diff --git a/workflow/main.nf b/workflow/main.nf
index 1908dfdfb2724a07916d7a342a088c3becf7a12c..0f4b58f8b18c15ac1398f042587cac6c9e9fc2e4 100644
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -38,6 +38,7 @@ readsList = Channel
pairedEnd = params.pairedEnd
designFile = params.designFile
genomeSize = params.genomeSize
+genome = params.genome
chromSizes = params.chromSizes
fasta = params.fasta
cutoffRatio = params.cutoffRatio
@@ -422,6 +423,7 @@ process motifSearch {
output:
file "*memechip" into motifSearch
+ file "sorted-*" into filteredPeaks
script:
diff --git a/workflow/scripts/annotate_peaks.R b/workflow/scripts/annotate_peaks.R
index 98bb8bdc846442e22ff354165c4580fd7777e25c..3629c4acf85e87440e17f2846e3beb56ba2c43ce 100644
--- a/workflow/scripts/annotate_peaks.R
+++ b/workflow/scripts/annotate_peaks.R
@@ -21,16 +21,16 @@ if (length(args) != 2) {
}
design_file <- args[1]
-genome <-args[2]
+genome_assembly <- args[2]
# Load UCSC Known Genes
-if(genome=='GRCh37') {
+if(genome_assembly=='GRCh37') {
txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene
annodb <- 'org.Hs.eg.db'
-} else if(genome=='GRCm38') {
+} else if(genome_assembly=='GRCm38') {
txdb <- TxDb.Mmusculus.UCSC.mm10.knownGene
annodb <- 'org.Mm.eg.db'
-} else if(genome=='GRCh38') {
+} else if(genome_assembly=='GRCh38') {
txdb <- TxDb.Hsapiens.UCSC.hg38.knownGene
annodb <- 'org.Hs.eg.db'
}
diff --git a/workflow/tests/test_annotate_peaks.py b/workflow/tests/test_annotate_peaks.py
index 13813505403067eadce9d9c31f6c26b4ae210f2e..e3f5746c3087e2d0f8eb97dc7f0050994270000d 100644
--- a/workflow/tests/test_annotate_peaks.py
+++ b/workflow/tests/test_annotate_peaks.py
@@ -16,7 +16,7 @@ def test_annotate_peaks_singleend():
assert os.path.exists(os.path.join(test_output_path, 'ENCSR238SGC.chipseeker_upsetplot.pdf'))
annotation_file = test_output_path + 'ENCSR238SGC.chipseeker_annotation.csv'
assert os.path.exists(annotation_file)
- assert utils.count_lines(annotation_file) == 149820
+ assert utils.count_lines(annotation_file) == 152840
@pytest.mark.pairedend
diff --git a/workflow/tests/test_call_peaks_macs.py b/workflow/tests/test_call_peaks_macs.py
index a0792c6d2919f0fdf255c19e5ffc330ef805b91b..71358bc045801d23d28b8f7385c5ef9f608347b6 100644
--- a/workflow/tests/test_call_peaks_macs.py
+++ b/workflow/tests/test_call_peaks_macs.py
@@ -13,7 +13,7 @@ def test_call_peaks_macs_singleend():
assert os.path.exists(os.path.join(test_output_path, 'ENCLB144FDT.fc_signal.bw'))
assert os.path.exists(os.path.join(test_output_path, 'ENCLB144FDT.pvalue_signal.bw'))
peak_file = test_output_path + 'ENCLB144FDT_peaks.narrowPeak'
- assert utils.count_lines(peak_file) == 210349
+ assert utils.count_lines(peak_file) == 227389
@pytest.mark.pairedend
diff --git a/workflow/tests/test_diff_peaks.py b/workflow/tests/test_diff_peaks.py
index 6b4a6ed272f2ef8ad530a600aee52745da9e2656..ad66c4a1a667110790e5de626dbdad7820751888 100644
--- a/workflow/tests/test_diff_peaks.py
+++ b/workflow/tests/test_diff_peaks.py
@@ -12,20 +12,11 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
@pytest.mark.singleend
def test_diff_peaks_singleend_single_rep():
- assert os.path.exists(os.path.join(test_output_path, 'no_diffbind.bed'))
- assert os.path.exists(os.path.join(test_output_path, 'no_diffbind.csv'))
- assert os.path.exists(os.path.join(test_output_path, 'no_heatmap.pdf'))
- assert os.path.exists(os.path.join(test_output_path, 'no_pca.pdf'))
- assert os.path.exists(os.path.join(test_output_path, 'normcount_peaksets.pdf'))
-
+ assert os.path.isdir(test_output_path) == False
@pytest.mark.pairedend
def test_annotate_peaks_pairedend_single_rep():
- assert os.path.exists(os.path.join(test_output_path, 'no_diffbind.bed'))
- assert os.path.exists(os.path.join(test_output_path, 'no_diffbind.csv'))
- assert os.path.exists(os.path.join(test_output_path, 'no_heatmap.pdf'))
- assert os.path.exists(os.path.join(test_output_path, 'no_pca.pdf'))
- assert os.path.exists(os.path.join(test_output_path, 'normcount_peaksets.pdf'))
+ assert os.path.isdir(test_output_path) == False
@pytest.mark.singlediff
def test_diff_peaks_singleend_multiple_rep():
diff --git a/workflow/tests/test_overlap_peaks.py b/workflow/tests/test_overlap_peaks.py
index a239b4144f0c780805ea07ac540c828e0154d5e5..ccbf186aa12798878db6b982a5a5d4574df01461 100644
--- a/workflow/tests/test_overlap_peaks.py
+++ b/workflow/tests/test_overlap_peaks.py
@@ -37,7 +37,7 @@ 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) == 150302
+ assert utils.count_lines(peak_file) == 149828
@pytest.mark.pairedend
diff --git a/workflow/tests/test_trim_reads.py b/workflow/tests/test_trim_reads.py
index 502312f20092a03c688f25fd8e597fd0e79f1940..aeb3eb3bbe2be77479b88fb82391efab687a0063 100644
--- a/workflow/tests/test_trim_reads.py
+++ b/workflow/tests/test_trim_reads.py
@@ -24,7 +24,7 @@ def test_trim_reads_singleend():
@pytest.mark.pairedend
def test_trim_reads_pairedend():
raw_fastq = test_data_path + 'ENCFF582IOZ.fastq.gz'
- trimmed_fastq = test_output_path + ' ENCLB637LZP_val_2.fq.gz'
+ trimmed_fastq = test_output_path + 'ENCFF582IOZ_val_2.fq.gz'
trimmed_fastq_report = test_output_path + \
'ENCLB637LZP.fastq.gz_trimming_report.txt'
assert os.path.getsize(raw_fastq) != os.path.getsize(trimmed_fastq)
diff --git a/workflow/tests/test_xcor.py b/workflow/tests/test_xcor.py
index 0c27795253040544676835fce6109c6889539087..8492de444ddc8f17d5d4ad9d7ce2f19785859753 100644
--- a/workflow/tests/test_xcor.py
+++ b/workflow/tests/test_xcor.py
@@ -9,13 +9,13 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
@pytest.mark.singleend
-def test_convert_reads_singleend():
+def test_map_qc_singleend():
assert os.path.exists(os.path.join(test_output_path, 'ENCFF833BLU.filt.nodup.tagAlign.15.tagAlign.gz.cc.plot.pdf'))
qc_file = os.path.join(test_output_path,"ENCFF833BLU.filt.nodup.tagAlign.15.tagAlign.gz.cc.qc")
df_xcor = pd.read_csv(qc_file, sep="\t", header=None)
- assert df_xcor[2].iloc[0] == '195,215,230'
- assert df_xcor[8].iloc[0] == 1.024836
- assert df_xcor[9].iloc[0] == 1.266678
+ assert df_xcor[2].iloc[0] == '190,200,210'
+ assert df_xcor[8].iloc[0] == 1.025906
+ assert df_xcor[9].iloc[0] == 1.139671
@pytest.mark.pairedend
@@ -23,6 +23,6 @@ def test_map_qc_pairedend():
assert os.path.exists(os.path.join(test_output_path, 'ENCFF582IOZ_val_2ENCFF957SQS_val_1.filt.nodup.tagAlign.15.tagAlign.gz.cc.plot.pdf'))
qc_file = os.path.join(test_output_path,"ENCFF582IOZ_val_2ENCFF957SQS_val_1.filt.nodup.tagAlign.15.tagAlign.gz.cc.qc")
df_xcor = pd.read_csv(qc_file, sep="\t", header=None)
- assert df_xcor[2].iloc[0] == '205,410,430'
- assert df_xcor[8].iloc[0] == 1.060266
- assert df_xcor[9].iloc[0] == 4.308793
+ assert df_xcor[2].iloc[0] == '210,220,475'
+ assert df_xcor[8].iloc[0] == 1.062032
+ assert df_xcor[9].iloc[0] == 3.737722