Merge branch '50-change-peak-comparisons' into 'master'

Resolve "Change Tests for Peak comparison to be greater than or equal to"

Closes #50

See merge request BICF/Astrocyte/chipseq_analysis!44

CHANGELOG.md

+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+## [Unreleased]
+
+## [publish_1.0.4 ] - 2019-05-15
+### Fixed
+- Retitled documentation for skipDiff and skipMotif to be more clear
+- Add missing python module for motif search
+- Updated links for phantompeaktools and references
+- Fix callPeaks for single control experiments
+
+## [publish_1.0.3 ] - 2019-04-23
+### Fixed
+- Variable name for design file for Astrocyte
+- File path for design file to work for Astrocyte
+
+## [publish_1.0.0 ] - 2019-04-23
+Initial release of 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**:
-  * Venkat S. Malladi and Beibei Chen. (2019). BICF ChIP-seq Analysis Workflow (publish_1.0.0). Zenodo. doi:[10.5281/zenodo.2648845](https://doi.org/10.5281/zenodo.2648845)
+  * Spencer D. Barnes, Holly Ruess, Beibei Chen, & Venkat S. Malladi. (2019). BICF ChIP-seq Analysis Workflow (publish_1.0.4). 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/tests/test_annotate_peaks.py

@@ -24,7 +24,7 @@ def test_upsetplot_singleend():
 def test_annotation_singleend():
     annotation_file = test_output_path + 'ENCSR238SGC.chipseeker_annotation.tsv'
     assert os.path.exists(annotation_file)
-    assert utils.count_lines(annotation_file) == 152255
+    assert utils.count_lines(annotation_file) == 149284
 
 
 @pytest.mark.pairedend
@@ -41,4 +41,4 @@ def test_upsetplot_pairedend():
 def test_annotation_pairedend():
     annotation_file = test_output_path + 'ENCSR729LGA.chipseeker_annotation.tsv'
     assert os.path.exists(annotation_file)
-    assert utils.count_lines(annotation_file) == 25494
+    assert utils.count_lines(annotation_file) >= 25494

workflow/tests/test_diff_peaks.py

@@ -44,7 +44,7 @@ def test_diffbind_singleend_multiple_rep():
         assert os.path.exists(os.path.join(test_output_path, 'ENCSR238SGC_vs_ENCSR272GNQ_diffbind.bed'))
         diffbind_file = test_output_path + 'ENCSR238SGC_vs_ENCSR272GNQ_diffbind.csv'
     assert os.path.exists(diffbind_file)
-    assert utils.count_lines(diffbind_file) == 201217
+    assert utils.count_lines(diffbind_file) >= 197471
 
 
 @pytest.mark.paireddiff
@@ -71,4 +71,4 @@ def test_diffbind_pairedend_single_rep():
         assert os.path.exists(os.path.join(test_output_path, 'ENCSR729LGA_vs_ENCSR757EMK_diffbind.bed'))
         diffbind_file = test_output_path + 'ENCSR729LGA_vs_ENCSR757EMK_diffbind.csv'
     assert os.path.exists(diffbind_file)
-    assert utils.count_lines(diffbind_file) == 66201
+    assert utils.count_lines(diffbind_file) >= 66201

workflow/tests/test_overlap_peaks.py

@@ -37,11 +37,11 @@ def test_check_update_design(design_diff):
 def test_overlap_peaks_singleend():
     assert os.path.exists(os.path.join(test_output_path, 'ENCSR238SGC.rejected.narrowPeak'))
     peak_file = test_output_path + 'ENCSR238SGC.replicated.narrowPeak'
-    assert utils.count_lines(peak_file) == 152262
+    assert utils.count_lines(peak_file) >= 149291
 
 
 @pytest.mark.pairedend
 def test_overlap_peaks_pairedend():
     assert os.path.exists(os.path.join(test_output_path, 'ENCSR729LGA.rejected.narrowPeak'))
     peak_file = test_output_path + 'ENCSR729LGA.replicated.narrowPeak'
-    assert utils.count_lines(peak_file) == 25758
+    assert utils.count_lines(peak_file) >= 25758