Mercurial > repos > gaelcge > cellranger_atac_galaxy

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README.md	Tue Aug 02 19:40:03 2022 +0000
@@ -0,0 +1,18 @@
+# GenAP2 Galaxy implementation of CellRanger-ATAC
+Disclaimer: This wrapper for CellRanger-ATAC is not developed or supported by 10x Genomics. This wrapper was written by scientists at GenAP to help facilitate usage of CellRanger tools inside of Galaxy.
+Please find the full, official 10x Genomics licensing information at : https://support.10xgenomics.com/docs/license.
+
+What is CellRanger ATAC?
+
+https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/what-is-cell-ranger-atac
+
+Naming convention of FASTQ files internally in Galaxy follows thes guidelines:
+
+https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/using/fastq-input#rightname
+
+Installation:
+1) Install this wrapper via the Galaxy toolshed.
+2) CellRanger-ATAC (v2.0.0) is required for this wrapper and should be installed separately (see below).
+
+To use this tool, we assume that cellranger-atac (v.2.0.0) is available to Galaxy on the system, via the command cellranger-atac. Unfortunately at this point, we cannot include Cellranger-ATAC as part of this wrapper due to Licensing and distribution limitations. For more information on how to install CellRanger-ATAC on your system, please see :
+https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/installation
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Tool-test.txt	Tue Aug 02 19:40:03 2022 +0000
@@ -0,0 +1,38 @@
+            ***** links to input data for 10X single-analysis and Seurat tutorials ****
+                                               ****
+
+***** Single-Cell ATACseq (10X Genomics) - from fastq to dimentionality reduction
+
+Fastq = https://support.10xgenomics.com/single-cell-atac/datasets/1.2.0/atac_v1_pbmc_5k
+small_fastq_files = https://support.10xgenomics.com/single-cell-atac/datasets/2.0.0/atac_pbmc_500_nextgem
+
+Software = Cell Ranger ATAC 1.2.0 (https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/installation)
+
+Tutorial from cell ranger output to clustering = https://satijalab.org/signac/articles/pbmc_vignette.html
+
+
+
+****** Multiome (ARC) = scRNA + scATACseq (10X Genomics) - from fastq to dimentionality reduction
+
+Fastq = https://support.10xgenomics.com/single-cell-multiome-atac-gex/datasets/1.0.0/pbmc_unsorted_3k
+
+Software = Cell Ranger ARC 1.0.0 (https://support.10xgenomics.com/single-cell-multiome-atac-gex/software/pipelines/latest/installation)
+
+Tutorial from cell ranger output to clustering (PBMC - RNA & ATAC) = https://satijalab.org/seurat/v4.0/weighted_nearest_neighbor_analysis.html
+
+
+
+                ********** Pipeline implentation *********
+                                *******
+
+***** Galaxy
+
+
+
+***** NextFlow
+https://github.com/WarrenLab/single-cell
+https://figshare.com/articles/BICF_Cellranger_count_Analysis_Workflow/9702698
+https://nf-co.re/scrnaseq/1.0.0
+https://hub.docker.com/r/nfcore/demultiplex
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cellranger_atac.xml	Tue Aug 02 19:40:03 2022 +0000
@@ -0,0 +1,87 @@
+<tool id="cellranger_atac" name="CellRanger ATAC" version="0.1.0" python_template_version="3.5">
+    <description>performs processing of 10x single-cell ATAC-seq data.</description>
+    <requirements>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+        mkdir ./fastq_dir &&
+        #for $i1 in $fastq_i1#
+            ln -s $i1 ./fastq_dir/$i1.element_identifier;
+        #end for#
+
+        #for $r1 in $fastq_r1#
+            ln -s $r1 ./fastq_dir/$r1.element_identifier;
+        #end for#
+
+        #for $r2 in $fastq_r2#
+            ln -s $r2 ./fastq_dir/$r2.element_identifier;
+        #end for#
+
+        #for $r3 in $fastq_r3#
+            ln -s $r3 ./fastq_dir/$r3.element_identifier;
+	    #end for#
+	    /cellranger/cellranger-atac count --id=$sample_ID --reference=/references/refdata-cellranger-arc-GRCh38-2020-A-2.0.0/ --fastqs ./fastq_dir --sample=$sample_name --localcores=8 --localmem=80 --disable-ui &&
+        ln -s $sample_ID cellranger_atac
+    ]]></command>
+    <inputs>
+        <param type="data" name="fastq_i1" label="Select the I1 fastq file (Dual index i7 read (optional)):"  format="fastq.gz" multiple="true"/>
+        <param type="data" name="fastq_r1" label="Select the read1 (R1) fastq file (BC):" format="fastq.gz" multiple="true"/>
+		<param type="data" name="fastq_r2" label="Select the Dual index i5 read file (R2/I2):" format="fastq.gz" multiple="true"/>
+        <param type="data" name="fastq_r3" label="Select the read (R3) fastq file (DNA):" format="fastq.gz" multiple="true"/>
+        <param type="text" name="sample_ID" label="What is the sample ID? (no spaces or special characters! example: my_sample)" optional="false"/>
+        <param type="text" name="sample_name" label="What is the sample name?" optional="false"/>
+    </inputs>
+    <outputs>
+	    <data name="Per-barcode fragment counts and metrics" label="singlecell.csv" format="csv" from_work_dir="cellranger_atac/outs/singlecell.csv"/>
+        <collection type="list" label="BAM files" name="">
+            <data name="possorted_bam.bam" label="possorted_bam.bam" format="bam" from_work_dir="cellranger_atac/outs/possorted_bam.bam"/>
+            <data name="possorted_bam.bai" label="possorted_bam.bai" format="bai" from_work_dir="cellranger_atac/outs/possorted_bam.bam.bai"/>
+        </collection>
+        <data name="Summary of all data metrics" label="summary.json" format="json" from_work_dir='cellranger_atac/outs/summary.json'/>
+	    <data name="HTML file summarizing data and analysis" label="web_summary.html" format="html" from_work_dir="cellranger_atac/outs/web_summary.html" />
+        <collection type="list" label="Filtered peak bc matrix" name="filtered_peak_bc_matrix">
+            <data name="barcodes.tsv" label="barcodes.tsv" format="tsv" from_work_dir='cellranger_atac/outs/filtered_peak_bc_matrix/barcodes.tsv'/>
+            <data name="peaks.bed" label="peaks.bed" format="bed" from_work_dir='cellranger_atac/outs/filtered_peak_bc_matrix/peaks.bed'/>
+        </collection>
+	    <data name="Raw peak barcode matrix in hdf5 format" label="raw_peak_bc_matrix.h5" format="h5" from_work_dir='cellranger_atac/outs/raw_peak_bc_matrix.h5'/>
+        <data name="Filtered peak barcode matrix in hdf5 format" label="filtered_peak_bc_matrix.h5" format="h5" from_work_dir='cellranger_atac/outs/filtered_peak_bc_matrix.h5'/>
+        <data name="fragments.tsv.gz" label="fragments.tsv.gz" format="bgzip" from_work_dir='cellranger_atac/outs/fragments.tsv.gz'/>
+        <data name="fragments.tsv.gz.tbi" label="fragments.tsv.gz.tbi" format="text" from_work_dir='cellranger_atac/outs/fragments.tsv.gz.tbi'/>
+        <data name="Filtered tf barcode matrix in hdf5 format" label="filtered_tf_bc_matrix.h5" format="h5" from_work_dir='cellranger_atac/outs/filtered_tf_bc_matrix.h5'/>
+        <data name="Cloupe file" label="cloupe.cloupe" format="data" from_work_dir='cellranger_atac/outs/cloupe.cloupe'/>
+        <data name="csv summarizing important metrics and values" label="summary.csv" format="csv" from_work_dir='cellranger_atac/outs/summary.csv'/>
+        <data name="Annotation of peaks with genes" label="peak_annotation.tsv" format="tsv" from_work_dir='cellranger_atac/outs/peak_annotation.tsv'/>
+        <data name="Peak-motif associations" label="peak_motif_mapping.bed" format="bed" from_work_dir='cellranger_atac/outs/peak_motif_mapping.bed'/>
+		<data name="Filtered CellRanger BC matrix" label="matrix.mtx" format="mtx" from_work_dir='cellranger_atac/outs/filtered_peak_bc_matrix/matrix.mtx'/>
+        <collection type="list" label="Raw peak bc matrix" name="raw_peak_bc_matrix">
+		    <data name="barcodes.txt" label="barcodes.txt" format="txt" from_work_dir='cellranger_atac/outs/raw_peak_bc_matrix/barcodes.tsv'/>
+		    <data name="peaks.bed" label="peaks.bed" format="bed" from_work_dir='cellranger_atac/outs/raw_peak_bc_matrix/peaks.bed'/>
+		    <data name="matrix.mtx" label="matrix.mtx" format="mtx" from_work_dir='cellranger_atac/outs/raw_peak_bc_matrix/matrix.mtx'/>
+        </collection>
+    </outputs>
+    <help><![CDATA[
+	Disclaimer: This wrapper for CellRanger-ATAC is not developed or supported by 10x Genomics. This wrapper was written by scientists at GenAP to help facilitate usage of CellRanger tools inside of Galaxy. Please find the full, official 10x Genomics licensing information at : https://support.10xgenomics.com/docs/license.
+
+        What is CellRanger ATAC?
+        https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/what-is-cell-ranger-atac
+
+        Naming convention of FASTQ files internally in Galaxy follows thes guidelines: https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/using/fastq-input#rightname
+
+        Installation:
+         1) Install this wrapper via the Galaxy toolshed.
+         2) CellRanger-ATAC (v2.0.0) is required for this r
+
+
+        To use this tool, we assume that cellranger-atac (v.2.0.0) is available to Galaxy on the system, via the command cellranger-atac. Unfortunately at this point, we cannot include Cellranger-ATAC as
+        part of this wrapper due to Licensing and distribution limitations. For more information on how to install CellRanger-ATAC on your system, please see :
+        https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/installation
+    ]]></help>
+    <citations>
+        <citation type="bibtex">
+@misc{renameTODO,
+  author = 10x Genomics,
+  year = 2021,
+  title = CellRanger-ATAC,
+  url = {https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/using/fastq-input#ATACIntro},
+}</citation>
+    </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_setup.md	Tue Aug 02 19:40:03 2022 +0000
@@ -0,0 +1,19 @@
+# Setup for creating a Galaxy wrapper for Cellranger-ATAC with planemo
+
+Make sure you have a working planemo installation. To find out how to install planemo, check here: https://planemo.readthedocs.io/en/latest/installation.html
+
+## Generate galaxy tool xml using planemo tool_init
+planemo tool_init --force \
+  --id 'cellranger_atac' \
+  --name 'Process 10x Genomics single-cell ATAC-seq data using CellRanger-ATAC.'\
+  --example_command 'cellranger-atac count' \
+  --cite_url 'https://support.10xgenomics.com/single-cell-atac/software/pipelines/latest/using/fastq-input#ATACIntro' \
+  --help_from_command 'cellranger-atac'
+
+  ## Test run with very small test data
+  cellranger-atac count --id=sample345 \
+    --reference= \
+    --fastqs=/home/florian/GenAP2/test_datasets/cellranger_ATAC/atac_pbmc_500_nextgem_fastqs/100k_sub \
+    --sample=test \
+    --localcores=2 \
+    --localmem=6
\ No newline at end of file