diff --git a/.gitignore b/.gitignore old mode 100755 new mode 100644 diff --git a/.gitmodules b/.gitmodules old mode 100755 new mode 100644 diff --git a/README.md b/README.md old mode 100755 new mode 100644 diff --git a/astrocyte_pkg.yml b/astrocyte_pkg.yml old mode 100755 new mode 100644 index da8cb77fc6ac9791ead218425c51215927c87d46..73fc676e33f3ec9ff1ccf91c884e57447e203e0e --- a/astrocyte_pkg.yml +++ b/astrocyte_pkg.yml @@ -9,12 +9,14 @@ # A unique identifier for the workflow package, text/underscores only name: 'atac-seq-source' # Who wrote this? -author: 'Achisha Saikia, Felix Perez, Peng Lian' +author: 'Felix Perez, Achisha Saikia, Peng Lian' # A contact email address for questions -email: 'achisha.saikia@utsouthwestern.edu, felix.perez@utsouthwestern.edu, biohpc-help@utsouthwestern.edu' +email: 'felix.perez@utsouthwestern.edu, achisha.saikia@utsouthwestern.edu, biohpc-help@utsouthwestern.edu' # A more informative title for the workflow package title: 'ATAC-seq Source Workflow" -# A summary of the workflow package in plain text + +This pipeline is designed for automated end-to-end quality control and processing of ATAC-seq. The pipeline can be run end-to-end, starting from raw FASTQ files all the way to peak calling and signal track generation using a single caper submit command. One can also start the pipeline from intermediate stages (for example, using alignment files as input). The pipeline supports both single-end and paired-end data as well as replicated or non-replicated datasets. The outputs produced by the pipeline include 1) formatted HTML reports that include quality control measures specifically designed for ATAC-seq and DNase-seq data, 2) analysis of reproducibility, 3) stringent and relaxed thresholding of peaks, 4) fold-enrichment and pvalue signal tracks. + description: | # TODO: Please describe the workflow. (AS) diff --git a/docs/.keep b/docs/.keep old mode 100755 new mode 100644 diff --git a/docs/index.md b/docs/index.md old mode 100755 new mode 100644 index 8df3fb1c6faaabc2ba565660b993102d335895c7..77b3eefda3d5d1c1fbbbda328a2c0d5123c3d9da --- a/docs/index.md +++ b/docs/index.md @@ -8,7 +8,7 @@ This repo is used to wrap the existing ATAC-seq pipeline listed below (Runner), - The ATAC-seq Runner workflow, 'astrocyte-atac-runner] (https://git.biohpc.swmed.edu/s219741/astrocyte-atac-runner). This repo contains the original ATAC-seq pipeline developed by the ENCODE team. ## The ATAC-seq Runner workflow -<!-- TODO: Fill out intro to ATAC-seq pipeline. Which commands do we use to run this pipeline? What will the NextFlow script use? (AS) --> +<!-- TODO: Fill out intro to ATAC-seq pipeline. Which commands do we use to run this pipeline? What will the NextFlow script use? (AS) (DONE)--> This pipeline is designed for automated end-to-end quality control and processing of ATAC-seq. The pipeline can be run end-to-end, starting from raw FASTQ files all the way to peak calling and signal track generation using a single caper submit command. One can also start the pipeline from intermediate stages (for example, using alignment files as input). The pipeline supports both single-end and paired-end data as well as replicated or non-replicated datasets. The outputs produced by the pipeline include 1) formatted HTML reports that include quality control measures specifically designed for ATAC-seq and DNase-seq data, 2) analysis of reproducibility, 3) stringent and relaxed thresholding of peaks, 4) fold-enrichment and pvalue signal tracks. diff --git a/test_data/.keep b/test_data/.keep old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/ENCSR356KRQ_subsampled.json b/test_data/example_input_json/ENCSR356KRQ_subsampled.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx/ENCSR356KRQ_subsampled_dx.json b/test_data/example_input_json/dx/ENCSR356KRQ_subsampled_dx.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx/ENCSR356KRQ_subsampled_rep1_dx.json b/test_data/example_input_json/dx/ENCSR356KRQ_subsampled_rep1_dx.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx/template_general.json b/test_data/example_input_json/dx/template_general.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx/template_hg19.json b/test_data/example_input_json/dx/template_hg19.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx/template_hg38.json b/test_data/example_input_json/dx/template_hg38.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx/template_mm10.json b/test_data/example_input_json/dx/template_mm10.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx/template_mm9.json b/test_data/example_input_json/dx/template_mm9.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx_azure/ENCSR356KRQ_subsampled_dx_azure.json b/test_data/example_input_json/dx_azure/ENCSR356KRQ_subsampled_dx_azure.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx_azure/template_general.json b/test_data/example_input_json/dx_azure/template_general.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx_azure/template_hg19.json b/test_data/example_input_json/dx_azure/template_hg19.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx_azure/template_hg38.json b/test_data/example_input_json/dx_azure/template_hg38.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx_azure/template_mm10.json b/test_data/example_input_json/dx_azure/template_mm10.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/dx_azure/template_mm9.json b/test_data/example_input_json/dx_azure/template_mm9.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/template.full.json b/test_data/example_input_json/template.full.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/template.json b/test_data/example_input_json/template.json old mode 100755 new mode 100644 diff --git a/test_data/example_input_json/terra/ENCSR356KRQ_subsampled.terra.json b/test_data/example_input_json/terra/ENCSR356KRQ_subsampled.terra.json old mode 100755 new mode 100644 diff --git a/vizapp/.keep b/vizapp/.keep old mode 100755 new mode 100644 diff --git a/workflow/configs/biohpc.config b/workflow/configs/biohpc.config old mode 100755 new mode 100644 diff --git a/workflow/images/singularity/.keep b/workflow/images/singularity/.keep old mode 100755 new mode 100644 diff --git a/workflow/main.nf b/workflow/main.nf old mode 100755 new mode 100644 index 25f81fe3d0b0420c385dbadde44baf0404daba65..27a4f304835e144c1de84e8b2e80b0ee7a86c0c8 --- a/workflow/main.nf +++ b/workflow/main.nf @@ -1,10 +1,10 @@ /* * Copyright (c) 2024. The University of Texas Southwestern Medical Center * - * TODO: (AC) Brief description of ATAC-seq - * + * TODO: (AC) Brief description of ATAC-seq (DONE) + * ATAC-seq is a molecular biology technique that assesses chromatin accessibility in a genome. It uses a hyperactive Tn5 transposase to insert sequencing adapters into open chromatin regions, allowing researchers to identify and sequence these accessible genomic regions. ATAC-seq is widely used to study gene regulation, identify enhancers and promoters, and gain insights into chromatin structure. * @authors - * Achisha Saikia, Felix Perez + * Felix Perez, Achisha Saikia * */ diff --git a/workflow/scripts/.keep b/workflow/scripts/.keep old mode 100755 new mode 100644