template for test data and fix trimming PE

README.md

@@ -223,11 +223,15 @@ snakemake --report
 
 ## Expected outputs
 
-With real yeast data:
+For the test data:
 
 - the `snakemake` report: `report.html`, download a [copy here](https://xsOdPxjHMEpp3hc:123456@owncloud.lcsb.uni.lu/public.php/webdav/report.html)
 - the `multiqc` report: `results/qc/multiqc/multiqc_report.html`, download a [copy here](https://xsOdPxjHMEpp3hc:123456@owncloud.lcsb.uni.lu/public.php/webdav/multiqc.html)
 
+With real yeast data:
+
+- the `snakemake` report: `report.html`, download a [copy here](https://xsOdPxjHMEpp3hc:123456@owncloud.lcsb.uni.lu/public.php/webdav/report_yeast.html)
+- the `multiqc` report: `results/qc/multiqc/multiqc_report.html`, download a [copy here](https://xsOdPxjHMEpp3hc:123456@owncloud.lcsb.uni.lu/public.php/webdav/multiqc_yeast.html)
 
 
 # Credits

config/config.yaml

@@ -34,7 +34,7 @@ trimming:
 
 params:
   # choose "narrow" or "broad" for macs2 callpeak analysis, for documentation and source code please see https://github.com/macs3-project/MACS
-  peak-analysis: "broad"
+  peak-analysis: "narrow"
   # Number of biological replicates required from a given condition for a peak to contribute to a consensus peak
   min-reps-consensus: 1
   callpeak:
@@ -51,10 +51,11 @@ params:
     # set to True to use the vst transformation instead of the rlog transformation for the DESeq2 analysis
     vst: False
   peak-annotation-analysis:
-    activate: False
+    activate: True
   peak-qc:
     activate: True
   consensus-peak-analysis:
+    # when more than one sample
     activate: False
   # samtools view parameter suggestions (for full parameters, see: https://www.htslib.org/doc/samtools-view.html):
   # if duplicates should be removed in this filtering, add "-F 0x0400" to the params

config/samples.tsv

 sample	group	batch_effect	control	antibody
-IN_FY4	WT	batch1		K4
-FY4	WT	batch1	IN_FY4	K4
-IN_FY4dld3	dld3	batch1		K4
-FY4_dld3	dld3	batch1	IN_FY4dld3	K4
\ No newline at end of file
+Spt5_IN	SptA	batch1		Spt
+Spt5	SptA	batch1	Spt5_IN	Spt
\ No newline at end of file

config/samples_yeast.tsv

+sample	group	batch_effect	control	antibody
+IN_FY4	WT	batch1		K4
+FY4	WT	batch1	IN_FY4	K4
+IN_FY4dld3	dld3	batch1		K4
+FY4_dld3	dld3	batch1	IN_FY4dld3	K4
\ No newline at end of file

config/units.tsv

 sample	unit	fq1	fq2	sra_accession	platform
-IN_FY4	1	data/2020-08-II/IN_FY4_A_Lasse_S22_R1_001.fastq.gz			ILLUMINA
-IN_FY4	2	data/2020-08-II/IN_FY4_B_Lasse_S23_R1_001.fastq.gz			ILLUMINA
-IN_FY4	3	data/2020-08-II/IN_FY4_C_Lasse_S24_R1_001.fastq.gz			ILLUMINA
-IN_FY4	4	data/2020-08-II/IN_FY4_D_Lasse_S64_R1_001.fastq.gz			ILLUMINA
-IN_FY4	5	data/2020-08-II/IN_FY4_E_Lasse_S65_R1_001.fastq.gz			ILLUMINA
-IN_FY4	6	data/2020-08-II/IN_FY4_F_Lasse_S66_R1_001.fastq.gz			ILLUMINA
-FY4	1	data/2020-08-II/K4_FY4_A_Lasse_S1_R1_001.fastq.gz			ILLUMINA
-FY4	2	data/2020-08-II/K4_FY4_B_Lasse_S2_R1_001.fastq.gz			ILLUMINA
-FY4	3	data/2020-08-II/K4_FY4_C_Lasse_S3_R1_001.fastq.gz			ILLUMINA
-IN_FY4dld3	1	data/2020-08-II/IN_FY4dld3_A_Lasse_S25_R1_001.fastq.gz			ILLUMINA
-IN_FY4dld3	2	data/2020-08-II/IN_FY4dld3_B_Lasse_S26_R1_001.fastq.gz			ILLUMINA
-IN_FY4dld3	3	data/2020-08-II/IN_FY4dld3_C_Lasse_S27_R1_001.fastq.gz			ILLUMINA
-IN_FY4dld3	4	data/2020-08-II/IN_FY4dld3_D_Lasse_S67_R1_001.fastq.gz			ILLUMINA
-IN_FY4dld3	5	data/2020-08-II/IN_FY4dld3_E_Lasse_S68_R1_001.fastq.gz			ILLUMINA
-IN_FY4dld3	6	data/2020-08-II/IN_FY4dld3_F_Lasse_S69_R1_001.fastq.gz			ILLUMINA
-FY4_dld3	1	data/2020-08-II/K4_FY4dld3_A_Lasse_S4_R1_001.fastq.gz			ILLUMINA
-FY4_dld3	2	data/2020-08-II/K4_FY4dld3_B_Lasse_S5_R1_001.fastq.gz			ILLUMINA
-FY4_dld3	3	data/2020-08-II/K4_FY4dld3_C_Lasse_S6_R1_001.fastq.gz			ILLUMINA
+Spt5_IN	1	test-datasets/testdata/SRR5204809_Spt5-ChIP_Input1_SacCer_ChIP-Seq_ss100k_R1.fastq.gz	test-datasets/testdata/SRR5204809_Spt5-ChIP_Input1_SacCer_ChIP-Seq_ss100k_R2.fastq.gz		ILLUMINA
+Spt5_IN	2	test-datasets/testdata/SRR5204810_Spt5-ChIP_Input2_SacCer_ChIP-Seq_ss100k_R1.fastq.gz	test-datasets/testdata/SRR5204810_Spt5-ChIP_Input2_SacCer_ChIP-Seq_ss100k_R2.fastq.gz		ILLUMINA
+Spt5	1	test-datasets/testdata/SRR5204807_Spt5-ChIP_IP1_SacCer_ChIP-Seq_ss100k_R1.fastq.gz	test-datasets/testdata/SRR5204807_Spt5-ChIP_IP1_SacCer_ChIP-Seq_ss100k_R2.fastq.gz		ILLUMINA
+Spt5	2	test-datasets/testdata/SRR5204808_Spt5-ChIP_IP2_SacCer_ChIP-Seq_ss100k_R1.fastq.gz	test-datasets/testdata/SRR5204808_Spt5-ChIP_IP2_SacCer_ChIP-Seq_ss100k_R2.fastq.gz		ILLUMINA

config/units_yeast.tsv

+sample	unit	fq1	fq2	sra_accession	platform
+IN_FY4	1	data/2020-08-II/IN_FY4_A_Lasse_S22_R1_001.fastq.gz			ILLUMINA
+IN_FY4	2	data/2020-08-II/IN_FY4_B_Lasse_S23_R1_001.fastq.gz			ILLUMINA
+IN_FY4	3	data/2020-08-II/IN_FY4_C_Lasse_S24_R1_001.fastq.gz			ILLUMINA
+IN_FY4	4	data/2020-08-II/IN_FY4_D_Lasse_S64_R1_001.fastq.gz			ILLUMINA
+IN_FY4	5	data/2020-08-II/IN_FY4_E_Lasse_S65_R1_001.fastq.gz			ILLUMINA
+IN_FY4	6	data/2020-08-II/IN_FY4_F_Lasse_S66_R1_001.fastq.gz			ILLUMINA
+FY4	1	data/2020-08-II/K4_FY4_A_Lasse_S1_R1_001.fastq.gz			ILLUMINA
+FY4	2	data/2020-08-II/K4_FY4_B_Lasse_S2_R1_001.fastq.gz			ILLUMINA
+FY4	3	data/2020-08-II/K4_FY4_C_Lasse_S3_R1_001.fastq.gz			ILLUMINA
+IN_FY4dld3	1	data/2020-08-II/IN_FY4dld3_A_Lasse_S25_R1_001.fastq.gz			ILLUMINA
+IN_FY4dld3	2	data/2020-08-II/IN_FY4dld3_B_Lasse_S26_R1_001.fastq.gz			ILLUMINA
+IN_FY4dld3	3	data/2020-08-II/IN_FY4dld3_C_Lasse_S27_R1_001.fastq.gz			ILLUMINA
+IN_FY4dld3	4	data/2020-08-II/IN_FY4dld3_D_Lasse_S67_R1_001.fastq.gz			ILLUMINA
+IN_FY4dld3	5	data/2020-08-II/IN_FY4dld3_E_Lasse_S68_R1_001.fastq.gz			ILLUMINA
+IN_FY4dld3	6	data/2020-08-II/IN_FY4dld3_F_Lasse_S69_R1_001.fastq.gz			ILLUMINA
+FY4_dld3	1	data/2020-08-II/K4_FY4dld3_A_Lasse_S4_R1_001.fastq.gz			ILLUMINA
+FY4_dld3	2	data/2020-08-II/K4_FY4dld3_B_Lasse_S5_R1_001.fastq.gz			ILLUMINA
+FY4_dld3	3	data/2020-08-II/K4_FY4dld3_C_Lasse_S6_R1_001.fastq.gz			ILLUMINA

workflow/rules/common.smk

@@ -216,10 +216,10 @@ def get_multiqc_input(wildcards):
         reads = [ "1", "2" ]
         if is_single_end(sample, unit):
             reads = [ "0" ]
-            multiqc_input.extend(expand (["logs/trimming/{sample}-{unit}.se.log"],
+            multiqc_input.extend(expand (["results/trimmed_se/{sample}-{unit}.settings"],
             sample = sample, unit = unit))
         else:
-            multiqc_input.extend(expand (["logs/trimming/{sample}-{unit}.pe.log"],
+            multiqc_input.extend(expand (["results/trimmed_pe/{sample}-{unit}.settings"],
             sample = sample, unit = unit))
 
         multiqc_input.extend(

workflow/rules/trimming.smk

@@ -4,8 +4,8 @@ rule trimming_pe:
         # unpack to convert the returned dict to a list
         unpack(get_fastq)
     output:
-        fastq1="results/trimmed_pe/{sample}-{unit}.1.fastq.gz",
-        fastq2="results/trimmed_pe/{sample}-{unit}.2.fastq.gz",
+        fq1="results/trimmed_pe/{sample}-{unit}.1.fastq.gz",
+        fq2="results/trimmed_pe/{sample}-{unit}.2.fastq.gz",
         single="results/trimmed_pe/{sample}-{unit}.singletons.gz",
         discarded="results/trimmed_pe/{sample}-{unit}.discarded.gz",
         settings="results/trimmed_pe/{sample}-{unit}.settings"