Merge branch '55-CheckGenomeMapPeaks' into 'master'

Fix fasta file refernce and add check for correct genome version

Closes #55 and #56

See merge request BICF/Astrocyte/chipseq_analysis!49

CHANGELOG.md

@@ -3,8 +3,15 @@
 All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
+
+## [publish_1.0.6 ] - 2019-05-31
 ### Added
 - MIT LICENSE
+- Check for correct genome input
+- Check for correct output for motif serach
+
+### Fixed
+- Path to reference fasta file
 
 ## [publish_1.0.5 ] - 2019-05-16
 ### Fixed

LICENSE.md

@@ -4,7 +4,7 @@ Copyright (c) 2019, University of Texas Southwestern Medical Center.
 
 All rights reserved.
 
-Contributors: Spencer D. Barnes, Holly Ruess, Beibei Chen, Venkat S. Malladi
+Contributors: Spencer D. Barnes, Holly Ruess, Jeremy A. Mathews, Beibei Chen, Venkat S. Malladi
 
 Department: Bioinformatic Core Facility, Department of Bioinformatics
 

README.md

 # **CHIPseq Manual**
-## Version 1.0.5
-## May 16, 2019
+## Version 1.0.6
+## May 31, 2019
 
 # BICF ChIP-seq Pipeline
 

docs/references.md

@@ -52,6 +52,6 @@
   * Ewels P., Magnusson M., Lundin S. and Käller M. 2016. MultiQC: Summarize analysis results for multiple tools and samples in a single report. Bioinformatics 32(19): 3047–3048. doi:[10.1093/bioinformatics/btw354](https://dx.doi.org/10.1093/bioinformatics/btw354)
 
 17. **BICF ChIP-seq Analysis Workflow**:
-  * Spencer D. Barnes, Holly Ruess, Beibei Chen, & Venkat S. Malladi. (2019). BICF ChIP-seq Analysis Workflow (publish_1.0.5). Zenodo. doi:[10.5281/zenodo.2648844](https://doi.org/10.5281/zenodo.2648844)
+  * Spencer D. Barnes, Holly Ruess, Jeremy A. Mathews, Beibei Chen, & Venkat S. Malladi. (2019). BICF ChIP-seq Analysis Workflow (publish_1.0.5). Zenodo. doi:[10.5281/zenodo.2648844](https://doi.org/10.5281/zenodo.2648844)
 
 Please cite in publications: Pipeline was developed by BICF from funding provided by **Cancer Prevention and Research Institute of Texas (RP150596)**.

workflow/main.nf

@@ -34,7 +34,7 @@ if (params.astrocyte) {
   referenceLocation = "/project/shared/bicf_workflow_ref"
   params.bwaIndex = "$referenceLocation/$params.genome"
   params.chromSizes = "$referenceLocation/$params.genome/genomefile.txt"
-  params.fasta = "$referenceLocation/$params.genome/genome.fa.txt"
+  params.fasta = "$referenceLocation/$params.genome/genome.fa"
   if (params.genome == 'GRCh37' || params.genome == 'GRCh38') {
     params.genomeSize = 'hs'
   } else if (params.genome == 'GRCm38') {

workflow/scripts/annotate_peaks.R

 #!/bin/Rscript
 
-/*
- * --------------------------------------------------------------------------
- * Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/chipseq_analysis/LICENSE.md)
- * --------------------------------------------------------------------------
- */
+#*
+#* --------------------------------------------------------------------------
+#* Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/chipseq_analysis/LICENSE.md)
+#* --------------------------------------------------------------------------
+#*
 
 # Load libraries
 library("ChIPseeker")

workflow/scripts/diff_peaks.R

 #!/bin/Rscript
 
-/*
- * --------------------------------------------------------------------------
- * Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/chipseq_analysis/LICENSE.md)
- * --------------------------------------------------------------------------
- */
+#*
+#* --------------------------------------------------------------------------
+#* Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/chipseq_analysis/LICENSE.md)
+#* --------------------------------------------------------------------------
+#*
 
 # Load libraries
 library("DiffBind")

workflow/scripts/map_reads.py

@@ -218,6 +218,13 @@ def main():
             shlex.split("samtools flagstat %s" % (bam_filename)),
             stdout=temp_file)
 
+    #Genome/Bad fastq File Check
+    file_check = open(bam_mapstats_filename).readlines()
+    percent = file_check[4].split('(')[1]
+    percent = percent.split('%')[0]
+    if float(percent) < 10:
+        raise Exception ('Mapped Genes too low: Check for correct Genotype')
+
     # Remove sai files
     for sai_file in sai:
         os.remove(sai_file)

workflow/tests/test_motif_search.py

@@ -21,7 +21,7 @@ def test_limited_peaks_singleend():
 def test_motif_search_singleend():
     assert os.path.exists(os.path.join(test_output_path, 'ENCSR238SGC_memechip', 'ENCSR238SGC.fa'))
     assert os.path.exists(os.path.join(test_output_path, 'ENCSR238SGC_memechip', 'index.html'))
-
+    assert os.path.getsize(os.path.join(test_output_path, 'ENCSR238SGC_memechip', 'ENCSR238SGC.fa')) > 0
 
 @pytest.mark.singleskip_true
 def test_motif_search_singleend():
@@ -39,3 +39,4 @@ def test_limited_peaks_pairedend():
 def test_motif_search_pairedend():
     assert os.path.exists(os.path.join(test_output_path, 'ENCSR729LGA_memechip',  'ENCSR729LGA.fa'))
     assert os.path.exists(os.path.join(test_output_path, 'ENCSR729LGA_memechip', 'index.html'))
+    assert os.path.getsize(os.path.join(test_output_path, 'ENCSR729LGA_memechip', 'ENCSR729LGA.fa')) > 0