Mercurial > repos > ebi-gxa > sccaf_regress_out
changeset 0:885db50f1bc1 draft
planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/sccaf commit 39b0809db1e17c2a24930fe8fb8ceaf3ea454a7d
author | ebi-gxa |
---|---|
date | Tue, 19 Nov 2019 13:06:04 -0500 |
parents | |
children | 5ef0610e9f50 |
files | sccaf_macros.xml sccaf_regress_out.xml static/images/example_sccaf_workflow.png |
diffstat | 3 files changed, 142 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/sccaf_macros.xml Tue Nov 19 13:06:04 2019 -0500 @@ -0,0 +1,97 @@ +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">sccaf</requirement> + </requirements> + </xml> + <token name="@TOOL_VERSION@">0.0.8</token> + <token name="@SCCAF_INTRO@"> +SCCAF explained +=============== + +Single Cell Clustering Assessment Framework (SCCAF) is a novel method for +automated identification of putative cell types from single cell RNA-seq +(scRNA-seq) data. By iteratively applying clustering and a machine learning +approach to gene expression profiles of a given set of cells, SCCAF +simultaneously identifies distinct cell groups and a weighted list of feature +genes for each group. The feature genes, which are overexpressed in the +particular cell group, jointly discriminate the given cell group from other +cells. Each such group of cells corresponds to a putative cell type or state, +characterised by the feature genes as markers. + </token> + <token name="@HELP@">More information can be found at https://github.com/SCCAF/SCCAF</token> + <token name="@PLOT_OPTS@"> + #if $do_plotting.plot + -P output.png + --projectio $do_plotting.projection + --components $do_plotting.components + #if $do_plotting.color_by + --color-by $do_plotting.color_by + #end if + #if $do_plotting.groups + --group $do_plotting.groups + #end if + #if $do_plotting.use_raw + --use-raw + #end if + #if $do_plotting.palette + --palette $do_plotting.palette + #end if + #if $do_plotting.show_edges + --edges + #end if + #if $do_plotting.show_arrows + --arrows + #end if + #if not $do_plotting.color_order + --no-sort-order + #end if + #if $do_plotting.omit_frame + --frameoff + #end if +#end if + </token> + <xml name="citations"> + <citations> + <citation type="doi"></citation> + <citation type="bibtex"> + @misc{githubsccaf, + author = {Miao, Zhichao}, + year = {2018}, + title = {SCCAF}, + publisher = {GitHub}, + journal = {GitHub repository}, + url = {https://github.com/Functional-Genomics/SCCAF}, + }</citation> + <yield /> + </citations> + </xml> + <xml name="input_object_params"> + <param name="input_obj_file" argument="--input-object-file" type="data" format="h5" label="Input object in AnnData hdf5 format" help="Normally the result of Scanpy (or equivalent), which already has both a visualisation (either tSNE, UMAP or PCA - needed) and clustering (ideally) pre-computed."/> + <param name="input_format" argument="--input-format" type="select" label="Format of input object"> + <option value="anndata" selected="true">AnnData format hdf5</option> + <option value="loom">Loom format hdf5, current support is incomplete</option> + </param> + </xml> + <xml name="output_object_params"> + <param name="output_format" argument="--output-format" type="select" label="Format of output object"> + <option value="anndata" selected="true">AnnData format hdf5</option> + <option value="loom">Loom format hdf5, current support is defective</option> + </param> + </xml> + <xml name="output_plot_params"> + <param name="color_by" argument="--color-by" type="text" value="n_genes" label="Color by attributes, comma separated strings"/> + <param name="groups" argument="--groups" type="text" optional="ture" label="Restrict plotting to named groups, comma separated strings"/> + <param name="projection" argument="--projection" type="select" label="Plot projection"> + <option value="2d" selected="true">2D</option> + <option value="3d">3D</option> + </param> + <param name="components" argument="--components" type="text" value="1,2" label="Components to plot, comma separated integers"/> + <param name="palette" argument="--palette" type="text" optional="true" label="Palette"/> + <param name="use_raw" argument="--use-raw" type="boolean" checked="false" label="Use raw attributes if present"/> + <param name="show_edges" argument="--edges" type="boolean" checked="false" label="Show edges"/> + <param name="show_arrows" argument="--arrows" type="boolean" checked="false" label="Show arrows"/> + <param name="color_order" argument="--no-sort-order" type="boolean" checked="true" label="Element with high color-by value plot on top"/> + <param name="omit_frame" argument="--frameoff" type="boolean" checked="false" label="Show frame"/> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/sccaf_regress_out.xml Tue Nov 19 13:06:04 2019 -0500 @@ -0,0 +1,45 @@ +<?xml version="1.0" encoding="utf-8"?> +<tool id="sccaf_regress_out" name="SCCAF mulitple regress out" version="@TOOL_VERSION@+galaxy0"> + <description>with multiple categorical keys on an AnnData object.</description> + <macros> + <import>sccaf_macros.xml</import> + </macros> + <expand macro="requirements"/> + <command detect_errors="exit_code"><![CDATA[ + ln -s '${input_obj_file}' input.h5 && + sccaf-regress-out -i input.h5 -o output.h5 -k '${keys_to_regress}' + ]]></command> + <inputs> + <param name="input_obj_file" argument="input-object-file" type="data" format="h5" label="Input object in hdf5 AnnData format"/> + <param name="keys_to_regress" label="Keys to regress" help="Comma separated keys for regressing out; they need to exist in the observations part of the AnnData object." type="text"/> + </inputs> + <outputs> + <data name="output" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: regressesed out on ${keys_to_regress}"/> + </outputs> + + <tests> + <test> + <param name="input_obj_file" value="find_cluster.h5"/> + <param name="input_format" value="anndata"/> + <param name="color_by" value="louvain"/> + <output name="output" file="output.h5" ftype="h5" compare="sim_size"/> + </test> + </tests> + + <help><![CDATA[ +============================= +Operations on AnnData objects +============================= + +Performs the following operations: + +* Change observation fields, mostly for downstreaming processes convenience. Multiple fields can be changed as one. +* Flag genes that start with a certain text: useful for flagging mitochondrial, spikes or other groups of genes. +* For the flags created, calculates qc metrics (pct_<flag>_counts). +* Calculates `n_genes`, `n_counts` for cells and `n_cells`, `n_counts` for genes. +* For top <N> genes specified, calculate qc metrics (pct_counts_in_top_<N>_genes). + +This functionality will probably be added in the future to a larger package. +]]></help> + <!-- <expand macro="citations"/> --> +</tool>