Merge pull request #151 from NCI-RBL/dev

complete feature branch merge

Author: slsevilla

.tests/cluster_config.yaml

@@ -2,125 +2,137 @@
 __default__:
     gres: lscratch:96
     mem: 40g
-    partition: norm
-    time: 00-02:00:00
+    partition: ccr,norm
+    time: 00-08:00:00
     threads: 32
     output: .%j.{wildcards}.out
     error: .%j.{wildcards}.err
 
 qc_barcode:
-    threads: 3
-    mem: 3g
+    threads: 8
+    mem: 75g
     time: 00-04:00:00
 
 demultiplex:
-    threads: 3
-    mem: 3g
-    time: 04-00:00:00
+    threads: 56
+    mem: 32g
+    gres: lscratch:800
+    time: 00-05:00:00
 
-remove_adaptors:
-    threads: 3
-    time: 1-00:00:00
-    mem: 3g
-
-qc_fastq_pre:
-    threads: 3
-    mem: 3g
-    time: 00-03:00:00
+nondemux:
+    time: 00-01:00:00
 
-qc_fastq_post:
-    threads: 3
+qc_fastq:
+    threads: 4
     mem: 3g
     time: 00-03:00:00
 
 qc_screen_validator:
-    mem: 15g
+    mem: 32g
     time: 00-03:00:00
 
-split_files:
-    threads: 3
-    mem: 3g
-    time: 00-03:00:00
-
-novoalign:
-    mem: 50g
-    time: 10-00:00:00
-
-cleanup_conversion:
-    threads: 5
-    mem: 30g
-    time: 00-3:00:00
-
-merge_unmapped_splits:
-    time: 01-00:00:00
-    mem: 75g
-
-create_bam_mm_unique:
-    threads: 6
-    gres: lscratch:256
-    mem: 30g
+star:
     time: 04-00:00:00
-
-merge_splits_unique_mm:
-    mem: 512g
-    time: 02-06:00:00
-    partition: largemem
-
-merge_mm_and_unique:
-    threads: 2
-    gres: lscratch:256
-    mem: 5g
-    time: 02-00:00:00
-
-qc_alignment:
-    mem: 10g
+    gres: lscratch:800
+    threads: 16
+    mem: 120g
+
+index_stats:
+    threads: 8
+    gres: lscratch:800
+    mem: 200g
+    time: 01-00:00:00
 
 qc_troubleshoot:
-    threads: 3
+    threads: 4
     mem: 3g
 
 dedup:
-    threads: 2
-    mem: 64g
+    threads: 8
+    mem: 200g
     gres: lscratch:256
-    time: 01-00:00:00
+    time: 02-00:00:00
 
 create_beds_safs:
-    mem: 350g
-    gres: lscratch:256
+    mem: 200g
+    gres: lscratch:512
+    threads: 8
+
+bgzip_beds:
+    mem: 100g
     threads: 4
-    partition: largemem
+
+feature_counts:
+    threads: 8
+    mem: 200g
 
 project_annotations:
     threads: 2
     mem: 10g
     time: 00-01:00:00
 
-peak_annotations:
-    threads: 3
+peak_junctions:
+    threads: 10
+    gres: lscratch:128
+    mem: 36g
+    time: 04-00:00:00
+    
+peak_Transcripts:
+    threads: 4
+    gres: lscratch:128
+    mem: 30g
+    time: 04-00:00:00    
+
+peak_ExonIntron:
+    threads: 4
     gres: lscratch:128
     mem: 30g
-    time: 00-12:00:00
+    time: 04-00:00:00 
 
+peak_RMSK:
+    threads: 4
+    gres: lscratch:128
+    mem: 30g
+    time: 04-00:00:00 
+    
 annotation_report:
-    mem: 10g
+    threads: 4
+    gres: lscratch:128
+    mem: 30g
+    time: 00-12:00:00
+
+MANORM_beds:
+    threads: 4
+    mem: 30g
 
 MANORM_analysis:
     threads: 4
     mem: 30g
+    time: 04-00:00:00
 
 MANORM_post_processing:
     threads: 2
-    mem: 2g
-    time: 00-01:00:00
+    mem: 30g
+    time: 00-12:00:00
 
 MANORM_RMD:
     threads: 2
-    mem: 3g
-    time: 00-01:00:00
+    mem: 30g
+    time: 00-02:00:00
 
-mapq_recalc:
-    mem: 1TB
-    gres: lscratch:256
-    partition: largemem
-    time: 00-06:00:00
+DIFFBIND_beds:
+    threads: 4
+    mem: 30g
+    
+DIFFBIND_preprocess:
+    threads: 4
+    mem: 30g
+
+DIFFBIND_analysis:
+    threads: 4
+    mem: 30g
+
+
+DIFFBIND_report:
+    threads: 4
+    mem: 30g

.tests/multiplex_hg38_full.tsv

@@ -1,2 +1,2 @@
-file_name	multiplex
-test_6.fastq.gz	test_6
+file_name,multiplex
+test_6.fastq.gz,test_6

.tests/sample_hg38_full.tsv

@@ -1,3 +1,3 @@
-multiplex	sample	group	barcode	adaptor
-test_6	Ro_Clip	CLIP	NNNNNCACTGTNNNN	AGATCGGAAGAGCGTCGTG
-test_6	Control_Clip	CNTRL	NNNNNATTGGCNNNN	AGATCGGAAGAGCGTCGTG
+multiplex,sample,group,barcode,adaptor
+test_6,Ro_Clip,CLIP,NNNNNCACTGTNNNN,AGATCGGAAGAGCGTCGTG
+test_6,Control_Clip,CNTRL,NNNNNATTGGCNNNN,AGATCGGAAGAGCGTCGTG

.tests/snakemake_config.yaml

@@ -1,52 +1,102 @@
+#########################################################################################
 # Global configuration file for the pipeline
+#########################################################################################
+
+#########################################################################################
+#Folders and Paths
+#########################################################################################
 #path to snakemake file
 sourceDir: ""
-
 #path to output directory
 outputDir: "hg38_full/"
-
+#path to fastq files
+fastqDir: ".tests/"
 #path to manifest files
 sampleManifest: ".tests/sample_hg38_full.tsv"
 multiplexManifest: ".tests/multiplex_hg38_full.tsv"
 contrastManifest: ".test/contrasts_example.tsv"
 
-#path to fastq files
-fastqDir: ".tests/"
-
+########################################################################################
 #user parameters
-filterlength: 20 #minimum read length to include in analysis [any int >20]
+#########################################################################################
 multiplexflag: "Y" #flag that samples are multiplexed ["Y","N"]
+umiSeparator: "rbc:" #required for nondemultiplexed samples to determine delimiter for deduplication [":", "_", "rbc:"]
 mismatch: 1 #number of bp mismatches allowed in demultiplexing [1,2,3]
+barcode_qc_flag: "PROCESS" #barcodes will undergo QC to ensure uniformity within samples; ["PROCESS", "IGNORE"]
+min_reads_mapped: 0.5 #minimum percent of reads that should be mapped; IE .5 for 50% of all reads must be mapped [0.5]
 reference: "hg38" #reference organism ["mm10", "hg38"]
-spliceaware: "N" #whether to run splice_aware part of the pipeline ['y', 'n']
+filterlength: 20 #minimum read length to include in analysis [any int >20]
+phredQuality: 20 #minimum quality score for 3’ end trimming
 includerRNA: "N" #include refseq rRNA's in annotations ["Y", "N"]
-spliceBPlength: 75 #length of splice index to use [50, 75, 150]
 splicejunction: "N" #include splice junctions in peak calls: "manorm"
-condenseexon: "N" #whether to collapse exons
+AnnoAnchor: "max_total" #whether annotations for spliced peaks will be based on either 5' most region or region with max reads ["max","5prime"]
 mincount: 3 #minimum number of matches to count as a peak [1,2,3]
 ntmerge: 50 #minimum distance of nucleotides to merge peaks [10,20,30,40,50,60]
 peakid: "ALL" #report peaks for unique peaks only or unique and fractional mm ["unique","all"]
 DEmethod: "none" #choose DE method ["manorm","none"]
+MANormWidth: 50 #Width of window to calculate read density. [any integer >1; default 50]
+MNormDistance: 25 #Summit-to-summit distance cutoff for common peaks. [ any integer >1; default MANormWidth/2]
 sampleoverlap: 1 #if DEmethod DIFFBIND, minimum number of samples a peak must be found in to be counted [>1]
 pval: 0.005 #if DEmethod, pval cutoff for significance
 fc: 1 #if DEmethod, fold change cut off for significance
+single_qc_threshold: 95 #maximum threshold for unmampped reads in any single sample
+project_qc_threshold: 50 #maximum threshold for unmapped reads across average of all project samples
+
+#########################################################################################
+# STAR parameters
+#########################################################################################
+alignEndsType: "Local" #type of read ends alignment ["Local", "EndToEnd", "Extend5pOfRead1", "Extend5pOfReads12"]
+alignIntronMax: 50000 #maximum intron length
+alignSJDBoverhangMin: 3 # minimum overhang value for annotated spliced junctions
+alignSJoverhangMin: 5 # minimum overhang value for non-cannonical splied junctions
+alignTranscriptsPerReadNmax: 10000 #max number of different alignments per read to consider [int>0]
+alignWindowsPerReadNmax: 10000 #max number of windows per read [int>0]
+limitOutSJcollapsed: 1000000 # max number of collapsed junctions [int>0]
+outFilterMatchNmin: 15 # alignment will be output only if the number of matched bases is higher than or equal to this value.
+outFilterMatchNminOverLread: 0.9 #alignment will be output only if the number of matched bases is >= to value; normalized to sum of mates’ lengths for paired-end reads
+outFilterMismatchNmax: 999 #alignment will be output only if it has no more mismatches than this value.
+outFilterMismatchNoverReadLmax: 0.04 #alignment will be output only if its ratio of mismatches to *read* length is less than or equal to this value.
+outFilterMultimapNmax: 10000 #max number of multiple alignments allowed for a read: if exceeded, the read is considered unmapped
+outFilterMultimapScoreRange: 0 #the score range below the maximum score for multimapping alignments
+outFilterScoreMin: 0 #alignment will be output only if its score is higher than or equal to this value.
+outFilterType: "Normal" #type of filtering ["Normal", "BySJout"]
+outSAMattributes: "All" #a string of desired SAM attributes, in the order desired for the output SAM
+outSAMunmapped: "None" #output of unmapped reads in the SAM format ["None", "Within"]
+outSJfilterCountTotalMin: "3,1,1,1" #minimum total (multi-mapping+unique) read count per junction for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif
+outSJfilterOverhangMin: "30,12,12,12" #minimum overhang length for splice junctions on both sides for: (1) non-canonical motifs, (2) GT/AG and CT/AC motif, (3) GC/AG and CT/GC motif, (4) AT/AC and GT/AT motif
+outSJfilterReads: "All" #which reads to consider for collapsed splice junctions output ["All", "Unique"]
+seedMultimapNmax: 10000 #only pieces that map fewer than this value are utilized in the stitching procedure [int>0]
+seedNoneLociPerWindow: 20 #max number of one seed loci per window [int>0]
+seedPerReadNmax: 10000 #max number of seeds per read
+seedPerWindowNmax: 500 #max number of seeds per window
+sjdbScore: 2 #extra alignment score for alignmets that cross database junctions
+winAnchorMultimapNmax: 500 #max number of loci anchors are allowed to map to
+
 
+#########################################################################################
+# modules, container parameters
+#########################################################################################
 #modules, container parameters
 containerDir: "/data/CCBR_Pipeliner/iCLIP/container"
 fastq_val: "/data/CCBR_Pipeliner/db/PipeDB/bin/fastQValidator"
+
 bedtools: "bedtools/2.29.2"
 bowtie2: "bowtie/2-2.3.4"
 fastq_screen: "fastq_screen/0.14.0"
 fastqc: "fastqc/0.11.9"
-java: "java/12.0.1"
 manorm: "manorm/1.1.4"
 multiqc: "multiqc/1.9"
-novocraft: "novocraft/4.03.01"
 perl: "perl/5.24.3"
-python: "python/3.7"
-Qt: "Qt/5.13.2"
-singularity: "singularity"
+python: "python/3.8"
+R: "R/4.0"
 samtools: "samtools/1.11"
-umitools: "umitools/1.1.1"
+star: "STAR/2.7.8a"
 subread: "subread/2.0.1"
-R: "R/4.0"
+ultraplex: "ultraplex/1.2.5"
+umitools: "umitools/1.1.1"
+
+#########################################################################################
+# dev
+#########################################################################################
+#testing parameter
+testing_option: "N"

config/snakemake_config.yaml

@@ -71,6 +71,7 @@ seedPerReadNmax: 10000 #max number of seeds per read
 seedPerWindowNmax: 500 #max number of seeds per window
 sjdbScore: 2 #extra alignment score for alignmets that cross database junctions
 winAnchorMultimapNmax: 500 #max number of loci anchors are allowed to map to
+quantmod: 'TranscriptomeSAM' #additionnal alignment on transcriptome
 
 #########################################################################################
 # modules, container parameters

workflow/Snakefile

@@ -89,6 +89,7 @@ star_seed_read = config['seedPerReadNmax']
 star_seed_wind = config['seedPerWindowNmax']
 star_sj = config['sjdbScore']
 star_win_anchor = config['winAnchorMultimapNmax']
+star_quantmod = config['quantmod']
 
 # modules, container
 cont_dir = config['containerDir']
@@ -771,6 +772,7 @@ rule star:
         s_wind = star_seed_wind,
         s_sj = star_sj,
         s_anchor = star_win_anchor,
+        s_quantmod = star_quantmod,
         out_prefix = '{sp}_'
     envmodules:
         config['star'],
@@ -824,7 +826,8 @@ rule star:
         --seedPerReadNmax {params.s_read} \
         --seedPerWindowNmax {params.s_wind} \
         --sjdbScore {params.s_sj} \
-        --winAnchorMultimapNmax {params.s_anchor}
+        --winAnchorMultimapNmax {params.s_anchor} \
+        --quantMode {params.s_quantmod}
 
         # sort file
         samtools sort -m 80G -T $tmp_dir $tmp_dir/{params.out_prefix}Aligned.out.bam -o $tmp_dir/{params.out_prefix}Aligned.sortedByCoord.out.bam

workflow/scripts/02_barcode_qc.R

@@ -29,6 +29,7 @@ barcode_input = args$barcode_input
 output_dir = args$output_dir
 mismatch = as.integer(args$mismatch)
 mpid = args$mpid
+qc_dir = args$qc_dir
 
 #test input
 testing="N"