Mercurial > repos > iuc > seurat_clustering
changeset 0:94f1b9c7286f draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/seurat_v5 commit a9214c07b0cc929a51fd92a369bb89c675b6c88d
author | iuc |
---|---|
date | Wed, 11 Sep 2024 10:21:37 +0000 |
parents | |
children | 51eb02d9b17a |
files | macros.xml neighbors_clusters_markers.xml |
diffstat | 2 files changed, 1268 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Wed Sep 11 10:21:37 2024 +0000 @@ -0,0 +1,437 @@ +<macros> + <token name="@TOOL_VERSION@">5.0</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@PROFILE@">23.0</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">r-seurat</requirement> + <requirement type="package" version="1.2.1">fit-sne</requirement> + <requirement type="package" version="3.58.1">bioconductor-limma</requirement> + <requirement type="package" version="1.28.0">bioconductor-mast</requirement> + <requirement type="package" version="1.42.0">bioconductor-deseq2</requirement> + <requirement type="package" version="2.1.3">r-svglite</requirement> + <requirement type="package" version="1.1">r-metap</requirement> + <requirement type="package" version="1.14.0">bioconductor-glmGamPoi</requirement> + <requirement type="package" version="0.5.3">umap-learn</requirement> <!-- https://github.com/satijalab/seurat/issues/8283 --> + <requirement type="package" version="0.10.2">leidenalg</requirement> + <requirement type="package" version="1.2.0">r-harmony</requirement> + <requirement type="package" version="1.18.0">bioconductor-batchelor</requirement> + <requirement type="package" version="2.0.0">numpy</requirement> + <requirement type="package" version="2.2.2">pandas</requirement> + </requirements> + </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.1038/s41587-023-01767-y</citation> + </citations> + </xml> + <xml name="sanitize_query" token_validinitial="string.printable"> + <sanitizer> + <valid initial="@VALIDINITIAL@"> + <remove value="'" /> + </valid> + </sanitizer> + </xml> + <xml name="sanitize_vectors" token_validinitial="string.digits"> + <sanitizer> + <valid initial="@VALIDINITIAL@"> + <add value=","/> + </valid> + </sanitizer> + </xml> + <xml name="version_command"> + <version_command><![CDATA[ +echo $(R --version | grep version | grep -v GNU)", Seurat version" $(R --vanilla --slave -e "library(Seurat); cat(sessionInfo()\$otherPkgs\$DESeq2\$Version)" 2> /dev/null | grep -v -i "WARNING: ") + ]]></version_command> + </xml> + + <token name="@CMD_imports@"><![CDATA[ +library(Seurat) + ]]> + </token> + <token name="@reticulate_hack@"><![CDATA[ +library(reticulate) +## HACK: CI biocontainers do not contain a useable conda binary, just the env. +## see: https://github.com/galaxyproject/tools-iuc/issues/5585#issuecomment-1803773923 +is_biocontainer = grepl("^# cmd: /opt/conda/bin/", + paste0(reticulate:::python_info_condaenv_find("/usr/local/"), + "-none")) +if (is_biocontainer) { + ## conda detection false positive + assignInNamespace("is_conda_python", function(x) FALSE, ns="reticulate") + use_python("/usr/local/bin/python") +} else { + conda_path = Sys.getenv("CONDA_PREFIX") + if (conda_path != "") { + ## Active conda env found + use_python(file.path(conda_path, "bin", "python3")) + } else { + ## Not biocontainer or conda, assume system python + use_python("/usr/bin/python3") + } +}]]> + </token> + <xml name="input_rds"> + <param name="seurat_rds" type="data" format="rds" label="Input file with the Seurat object"/> + </xml> + <token name="@CMD_read_inputs@"><![CDATA[ +seurat_obj = readRDS('seurat.rds') + ]]> + </token> + <token name="@CMD_read_expression_matrix@"><![CDATA[ +counts<-read.table("matrix.tab", header=TRUE, row.names=1, sep="\t") + ]]>] + </token> + <token name="@CMD@"><![CDATA[ +cp '$seurat_rds' seurat.rds && +cat '$script_file' > $hidden_output && +Rscript '$script_file' >> $hidden_output + ]]> + </token> + <xml name="inputs_common_advanced"> + <section name="advanced_common" title="Advanced Output" expanded="false"> + <param name="show_log" type="boolean" checked="false" label="Output Log?" /> + </section> + </xml> + <xml name="outputs_common_advanced"> + <data name="hidden_output" format="txt" label="Log file" > + <filter>advanced_common['show_log']</filter> + </data> + </xml> + <xml name="seurat_outputs"> + <data name="rds_out" format="rds" from_work_dir="seurat.rds" label="${tool.name} (${method.method}) on ${on_string}: RDS"> + <filter>method['method'] != 'Inspect'</filter> + </data> + <expand macro="outputs_common_advanced"/> + </xml> + <token name="@CMD_rds_write_outputs@"><![CDATA[ +saveRDS(seurat_obj, 'seurat.rds') + ]]> + </token> + <xml name="variable_out"> + <data name="variable_tabular" format="txt" from_work_dir="variable_out.txt" label="${tool.name} (${method.method}) on ${on_string}: Top variable features list"> + <filter>method['method'] == 'FindVariableFeatures' or method['method'] == 'SCTransform'</filter> + <filter>method['output_topN']['output_topN'] == 'true'</filter> + </data> + </xml> + <token name="@CMD_write_variable_tab@"><![CDATA[ +write.table(top_N, 'variable_out.txt', sep= "\t", col.names = FALSE, quote = FALSE) + ]]> + </token> + <xml name="markers_out"> + <data name="markers_tabular" format="csv" from_work_dir="markers_out.csv" label="${tool.name} (${method.method}) on ${on_string}: Markers list"> + <filter>method['method'] == 'FindAllMarkers' or method['method'] == 'FindMarkers' or method['method'] == 'FindConservedMarkers'</filter> + </data> + </xml> + <token name="@CMD_write_markers_tab@"><![CDATA[ +write.csv(seurat_obj, 'markers_out.csv', quote = FALSE) + ]]> + </token> + <xml name="print_top_pcs"> + <data name="top_pcs" format="txt" from_work_dir="print_pcs.txt" label="${tool.name} Print PCs on ${on_string}"> + <filter>method['method'] == 'RunPCA' and method['print_pcs']['print_pcs'] == 'true'</filter> + </data> + </xml> + <xml name="inspect_out"> + <data name="inspect_tabular" format="tabular" from_work_dir="inspect_out.tab" label="${tool.name} Inspect (${method.inspect.inspect}) on ${on_string}"> + <filter>method['method'] == 'Inspect' and method['inspect']['inspect'] != 'General'</filter> + </data> + <data name="inspect_general" format="txt" from_work_dir="inspect.txt" label="${tool.name} Inspect General on ${on_string}"> + <filter>method['method'] == 'Inspect' and method['inspect']['inspect'] == 'General'</filter> + </data> + </xml> + <token name="@CMD_inspect_rds_outputs@"><![CDATA[ +write.table(inspect, 'inspect_out.tab', sep="\t", col.names = col.names, row.names = row.names, quote = FALSE) + ]]> + </token> + <xml name="plot_out"> + <data name="plot_out_png" format="png" from_work_dir="plot.png" label="${tool.name} (${method.method}) on ${on_string}: png plot"> + <filter>plot_format == 'png'</filter> + </data> + <data name="plot_out_pdf" format="pdf" from_work_dir="plot.pdf" label="${tool.name} (${method.method}) on ${on_string}: pdf plot"> + <filter>plot_format == 'pdf'</filter> + </data> + <data name="plot_out_svg" format="svg" from_work_dir="plot.svg" label="${tool.name} (${method.method}) on ${on_string}: svg plot"> + <filter>plot_format == 'svg'</filter> + </data> + <data name="plot_out_jpeg" format="jpeg" from_work_dir="plot.jpeg" label="${tool.name} (${method.method}) on ${on_string}: jpeg plot"> + <filter>plot_format == 'jpeg'</filter> + </data> + <data name="plot_out_tex" format="tex" from_work_dir="plot.tex" label="${tool.name} (${method.method}) on ${on_string}: tex plot"> + <filter>plot_format == 'tex'</filter> + </data> + <data name="plot_out_tiff" format="tiff" from_work_dir="plot.tiff" label="${tool.name} (${method.method}) on ${on_string}: tiff plot"> + <filter>plot_format == 'tiff'</filter> + </data> + <data name="plot_out_eps" format="eps" from_work_dir="plot.eps" label="${tool.name} (${method.method}) on ${on_string}: eps plot"> + <filter>plot_format == 'eps'</filter> + </data> + </xml> + <xml name="param_eps" tokens="eps_value"> + <param argument="eps" type="float" value="@EPS_VALUE@" label="Small number to avoid numerical errors"/> + </xml> + <xml name="valid_name"> + <validator type="regex" message="Please only use letters, numbers, or _ - .">^[\w\-.]+$</validator> + </xml> + <xml name="valid_reduction_key"> + <validator type="regex" message="Please only use letters and _">^[A-Za-z_]+$</validator> + </xml> + <xml name="valid_list"> + <validator type="regex" message="Please only use letters, numbers, or _ - . ,">^[\w\-., ]+$</validator> + </xml> + <xml name="valid_cell_name"> + <validator type="regex" message="Please only use letters, numbers, or punctuation marks">^[\w[:punct:]]+$</validator> + </xml> + <xml name="valid_cell_list"> + <validator type="regex" message="Please only use letters, numbers, or punctuation marks">^[\w[:punct:]]+$</validator> + </xml> + <xml name="select_assay"> + <param argument="assay" type="text" optional="true" value="" label="Name of assay to use" help="leave blank to use default assay"> + <expand macro="valid_name"/> + </param> + </xml> + <xml name="select_assay_RNA"> + <param argument="assay" type="text" value="RNA" label="Name of assay to use"> + <expand macro="valid_name"/> + </param> + </xml> + <xml name="select_slot_data"> + <param argument="slot" type="select" label="Slot to pull data from"> + <option value="counts">counts</option> + <option value="data" selected="true">data</option> + <option value="scale.data">scale.data</option> + <option value="raw.data">raw.data</option> + </param> + </xml> + <xml name="select_slot_scale"> + <param argument="slot" type="select" label="Slot to pull data from"> + <option value="counts">counts</option> + <option value="data">data</option> + <option value="scale.data" selected="true">scale.data</option> + <option value="raw.data">raw.data</option> + </param> + </xml> + <xml name="select_slot_counts"> + <param argument="slot" type="select" label="Slot to pull data from"> + <option value="counts" selected="true">counts</option> + <option value="data">data</option> + <option value="scale.data">scale.data</option> + <option value="raw.data">raw.data</option> + </param> + </xml> + <xml name="select_layer"> + <param argument="layer" type="text" optional="true" value="" label="Layer to pull data from" help="leave blank to use default"> + <expand macro="valid_name"/> + </param> + </xml> + <xml name="select_reduction_pca"> + <param argument="reduction" type="text" value="pca" label="Name of reduction to use" help="default is pca"> + <expand macro="valid_name"/> + </param> + </xml> + <xml name="select_reduction_umap"> + <param argument="reduction" type="text" value="umap" label="Name of reduction to use" help="first defaults to umap, then tsne, then pca"> + <expand macro="valid_name"/> + </param> + </xml> + <xml name="set_topN"> + <param name="topN" type="integer" value="10" label="Number to show"/> + </xml> + <xml name="set_dims"> + <param argument="dims" type="integer" optional="true" value="10" label="Number of dimensions from reduction to use as input"/> + </xml> + <xml name="normalize"> + <conditional name="normalization_method"> + <param name="normalization_method" type="select" label="Method for normalization" help="(normalization.method)"> + <option value="LogNormalize" selected="true">LogNormalize</option> + <option value="CLR">CLR</option> + <option value="RC">RC</option> + </param> + <when value="LogNormalize"></when> + <when value="CLR"> + <param argument="margin" type="select" checked="true" label="Normalize across features (1) or cells (2)"> + <option value="1" selected="true">features</option> + <option value="2">cells</option> + </param> + </when> + <when value="RC"></when> + </conditional> + <param name="scale_factor" type="integer" value="10000" label="Set scale factor for normalization" help="(scale.factor)"/> + <param name="block_size" type="integer" optional="true" value="" label="Number of cells to run in each block" help="(block.size)"/> + </xml> + <xml name="integration_inputs"> + <param argument="dims" type="integer" value="30" label="Number of dimensions from reduction to use for integration"/> + <param name="dims_to_integrate" type="integer" optional="true" value="" label="Number of dimensions to return integrated values for" help="(dims.to.integrate)"/> + <param name="k_weight" type="integer" value="100" label="Number of neighbors to consider when weighting anchors" help="(k.weight)"/> + <param name="weight_reduction" type="text" optional="true" value="" label="Name of reduction(s) to use for calculating anchor weights" help="leave blank to use full corrected space (weight.reduction)"> + <expand macro="valid_list"/> + </param> + <param name="sd_weight" type="float" value="1" label="Controls bandwidth of Gaussian kernel for weighting"/> + <param name="preserve_order" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Preserve order" help="do not reorder objects based on size for each pairwise integration (preserve.order)"/> + </xml> + <xml name="markers_inputs"> + <param argument="features" type="data" format="txt,tabular" optional="true" value="" label="Features to test" help="text file with one feature on each line, leave empty to use all genes"/> + <param name="logfc_threshold" type="float" value="0.1" label="Minimum log-fold difference to test" help="(logfc.threshold)"/> + <conditional name="test_use"> + <param name="test_use" type="select" label="Select test to run" help="(test.use)"> + <option value="wilcox" selected="true">wilcox</option> + <option value="wilcox_limma">wilcox_limma</option> + <option value="bimod">bimod</option> + <option value="roc">roc</option> + <option value="t">t</option> + <option value="negbinom">negbinom</option> + <option value="poisson">poisson</option> + <option value="LR">LR</option> + <option value="MAST">MAST</option> + <option value="DESeq2">DESeq2</option> + </param> + <when value="wilcox"> + <expand macro="select_slot_data"/> + </when> + <when value="wilcox_limma"> + <expand macro="select_slot_data"/> + </when> + <when value="bimod"> + <expand macro="select_slot_data"/> + </when> + <when value="roc"> + <expand macro="select_slot_data"/> + <param name="return_thresh" type="float" value="0.01" min="0.0" max="1.0" label="Only return markers with a p-value below or power above this threshold" help="(return.thresh)"/> + </when> + <when value="t"> + <expand macro="select_slot_data"/> + </when> + <when value="negbinom"> + <expand macro="select_slot_counts"/> + <param name="latent_vars" type="text" optional="true" value="" label="Select variables to test" help="(latent.vars)"/> + <param name="min_cells_feature" type="integer" value="3" label="Minimum number of cells expressing the feature in at least one cluster" help="(min.cells.feature)"/> + </when> + <when value="poisson"> + <expand macro="select_slot_counts"/> + <param name="latent_vars" type="text" optional="true" value="" label="Select variables to test" help="(latent.vars)"/> + <param name="min_cells_feature" type="integer" value="3" label="Minimum number of cells expressing the feature in at least one cluster" help="(min.cells.feature)"/> + </when> + <when value="LR"> + <expand macro="select_slot_data"/> + <param name="latent_vars" type="text" optional="true" value="" label="Select variables to test" help="(latent.vars)"/> + </when> + <when value="MAST"> + <expand macro="select_slot_data"/> + <param name="latent_vars" type="text" optional="true" value="" label="Select variables to test" help="(latent.vars)"/> + </when> + <when value="DESeq2"> + <expand macro="select_slot_counts"/> + </when> + </conditional> + </xml> + <xml name="advanced_markers_inputs"> + <expand macro="select_assay"/> + <param name="fc_name" type="text" optional="true" value="" label="Choose a name for the fold change, average difference, or custom function column" help="(fc.name)"> + <expand macro="valid_name"/> + </param> + <param name="min_pct" type="float" value="0.01" min="0" max="100" label="Minimum percentage of cells genes must be present in to be tested" help="(min.pct)"/> + <param name="min_diff_pct" type="float" optional="true" value="" label="Minimum difference in percentage of expression between groups for genes to be tested" help="defaults to -Inf (min.diff.pct)"/> + <param name="only_pos" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Only return positive markers" help="(only.pos)"/> + <param name="max_cells_per_ident" type="integer" optional="true" value="" label="Downsample each identity class to a max number of cells" help="defaults to Inf for no downsampling (max.cells.per.ident)"/> + <param name="random_seed" type="integer" optional = "true" value="1" label="Set a random seed for downsampling" help="(random.seed)"/> + <param name="min_cells_group" type="integer" value="3" label="Minimum number of cells in one group" help="(min.cells.group)"/> + <param argument="densify" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Convert to dense matrix before running DE test"/> + </xml> + <xml name="plot_types"> + <param name="plot_format" type="select" label="Format of plot to produce"> + <option value="png">png</option> + <option value="pdf">pdf</option> + <option value="svg">svg</option> + <option value="jpeg">jpeg</option> + <option value="tex">tex</option> + <option value="tiff">tiff</option> + <option value="eps">eps</option> + </param> + </xml> + <xml name="plot_sizes"> + <conditional name="resize"> + <param name="resize" type="select" label="Change size of plot"> + <option value="false" selected="true">No</option> + <option value="true">Yes</option> + </param> + <when value="false"></when> + <when value="true"> + <param argument="width" type="integer" value="2100" label="Width of plot in pixels"/> + <param argument="height" type="integer" value="2100" label="Height of plot in pixels"/> + </when> + </conditional> + </xml> + <xml name="plot_cols"> + <param argument="cols" type="text" optional="true" value="" label="Colours to use for plotting" help="comma separated list"> + <expand macro="valid_list"/> + </param> + </xml> + <xml name="plot_log_scale"> + <param argument="log" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Plot on a log scale"/> + </xml> + <xml name="plot_2_dims"> + <param name="dims_1" type="integer" value="1" label="Dimension to plot on x axis"/> + <param name="dims_2" type="integer" value="2" label="Dimension to plot on y axis"/> + </xml> + <xml name="plot_projected_and_balanced"> + <param argument="projected" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Use reduction values for full dataset" help="i.e. projected dimensional reduction values"/> + <param argument="balanced" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Return an equal number of genes with + and - scores"/> + </xml> + <xml name="plot_disp_min_max"> + <param name="disp_min" type="float" optional="true" value="-2.5" label="Minimum display value" help="all values below are clipped (disp.min)"/> + <param name="disp_max" type="float" optional="true" value="" label="Maximum display value" help="all values above are clipped. Defaults to 2.5 if slot is scale.data, otherwise defaults to 6 (disp.max)"/> + </xml> + <xml name="plot_shuffle_and_seed"> + <conditional name="shuffle"> + <param argument="shuffle" type="select" label="Randomly shuffle order of points" help="can help with crowded plots if points of interest are hidden"> + <option value="TRUE">Yes</option> + <option value="FALSE" selected="true">No</option> + </param> + <when value="TRUE"> + <param argument="seed" type="integer" value="1" label="Set random seed for shuffling"/> + </when> + <when value="FALSE"></when> + </conditional> + </xml> + <xml name="plot_order"> + <param argument="order" type="text" optional="true" value="" label="Specify the order of plotting for the idents" help="a full comma-separated list or the ident to be plotted last on the top"> + <expand macro="valid_list"/> + </param> + </xml> + <xml name="plot_group_by"> + <param name="group_by" type="text" optional="true" value="" label="Factor to group cells by" help="(group.by)"/> + </xml> + <xml name="plot_split_by"> + <param name="split_by" type="text" optional="true" value="" label="Factor or identity to split the plot by" help="(split.by)"/> + </xml> + <xml name="plot_alpha"> + <param argument="alpha" type="integer" value="1" label="Alpha value for points"/> + </xml> + <xml name="plot_pt_size"> + <param name="pt_size" type="float" optional="true" value="" label="Point size for plot" help="(pt.size)"/> + </xml> + <xml name="plot_smooth"> + <param argument="smooth" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Smooth the graph"/> + </xml> + <xml name="plot_ncol"> + <param argument="ncol" type="integer" optional="true" value="" label="Number of columns to display"/> + </xml> + <xml name="raster_select"> + <conditional name="raster"> + <param argument="raster" type="select" label="Convert points to raster format" help="NULL will automatically use raster if more than 100,000 points plotted"> + <option value="NULL" selected="true">NULL</option> + <option value="TRUE">TRUE</option> + <option value="FALSE">FALSE</option> + </param> + <when value="NULL"></when> + <when value="TRUE"> + <param name="raster_x" type="integer" value="512" label="Horizontal length of raster plot (pixels)"/> + <param name="raster_y" type="integer" value="512" label="Vertical height of raster plot (pixels)"/> + </when> + <when value="FALSE"></when> + </conditional> + </xml> + <xml name="raster_boolean"> + <param argument="raster" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Convert to raster format"/> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/neighbors_clusters_markers.xml Wed Sep 11 10:21:37 2024 +0000 @@ -0,0 +1,831 @@ +<tool id="seurat_clustering" name="Seurat Find Clusters" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> + <description>- Neighbors and Markers</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="version_command"/> + <command detect_errors="exit_code"><![CDATA[ +@CMD@ + ]]></command> + <configfiles> + <configfile name="script_file"><![CDATA[ +@CMD_imports@ +@CMD_read_inputs@ + +#if $method.method == 'FindNeighbors' +seurat_obj<-FindNeighbors( + seurat_obj, + #if $method.reduction != '' + reduction = '$method.reduction', + #end if + #if $method.dims != '' + dims = 1:$method.dims, + #end if + k.param = $method.k_param, + nn.method = '$method.nn_method.nn_method', + #if $method.nn_method.nn_method == 'rann' + nn.eps = $method.nn_method.nn_eps, + #else if $method.nn_method.nn_method == 'annoy' + annoy.metric = '$method.nn_method.annoy_metric', + #end if + compute.snn = $method.adv.compute_snn.compute_snn, + #if $method.adv.compute_snn.compute_snn == 'TRUE' + #if $method.adv.compute_snn.prune_snn + prune.snn = $method.adv.compute_snn.prune_snn, + #end if + distance.matrix = $method.adv.compute_snn.distance_matrix, + #else if $method.adv.compute_snn.compute_snn == 'FALSE' + distance.matrix = $method.adv.compute_snn.distance_matrix.distance_matrix, + #if $method.adv.compute_snn.distance_matrix.distance_matrix == 'FALSE' + return.neighbor = $method.adv.compute_snn.distance_matrix.return_neighbor, + #end if + #end if + l2.norm = $method.adv.l2_norm, + n.trees = $method.adv.n_trees +) + +#else if $method.method == 'FindMultiModalNeighbors' +seurat_obj<-FindMultiModalNeighbors( + seurat_obj, + reduction.list = list('$method.reduction_1', '$method.reduction_2'), + dims.list = list(1:$method.dims_1, 1:$method.dims_2), + k.nn = $method.k_nn, + knn.graph.name = '$method.adv.knn_graph_name', + snn.graph.name = '$method.adv.snn_graph_name', + weighted.nn.name = '$method.adv.weighted_nn_name', + #if $method.adv.modality_weight_name != '' + modality.weight.name = '$method.adv.modality_weight_name', + #end if + knn.range = $method.adv.knn_range +) + +#else if $method.method == 'FindClusters' +@reticulate_hack@ +seurat_obj<-FindClusters( + seurat_obj, + modularity.fxn = $method.modularity_fxn, + resolution = $method.resolution, + algorithm = $method.algorithm.algorithm, + #if $method.algorithm.algorithm == '4' + #if $method.algorithm.initial_membership + initial.membership = $method.algorithm.initial_membership, + #end if + #if $method.algorithm.node_sizes + node.sizes = $method.algorithm.node_sizes, + #end if + method = '$method.algorithm.method_cluster', + #end if + n.start = $method.n_start, + n.iter = $method.n_iter, + random.seed = $method.random_seed, + #if $method.graph_name != '' + graph.name = '$method.graph_name', + #end if + #if $method.cluster_name != '' + cluster.name = '$method.cluster_name' + #end if +) + +#else if $method.method == 'FindAllMarkers' + + #if $method.features + features_list<-paste(readLines('$method.features'), collapse=",") + #end if + +seurat_obj<-FindAllMarkers( + seurat_obj, + #if $method.features + features = c(unlist(strsplit(features_list, ","))), + #end if + logfc.threshold = $method.logfc_threshold, + test.use = '$method.test_use.test_use', + #if $method.test_use.test_use == 'negbinom' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + min.cells.feature = $method.test_use.min_cells_feature, + #else if $method.test_use.test_use == 'poisson' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + min.cells.feature = $method.test_use.min_cells_feature, + #else if $method.test_use.test_use =='LR' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + #else if $method.test_use.test_use == 'MAST' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + #else if $method.test_use.test_use == 'roc' + return.thresh = $method.test_use.return_thresh, + #end if + slot = '$method.slot', + #if $method.adv.assay != '' + assay = '$method.adv.assay', + #end if + min.pct = $method.adv.min_pct, + #if $method.adv.min_diff_pct + min.diff.pct = $method.adv.min_diff_pct, + #end if + only.pos = $method.adv.only_pos, + #if $method.adv.max_cells_per_ident + max.cells.per.ident = $method.adv.max_cells_per_ident, + #end if + #if $method.adv.random_seed + random.seed = $method.adv.random_seed, + #end if + min.cells.group = $method.adv.min_cells_group, + #if $method.fc_name != '' + fc.name = '$method.adv.fc_name', + #end if + base = $method.adv.base, + densify = $method.adv.densify +) + + #if $method.set_top_markers.set_top_markers == 'true' + N = $method.set_top_markers.topN + seurat_obj<-dplyr::slice_head(seurat_obj, n = N, by = cluster) + #end if + +@CMD_write_markers_tab@ + +#else if $method.method == 'FindMarkers' + + #if $method.features + features_list<-paste(readLines('$method.features'), collapse=",") + #end if + #if $method.cells.cells == 'true' + cell_1_list<-paste(readLines('$method.cells_1'), collapse=",") + cell_2_list<-paste(readLines('$method.cells_2'), collapse=",") + #end if + +seurat_obj<-FindMarkers( + seurat_obj, + slot = '$method.slot', + #if $method.cells.cells == 'true' + cells.1 = c(unlist(strsplit(cell_1_list, ","))), + cells.2 = c(unlist(strsplit(cell_2_list, ","))), + #end if + #if $method.regroup.regroup == 'true' + group.by = '$method.regroup.group_by', + #if $method.regroup.subset_ident != '' + subset.ident = '$method.regroup.subset_ident', + #end if + #end if + #if $method.ident.ident == 'true' + ident.1 = '$method.ident.ident_1', + #if $method.ident.ident_2 != '' + ident.2 = c(unlist(strsplit(gsub(" ", "", '$method.ident.ident_2'), ","))), + #end if + #end if + #if $method.features + features = c(unlist(strsplit(features_list, ","))), + #end if + logfc.threshold = $method.logfc_threshold, + test.use = '$method.test_use.test_use', + #if $method.test_use.test_use == 'negbinom' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + min.cells.feature = $method.test_use.min_cells_feature, + #else if $method.test_use.test_use == 'poisson' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + min.cells.feature = $method.test_use.min_cells_feature, + #else if $method.test_use.test_use =='LR' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + #else if $method.test_use.test_use == 'MAST' + #if $method.test_use.latent_vars != '' + latent.vars = c(unlist(strsplit(gsub(" ", "", '$method.test_use.latent_vars'), ","))), + #end if + #end if + #if $method.adv.assay != '' + assay = '$method.adv.assay', + #end if + min.pct = $method.adv.min_pct, + #if $method.adv.min_diff_pct + min.diff.pct = $method.adv.min_diff_pct, + #end if + only.pos = $method.adv.only_pos, + #if $method.adv.max_cells_per_ident + max.cells.per.ident = $method.adv.max_cells_per_ident, + #end if + #if $method.adv.random_seed + random.seed = $method.adv.random_seed, + #end if + min.cells.group = $method.adv.min_cells_group, + #if $method.adv.fc_name != '' + fc.name = '$method.adv.fc_name', + #end if + densify = $method.adv.densify +) + +@CMD_write_markers_tab@ + +#else if $method.method == 'FindConservedMarkers' +seurat_obj<-FindConservedMarkers( + seurat_obj, + ident.1 = $method.ident_1, + #if $method.ident_2 != '' + ident.2 = $method.ident_2, + #end if + grouping.var = '$method.grouping_var', + #if $method.assay != '' + assay = '$method.assay', + #end if + slot = '$method.slot', + min.cells.group = $method.min_cells_group +) + +@CMD_write_markers_tab@ + +#end if + +@CMD_rds_write_outputs@ + +]]></configfile> + </configfiles> + <inputs> + <expand macro="input_rds"/> + <conditional name="method"> + <param name="method" type="select" label="Method used"> + <option value="FindNeighbors">Compute nearest neighbors with 'FindNeighbors'</option> + <option value="FindMultiModalNeighbors">Compute nearest neighbors for multimodal data with 'FindMultiModalNeighbors'</option> + <option value="FindClusters">Identify cell clusters with 'FindClusters'</option> + <option value="FindAllMarkers">Identify marker genes with 'FindAllMarkers'</option> + <option value="FindMarkers">Identify marker genes for specific groups with 'FindMarkers'</option> + <option value="FindConservedMarkers">Find markers conserved between groups with 'FindConservedMarkers'</option> + </param> + <when value="FindNeighbors"> + <expand macro="select_reduction_pca"/> + <expand macro="set_dims"/> + <param name="k_param" type="integer" value="20" label="Set k for k-nearest neighbors" help="(k.param)"/> + <conditional name="nn_method"> + <param name="nn_method" type="select" label="Method for finding nearest neighbors" help="(nn.method)"> + <option value="rann">rann</option> + <option value="annoy" selected="true">annoy</option> + </param> + <when value="rann"> + <param name="nn_eps" type="float" value="0.0" label="Set error bound for nearest neighbor search" help="(nn.eps)"/> + </when> + <when value="annoy"> + <param name="annoy_metric" type="select" label="Distance metric for annoy method" help="(annoy.metric)"> + <option value="euclidean" selected="true">euclidean</option> + <option value="cosine">cosine</option> + <option value="manhattan">manhattan</option> + <option value="hamming">hamming</option> + </param> + </when> + </conditional> + <section name="adv" title="Advanced Options"> + <param name="n_trees" type="integer" value="50" label="Number of trees for nearest neighbor search" help="(n.trees)"/> + <param name="l2_norm" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Take l2Norm of data" help="(l2.norm)"/> + <conditional name="compute_snn"> + <param name="compute_snn" type="select" label="Compute the shared nearest neighbor (SNN) graph" help="(compute.snn)"> + <option value="FALSE">No</option> + <option value="TRUE" selected="true">Yes</option> + </param> + <when value="FALSE"> + <conditional name="distance_matrix"> + <param name="distance_matrix" type="select" label="Use a distance matrix" help="(distance.matrix)"> + <option value="FALSE" selected="true">No</option> + <option value="TRUE">Yes</option> + </param> + <when value="FALSE"> + <param name="return_neighbor" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Return result as neighbor object" help="(return.neighbor)"/> + </when> + <when value="TRUE"></when> + </conditional> + </when> + <when value="TRUE"> + <param name="prune_snn" type="float" optional="true" value="" min="0" max="1" label="Set cutoff for Jaccard index when computing overlap for SNN" help="0 no pruning, 1 prune everything (prune.SNN)"/> + <param name="distance_matrix" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Use a distance matrix" help="(distance.matrix)"/> + </when> + </conditional> + </section> + </when> + <when value="FindMultiModalNeighbors"> + <param name="reduction_1" type="text" value="pca" label="Reduction to use for first modality"> + <expand macro="valid_name"/> + </param> + <param name="dims_1" type="integer" value="10" label="Number of dimensions to use from first reduction"/> + <param name="reduction_2" type="text" value="apca" label="Reduction to use for second modality"> + <expand macro="valid_name"/> + </param> + <param name="dims_2" type="integer" value="10" label="Number of dimensions to use from second reduction"/> + <param name="k_nn" type="integer" value="20" label="Number of multimodal neighbors to compute" help="(k.nn)"/> + <section name="adv" title="Advanced Options"> + <param name="knn_graph_name" type="text" value="wknn" label="Name for multimodal knn graph" help="(knn.graph.name)"> + <expand macro="valid_name"/> + </param> + <param name="snn_graph_name" type="text" value="wsnn" label="Name for multimodal snn graph" help="(snn.graph.name)"> + <expand macro="valid_name"/> + </param> + <param name="weighted_nn_name" type="text" value="weighted.nn" label="Name for multimodal neighbor object" help="(weighted.nn.name)"> + <expand macro="valid_name"/> + </param> + <param name="modality_weight_name" optional="true" type="text" value="" label="Name for storing modality weights in metadata" help="(modality.weight.name)"> + <expand macro="valid_name"/> + </param> + <param name="knn_range" type="integer" value="200" label="Number of approximate neighbors to compute" help="(knn.range)"/> + </section> + </when> + <when value="FindClusters"> + <param name="modularity_fxn" type="select" label="Select modularity function" help="(modularity.fxn)"> + <option value="1" selected="true">standard</option> + <option value="2">alternative</option> + </param> + <param argument="resolution" type="float" value="0.8" label="Resolution"/> + <conditional name="algorithm"> + <param argument="algorithm" type="select" label="Algorithm for modularity optimization"> + <option value="1" selected="true">1. Original Louvain</option> + <option value="2">2. Louvain with multilevel refinement</option> + <option value="3">3. SLM</option> + <option value="4">4. Leiden</option> + </param> + <when value="4"> + <param name="initial_membership" type="integer" optional="true" value="" label="Set initial membership when using Python leidenalg function" help="defaults to singleton partition (initial.membership)"/> + <param name="node_sizes" type="integer" optional="true" value="" label="Set node size when using Python leidenalg function" help="(node.sizes)"/> + <param name="method_cluster" type="select" label="Method for leiden" help="matrix is fast for small data, enable igraph for larger data (method.cluster)"> + <option value="matrix" selected="true">matrix</option> + <option value="igraph">igraph</option> + </param> + </when> + <when value="1"> + </when> + <when value="2"> + </when> + <when value="3"> + </when> + </conditional> + <param name="n_start" type="integer" value="10" label="Number of random starts" help="(n.start)"/> + <param name="n_iter" type="integer" value="10" label="Maximal number of iterations per random start" help="(n.iter)"/> + <param name="random_seed" type="integer" value="0" label="Set random seed" help="(random.seed)"/> + <param name="group_singletons" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Group singletons into nearest cluster" help="Set to false to create a cluster for all singletons (group.singletons)"/> + <param name="graph_name" type="text" optional="true" value="" label="Name of graph to use for the clustering algorithm" help="(graph.name)"> + <expand macro="valid_name"/> + </param> + <param name="cluster_name" type="text" optional="true" value="" label="Name for output clusters" help="(cluster.name)"> + <expand macro="valid_name"/> + </param> + </when> + <when value="FindAllMarkers"> + <expand macro="markers_inputs"/> + <conditional name="set_top_markers"> + <param name="set_top_markers" type="select" label="Limit output to top N markers per cluster"> + <option value="true">Yes</option> + <option value="false" selected="true">No</option> + </param> + <when value="true"> + <expand macro="set_topN"/> + </when> + <when value="false"> + </when> + </conditional> + <section name="adv" title="Advanced Options"> + <param argument="base" type="integer" value="2" label="Base with respect to which logarithms are computed"/> + <expand macro="advanced_markers_inputs"/> + </section> + </when> + <when value="FindMarkers"> + <conditional name="cells"> + <param name="cells" type="select" label="Compare markers for two groups of cells"> + <option value="true">Yes</option> + <option value="false" selected="true">No</option> + </param> + <when value="true"> + <param name="cells_1" type="data" format="txt,tabular" label="List of cell names for group 1" help="text file with one cell on each line (cells.1)"/> + <param name="cells_2" type="data" format="txt,tabular" label="List of cell names for group 2" help="text file with one cell on each line (cells.2)"/> + </when> + <when value="false"> + </when> + </conditional> + <conditional name="regroup"> + <param name="regroup" type="select" label="Change cell identities before finding markers"> + <option value="true">Yes</option> + <option value="false" selected="true">No</option> + </param> + <when value="true"> + <param name="group_by" type="text" value="group" label="Name of identity class to regroup cells into" help="a group from the cell metadata to find markers for (group.by)"/> + <param name="subset_ident" type="text" optional="true" value="" label="Identity class to subset before regrouping" help="only include cells from this cluster/identity in each new group (subset.ident)"/> + </when> + <when value="false"> + </when> + </conditional> + <conditional name="ident"> + <param name="ident" type="select" label="Compare markers between clusters of cells"> + <option value="true">Yes</option> + <option value="false" selected="true">No</option> + </param> + <when value="true"> + <param name="ident_1" type="text" optional="true" value="" label="Identity class to define markers for" help="e.g. cluster number or ident group name (ident.1)"/> + <param name="ident_2" type="text" optional="true" value="" label="Second identity class to compare" help="e.g. comma-separated list of cluster numbers or idents, leave blank to compare ident.1 against all other clusters. (ident.2)"> + <expand macro="valid_list"/> + </param> + </when> + <when value="false"> + </when> + </conditional> + <expand macro="markers_inputs"/> + <section name="adv" title="Advanced Options"> + <expand macro="advanced_markers_inputs"/> + </section> + </when> + <when value="FindConservedMarkers"> + <param name="ident_1" type="text" value="ident1" label="Identity class to define markers for" help="(ident.1)"/> + <param name="ident_2" type="text" optional="true" value="" label="Second identity class for comparison" help="leave blank to compare ident.1 to all other cells (ident.2)"/> + <param name="grouping_var" type="text" value="group" label="Grouping variable" help="(grouping.var)"/> + <expand macro="select_assay_RNA"/> + <expand macro="select_slot_data"/> + <param name="min_cells_group" type="integer" value="3" label="Minimum number of cells in one group" help="(min.cells.group)"/> + </when> + </conditional> + <expand macro="inputs_common_advanced"/> + </inputs> + <outputs> + <expand macro="seurat_outputs"/> + <expand macro="markers_out"/> + </outputs> + <tests> + <test expect_num_outputs="2"> + <!-- test1: FindNeighbors --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/pca.rds"/> + <conditional name="method"> + <param name="method" value="FindNeighbors"/> + <param name="dims" value="9"/> + <conditional name="nn_method"> + <param name="nn_method" value="annoy"/> + <param name="annoy_metric" value="euclidean"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindNeighbors"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/neighbors.rds" ftype="rds" compare="sim_size"/> + </test> + <test expect_num_outputs="2"> + <!-- test2: FindMultiModalNeighbors --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/citeseq_dims.rds"/> + <conditional name="method"> + <param name="method" value="FindMultiModalNeighbors"/> + <param name="reduction_1" value="pca"/> + <param name="dims_1" value="8"/> + <param name="reduction_2" value="apca"/> + <param name="dims_2" value="8"/> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindMultiModalNeighbors"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/multimodalneighbors.rds" ftype="rds" compare="sim_size"/> + </test> + <test expect_num_outputs="2"> + <!-- test3: FindClusters --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/neighbors.rds"/> + <conditional name="method"> + <param name="method" value="FindClusters"/> + <param name="resolution" value="0.8"/> + <conditional name="algorithm"> + <param name="algorithm" value="1"/> + </conditional> + <param name="n_start" value="10"/> + <param name="n_iter" value="10"/> + <param name="random_seed" value="0"/> + <param name="group_singletons" value="TRUE"/> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindClusters"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/clusters.rds" ftype="rds" compare="sim_size"/> + </test> + <test expect_num_outputs="2"> + <!-- test4: FindClusters - leidenalg Installed --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/neighbors.rds"/> + <conditional name="method"> + <param name="method" value="FindClusters"/> + <param name="modularity_fxn" value="1"/> + <param name="resolution" value="0.5"/> + <conditional name="algorithm"> + <param name="algorithm" value="4"/> + <param name="method_cluster" value="matrix"/> + </conditional> + <param name="n_start" value="10"/> + <param name="n_iter" value="10"/> + <param name="random_seed" value="0"/> + <param name="group_singletons" value="TRUE"/> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindClusters"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/clusters_leiden.rds" ftype="rds" compare="sim_size"/> + </test> + <test expect_num_outputs="3"> + <!-- test5: FindAllMarkers --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/clusters.rds"/> + <conditional name="method"> + <param name="method" value="FindAllMarkers"/> + <param name="logfc_threshold" value="0.1"/> + <param name="slot" value="data"/> + <conditional name="test_use"> + <param name="test_use" value="wilcox"/> + </conditional> + <conditional name="set_top_markers"> + <param name="set_top_markers" value="true"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindAllMarkers"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/allmarkers.rds" ftype="rds"/> + <output name="markers_tabular" location="https://zenodo.org/records/13732784/files/allmarkers.csv" ftype="csv"> + <assert_contents> + <has_text_matching expression="avg_log2FC"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="3"> + <!-- test6: FindMarkers - Default --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/clusters.rds"/> + <conditional name="method"> + <param name="method" value="FindMarkers"/> + <param name="slot" value="data"/> + <conditional name="cells"> + <param name="cells" value="false"/> + </conditional> + <conditional name="ident"> + <param name="ident" value="true"/> + <param name="ident_1" value="0"/> + <param name="ident_2" value="1"/> + </conditional> + <param name="logfc_threshold" value="0.1"/> + <conditional name="test_use"> + <param name="test_use" value="wilcox"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindMarkers"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/markers.rds" ftype="rds"/> + <output name="markers_tabular" location="https://zenodo.org/records/13732784/files/markers.csv" ftype="csv"> + <assert_contents> + <has_text_matching expression="avg_log2FC"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="3"> + <!-- test7: FindMarkers - Limma Installed --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/clusters.rds"/> + <conditional name="method"> + <param name="method" value="FindMarkers"/> + <param name="slot" value="data"/> + <conditional name="cells"> + <param name="cells" value="false"/> + </conditional> + <conditional name="ident"> + <param name="ident" value="true"/> + <param name="ident_1" value="0"/> + <param name="ident_2" value="1"/> + </conditional> + <param name="logfc_threshold" value="0.1"/> + <conditional name="test_use"> + <param name="test_use" value="wilcox_limma"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindMarkers"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/markersLimma.rds" ftype="rds"/> + <output name="markers_tabular" location="https://zenodo.org/records/13732784/files/markersLimma.csv" ftype="csv"> + <assert_contents> + <has_text_matching expression="avg_log2FC"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="3"> + <!-- test8: FindMarkers - MAST Installed --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/clusters.rds"/> + <conditional name="method"> + <param name="method" value="FindMarkers"/> + <param name="slot" value="data"/> + <conditional name="cells"> + <param name="cells" value="false"/> + </conditional> + <conditional name="ident"> + <param name="ident" value="true"/> + <param name="ident_1" value="0"/> + <param name="ident_2" value="1"/> + </conditional> + <param name="logfc_threshold" value="0.1"/> + <conditional name="test_use"> + <param name="test_use" value="MAST"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindMarkers"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/markersMAST.rds" ftype="rds"/> + <output name="markers_tabular" location="https://zenodo.org/records/13732784/files/markersMAST.csv" ftype="csv"> + <assert_contents> + <has_text_matching expression="avg_log2FC"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="3"> + <!-- test9: FindMarkers - DESeq2 Installed --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/clusters.rds"/> + <conditional name="method"> + <param name="method" value="FindMarkers"/> + <param name="slot" value="counts"/> + <conditional name="cells"> + <param name="cells" value="false"/> + </conditional> + <conditional name="ident"> + <param name="ident" value="true"/> + <param name="ident_1" value="0"/> + <param name="ident_2" value="1"/> + </conditional> + <param name="logfc_threshold" value="0.1"/> + <conditional name="test_use"> + <param name="test_use" value="DESeq2"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindMarkers"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/markersDESeq2.rds" ftype="rds"/> + <output name="markers_tabular" location="https://zenodo.org/records/13732784/files/markersDESeq2.csv" ftype="csv"> + <assert_contents> + <has_text_matching expression="avg_log2FC"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="3"> + <!-- test10: FindConservedMarkers --> + <param name="seurat_rds" location="https://zenodo.org/records/13732784/files/integrated_umap.rds"/> + <conditional name="method"> + <param name="method" value="FindConservedMarkers"/> + <param name="ident_1" value="0"/> + <param name="ident_2" value="1"/> + <param name="grouping_var" value="Group"/> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="FindConservedMarkers"/> + </assert_contents> + </output> + <output name="rds_out" location="https://zenodo.org/records/13732784/files/conserved_markers.rds" ftype="rds"/> + <output name="markers_tabular" location="https://zenodo.org/records/13732784/files/conserved_markers.csv" ftype="csv"> + <assert_contents> + <has_text_matching expression="Group_B_avg_log2FC"/> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ +Seurat +====== + +Seurat is an R package designed for QC, analysis, and exploration of single-cell RNA-seq data. + +Seurat aims to enable users to identify and interpret sources of heterogeneity from single-cell transcriptomic measurements, and to integrate diverse types of single-cell data. + +FindNeighbors +============= + +Compute the k.param nearest neighbors for a given dataset. + +Can also optionally (via compute.SNN), construct a shared nearest neighbor graph by calculating the neighborhood overlap (Jaccard index) between every cell and its k.param nearest neighbors. + +More details on the `seurat documentation +<https://satijalab.org/seurat/reference/findneighbors>`__ + +FindMultiModalNeighbors +======================= + +This function will construct a weighted nearest neighbor (WNN) graph for two modalities (e.g. RNA-seq and CITE-seq). For each cell, we identify the nearest neighbors based on a weighted combination of two modalities. + +Takes as input two dimensional reductions, one computed for each modality. + +More details on the `seurat documentation +<https://satijalab.org/seurat/reference/findmultimodalneighbors>`__ + +FindClusters +============ + +Identify clusters of cells by a shared nearest neighbor (SNN) modularity optimization based clustering algorithm. + +First calculate k-nearest neighbors and construct the SNN graph. Then optimize the modularity function to determine clusters. + +More details on the `seurat documentation +<https://satijalab.org/seurat/reference/findclusters>`__ + + +FindAllMarkers +============== + +Find markers (differentially expressed genes) for each of the identity classes in a dataset + +Outputs a matrix containing a ranked list of putative markers, and associated statistics (p-values, ROC score, etc.) + +Methods: + +"wilcox" : Identifies differentially expressed genes between two groups of cells using a Wilcoxon Rank Sum test (default); will use a fast implementation by Presto if installed + +"wilcox_limma" : Identifies differentially expressed genes between two groups of cells using the limma implementation of the Wilcoxon Rank Sum test; set this option to reproduce results from Seurat v4 + +"bimod" : Likelihood-ratio test for single cell gene expression, (McDavid et al., Bioinformatics, 2013) + +"roc" : Identifies 'markers' of gene expression using ROC analysis. For each gene, evaluates (using AUC) a classifier built on that gene alone, to classify between two groups of cells. An AUC value of 1 means that expression values for this gene alone can perfectly classify the two groupings (i.e. Each of the cells in cells.1 exhibit a higher level than each of the cells in cells.2). An AUC value of 0 also means there is perfect classification, but in the other direction. A value of 0.5 implies that the gene has no predictive power to classify the two groups. Returns a 'predictive power' (abs(AUC-0.5) * 2) ranked matrix of putative differentially expressed genes. + +"t" : Identify differentially expressed genes between two groups of cells using Student's t-test. + +"negbinom" : Identifies differentially expressed genes between two groups of cells using a negative binomial generalized linear model. Use only for UMI-based datasets + +"poisson" : Identifies differentially expressed genes between two groups of cells using a poisson generalized linear model. Use only for UMI-based datasets + +"LR" : Uses a logistic regression framework to determine differentially expressed genes. Constructs a logistic regression model predicting group membership based on each feature individually and compares this to a null model with a likelihood ratio test. + +"MAST" : Identifies differentially expressed genes between two groups of cells using a hurdle model tailored to scRNA-seq data. Utilizes the MAST package to run the DE testing. + +"DESeq2" : Identifies differentially expressed genes between two groups of cells based on a model using DESeq2 which uses a negative binomial distribution (Love et al, Genome Biology, 2014).This test does not support pre-filtering of genes based on average difference (or percent detection rate) between cell groups. However, genes may be pre-filtered based on their minimum detection rate (min.pct) across both cell groups. + +More details on the `seurat documentation +<https://satijalab.org/seurat/reference/findallmarkers>`__ + +FindMarkers +=========== + +Find markers (differentially expressed genes) for identity classes (clusters) or groups of cells + +Outputs a data.frame with a ranked list of putative markers as rows, and associated statistics as columns (p-values, ROC score, etc., depending on the test used (test.use)). + +Methods - as for FindAllMarkers + +More details on the `seurat documentation +<https://satijalab.org/seurat/reference/findmarkers>`__ + +FindConservedMarkers +==================== + +Finds markers that are conserved between the groups + +Uses metap::minimump as meta.method. + +More details on the `seurat documentation +<https://satijalab.org/seurat/reference/findconservedmarkers>`__ + + ]]></help> + <expand macro="citations"/> +</tool> \ No newline at end of file