 #if $basis | |
14 --basis '${basis}' | |
15 #end if | |
16 --adjusted-basis '${adjusted_basis}' | |
17 #if not $settings.default | |
18 #if $settings.theta | |
19 --theta '${settings.theta}' | |
20 #end if | |
21 #if $settings.lambda | |
22 --lambda '${settings.lambda}' | |
23 #end if | |
24 #if $settings.sigma | |
25 --sigma '${settings.sigma}' | |
26 #end if | |
27 #if $settings.nclust | |
28 --nclust '${settings.nclust}' | |
29 #end if | |
30 #if $settings.tau | |
31 --tau '${settings.tau}' | |
32 #end if | |
33 #if $settings.block_size | |
34 --block-size '${settings.block_size}' | |
35 #end if | |
36 #if $settings.max_iter_cluster | |
37 --max-iter-cluster '${settings.max_iter_cluster}' | |
38 #end if | |
39 #if $settings.max_iter_harmony | |
40 --max-iter-harmony '${settings.max_iter_harmony}' | |
41 #end if | |
42 #if $settings.epsilon_cluster | |
43 --epsilon-cluster '${settings.epsilon_cluster}' | |
44 #end if | |
45 #if $settings.epsilon_harmony | |
46 --epsilon-harmony '${settings.epsilon_harmony}' | |
47 #end if | |
48 #if $settings.random_state | |
49 --random-state '${settings.random_state}' | |
50 #end if | |
51 #end if | |
52 @INPUT_OPTS@ | |
53 @OUTPUT_OPTS@ | |
54 #else | |
55 echo "No batch variables passed, simply passing original input as output unchanged."; | |
56 cp '${input_obj_file}' '${output_h5}' | |
57 #end if | |
58 ]]></command> | |
59 | |
60 <inputs> | |
61 <expand macro="input_object_params"/> | |
62 <expand macro="output_object_params"/> | |
63 <param name="batch_key" type="text" argument="--batch-key" label="The name of the column in adata.obs that differentiates among experiments/batches."> | |
64 <sanitizer> | |
65 <valid initial="string.printable"/> | |
66 </sanitizer> | |
67 </param> | |
68 <param name="basis" argument="--basis" type="text" value='X_pca' label="The name of the field in adata.obsm where the PCA table is stored. Defaults to 'X_pca', which is the default for sc.tl.pca()."> | |
69 <sanitizer> | |
70 <valid initial="string.printable"/> | |
71 </sanitizer> | |
72 </param> | |
73 <param name="adjusted_basis" argument="--adjusted-basis" type="text" value='X_pca_harmony' label="he name of the field in adata.obsm where the adjusted PCA table will be stored after running this function."> | |
74 <sanitizer> | |
75 <valid initial="string.printable"/> | |
76 </sanitizer> | |
77 </param> | |
78 <conditional name="settings"> | |
79 <param name="default" type="boolean" checked="true" label="Use programme defaults"/> | |
80 <when value="true"/> | |
81 <when value="false"> | |
82 <param name="theta" argument="--theta" type="float" value="2.0" | |
83 label="Diversity clustering penalty parameter" help="theta=0 does not encourage any diversity. Larger values of theta result in more diverse clusters." /> | |
84 <param name="lambda" argument="--lambda" type="float" min="0" value="1.0" | |
85 label="Ridge regression penalty parameter" help="Lambda must be strictly positive. Smaller values result in more aggressive correction." /> | |
86 <param name="sigma" argument="--sigma" type="float" value="0.1" | |
87 label="Ridge regression penalty parameter" help="Width of soft kmeans clusters. Sigma scales the distance from a cell to cluster centroids. Larger values of sigma result in cells assigned to more clusters. Smaller values of sigma make soft kmeans cluster approach hard clustering." /> | |
88 <param name="nclust" argument="--nclust" type="integer" value="" optional="true" | |
89 label="Number of clusters in model." help="nclust=1 equivalent to simple linear regression." /> | |
90 <param name="tau" argument="--tau" type="integer" value="0" | |
91 label="Protection against overclustering small datasets with large ones." help="'tau is the expected number of cells per cluster." /> | |
92 <param name="block_size" argument="--block-size" type="float" value="0.05" | |
93 label="What proportion of cells to update during clustering" min="0" max="1" help="Between 0 to 1, default 0.05. Larger values may be faster but less accurate." /> | |
94 <param name="max_iter_cluster" argument="--max-iter-cluster" type="integer" value="20" | |
95 label="Maximum number of rounds to run clustering at each round of Harmony" /> | |
96 <param name="max_iter_harmony" argument="--max-iter-harmony" type="integer" value="10" | |
97 label="Maximum number of rounds to run Harmony. One round of Harmony involves one clustering and one correction step." /> | |
98 <param name="epsilon_cluster" argument="--epsilon-cluster" type="float" value="0.00001" | |
99 label="Convergence tolerance for clustering round of Harmony" help="Set to -Inf to never stop early." /> | |
100 <param name="epsilon_harmony" argument="--epsilon-harmony" type="float" value="0.00001" | |
101 label="Convergence tolerance for Harmony." help="Set to -Inf to never stop early." /> | |
102 <param name="random_state" argument="--random-state" type="integer" value="0" | |
103 label="Seed for random number generator." /> | |
104 </when> | |
105 </conditional> | |
106 </inputs> | |
107 | |
108 <outputs> | |
109 <expand macro="output_data_obj" description="Batch-corrected for ${batch_key}"/> | |
110 </outputs> | |
111 | |
112 <tests> | |
113 <test> | |
114 <param name="input_obj_file" value="find_cluster.h5"/> | |
115 <param name="input_format" value="anndata"/> | |
116 <param name="output_format" value="anndata"/> | |
117 <param name="batch_key" value="louvain"/> | |
118 <output name="output_h5" file="harmony.h5" ftype="h5" compare="sim_size"/> | |
119 </test> | |
120 </tests> | |
121 | |
122 <help><![CDATA[ | |
123 .. class:: infomark | |
124 | |
125 **What it does** | |
126 | |
127 Uses harmonypy [Korunsky19] to integrate different experiments at the principal components level. | |
128 | |
129 @HELP@ | |
130 | |
131 @VERSION_HISTORY@ | |
132 ]]></help> | |
133 <expand macro="citations"/> | |
134 </tool> |