Mercurial > repos > artbio > gsc_high_dimensions_visualisation
diff high_dim_visu.xml @ 4:8e17c31c536a draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/gsc_high_dimension_visualization commit 1282ac9de7c926ab251f88afb2453f52c8b14200
| author | artbio |
|---|---|
| date | Thu, 11 Jul 2019 12:31:28 -0400 |
| parents | 8e44c9e18a56 |
| children | 569334568afa |
line wrap: on
line diff
--- a/high_dim_visu.xml Thu Jun 27 06:17:08 2019 -0400 +++ b/high_dim_visu.xml Thu Jul 11 12:31:28 2019 -0400 @@ -1,12 +1,12 @@ -<tool id="high_dimensions_visualisation" name="Generate PCA, tSNE and HCPC" version="0.9.3"> +<tool id="high_dimensions_visualisation" name="Generate PCA, tSNE and HCPC" version="0.9.4"> <description>from highly dimensional expression data</description> <requirements> - <requirement type="package" version="1.3.2=r3.3.2_0">r-optparse</requirement> - <requirement type="package" version="1.39=r3.3.2_0">r-factominer</requirement> - <requirement type="package" version="1.0.5=r3.3.2_0">r-factoextra</requirement> - <requirement type="package" version="0.13=r3.3.2_0">r-rtsne</requirement> - <requirement type="package" version="2.2.1=r3.3.2_0">r-ggplot2</requirement> - <requirement type="package" version="0.4.1=r3.3.2_0">r-ggfortify</requirement> + <requirement type="package" version="1.6.2=r35h6115d3f_0">r-optparse</requirement> + <requirement type="package" version="1.42=r35h6115d3f_0">r-factominer</requirement> + <requirement type="package" version="1.0.5">r-factoextra</requirement> + <requirement type="package" version="0.15=r351he1b5a44_0">r-rtsne</requirement> + <requirement type="package" version="0.4.7=r351h6115d3f_0">r-ggfortify</requirement> + <requirement type="package" version="1.1.9=r351h0357c0b_0">r-clusterr</requirement> </requirements> <stdio> <exit_code range="1:" level="fatal" description="Tool exception" /> @@ -53,13 +53,21 @@ --HCPC_max '$visualisation.HCPC_max' --HCPC_clusterCA '$visualisation.HCPC_clusterCA' --HCPC_kk '$visualisation.HCPC_kk' + #if $visualisation.res_clustering == "yes": + --HCPC_clust '$HCPC_clust' + #end if #end if #if $visualisation.visu_choice == "PCA": --PCA_npc '$visualisation.PCA_npc' + --PCA_x_axis '$visualisation.PCA_x_axis' + --PCA_y_axis '$visualisation.PCA_y_axis' #end if - + #if $visualisation.visu_choice == "HCPC" and $factor_condition.factor_choice == "Yes": + --mutual_info '$mutual_info' + #end if + --pdf_out '$pdf_out' ]]></command> @@ -111,10 +119,10 @@ <option value="TRUE">Yes</option> <option value="FALSE" selected="true">False</option> </param> - <param name="Rtsne_normalize" type="select" label="Normalisation of data" - help="Should variables (gene expressions) be normalized internally prior to distance calculations? " > - <option value="TRUE" selected="true">Yes</option> - <option value="FALSE">False</option> + <param name="Rtsne_normalize" type="select" label="Normalisation of data" + help="Should variables (gene expressions) be normalized internally prior to distance calculations? " > + <option value="TRUE" selected="true">Yes</option> + <option value="FALSE">False</option> </param> <param name="Rtsne_perplexity" value="10.0" type="float" label="perplexity (t-SNE)" help="should be less than ((nbr observations)-1)/3" /> <param name="Rtsne_theta" value="1.0" type="float" label="theta (t-SNE)"/> @@ -154,9 +162,15 @@ </param> <param name="HCPC_kk" value="-1" type="text" label="kk, Number of clusters used in a Kmeans preprocessing " help="No k-means consolidation is done if a kk value is provided (default=-1)" /> + <param label="Return HCPC clustering table" name="res_clustering" type="select"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> </when> <when value="PCA"> <param name="PCA_npc" value="5" type="integer" label="Number of principal components to keep" help="The number of dimensions which are kept for PCA analysis (default=5)" /> + <param name="PCA_x_axis" value="1" type="integer" label="First principal component to plot" help="X axis for PCA plot (default=1)" /> + <param name="PCA_y_axis" value="2" type="integer" label="Second principal component to plot" help="Y axis for PCA plot (default=2)" /> </when> </conditional> <param label="Return scatter plot table coordinates" name="coord" type="select"> @@ -170,6 +184,12 @@ <data name="table_coordinates" format="tabular" label="Scatter plot coordinates from ${visualisation.visu_choice} of ${on_string}" > <filter>coord == 'yes'</filter> </data> + <data name="mutual_info" format="txt" label="External validation of clustering from ${visualisation.visu_choice} of ${on_string}" > + <filter>visualisation['visu_choice'] == 'HCPC' and factor_condition['factor_choice'] == 'Yes'</filter> + </data> + <data name="HCPC_clust" format="tabular" label="Clustering table from ${visualisation.visu_choice} of ${on_string}" > + <filter>visualisation['visu_choice'] == 'HCPC' and visualisation['res_clustering'] == 'yes'</filter> + </data> </outputs> <tests> <!-- test PCA --> @@ -187,6 +207,17 @@ <param name="factor_choice" value="No" /> <output name="pdf_out" file="pca.nolabels.pdf" ftype="pdf"/> </test> + <!-- test PCA PC2 vs PC3 --> + <test> + <param name="input" value="cpm_input.tsv" ftype="txt"/> + <param name="labels" value="no" /> + <param name="visu_choice" value="PCA" /> + <param name="factor_choice" value="No" /> + <param name="PCA_x_axis" value="2" /> + <param name="PCA_y_axis" value="3" /> + <output name="pdf_out" file="pca.2vs3.pdf" ftype="pdf"/> + </test> + <!-- test Coordinates tables on PCA --> <test> <param name="input" value="cpm_input.tsv" ftype="txt"/> @@ -213,7 +244,16 @@ <param name="visu_choice" value="PCA" /> <param name="factor_choice" value="Yes" /> <param name="factor" value="2-lev_factor.tsv" ftype="txt"/> - <output name="pdf_out" file="pca.nolabels.2-lev-factor.pdf" ftype="pdf"/> + <output name="pdf_out" file="pca.nolabels.2-lev-factor.pdf" compare="sim_size" ftype="pdf"/> + </test> + <!-- test numerical factor contrasting on PCA --> + <test> + <param name="input" value="cpm_input.tsv" ftype="txt"/> + <param name="labels" value="no" /> + <param name="visu_choice" value="PCA" /> + <param name="factor_choice" value="Yes" /> + <param name="factor" value="numeric_factor.tsv" ftype="txt"/> + <output name="pdf_out" file="pca.nolabels.numerical-factor.pdf" compare="sim_size" ftype="pdf"/> </test> <test> <param name="input" value="cpm_input.tsv" ftype="txt"/> @@ -221,7 +261,7 @@ <param name="visu_choice" value="PCA" /> <param name="factor_choice" value="Yes" /> <param name="factor" value="shuffled_factor.tsv" ftype="txt"/> - <output name="pdf_out" file="pca.nolabels.factors.pdf" ftype="pdf"/> + <output name="pdf_out" file="pca.nolabels.factors.pdf" compare="sim_size" ftype="pdf"/> </test> <!-- test HCPC --> <test> @@ -230,7 +270,7 @@ <param name="visu_choice" value="HCPC" /> <param name="HCPC_npc" value="5"/> <param name="HCPC_ncluster" value="-1"/> - <output name="pdf_out" file="hcpc.labels.pdf" ftype="pdf"/> + <output name="pdf_out" file="hcpc.labels.pdf" compare="sim_size" ftype="pdf"/> </test> <!-- test factor contrasting on HCPC --> <test> @@ -239,9 +279,12 @@ <param name="visu_choice" value="HCPC" /> <param name="HCPC_npc" value="5"/> <param name="HCPC_ncluster" value="-1"/> + <param name="res_clustering" value="yes"/> <param name="factor_choice" value="Yes" /> <param name="factor" value="factor.tsv" ftype="txt"/> - <output name="pdf_out" file="hcpc.nolabels.factor.pdf" ftype="pdf"/> + <output name="pdf_out" file="hcpc.nolabels.factor.pdf" compare="sim_size" ftype="pdf"/> + <output name="mutual_info" file="hcpc.factor.extval.txt" ftype="txt"/> + <output name="HCPC_clust" file="hcpc.clusters.tab" ftype="tabular"/> </test> <test> <param name="input" value="cpm_input.tsv" ftype="txt"/> @@ -249,7 +292,7 @@ <param name="HCPC_npc" value="5"/> <param name="HCPC_ncluster" value="-1"/> <param name="visu_choice" value="HCPC" /> - <output name="pdf_out" file="hcpc.nolabels.pdf" ftype="pdf"/> + <output name="pdf_out" file="hcpc.nolabels.pdf" compare="sim_size" ftype="pdf"/> </test> <test> <param name="input" value="cpm_input.tsv" ftype="txt"/> @@ -271,7 +314,7 @@ <param name="HCPC_metric" value="euclidian"/> <param name="HCPC_npc" value="4" /> <param name="HCPC_clusterCA" value="cols" /> - <output name="pdf_out" file="hcpc-3.labels.pdf" ftype="pdf"/> + <output name="pdf_out" file="hcpc-3.labels.pdf" compare="sim_size" ftype="pdf"/> <output name="table_coordinates" file="hcpc-3.coord.tab" ftype="tabular"/> </test> <!-- test t-SNE --> @@ -282,7 +325,7 @@ <param name="Rtsne_seed" value="49"/> <param name="Rtsne_perplexity" value="10"/> <param name="Rtsne_theta" value="1" /> - <output name="pdf_out" file="tsne.labels.pdf" ftype="pdf"/> + <output name="pdf_out" file="tsne.labels.pdf" ftype="pdf" compare="sim_size" delta="500"/> </test> <test> <param name="input" value="cpm_input.tsv" ftype="txt"/> @@ -291,22 +334,9 @@ <param name="Rtsne_seed" value="49"/> <param name="Rtsne_perplexity" value="10"/> <param name="Rtsne_theta" value="1" /> - <output name="pdf_out" file="tsne.nolabels.pdf" ftype="pdf"/> + <output name="pdf_out" file="tsne.nolabels.pdf" ftype="pdf" compare="sim_size" delta="500"/> </test> - <test> - <param name="input" value="cpm_input.tsv" ftype="txt"/> - <param name="labels" value="no" /> - <param name="visu_choice" value="tSNE" /> - <param name="coord" value="yes" /> - <param name="Rtsne_seed" value="42"/> - <param name="Rtsne_perplexity" value="5.0"/> - <param name="Rtsne_theta" value="1.0" /> - <param name="Rtsne_dims" value="3" /> - <param name="Rtsne_exaggeration_factor" value="15.0" /> - <output name="pdf_out" file="tsne-2.nolabels.pdf" ftype="pdf"/> - <output name="table_coordinates" file="tsne-2.coord.tab" ftype="tabular"/> - </test> - <!-- test factor contrasting on t-SNE --> + <!-- test factor contrasting on t-SNE --> <test> <param name="input" value="cpm_input.tsv" ftype="txt"/> <param name="labels" value="yes" /> @@ -316,7 +346,20 @@ <param name="Rtsne_seed" value="49"/> <param name="Rtsne_perplexity" value="10"/> <param name="Rtsne_theta" value="1" /> - <output name="pdf_out" file="tsne.labels.factor.pdf" ftype="pdf"/> + <output name="pdf_out" file="tsne.labels.factor.pdf" ftype="pdf" compare="sim_size" delta="500"/> + </test> + <test> + <param name="input" value="cpm_input.tsv" ftype="txt"/> + <param name="labels" value="no" /> + <param name="visu_choice" value="tSNE" /> + <param name="Rtsne_seed" value="49" /> + <param name="coord" value="yes" /> + <param name="Rtsne_dims" value="3" /> + <param name="Rtsne_perplexity" value="10"/> + <param name="Rtsne_theta" value="1" /> + <param name="Rtsne_normalize" value="FALSE" /> + <output name="pdf_out" file="tsne-2.nolabels.pdf" ftype="pdf" compare="sim_size" delta="500"/> + <output name="table_coordinates" file="tsne-2.coord.tab" ftype="tabular" compare="sim_size" delta="500"/> </test> </tests> <help> @@ -339,19 +382,31 @@ * Principal Components Analysis (PCA) * Hierarchical Clustering of Principal Components (HCPC) -* t-distributed Stochastic Neighbor Embedding +* t-distributed Stochastic Neighbor Embedding (t-SNE) The tool returns in addition the table of the coordinates of the observations (eg RNAseq libraries) in the low dim space, which can be used for post-treatment or to further adjust the provided visualisation. +If HCPC is used, this tool can also return the clustering table. It contains two columns of n observations : + +* Observation labels +* Cluster labels + ** Contrast data with a factor ** The tool offers the possibility to colour data points according to the levels of a factor. To use the option "Factor to contrast data", provide a tabulated-separated, two-column table with first column containing the cell/data library identifiers (same identifiers as those provided as column headers in the input data table) and second column containing the corresponding -factor levels value. This table does not need to be sorted in the same order as in the data +factor levels value (if this vector is numerical, then the color palette used is quantitative). +This table does not need to be sorted in the same order as in the data table. It may also contain more identifiers than those provided in the data table. +If HCPC visualisation and constrasting data are chosen, an additional text file is given. It contains +several metrics of external validation of clustering. It will compare the capacity of HCPC clustering +to recreate classes contained in the factor data file. If the constrasting factor is quantitative, +the file will be empty. + + </help> <citations> <citation type="bibtex">@Article{, @@ -381,5 +436,14 @@ url = {https://github.com/jkrijthe/Rtsne}, } </citation> + <citation type="bibtex">@Manual{, + title = {{ClusterR}: Gaussian Mixture Models, K-Means, Mini-Batch-Kmeans, + K-Medoids and Affinity Propagation Clustering}, + author = {Lampros Mouselimis}, + year = {2019}, + note = {R package version 1.1.9}, + url = {https://github.com/mlampros/ClusterR}, + } + </citation> </citations> </tool>