Mercurial > repos > iuc > snapatac2_peaks_and_motif
changeset 5:02a7162fc510 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/snapatac2 commit e0f59fae19e57f54ae0c351a16dd1805d12aba1d
| author | iuc |
|---|---|
| date | Tue, 25 Nov 2025 16:41:19 +0000 |
| parents | 64fa083411f1 |
| children | |
| files | macros.xml peaks_and_motif_analysis.xml test-data/all_fasta.loc test-data/chr21.gff3.gz test-data/chr21_small.fasta.gz test-data/cisBP_human.meme.gz test-data/gene_sets.loc test-data/meme.loc tool-data/all_fasta.loc.sample tool-data/gene_sets.loc.sample tool-data/meme.loc.sample tool_data_table_conf.xml.sample tool_data_table_conf.xml.test |
| diffstat | 13 files changed, 629 insertions(+), 255 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Thu Nov 07 13:07:55 2024 +0000 +++ b/macros.xml Tue Nov 25 16:41:19 2025 +0000 @@ -1,7 +1,7 @@ <macros> - <token name="@TOOL_VERSION@">2.6.4</token> - <token name="@VERSION_SUFFIX@">1</token> - <token name="@PROFILE@">23.0</token> + <token name="@TOOL_VERSION@">2.8.0</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@PROFILE@">24.0</token> <xml name="xrefs"> <xrefs> <xref type="bio.tools">snapatac</xref> @@ -9,168 +9,74 @@ </xml> <xml name="requirements"> <requirement type="package" version="@TOOL_VERSION@">snapatac2</requirement> - <requirement type="package" version="5.22.0">plotly</requirement> - <requirement type="package" version="0.2.1">python-kaleido</requirement> - <requirement type="package" version="1.1.0">polars</requirement> - <requirement type="package" version="16.1.0">pyarrow</requirement> - <requirement type="package" version="0.11.6">python-igraph</requirement> - <requirement type="package" version="0.8.37">hdbscan</requirement> - <requirement type="package" version="0.0.10">harmonypy</requirement> - <requirement type="package" version="1.7.4">scanorama</requirement> - <requirement type="package" version="3.0.1">macs3</requirement> - <requirement type="package" version="0.70.16">multiprocess</requirement> - <requirement type="package" version="0.10.2">leidenalg</requirement> + <requirement type="package" version="0.8.37">hdbscan</requirement> + <requirement type="package" version="0.10.2">leidenalg</requirement> + <requirement type="package" version="0.5.7">umap-learn</requirement> + <requirement type="package" version="3.0.4">xgboost</requirement> + <requirement type="package" version="0.2.1">python-kaleido</requirement> + <requirement type="package" version="1.31.0">polars</requirement> + <requirement type="package" version="5.24.1">plotly</requirement> + <requirement type="package" version="0.2.1">python-kaleido</requirement> + <requirement type="package" version="0.0.10">harmonypy</requirement> + <requirement type="package" version="1.7.4">scanorama</requirement> <yield /> </xml> - <token name="@PREP_ADATA@"><![CDATA[ + <!-- command section --> + <token name="@CMD_PREP_ADATA@"><![CDATA[ + ## ln -s does not work here cp '$method.adata' 'anndata.h5ad' && - ]]> - </token> - + ]]></token> <token name="@CMD@"><![CDATA[ cat '$script_file' > '$hidden_output' && python '$script_file' >> '$hidden_output' && touch 'anndata_info.txt' && - cat 'anndata_info.txt' @CMD_prettify_stdout@ - ]]> - </token> - - <token name="@CMD_prettify_stdout@"><![CDATA[ | sed -r '1 s|AnnData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g" | sed -r 's|^\s*(.*):\s(.*)|[\1]\n- \2|g' | sed 's|, |\n- |g' + cat 'anndata_info.txt' @CMD_PRETTIFY_STDOUT@ + ]]></token> + <token name="@CMD_PRETTIFY_STDOUT@"><![CDATA[ + | sed -r '1 s|AnnData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g" | sed -r 's|^\s*(.*):\s(.*)|[\1]\n- \2|g' | sed 's|, |\n- |g' + ]]></token> + <token name="@CMD_GET_GFF@"><![CDATA[ + #if $method.gff_file_condi.gffSource == 'cached': + ln -s '$method.gff_file_condi.gff_pre_installed.fields.path' gff && + #else: + ln -s '$method.gff_file_condi.gff_history' gff && + #end if + ]]></token> + <token name="@CMD_GET_FASTA@"><![CDATA[ + #if $method.fasta_file_condi.fastaSource == 'indexed': + zcat '$method.fasta_file_condi.fasta_pre_installed.fields.path' > fasta.fa && + echo "Using built-in FASTA: '$method.fasta_file_condi.fasta_pre_installed.fields.name'" >&2 && + #else: + #if $method.fasta_file_condi.fasta_history.ext.endswith('.gz') + zcat '$method.fasta_file_condi.fasta_history' > fasta.fa && + #else: + ln -s '$method.fasta_file_condi.fasta_history' fasta.fa && + #end if + #end if ]]></token> - <token name="@CMD_imports@"><![CDATA[ -import snapatac2 as sa + <!-- Config section --> + <token name="@CONF_IMPORTS@"><![CDATA[ +import snapatac2 as snap import os - ]]> - </token> - <xml name="sanitize_query" token_validinitial="string.printable"> - <sanitizer> - <valid initial="@VALIDINITIAL@"> - <remove value="'" /> - </valid> - </sanitizer> - </xml> - - <xml name="inputs_anndata"> - <param name="adata" type="data" format="h5ad" label="Annotated data matrix"/> - </xml> - - <token name="@CMD_read_inputs@"><![CDATA[ - -adata = sa.read('anndata.h5ad', backed = None) -]]> - </token> - - <xml name="dimentions_plot"> - <param argument="width" type="integer" value="500" label="Width of the plot"/> - <param argument="height" type="integer" value="400" label="Height of the plot"/> - </xml> - - <xml name="param_groupby"> - <param argument="groupby" type="text" label="The key of the observation grouping to consider"> - <expand macro="sanitize_query" /> - </param> - </xml> - - <xml name="out_file"> - <param name="out_file" type="select" optional="true" label="Type of output plot"> - <option value="png" selected="true">PNG</option> - <option value="svg">SVG</option> - <option value="pdf">PDF</option> - </param> - </xml> - <token name="@CMD_anndata_write_outputs@"><![CDATA[ -adata.write('anndata.h5ad') + ]]></token> + <token name="@CONF_READ_INPUTS@"><![CDATA[ +adata = snap.read('anndata.h5ad', backed = None) + ]]></token> + <token name="@CONF_ANNDATA_WRITE_OUTPUTS@"><![CDATA[ +adata.write_h5ad('anndata.h5ad.gz', compression='gzip') with open('anndata_info.txt','w', encoding='utf-8') as ainfo: print(adata, file=ainfo) -]]> - </token> - <xml name="inputs_common_advanced"> - <section name="advanced_common" title="Advanced Options" expanded="false"> - <param name="show_log" type="boolean" checked="false" label="Output Log?" /> - </section> - </xml> - <xml name="params_render_plot"> - <param argument="width" type="integer" value="600" label="Width of the plot"/> - <param argument="height" type="integer" value="400" label="Height of the plot"/> - <expand macro="out_file"/> - </xml> - <xml name="param_shift"> - <param argument="shift_left" type="integer" value="4" label="Insertion site correction for the left end" help="Note this has no effect on single-end reads"/> - <param argument="shift_right" type="integer" value="-5" label="Insertion site correction for the right end" help="Note this has no effect on single-end reads"/> - </xml> - <xml name="param_chunk_size" tokens="size"> - <param argument="chunk_size" type="integer" value="@SIZE@" label="chunk size"/> - </xml> - <xml name="min_max_frag_size"> - <param argument="min_frag_size" type="integer" optional="true" value="" label="Minimum fragment size to include"/> - <param argument="max_frag_size" type="integer" optional="true" value="" label="Maximum fragment size to include"/> - </xml> - <xml name="params_data_integration"> - <param argument="use_rep" type="text" value="X_spectral" label="The key for the matrix"/> - <param argument="use_dims" type="text" optional="true" value="" label="The dimensions used for computation"> - <expand macro="sanitize_query"/> - </param> - <param argument="groupby" type="text" optional="true" value="" label="The key of the observation grouping to consider"> - <expand macro="sanitize_query" /> - </param> - <param argument="key_added" type="text" optional="true" value="" label="If specified, add the result to adata.obsm with this key"/> - </xml> - <xml name="param_n_comps"> - <param argument="n_comps" type="integer" value="30" label="Number of dimensions to keep" help="The result is insensitive to this parameter when `weighted_by_sd` is set, as long as it is large enough, e.g. 30."/> - </xml> - <xml name="param_random_state"> - <param argument="random_state" type="integer" value="0" label="Seed of the random state generator"/> - </xml> - <xml name="param_key_added" tokens="key_added"> - <param argument="key_added" type="text" value="@KEY_ADDED@" label="`adata.obs` key under which t add cluster labels"/> - </xml> - <xml name="param_use_rep"> - <param argument="use_rep" type="text" value="X_spectral" label="Use the indicated representation in `.obsm`"/> - </xml> - <xml name="genome_fasta"> - <param argument="genome_fasta" type="text" label="A fasta file containing the genome sequences or a Genome object"/> - </xml> - <xml name="background"> - <param argument="background" type="text" optional="true" value="" label="A list of regions to be used as the background"> - <expand macro="sanitize_query"/> - </param> - </xml> - <xml name="mat"> - <param argument="peak_mat" type="data" format="h5ad" optional="true" label="AnnData or AnnDataSet object storing the cell by peak count matrix"/> - <param argument="gene_mat" type="data" format="h5ad" optional="true" label="AnnData or AnnDataSet object storing the cell by gene count matrix"/> - </xml> - <xml name="param_network"> - <param argument="network" type="text" label="network"/> - </xml> - <xml name="param_n_iterations"> - <param argument="n_iterations" type="integer" value="-1" label="How many iterations of the Leiden clustering algorithm to perform" - help="Positive values above 2 define the total number of iterations to perform, -1 has the algorithm run until it reaches its optimal clustering."/> - </xml> - - <xml name="citations"> - <citations> - <citation type="doi">10.1038/s41592-023-02139-9</citation> - </citations> - </xml> - <xml name="render_plot_test"> - <param name="width" value="650"/> - <param name="height" value="450"/> - </xml> - <xml name="render_plot_matching_text"> - <has_text_matching expression="width = 650"/> - <has_text_matching expression="height = 450"/> - </xml> - <xml name="param_counting_strategy"> - <param argument="counting_strategy" type="select" label="The strategy to compute feature counts"> - <option value="fragment">"fragment": based on the number of fragments that overlap with a region of interest</option> - <option value="insertion" selected="true">"insertion": based on the number of insertions that overlap with a region of interest</option> - <option value="paired-insertion">"paired-insertion": similar to "insertion", but it only counts the insertions once if the pair of insertions of a fragment are both within the same region of interest</option> - </param> - </xml> - - <token name="@CMD_params_data_integration@"><![CDATA[ + ]]></token> + <token name="@CONF_PARAMS_RENDER_PLOT@"><![CDATA[ + width = $method.width, + height = $method.height, + show = False, + interactive = False, + out_file = 'plot.$method.out_file', + ]]></token> + <token name="@CONF_PARAMS_DATA_INTEGRATION@"><![CDATA[ use_rep = '$method.use_rep', #if $method.use_dims != '' #set $dims = ([x.strip() for x in str($method.use_dims).split(',')]) @@ -183,13 +89,168 @@ #if $method.key_added != '' key_added = '$method.key_added', #end if - ]]> - </token> + ]]></token> + <token name="@CONF_IMPORT_MEME@"><![CDATA[ +motifs = read_motifs("input.meme") +for motif in motifs: + motif.name = motif.id.split('+')[0] + +unique_motifs = {} +for motif in motifs: + name = motif.name + if ( + name not in unique_motifs or + unique_motifs[name].info_content() < motif.info_content() + ): + unique_motifs[name] = motif +motifs = list(unique_motifs.values()) + + +#else: +motifs = read_motifs("input.meme") +for motif in motifs: + motif.name = motif.id.split('_')[0] + motif.family = motif.id.split('+')[-1] + ]]></token> + + <!-- input section --> + <xml name="sanitize_query" token_validinitial="string.printable"> + <sanitizer> + <valid initial="@VALIDINITIAL@"> + <remove value="'" /> + <yield/> + </valid> + </sanitizer> + </xml> - <token name="@CMD_params_render_plot@"><![CDATA[ - width = $method.width, - height = $method.height, - out_file = 'plot.$method.out_file', - ]]> - </token> + <xml name="param_inputs_anndata" token_multiple="false" token_label="Annotated data matrix"> + <param name="adata" type="data" multiple="@MULTIPLE@" format="h5ad" label="@LABEL@"/> + </xml> + <xml name="param_groupby"> + <param argument="groupby" type="text" label="The key of the observation grouping to consider"> + <expand macro="sanitize_query" /> + </param> + </xml> + <xml name="param_common_advanced"> + <section name="advanced_common" title="Advanced Options" expanded="false"> + <param name="show_log" type="boolean" checked="false" label="Output Log?" /> + </section> + </xml> + <xml name="param_render_plot"> + <param argument="width" type="integer" value="600" label="Width of the plot"/> + <param argument="height" type="integer" value="400" label="Height of the plot"/> + <param name="out_file" type="select" optional="true" label="Type of output plot"> + <option value="png" selected="true">PNG</option> + <option value="svg">SVG</option> + <option value="pdf">PDF</option> + <option value="html">HTML</option> + </param> + </xml> + <xml name="param_shift" tokens="varname" token_value="0" token_label="Insertion site correction for the left end"> + <param argument="@VARNAME@" type="integer" value="@VALUE@" label="@LABEL@" help="Note this has no effect on single-end reads"/> + </xml> + <xml name="param_chunk_size" tokens="size"> + <param argument="chunk_size" type="integer" value="@SIZE@" label="chunk size"/> + </xml> + <xml name="param_min_max_frag_size"> + <param argument="min_frag_size" type="integer" optional="true" value="" label="Minimum fragment size to include"/> + <param argument="max_frag_size" type="integer" optional="true" value="" label="Maximum fragment size to include"/> + </xml> + <xml name="param_data_integration"> + <param argument="use_rep" type="text" value="X_spectral" label="The key for the matrix"/> + <param argument="use_dims" type="text" optional="true" value="" label="The dimensions used for computation"> + <expand macro="sanitize_query"/> + </param> + <param argument="groupby" type="text" optional="true" value="" label="The key of the observation grouping to consider"> + <expand macro="sanitize_query" /> + </param> + <param argument="key_added" type="text" optional="true" value="" label="If specified, add the result to adata.obsm with this key"/> + </xml> + <xml name="param_random_state" token_label="Seed of the random state generator" token_help=""> + <param argument="random_state" type="integer" value="0" label="@LABEL@" help="@HELP@"/> + </xml> + <xml name="param_key_added" tokens="key_added"> + <param argument="key_added" type="text" value="@KEY_ADDED@" label="`adata.obs` key under which t add cluster labels"/> + </xml> + <xml name="param_use_rep" token_label="Use the indicated representation in `.obsm`"> + <param argument="use_rep" type="text" value="X_spectral" label="@LABEL@"/> + </xml> + <xml name="param_n_iterations"> + <param argument="n_iterations" type="integer" value="-1" label="How many iterations of the Leiden clustering algorithm to perform" + help="Positive values above 2 define the total number of iterations to perform, -1 has the algorithm run until it reaches its optimal clustering."/> + </xml> + <xml name="param_counting_strategy"> + <param argument="counting_strategy" type="select" label="The strategy to compute feature counts"> + <option value="fragment">"fragment": based on the number of fragments that overlap with a region of interest</option> + <option value="insertion">"insertion": based on the number of insertions that overlap with a region of interest</option> + <option value="paired-insertion" selected="true">"paired-insertion": similar to "insertion", but it only counts the insertions once if the pair of insertions of a fragment are both within the same region of interest</option> + </param> + </xml> + <xml name="param_chrom_sizes"> + <param argument="chrom_sizes" type="data" format="tabular" label="Chromosome sizes" help="First column the chromosome name and second column the size"/> + </xml> + <xml name="param_genome_fasta"> + <conditional name="fasta_file_condi"> + <param name="fastaSource" type="select" label="Select a built-in FASTA or one from your history" help="Choose history if you don't see the correct FASTA."> + <option value="indexed" selected="true">Use a built-in FASTA</option> + <option value="history">Use a FASTA from history</option> + </param> + <when value="indexed"> + <param name="fasta_pre_installed" type="select" label="Select a FASTA file" help="Select the FASTA file from a list of pre-installed genomes"> + <options from_data_table="all_fasta"> + <filter type="sort_by" column="2" /> + </options> + </param> + </when> + <when value="history"> + <param name="fasta_history" type="data" format="fasta,fasta.gz" label="FASTA file" /> + </when> + </conditional> + </xml> + <xml name="param_gene_anno"> + <conditional name="gff_file_condi"> + <param name="gffSource" type="select" label="Select a built-in GFF file or one from your history" help="Choose history if you don't see the correct GFF" > + <option value="cached" selected="true">Use a built-in GFF</option> + <option value="history">Use a GFF from history</option> + </param> + <when value="cached"> + <param name="gff_pre_installed" type="select" label="Select a GFF file" help="Select the GFF from a list of pre-installed files"> + <options from_data_table="gene_sets"> + <filter type="sort_by" column="1" /> + </options> + </param> + </when> + <when value="history"> + <param name="gff_history" type="data" format="gff3.gz" label="Select a GFF file" help="Make sure that the GFF corresponds to the same genome as the FASTA"/> + </when> + </conditional> + </xml> + <xml name="param_n_comps" token_value="30" token_label="Number of dimensions to keep" token_help="The result is insensitive to this parameter when `weighted_by_sd` is set, as long as it is large enough, e.g. 30."> + <param argument="n_comps" type="integer" value="@VALUE@" label="@LABEL@" help="@HELP@"/> + </xml> + <xml name="param_meme_table"> + <param name="motifs" type="select" label="Select list of transcription factor motifs"> + <options from_data_table="meme"> + <filter type="sort_by" column="2" /> + </options> + </param> + </xml> + + + <!-- test section --> + <xml name="test_param_render_plot"> + <param name="width" value="650"/> + <param name="height" value="450"/> + </xml> + <xml name="test_render_plot_matching_text"> + <has_text_matching expression="width = 650"/> + <has_text_matching expression="height = 450"/> + </xml> + + + <xml name="citations"> + <citations> + <citation type="doi">10.1038/s41592-023-02139-9</citation> + </citations> + </xml> </macros>
--- a/peaks_and_motif_analysis.xml Thu Nov 07 13:07:55 2024 +0000 +++ b/peaks_and_motif_analysis.xml Tue Nov 25 16:41:19 2025 +0000 @@ -9,22 +9,34 @@ </requirements> <command detect_errors="exit_code"><![CDATA[ export NUMBA_CACHE_DIR="\${TEMP:-/tmp}"; -@PREP_ADATA@ +#if $method.method == 'tl.marker_regions' and str($method.enrichment_condi.motif_enrichment) == "yes": + gunzip -c '$method.enrichment_condi.motifs.fields.path' > 'input.meme' && +#end if +#if $method.method == 'tl.marker_regions' and str($method.enrichment_condi.motif_enrichment) == "yes": +@CMD_GET_FASTA@ +#end if +#if $method.method != 'pp.merge_peaks' +@CMD_PREP_ADATA@ +#end if @CMD@ ]]></command> <configfiles> <configfile name="script_file"><![CDATA[ -@CMD_imports@ -@CMD_read_inputs@ +@CONF_IMPORTS@ +#if $method.method != 'pp.merge_peaks' +@CONF_READ_INPUTS@ +#end if #if $method.method == 'tl.macs3' if __name__ == '__main__': ## a temporary fix https://github.com/kaizhang/SnapATAC2/issues/298 - sa.tl.macs3( + snap.tl.macs3( adata, #if $method.groupby != '' groupby = '$method.groupby', #end if qvalue = $method.qvalue, + call_broad_peaks = $method.call_broad_peaks, + broad_cutoff = $method.broad_cutoff, #if $method.replicate replicate = '$method.replicate', #end if @@ -46,53 +58,86 @@ key_added = '$method.key_added', inplace = True, tempdir = '.', - n_jobs = 1 + n_jobs = 1 ## it is set to 1 to avoid the issues with multiple threads in Galaxy. check here: https://github.com/galaxyproject/tools-iuc/pull/7078#discussion_r2376140575 ) #else if $method.method == 'tl.merge_peaks' -import json import pandas as pd -import csv -with open('$method.chrom_sizes') as f: - chr_sizes = {x[0]:int(x[1]) for x in csv.reader(f, delimiter='\t')} -peaks = sa.tl.merge_peaks( +chrom_sizes = {} +with open('$method.chrom_sizes', 'r') as f: + for line in f: + chrom, size = line.strip().split('\t') + chrom_sizes[chrom] = int(size) + +peaks = snap.tl.merge_peaks( adata.uns['$method.macs_key'], - chrom_sizes = chr_sizes, + chrom_sizes = chrom_sizes, half_width = $method.half_width ) +adata.uns['$method.merged_peaks_key'] = peaks.to_pandas() peaks.write_csv('merged_peaks.tabular', separator = '\t') #else if $method.method == 'pp.make_peak_matrix' -import polars -peaks = polars.read_csv('$method.merged_peaks', separator='\t') -adata = sa.pp.make_peak_matrix( +peak_mat = snap.pp.make_peak_matrix( adata, - use_rep = peaks['Peaks'], + #if $method.peaks_condi.peaks == 'uns' and $method.peaks_condi.use_rep != '' + use_rep = '$method.use_rep', + #end if + #if $method.peaks_condi.peaks == 'bed' and str($method.peaks_condi.peak_file) != 'None' + peak_file = '$method.peak_file', + #end if chunk_size = $method.chunk_size, use_x = $method.use_x, - #if $method.min_frag_size + #if $method.max_frag_size min_frag_size = $method.min_frag_size, #end if #if $method.max_frag_size max_frag_size = $method.max_frag_size, #end if - counting_strategy = '$method.counting_strategy' + counting_strategy = '$method.counting_strategy', + value_type = '$method.value_type', + summary_type = '$method.summary_type' ) +adata = peak_mat.copy() +del peak_mat #else if $method.method == 'tl.marker_regions' -marker_peaks = sa.tl.marker_regions( +marker_peaks = snap.tl.marker_regions( adata, groupby = '$method.groupby', pvalue = $method.pvalue ) -sa.pl.regions( +snap.pl.regions( adata, groupby = '$method.groupby', peaks = marker_peaks, - @CMD_params_render_plot@ + @CONF_PARAMS_RENDER_PLOT@ ) - + #if str($method.enrichment_condi.motif_enrichment) == "yes" +## import motifs +from snapatac2._snapatac2 import read_motifs, PyDNAMotif +#if $method.enrichment_condi.motifs == 'cisbp': +@CONF_IMPORT_MEME@ +#end if +motifs = snap.tl.motif_enrichment( + motifs = motifs, + regions = marker_peaks, + genome_fasta = 'fasta.fa', + background = None, # will update if requested + method = None # automatic based on background +) +snap.pl.motif_enrichment( + enrichment = motifs, + min_log_fc = $method.enrichment_condi.min_log_fc, + max_fdr = $method.enrichment_condi.max_fdr, + width = $method.enrichment_condi.width, + height = $method.enrichment_condi.height, + show = False, + interactive = False, + out_file = 'plot_enrichment.$method.enrichment_condi.out_file', +) + #end if #else if $method.method == 'tl.diff_test' import numpy as np @@ -121,7 +166,7 @@ peaks_selected = peaks[group1].to_numpy() #end if -diff_peaks = sa.tl.diff_test( +diff_peaks = snap.tl.diff_test( adata, cell_group1 = group1_cells, cell_group2 = group2_cells, @@ -145,15 +190,17 @@ } #end if -sa.pl.regions( +snap.pl.regions( adata, groupby = group_key, peaks = peaks_to_plot, - @CMD_params_render_plot@ + @CONF_PARAMS_RENDER_PLOT@ ) #end if -@CMD_anndata_write_outputs@ +#if $method.method != 'pp.merge_peaks' and $method.method != 'tl.marker_regions' and $method.method != 'tl.diff_test' +@CONF_ANNDATA_WRITE_OUTPUTS@ +#end if ]]></configfile> </configfiles> <inputs> @@ -166,9 +213,11 @@ <option value="tl.diff_test">Identify differentially accessible regions,using 'tl.diff_test'</option> </param> <when value="tl.macs3"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param argument="groupby" type="text" value="" optional="true" label="Group cells before peak calling based on key in `.obs`"/> <param argument="qvalue" type="float" value="0.05" label="qvalue cutoff used in MACS3"/> + <param argument="call_broad_peaks" type="boolean" checked="false" truevalue="True" falsevalue="False" label="If True, MACS3 will call broad peaks"/> + <param argument="broad_cutoff" type="float" value="0.1" label="qvalue cutoff used in MACS3 for calling broad peaks"/> <param argument="replicate" type="text" value="" optional="true" label="Replicate information based on key in `.obs`"/> <param argument="replicate_qvalue" type="float" value="" optional="true" label="qvalue cutoff used in MACS3 for calling peaks in replicates"/> <param argument="max_frag_size" type="integer" value="" optional="true" label="Maximum fragment size" @@ -182,30 +231,63 @@ <param argument="key_added" type="text" value="macs3" label="`.uns` key under which to add peak information"/> </when> <when value="tl.merge_peaks"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param name="macs_key" type="text" value="macs3" label="`.uns` key under which peak information was added while peak calling"/> - <param argument="chrom_sizes" type="data" format="tabular" label="Chromosome sizes"/> + <param name="merged_peaks_key" type="text" value="macs3_merged" label="`.uns` key under which merged peak information will be added. This can be used later for pp.make_peak_matrix"/> + <expand macro="param_chrom_sizes"/> <param argument="half_width" type="integer" value="250" label="Half width of the merged peaks"/> </when> <when value="pp.make_peak_matrix"> - <expand macro="inputs_anndata"/> - <param argument="use_rep" type="text" optional="true" value="" label="Used to read peak information from .uns[use_rep]"> - <expand macro="sanitize_query"/> + <expand macro="param_inputs_anndata"/> + <conditional name="peaks_condi"> + <param name="peaks" type="select" label="Use peaks from a bed file or a key in .uns" help="To save the peaks in a key in `.uns`, you can use 'tl.merge_peaks' first to generate merged peaks and save them in a key in `.uns`."> + <option value="uns">Key in `.uns`</option> + <option value="bed">Bed file</option> + </param> + <when value="uns"> + <param argument="use_rep" type="text" value="" optional="true" label="Used to read peak information from .uns"/> + </when> + <when value="bed"> + <param argument="peak_file" type="data" format="bed" optional="true" label="Bed file containing the peaks"/> + </when> + </conditional> + <expand macro="param_chunk_size" size="500"/> + <param argument="use_x" type="boolean" truevalue="True" falsevalue="False" checked="false" label="If True, use the matrix stored in .X as raw counts. Otherwise the .obsm['insertion'] is used."/> + <expand macro="param_min_max_frag_size"/> + <expand macro="param_counting_strategy"/> + <param argument="value_type" type="select" label="Value type" help="Only available when data is imported using import_values"> + <option value="target">Number of methylated bases</option> + <option value="total">Number of methylated bases plus unmethylated bases</option> + <option value="fraction">The fraction of methylated bases</option> </param> - <param argument="merged_peaks" type="data" format="tabular" label="Merged peaks file"/> - <expand macro="param_chunk_size" size="500"/> - <param argument="use_x" type="boolean" truevalue="True" falsevalue="False" checked="false" label="If True, use the matrix stored in .X as raw counts"/> - <expand macro="min_max_frag_size"/> - <expand macro="param_counting_strategy"/> + <param argument="summary_type" type="select" label="Summary type" help="Only available when data is imported using import_values"> + <option value="sum">Sum</option> + <option value="mean">Mean</option> + </param> </when> <when value="tl.marker_regions"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <expand macro="param_groupby"/> <param argument="pvalue" type="float" value="0.01" label="P-value threshold"/> - <expand macro="params_render_plot"/> + <expand macro="param_render_plot"/> + <conditional name="enrichment_condi"> + <param name="motif_enrichment" type="select" label="Perform motif enrichment analysis?"> + <option value="yes">Yes</option> + <option value="no">No</option> + </param> + <when value="yes"> + <expand macro="param_meme_table"/> + <expand macro="param_genome_fasta"/> + <param argument="--min_log_fc" type="float" value="1" label="Retain motifs with log2-fold-change more than min_log_fc"/> + <param argument="--max_fdr" type="float" min="0.0" value="0.01" label="Retain motifs with FDR less than max_fdr"/> + <expand macro="param_render_plot"/> + </when> + <when value="no"> + </when> + </conditional> </when> <when value="tl.diff_test"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param argument="merged_peaks" type="data" format="tabular" label="Merged peaks file"/> <param name="group_key" type="text" value="cell_type" label="key in `.obs` to select cell groups" help="for eg. cell_type"/> <conditional name="compare"> @@ -214,12 +296,12 @@ <option value="background_group">Background cell group built from random selection of cells from all other the groups</option> </param> <when value="single_group"> - <param name="group1_value" type="text" value="Naive B" label="name of the group 1 stored in .obs"/> - <param name="group2_value" type="text" value="Memory B" label="name of the group 2 stored in .obs"/> + <param name="group1_value" type="text" value="" optional="false" label="name of the group 1 stored in .obs"/> + <param name="group2_value" type="text" value="" optional="false" label="name of the group 2 stored in .obs"/> </when> <when value="background_group"> - <param name="group1_value" type="text" value="Naive B" label="name of the group 1 stored in .obs"/> - <param name="number_of_cells" type="integer" min="1" value="30" label="Number of cells to subsample from ther other groups"/> + <param name="group1_value" type="text" value="" optional="false" label="name of the group 1 stored in .obs"/> + <param name="number_of_cells" type="integer" min="1" value="30" label="Number of cells to subsample from the other groups"/> </when> </conditional> <param argument="direction" type="select" label="“positive”: return features that are enriched in group 1. “negative”: return features that are enriched in group 2"> @@ -229,15 +311,17 @@ </param> <param argument="min_log_fc" type="float" value="0.25" label="Limit testing to features which show, on average, at least this difference (log2-scale) between the two groups of cells"/> <param argument="min_pct" type="float" value="0.05" label="Only test features that are detected in a minimum fraction of min_pct cells in either of the two population"/> - <expand macro="params_render_plot"/> + <expand macro="param_render_plot"/> <param name="cutoff_p_adj" type="float" value="0.01" label="Adjusted p-value cutoff for plotting" help="This cutoff is applied for plotting only"/> <param name="cutoff_l2fc" type="float" value="1" label="Log2 fold change cutoff for plotting" help="This cutoff is applied for plotting only"/> </when> </conditional> - <expand macro="inputs_common_advanced"/> + <expand macro="param_common_advanced"/> </inputs> <outputs> - <data name="anndata_out" format="h5ad" from_work_dir="anndata.h5ad" label="${tool.name} (${method.method}) on ${on_string}: Annotated data matrix"/> + <data name="anndata_out" format="h5ad" from_work_dir="anndata.h5ad.gz" label="${tool.name} (${method.method}) on ${on_string}: Annotated data matrix"> + <filter>method['method'] != 'tl.marker_regions' and method['method'] != 'tl.diff_test'</filter> + </data> <data name="hidden_output" format="txt" label="Log file" > <filter>advanced_common['show_log']</filter> </data> @@ -253,6 +337,21 @@ <data name="out_svg" format="svg" from_work_dir="plot.svg" label="SVG plot from ${tool.name} (${method.method}) on ${on_string}"> <filter>(method['method'] == 'tl.marker_regions' or method['method'] == 'tl.diff_test') and method['out_file'] == 'svg'</filter> </data> + <data name="out_html" format="html" from_work_dir="plot.html" label="HTML plot from ${tool.name} (${method.method}) on ${on_string}"> + <filter>(method['method'] == 'tl.marker_regions' or method['method'] == 'tl.diff_test') and method['out_file'] == 'html'</filter> + </data> + <data name="out_png_motifs" format="png" from_work_dir="plot_enrichment.png" label="PNG plot from ${tool.name} (${method.method}) on ${on_string} - motif_enrichment"> + <filter>(method['method'] == 'tl.marker_regions' and method['enrichment_condi']['motif_enrichment'] == 'yes') and method['enrichment_condi']['out_file'] == 'png'</filter> + </data> + <data name="out_pdf_motifs" format="pdf" from_work_dir="plot_enrichment.pdf" label="PDF plot from ${tool.name} (${method.method}) on ${on_string} - motif_enrichment"> + <filter>(method['method'] == 'tl.marker_regions' and method['enrichment_condi']['motif_enrichment'] == 'yes') and method['enrichment_condi']['out_file'] == 'pdf'</filter> + </data> + <data name="out_svg_motifs" format="svg" from_work_dir="plot_enrichment.svg" label="SVG plot from ${tool.name} (${method.method}) on ${on_string} - motif_enrichment"> + <filter>(method['method'] == 'tl.marker_regions' and method['enrichment_condi']['motif_enrichment'] == 'yes') and method['enrichment_condi']['out_file'] == 'svg'</filter> + </data> + <data name="out_html_motifs" format="html" from_work_dir="plot_enrichment.html" label="HTML plot from ${tool.name} (${method.method}) on ${on_string} - motif_enrichment"> + <filter>(method['method'] == 'tl.marker_regions' and method['enrichment_condi']['motif_enrichment'] == 'yes') and method['enrichment_condi']['out_file'] == 'html'</filter> + </data> <data name="diff_peaks" format="tabular" from_work_dir="diff_peaks.tabular" label="${tool.name} on ${on_string}: Differential peaks" > <filter>method['method'] == 'tl.diff_test'</filter> </data> @@ -262,7 +361,7 @@ <!-- tl.macs3 --> <conditional name="method"> <param name="method" value="tl.macs3"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.leiden.modularity.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.leiden.modularity.pbmc_500_chr21.h5ad"/> <param name="groupby" value="leiden"/> <param name="qvalue" value="0.1"/> <param name="shift" value="-100"/> @@ -275,7 +374,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.macs3"/> + <has_text_matching expression="snap.tl.macs3"/> <has_text_matching expression="groupby = 'leiden'"/> <has_text_matching expression="qvalue = 0.1"/> <has_text_matching expression="shift = -100"/> @@ -284,14 +383,18 @@ <has_text_matching expression="key_added = 'macs3'"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta="20000" location="https://zenodo.org/records/11260316/files/tl.macs3.pbmc_500_chr21.h5ad"/> + <output name="anndata_out"> + <assert_contents> + <has_h5_keys keys="uns/macs3"/> + </assert_contents> + </output> </test> <test expect_num_outputs="3"> <!-- tl.merge_peaks --> <conditional name="method"> <param name="method" value="tl.merge_peaks"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.macs3.pbmc_500_chr21.h5ad"/> - <param name="chrom_sizes" location="https://zenodo.org/records/11260316/files/chr21_size.tabular"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.macs3.pbmc_500_chr21.h5ad"/> + <param name="chrom_sizes" location="https://zenodo.org/records/17512085/files/chrom_size.tabular"/> <param name="half_width" value="250"/> </conditional> <section name="advanced_common"> @@ -299,11 +402,15 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.merge_peaks"/> + <has_text_matching expression="snap.tl.merge_peaks"/> <has_text_matching expression="half_width = 250"/> </assert_contents> </output> - <output name="anndata_out" location="https://zenodo.org/records/11260316/files/tl.merge_peaks.pbmc_500_chr21.h5ad" ftype="h5ad" compare="sim_size" delta_frac="0.1" /> + <output name="anndata_out"> + <assert_contents> + <has_h5_keys keys="uns/macs3_merged"/> + </assert_contents> + </output> <output name="merged_peaks" > <assert_contents> <has_text_matching expression="chr21:5063027-5063528"/> @@ -315,29 +422,67 @@ </output> </test> <test expect_num_outputs="2"> - <!-- pp.make_peak_matrix --> + <!-- pp.make_peak_matrix with bed--> <conditional name="method"> <param name="method" value="pp.make_peak_matrix"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.merge_peaks.pbmc_500_chr21.h5ad"/> - <param name="merged_peaks" location="https://zenodo.org/records/11260316/files/merged_peaks.tabular"/> - <param name="chunk_size" value="500"/> - <param name="use_x" value="False"/> - <param name="counting_strategy" value="insertion"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl_macs3_merged.h5ad.gz"/> + <conditional name="peaks_condi"> + <param name="peaks" value="bed"/> + <param name="peak_file" location="https://zenodo.org/records/17512085/files/cre_hea.bed"/> </conditional> + </conditional> <section name="advanced_common"> <param name="show_log" value="true" /> </section> + <assert_stdout> + <has_text_matching expression="500 × 1154611"/> + </assert_stdout> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.pp.make_peak_matrix"/> + <has_text_matching expression="snap.pp.make_peak_matrix"/> <has_text_matching expression="chunk_size = 500"/> <has_text_matching expression="use_x = False"/> - <has_text_matching expression="counting_strategy = 'insertion'"/> + </assert_contents> + </output> + <output name="anndata_out"> + <assert_contents> + <has_h5_keys keys="obs/n_fragment"/> </assert_contents> </output> - <output name="anndata_out" location="https://zenodo.org/records/12800783/files/pp.make_peak_matrix.pbmc_500_chr21.h5ad" ftype="h5ad" compare="sim_size" delta_frac="0.1" /> </test> - <test expect_num_outputs="3"> + <test expect_num_outputs="2"> + <!-- pp.make_peak_matrix with uns--> + <conditional name="method"> + <param name="method" value="pp.make_peak_matrix"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl_macs3_merged.h5ad.gz"/> + <conditional name="peaks_condi"> + <param name="peaks" value="uns"/> + <param name="use_rep" value="macs3_merged"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true" /> + </section> + <assert_stdout> + <has_text_matching expression="500 × 110942"/> + </assert_stdout> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="snap.pp.make_peak_matrix"/> + <has_text_matching expression="chunk_size = 500"/> + <has_text_matching expression="use_rep"/> + <has_text_matching expression="macs3_merged"/> + <not_has_text text="peak_file"/> + <has_text_matching expression="use_x = False"/> + </assert_contents> + </output> + <output name="anndata_out"> + <assert_contents> + <has_h5_keys keys="obs/n_fragment"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="2"> <!-- tl.marker_regions --> <conditional name="method"> <param name="method" value="tl.marker_regions"/> @@ -345,29 +490,111 @@ <param name="groupby" value="leiden"/> <param name="pvalue" value="0.1"/> <param name="out_file" value="png"/> - <expand macro="render_plot_test"/> + <expand macro="test_param_render_plot"/> + <conditional name="enrichment_condi"> + <param name="motif_enrichment" value="no"/> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true" /> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="snap.tl.marker_regions"/> + <has_text_matching expression="snap.pl.regions"/> + <has_text_matching expression="groupby = 'leiden'"/> + <has_text_matching expression="pvalue = 0.1"/> + <expand macro="test_render_plot_matching_text"/> + </assert_contents> + </output> + <output name="out_png"> + <assert_contents> + <has_image_center_of_mass center_of_mass="335,220" eps="30"/> + <has_image_channels channels="4"/> + <has_image_height height="450"/> + <has_image_width width="650"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="3"> + <!-- tl.marker_regions + motif_enrichment - history --> + <conditional name="method"> + <param name="method" value="tl.marker_regions"/> + <param name="adata" location="https://zenodo.org/records/12800783/files/pp.make_peak_matrix.pbmc_500_chr21.h5ad"/> + <param name="groupby" value="leiden"/> + <param name="pvalue" value="0.1"/> + <param name="out_file" value="png"/> + <expand macro="test_param_render_plot"/> + <conditional name="enrichment_condi"> + <param name="motif_enrichment" value="yes"/> + <param name="motifs" value="cisbp"/> + <conditional name="fasta_file_condi"> + <param name="fastaSource" value="history"/> + <param name="fasta_history" location="https://zenodo.org/records/17512085/files/chr21.fasta.gz"/> + </conditional> + </conditional> </conditional> <section name="advanced_common"> <param name="show_log" value="true" /> </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.marker_regions"/> - <has_text_matching expression="sa.pl.regions"/> + <has_text_matching expression="snap.tl.marker_regions"/> + <has_text_matching expression="snap.pl.regions"/> <has_text_matching expression="groupby = 'leiden'"/> <has_text_matching expression="pvalue = 0.1"/> - <expand macro="render_plot_matching_text"/> + <expand macro="test_render_plot_matching_text"/> + </assert_contents> + </output> + <output name="out_png"> + <assert_contents> + <has_image_center_of_mass center_of_mass="335,220" eps="30"/> + <has_image_channels channels="4"/> + <has_image_height height="450"/> + <has_image_width width="650"/> + </assert_contents> + </output> + <output name="out_png_motifs"> + <assert_contents> + <has_image_center_of_mass center_of_mass="300,200" eps="50"/> + <has_image_channels channels="4"/> + <has_image_height height="400"/> + <has_image_width width="600"/> </assert_contents> </output> - <output name="anndata_out" location="https://zenodo.org/records/12800783/files/tl.marker_regions.pbmc_500_chr21.h5ad" ftype="h5ad" compare="sim_size" delta_frac="0.1" /> - <output name="out_png" location="https://zenodo.org/records/12800783/files/tl.marker_regions.pbmc_500_chr21.png" ftype="png" compare="sim_size" delta_frac="0.1"/> </test> - <test expect_num_outputs="4"> + <test expect_failure="true"> + <!-- tl.marker_regions + motif_enrichment - cached --> + <conditional name="method"> + <param name="method" value="tl.marker_regions"/> + <param name="adata" location="https://zenodo.org/records/12800783/files/pp.make_peak_matrix.pbmc_500_chr21.h5ad"/> + <param name="groupby" value="leiden"/> + <param name="pvalue" value="0.1"/> + <param name="out_file" value="png"/> + <expand macro="test_param_render_plot"/> + <conditional name="enrichment_condi"> + <param name="motif_enrichment" value="yes"/> + <param name="motifs" value="cisbp"/> + <conditional name="fasta_file_condi"> + <param name="fastaSource" value="indexed"/> + <param name="fasta_pre_installed" value="hg38"/> + </conditional> + </conditional> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true" /> + </section> + <assert_stderr> + <has_text text="Using built-in FASTA: 'Human (hg38)'"/> + <has_text text="NameError: sequence fetch error: expected length: 501, but got 0."/> + </assert_stderr> + </test> + <test expect_num_outputs="3"> <!-- tl.diff_test single_group --> <conditional name="method"> <param name="method" value="tl.diff_test"/> <param name="adata" location="https://zenodo.org/records/12800783/files/tl.marker_regions.pbmc_500_chr21.h5ad"/> - <param name="merged_peaks" location="https://zenodo.org/records/11260316/files/merged_peaks.tabular"/> + <param name="merged_peaks" location="https://zenodo.org/records/17512085/files/merged_peaks.tabular"/> <param name="group_key" value="leiden"/> <conditional name="compare"> <param name="with" value="single_group"/> @@ -383,28 +610,34 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.diff_test"/> + <has_text_matching expression="snap.tl.diff_test"/> <has_text_matching expression="group_key = 'leiden'"/> <has_text_matching expression="group1 = '1'"/> <has_text_matching expression="group2 = '2'"/> </assert_contents> </output> - <output name="anndata_out" location="https://zenodo.org/records/12800783/files/tl.diff_test.single_group.pbmc_500_chr21.h5ad" ftype="h5ad" compare="sim_size" delta_frac="0.1" /> <output name="diff_peaks" > + <assert_contents> + <has_text_matching expression="chr21:17512734-17513235\t-4.0297.*\t4.3826.*\t0.0016.*"/> + <has_text_matching expression="chr21:33384757-33385258\t0.278.*\t0.1502.*\t0.2644.*"/> + <has_text_matching expression="chr21:42683799-42684300\t-0.438.*\t0.99.*\t0.99.*"/> + </assert_contents> + </output> + <output name="out_png"> <assert_contents> - <has_text_matching expression="chr21:17512734-17513235\t-4.0297.*\t4.3713.*\t0.0016.*"/> - <has_text_matching expression="chr21:33384757-33385258\t0.278.*\t0.1502.*\t0.2644.*"/> - <has_text_matching expression="chr21:42683799-42684300\t-0.438.*\t0.992.*\t0.992.*"/> + <has_image_center_of_mass center_of_mass="330,200" eps="30"/> + <has_image_channels channels="4"/> + <has_image_height height="400"/> + <has_image_width width="600"/> </assert_contents> </output> - <output name="out_png" location="https://zenodo.org/records/12800783/files/tl.diff_test.single_group.pbmc_500_chr21.png" ftype="png" compare="sim_size" delta_frac="0.1"/> </test> - <test expect_num_outputs="4"> + <test expect_num_outputs="3"> <!-- tl.diff_test background_group --> <conditional name="method"> <param name="method" value="tl.diff_test"/> <param name="adata" location="https://zenodo.org/records/12800783/files/tl.marker_regions.pbmc_500_chr21.h5ad"/> - <param name="merged_peaks" location="https://zenodo.org/records/11260316/files/merged_peaks.tabular"/> + <param name="merged_peaks" location="https://zenodo.org/records/17512085/files/merged_peaks.tabular"/> <param name="group_key" value="leiden"/> <conditional name="compare"> <param name="with" value="background_group"/> @@ -422,20 +655,25 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.diff_test"/> + <has_text_matching expression="snap.tl.diff_test"/> <has_text_matching expression="group_key = 'leiden'"/> <has_text_matching expression="group1 = '1'"/> </assert_contents> </output> - <output name="anndata_out" location="https://zenodo.org/records/12800783/files/tl.diff_test.background_group.pbmc_500_chr21.h5ad" ftype="h5ad" compare="sim_size" delta_frac="0.1" /> <output name="diff_peaks" > <assert_contents> <has_text_matching expression="chr21:5123633-5124134"/> <has_text_matching expression="chr21:32403055-32403556"/> - <has_text_matching expression="chr21:36156247-36156748"/> </assert_contents> </output> - <output name="out_png" location="https://zenodo.org/records/12800783/files/tl.diff_test.background_group.pbmc_500_chr21.png" ftype="png" compare="sim_size" delta_frac="0.5"/> + <output name="out_png"> + <assert_contents> + <has_image_center_of_mass center_of_mass="300,200" eps="30"/> + <has_image_channels channels="4"/> + <has_image_height height="400"/> + <has_image_width width="600"/> + </assert_contents> + </output> </test> </tests> <help><![CDATA[ @@ -445,7 +683,7 @@ Call peaks using MACS3. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.macs3.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.macs3.html>`__ Merge peaks from different groups, using `tl.merge_peaks` ========================================================= @@ -457,19 +695,16 @@ This function initially expands the summits of identified peaks by `half_width` on both sides. Following this expansion, it addresses the issue of overlapping peaks through an iterative process. The procedure begins by prioritizing the most significant peak, determined by the smallest p-value. This peak is retained, and any peak that overlaps with it is excluded. Subsequently, the same method is applied to the next most significant peak. This iteration continues until all peaks have been evaluated, resulting in a final list of non-overlapping peaks, each with a fixed width determined by the initial extension. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.merge_peaks.html>`__ - -Generate cell by bin count matrix, using `pp.add_tile_matrix` -============================================================= +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.merge_peaks.html>`__ -Generate cell by bin count matrix. +Generate cell by peak count matrix, using `pp.make_peak_matrix` +=============================================================== -This function is used to generate and add a cell by bin count matrix to the AnnData object. - -`import_data` must be ran first in order to use this function. +This function will generate a cell by peak count matrix. +`import_fragments` must be ran first in order to use this function. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.pp.add_tile_matrix.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.pp.make_peak_matrix.html>`__ A quick-and-dirty way to get marker regions, using `tl.marker_regions` ====================================================================== @@ -477,7 +712,7 @@ A quick-and-dirty way to get marker regions. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.marker_regions.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.marker_regions.html>`__ Identify differentially accessible regions, using `tl.diff_test` ==================================================================== @@ -485,7 +720,7 @@ Identify differentially accessible regions. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.diff_test.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.diff_test.html>`__ ]]></help> <expand macro="citations"/> </tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/all_fasta.loc Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,1 @@ +hg38 hg38 Human (hg38) ${__HERE__}/chr21_small.fasta.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/gene_sets.loc Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,1 @@ +hg38 hg38 hg38GFF ${__HERE__}/chr21.gff3.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/meme.loc Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,1 @@ +cisbp snap.datasets.cis_bp(unique=True) ${__HERE__}/cisBP_human.meme.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,17 @@ +#This file lists the locations and dbkeys of all the genome and transcriptome fasta files +#under the "genome" directory (a directory that contains a directory +#for each build. This file has the format (white space characters are +#TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#So, all_fasta.loc could look something like this: +# +#apiMel4.5 apiMel4.5 Honeybee (Apis mellifera): apiMel4.5 /path/to/genome/apiMel4.5/apiMel4.5.fa +#hg38canon hg38 Human (Homo sapiens): hg38 Canonical /path/to/genome/hg38/hg38canon.fa +#hg38full hg38 Human (Homo sapiens): hg38 Full /path/to/genome/hg38/hg38full.fa +#hg38full.90 hg38 Human (Homo sapiens): hg38 Full Trans v90 /path/to/genome/hg38/hg38fulltrans.fa + +#Your all_fasta.loc file should contain an entry for each individual +#fasta file. So there will be multiple fasta files for each build, +#such as with hg38 above. \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/gene_sets.loc.sample Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,14 @@ +# This is a sample file distributed with featureCounts that enables it and other# tools to use gene/exon annotations in the GFF/GTF format. +# +# The gene_sets.loc file syntax is: +#<unique_build_id> <dbkey> <display_name> <path> +# +# Please ensure that the above fields are tab separated. +# +# In case you have TWO or MORE providers PER dbkey, the one mentioned +# first in the file, should have the "default" priority. +# +#Example: +# +#Homo_sapiens.GRCh38.90 hg38 GRCh38 (hg38) annotation from Ensembl, release 90 /depot/data2/galaxy/hg38/gene_sets/Homo_sapiens.GRCh38.90.gtf +#Homo_sapiens.GRCh37.87 hg19 GRCh37 (hg19) annotation from Ensembl, release 87 /depot/data2/galaxy/hg19/gene_sets/Homo_sapiens.GRCh37.87.gtf \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/meme.loc.sample Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,13 @@ +# This is a sample file distributed with snapatac2 which enables the tool to perform motif enrichment analysis +# +# The meme.loc file syntax is: +#<unique_id> <display_name> <path> +# +# Please ensure that the above fields are tab separated. +# +# Currently the files should be downloaded manually +# +#Example: +# +#cisbp cis_bp(unique=True) /path/to/cisBP_human.meme.gz +#meuleman_2020 Meuleman_2020 /path/to/Meuleman_2020.meme.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,17 @@ +<tables> + <!-- Locations of all fasta files under genome directory --> + <table name="all_fasta" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/all_fasta.loc" /> + </table> + <!-- Locations of all gff files with annotations of genome builds --> + <table name="gene_sets" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/gene_sets.loc" /> + </table> + <!-- Locations of all meme files --> + <table name="meme" comment_char="#" allow_duplicate_entries="False"> + <columns>value, name, path</columns> + <file path="tool-data/meme.loc" /> + </table> +</tables> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Tue Nov 25 16:41:19 2025 +0000 @@ -0,0 +1,14 @@ +<tables> + <table name="all_fasta" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="${__HERE__}/test-data/all_fasta.loc" /> + </table> + <table name="gene_sets" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="${__HERE__}/test-data/gene_sets.loc" /> + </table> + <table name="meme" comment_char="#"> + <columns>value, name, path</columns> + <file path="${__HERE__}/test-data/meme.loc" /> + </table> +</tables> \ No newline at end of file