[WIP] include diffbind in new downstream chipseq

.gitignore

@@ -12,6 +12,12 @@ workflows/rnaseq/downstream/final_clusters
 workflows/rnaseq/downstream/rnaseq.log
 workflows/rnaseq/downstream/*tsv
 workflows/chipseq/data
+workflows/chipseq/*.log
+workflows/chipseq/downstream/*.tsv
+workflows/chipseq/downstream/*.html
+workflows/chipseq/downstream/*.bed
+workflows/chipseq/downstream/*_cache
+workflows/chipseq/downstream/*_files
 workflows/rnaseq/data
 workflows/colocalization/results
 work

lib/lcdbwf/R/helpers.R

@@ -408,7 +408,10 @@ make.dds <- function(design_data, salmon.files=NULL, combine.by=NULL,
 
     if (remove.version){
         rownames(dds) <- sapply(strsplit(rownames(dds), '.', fixed=TRUE),
-                                function (x) x[1])
+                                function (x) {ifelse(grepl('_', x[2]),
+                                              paste(x[1], x[2], sep='.'),
+                                              x[1])}
+                                )
     }
 
     if(!is.null(combine.by)){

requirements-r.txt

@@ -1,9 +1,11 @@
 bioconductor-annotationhub
 bioconductor-apeglm
 bioconductor-biocparallel
+bioconductor-chipseeker
 bioconductor-clusterprofiler
 bioconductor-degreport
 bioconductor-deseq2
+bioconductor-diffbind
 bioconductor-dupradar
 bioconductor-genomeinfodbdata
 bioconductor-genomicfeatures
@@ -14,7 +16,9 @@ bioconductor-tximport
 r-base >3.5
 r-devtools
 r-dt
+r-future
 r-ggrepel
+r-ggupset
 r-heatmaply
 r-knitr
 r-plotly

workflows/chipseq/config/config.yaml

@@ -5,7 +5,7 @@
 sampletable: 'config/sampletable.tsv'
 
 # Which key in the `references` dict below to use
-organism: 'dmel'
+organism: 'human'
 
 # If not specified here, use the environment variable REFERENCES_DIR.
 references_dir: 'references_data'
@@ -37,103 +37,108 @@ chipseq:
   # at least a BED file of peaks.
   #
   peak_calling:
-    - label: gaf-embryo-sicer
-      algorithm: sicer
+    - label: BRD4_dBET6_1
+      algorithm: macs2
       ip:
-        - gaf-embryo-1
+        - BRD4_dBET6_1
       control:
-        - input-embryo-1
-      redundancy_threshold: 1
-      window_size: 200
-      fragment_size: 150
+        - mockIgG_dBET6_1
       # optional user-specified override mappable genome proportion if
       # specified here, SICER will use this value instead of the value specific
       # to the genome build if NOT specified here, SICER will use the
       # mappability value for your genome build
-      effective_genome_fraction: 0.75
-      genome_build: dm6
-      gap_size: 600
-      fdr: 0.01
+      #effective_genome_count: 7e7
+      extra: '--nomodel -p 0.001 --cutoff-analysis'    # --broad for histones, paper says  in ‘histone’ mode for MTHFD1, but got very small number of peaks with --broad
 
+    - label: BRD4_dBET6_2
+      algorithm: macs2
+      ip:
+        - BRD4_dBET6_2
+      control:
+        - mockIgG_dBET6_2
+      extra: '--nomodel -p 0.001 --cutoff-analysis'
 
-    - label: gaf-embryo-1
+    - label: BRD4_DMSO_1
       algorithm: macs2
       ip:
-        - gaf-embryo-1
+        - BRD4_DMSO_1
       control:
-        - input-embryo-1
-      # optional user-specified override mappable genome size if specified
-      # here, MACS will use this value instead of the value specific to the
-      # genome build if NOT specified here, MACS will use the mappability value
-      # for your genome build
-      effective_genome_count: 7e7
-      extra: '--nomodel --extsize 147'
-
-    - label: gaf-embryo-1
-      algorithm: spp
+        - mockIgG_DMSO_1
+      extra: '--nomodel -p 0.001 --cutoff-analysis'
+
+    - label: BRD4_DMSO_2
+      algorithm: macs2
       ip:
-        - gaf-embryo-1
+        - BRD4_DMSO_2
       control:
-        - input-embryo-1
-      extra:
-        fdr: 0.3
-        zthr: 4
+        - mockIgG_DMSO_2
+      extra: '--nomodel -p 0.001 --cutoff-analysis'
 
-    - label: gaf-embryo-1-defaults
-      algorithm: spp
+    - label: MTHFD1_dBET6_1
+      algorithm: macs2
       ip:
-        - gaf-embryo-1
+        - MTHFD1_dBET6_1
       control:
-        - input-embryo-1
+        - mockIgG_dBET6_1
+      extra: '--nomodel -p 0.001 --cutoff-analysis'    # --broad for histones, paper says  in ‘histone’ mode for MTHFD1
 
-    - label: gaf-wingdisc-pooled
+    - label: MTHFD1_dBET6_1_inputCTRL
       algorithm: macs2
       ip:
-        - gaf-wingdisc-1
-        - gaf-wingdisc-2
+        - MTHFD1_dBET6_1
       control:
-        - input-wingdisc-1
-        - input-wingdisc-2
-      extra: '--nomodel --extsize 147'
+        - input_dBET6_1
+      extra: '--nomodel -p 0.001 --cutoff-analysis'
 
-    - label: gaf-wingdisc-pooled
-      algorithm: spp
+    - label: MTHFD1_dBET6_2
+      algorithm: macs2
       ip:
-        - gaf-wingdisc-1
-        - gaf-wingdisc-2
+        - MTHFD1_dBET6_2
       control:
-        - input-wingdisc-1
-        # - input-wingdisc-2
-      extra:
-        fdr: 0.5
-        zthr: 4
+        - mockIgG_dBET6_2
+      extra: '--nomodel -p 0.001 --cutoff-analysis'
+
+    - label: MTHFD1_DMSO_1
+      algorithm: macs2
+      ip:
+        - MTHFD1_DMSO_1
+      control:
+        - mockIgG_DMSO_1
+      extra: '--nomodel -p 0.001 --cutoff-analysis'
+
+    - label: MTHFD1_DMSO_2
+      algorithm: macs2
+      ip:
+        - MTHFD1_DMSO_2
+      control:
+        - mockIgG_DMSO_2
+      extra: '--nomodel -p 0.001 --cutoff-analysis'
 
 fastq_screen:
   - label: rRNA
-    organism: dmel
-    tag: test
+    organism: human
+    tag: gencode-v28
   - label: PhiX
     organism: phix
     tag: default
-  - label: Fly
-    organism: dmel
-    tag: test
-
-merged_bigwigs:
-  input-wingdisc:
-    - input-wingdisc-1
-    - input-wingdisc-2
-  gaf-wingdisc:
-    - gaf-wingdisc-1
-    - gaf-wingdisc-2
-  gaf-embryo:
-    - gaf-embryo-1
+  - label: Human
+    organism: human
+    tag: gencode-v28
+
+#merged_bigwigs:
+#  input-wingdisc:
+#    - input-wingdisc-1
+#    - input-wingdisc-2
+#  gaf-wingdisc:
+#    - gaf-wingdisc-1
+#    - gaf-wingdisc-2
+#  gaf-embryo:
+#    - gaf-embryo-1
 
 aligner:
   index: 'bowtie2'
-  tag: 'test'
+  tag: 'gencode-v28'
 
 include_references:
   - '../../include/reference_configs/PhiX.yaml'
-  - '../../include/reference_configs/Drosophila_melanogaster.yaml'
-  - '../../include/reference_configs/test.yaml'
+  - '../../include/reference_configs/Homo_sapiens.yaml'

workflows/chipseq/config/sampletable.tsv

@@ -1,11 +1,17 @@
-# Samplenames with the same "label" will be considered technical replicates
-samplename	antibody	biological_material	replicate	label	orig_filename
-input_1	input	wingdisc-1	1	input-wingdisc-1	data/example_data/chipseq_input1.fq.gz
-input_2	input	wingdisc-2	2	input-wingdisc-2	data/example_data/chipseq_input2.fq.gz
-ip_1	gaf	wingdisc-1	1	gaf-wingdisc-1	data/example_data/chipseq_ip1.fq.gz
-ip_2	gaf	wingdisc-2	2	gaf-wingdisc-2	data/example_data/chipseq_ip2.fq.gz
-
-# Note here we are treating ip_3 and ip_4 as technical replicates for the sake of testing
-ip_3	gaf	embryo-1	1	gaf-embryo-1	data/example_data/chipseq_ip3.fq.gz
-ip_4	gaf	embryo-1	1	gaf-embryo-1	data/example_data/chipseq_ip4.fq.gz
-input_3	input	embryo-1	1	input-embryo-1	data/example_data/chipseq_input3.fq.gz
+samplename	label	biological_material	group	GEO_Run	LibraryLayout	source_name	Treatment	antibody	replicate	orig_filename
+BRD4_dBET6_1	BRD4_dBET6_1	HAP1_B1	BRD4_dBET6	SRR6202977	SINGLE	ChIP-seq for BRD4 in HAP1 cell line treated with dBET6	dBET6	BRD4	1	../../raw_files/SRR6202977.fastq.gz
+BRD4_dBET6_2	BRD4_dBET6_2	HAP1_B2	BRD4_dBET6	SRR6202978	SINGLE	ChIP-seq for BRD4 in HAP1 cell line treated with dBET6	dBET6	BRD4	2	../../raw_files/SRR6202978.fastq.gz
+BRD4_DMSO_1	BRD4_DMSO_1	HAP1_D1	BRD4_DMSO	SRR6202979	SINGLE	ChIP-seq for BRD4 in HAP1 cell line treated with DMSO	DMSO	BRD4	1	../../raw_files/SRR6202979.fastq.gz
+BRD4_DMSO_2	BRD4_DMSO_2	HAP1_D2	BRD4_DMSO	SRR6202980	SINGLE	ChIP-seq for BRD4 in HAP1 cell line treated with DMSO	DMSO	BRD4	2	../../raw_files/SRR6202980.fastq.gz
+mockIgG_dBET6_1	mockIgG_dBET6_1	HAP1_B1	mockIgG_dBET6	SRR6202981	SINGLE	ChIP-seq with mock IgG antibody in HAP1 cell line treated with dBET6	dBET6	mockIgG	1	../../raw_files/SRR6202981.fastq.gz
+mockIgG_dBET6_2	mockIgG_dBET6_2	HAP1_B2	mockIgG_dBET6	SRR6202982	SINGLE	ChIP-seq with mock IgG antibody in HAP1 cell line treated with dBET6	dBET6	mockIgG	2	../../raw_files/SRR6202982.fastq.gz
+mockIgG_DMSO_1	mockIgG_DMSO_1	HAP1_D1	mockIgG_DMSO	SRR6202983	SINGLE	ChIP-seq with mock IgG antibody in HAP1 cell line treated with DMSO	DMSO	mockIgG	1	../../raw_files/SRR6202983.fastq.gz
+mockIgG_DMSO_2	mockIgG_DMSO_2	HAP1_D2	mockIgG_DMSO	SRR6202984	SINGLE	ChIP-seq with mock IgG antibody in HAP1 cell line treated with DMSO	DMSO	mockIgG	2	../../raw_files/SRR6202984.fastq.gz
+input_dBET6_1	input_dBET6_1	HAP1_B1	input_dBET6	SRR6202985	SINGLE	ChIP-seq for Input in HAP1 cell line treated with dBET6	dBET6	input	1	../../raw_files/SRR6202985.fastq.gz
+input_dBET6_2	input_dBET6_2	HAP1_B2	input_dBET6	SRR6202986	SINGLE	ChIP-seq for Input in HAP1 cell line treated with dBET6	dBET6	input	2	../../raw_files/SRR6202986.fastq.gz
+input_DMSO_1	input_DMSO_1	HAP1_D1	input_DMSO	SRR6202987	SINGLE	ChIP-seq for Input in HAP1 cell line treated with DMSO	DMSO	input	1	../../raw_files/SRR6202987.fastq.gz
+input_DMSO_2	input_DMSO_2	HAP1_D2	input_DMSO	SRR6202988	SINGLE	ChIP-seq for Input in HAP1 cell line treated with DMSO	DMSO	input	2	../../raw_files/SRR6202988.fastq.gz
+MTHFD1_dBET6_1	MTHFD1_dBET6_1	HAP1_B1	MTHFD1_dBET6	SRR6202989	SINGLE	ChIP-seq for MTHFD1 in HAP1 cell line treated with dBET6	dBET6	MTHFD1	1	../../raw_files/SRR6202989.fastq.gz
+MTHFD1_dBET6_2	MTHFD1_dBET6_2	HAP1_B2	MTHFD1_dBET6	SRR6202990	SINGLE	ChIP-seq for MTHFD1 in HAP1 cell line treated with dBET6	dBET6	MTHFD1	2	../../raw_files/SRR6202990.fastq.gz
+MTHFD1_DMSO_1	MTHFD1_DMSO_1	HAP1_D1	MTHFD1_DMSO	SRR6202991	SINGLE	ChIP-seq for MTHFD1 in HAP1 cell line treated with DMSO	DMSO	MTHFD1	1	../../raw_files/SRR6202991.fastq.gz
+MTHFD1_DMSO_2	MTHFD1_DMSO_2	HAP1_D2	MTHFD1_DMSO	SRR6202992	SINGLE	ChIP-seq for MTHFD1 in HAP1 cell line treated with DMSO	DMSO	MTHFD1	2	../../raw_files/SRR6202992.fastq.gz<Paste>