Bug fixes and improvements in bound/unbound threshold setting for BIN…

…Detect; added minimal working example to test_data for use in snakemake and commandline; BINDetect plot plots all TFS with effectsize > 0.2 as well as 10% highest p-values
loosolab · Jan 3, 2019 · 7ae519d · 7ae519d
1 parent 4c53ac4
commit 7ae519d
Show file tree

Hide file tree

Showing 138 changed files with 36,122 additions and 46,093 deletions.
diff --git a/.gitignore b/.gitignore
@@ -5,4 +5,3 @@ build/
 dist/
 *.egg
 *.egg-info
-test_data/tobias_output/*
diff --git a/snakemake_pipeline/TOBIAS.config b/snakemake_pipeline/TOBIAS.config
diff --git a/snakemake_pipeline/TOBIAS_example.config b/snakemake_pipeline/TOBIAS_example.config
@@ -3,18 +3,16 @@
 #-------------------------------------------------------------------------#
 
 data:
-  Tcell: [../test_data/day1_chr4.bam,../test_data/day2_chr4.bam,../test_data/day3_chr4.bam]
-  Bcell: [../test_data/buenrostro_chr4.bam]
+  Bcell: [../test_data/Bcell_chr4.bam]                                   #list of .bam-files
+  Tcell: [../test_data/Tcell_chr4_1.bam, ../test_data/Tcell_chr4_2.bam]  #list of .bam-files
 
-
 run_info:
-  organism: human
-  fasta: ../test_data/homo_sapiens.94.chr4.fa
-  blacklist: ../test_data/homo_sapiens.blacklisted.chr4.bed
-  gtf: ../test_data/homo_sapiens.94.chr4.gtf
-  motifs: jaspar_core_vertebrates # adjust path
-  output: ../test_data/tobias_output
-
+  organism: human                                #mouse/human
+  fasta: ../test_data/genome_chr4.fa.gz          #.fasta-file containing organism genome
+  blacklist: ../test_data/blacklist_chr4.bed     #.bed-file containing blacklisted regions
+  gtf: ../test_data/genes_chr4.gtf               #.gtf-file for annotation of peaks
+  motifs: ../test_data/individual_motifs         #directory containing motifs (single files in MEME/JASPAR/PFM format)
+  output: ../test_output                         #output directory 
 
 
 #-------------------------------------------------------------------------#

diff --git a/test_data/BATFJUN_Bcell_bound.bed b/test_data/BATFJUN_Bcell_bound.bed
diff --git a/test_data/BATFJUN_Bcell_unbound.bed b/test_data/BATFJUN_Bcell_unbound.bed
diff --git a/test_data/BATFJUN_Tcell_bound.bed b/test_data/BATFJUN_Tcell_bound.bed
diff --git a/test_data/BATFJUN_Tcell_unbound.bed b/test_data/BATFJUN_Tcell_unbound.bed
diff --git a/test_data/BATFJUN_all.bed b/test_data/BATFJUN_all.bed
diff --git a/test_data/Bcell_bias.bw b/test_data/Bcell_bias.bw
diff --git a/test_data/Bcell_chr4.bam b/test_data/Bcell_chr4.bam
diff --git a/test_data/Bcell_chr4.bam.bai b/test_data/Bcell_chr4.bam.bai
diff --git a/test_data/Bcell_corrected.bw b/test_data/Bcell_corrected.bw
diff --git a/test_data/Bcell_expected.bw b/test_data/Bcell_expected.bw
diff --git a/test_data/Bcell_footprints.bw b/test_data/Bcell_footprints.bw
diff --git a/test_data/Bcell_uncorrected.bw b/test_data/Bcell_uncorrected.bw
diff --git a/test_data/IRF1_all.bed b/test_data/IRF1_all.bed
diff --git a/test_data/IRF1_bound.bed b/test_data/IRF1_bound.bed
diff --git a/test_data/IRF1_unbound.bed b/test_data/IRF1_unbound.bed
diff --git a/test_data/Tcell_chr4_1.bam b/test_data/Tcell_chr4_1.bam
diff --git a/test_data/Tcell_chr4_1.bam.bai b/test_data/Tcell_chr4_1.bam.bai
diff --git a/test_data/Tcell_chr4_2.bam b/test_data/Tcell_chr4_2.bam
diff --git a/test_data/Tcell_chr4_2.bam.bai b/test_data/Tcell_chr4_2.bam.bai
diff --git a/test_data/Tcell_corrected.bw b/test_data/Tcell_corrected.bw
diff --git a/test_data/Tcell_footprints.bw b/test_data/Tcell_footprints.bw
diff --git a/test_data/annotated_peaks.bed b/test_data/annotated_peaks.bed
diff --git a/test_data/annotated_peaks_header.txt b/test_data/annotated_peaks_header.txt
@@ -0,0 +1,13 @@
+peak_chr
+peak_start
+peak_end
+peak_id
+feature
+feat_start
+feat_end
+feat_strand
+feat_anchor
+distance
+gene_biotype
+gene_id
+gene_name
diff --git a/test_data/blacklist.bed b/test_data/blacklist.bed
diff --git a/test_data/blacklist_chr4.bed b/test_data/blacklist_chr4.bed
@@ -0,0 +1,2 @@
+chr4	49118760	49119010
+chr4	49120790	49121130