Merge pull request #58 from broadinstitute/dpark-dev

tweak assembly refinement parameters and add iSNV notes

old-scripts/iSNV/example_files/patients_all.txt

@@ -0,0 +1,92 @@
+patient
+EBOV_2014_EM096
+EBOV_2014_EM104
+EBOV_2014_EM106
+EBOV_2014_EM110
+EBOV_2014_EM111
+EBOV_2014_EM112
+EBOV_2014_EM113
+EBOV_2014_EM115
+EBOV_2014_EM119
+EBOV_2014_EM120
+EBOV_2014_EM121
+EBOV_2014_EM124.1
+EBOV_2014_EM124.2
+EBOV_2014_EM124.3
+EBOV_2014_G3670
+EBOV_2014_G3676.1
+EBOV_2014_G3676.2
+EBOV_2014_G3677.1
+EBOV_2014_G3677.2
+EBOV_2014_G3679
+EBOV_2014_G3680
+EBOV_2014_G3682
+EBOV_2014_G3683
+EBOV_2014_G3686
+EBOV_2014_G3687
+EBOV_2014_G3707
+EBOV_2014_G3713.2
+EBOV_2014_G3713.3
+EBOV_2014_G3713.4
+EBOV_2014_G3724
+EBOV_2014_G3729
+EBOV_2014_G3734.1
+EBOV_2014_G3735.1
+EBOV_2014_G3735.2
+EBOV_2014_G3750.1
+EBOV_2014_G3750.2
+EBOV_2014_G3750.3
+EBOV_2014_G3752
+EBOV_2014_G3758
+EBOV_2014_G3764
+EBOV_2014_G3769.1
+EBOV_2014_G3769.2
+EBOV_2014_G3769.3
+EBOV_2014_G3769.4
+EBOV_2014_G3770.1
+EBOV_2014_G3770.2
+EBOV_2014_G3771
+EBOV_2014_G3782
+EBOV_2014_G3786
+EBOV_2014_G3787
+EBOV_2014_G3788
+EBOV_2014_G3789.1
+EBOV_2014_G3795
+EBOV_2014_G3796
+EBOV_2014_G3798
+EBOV_2014_G3799
+EBOV_2014_G3800
+EBOV_2014_G3807
+EBOV_2014_G3808
+EBOV_2014_G3809
+EBOV_2014_G3810.1
+EBOV_2014_G3810.2
+EBOV_2014_G3814
+EBOV_2014_G3816
+EBOV_2014_G3817
+EBOV_2014_G3818
+EBOV_2014_G3819
+EBOV_2014_G3820
+EBOV_2014_G3821
+EBOV_2014_G3822
+EBOV_2014_G3823
+EBOV_2014_G3825.1
+EBOV_2014_G3825.2
+EBOV_2014_G3826
+EBOV_2014_G3827
+EBOV_2014_G3829
+EBOV_2014_G3831
+EBOV_2014_G3834
+EBOV_2014_G3838
+EBOV_2014_G3840
+EBOV_2014_G3841
+EBOV_2014_G3845
+EBOV_2014_G3846
+EBOV_2014_G3848
+EBOV_2014_G3850
+EBOV_2014_G3851
+EBOV_2014_G3856.1
+EBOV_2014_G3856.3
+EBOV_2014_G3857
+EBOV_2014_NM042.1
+EBOV_2014_NM042.3

old-scripts/iSNV/iSNV-pipeline.txt

@@ -0,0 +1,77 @@
+Instructions for calling and validating iSNVs:
+
+1. Calling of iSNVs using VPHASER V2
+
+# PREREQUISITES
+bash
+export LD_LIBRARY_PATH=/seq/viral/analysis/xyang/programs/Library/pezmaster31-bamtools-e235c55/lib:$LD_LIBRARY_PATH
+
+# CALCULATE SNPS WITH VPHASER V2
+for sample in EM096_r1 EM104_r1 EM106_r1 EM110_r1 EM111_r1 EM112_r1 EM113_r1 EM115_r1 EM119_r1 EM120_r1 EM121_r1 EM124.1_r1 EM124.2_r1 EM124.3_r1 EM124.4_r1 G3670.1_r1 G3676.1_r1 G3676.2_r1 G3677.1_r1 G3677.2_r1 G3679.1_r1 G3680.1_r1 G3682.1_r1 G3683.1_r1 G3686.1_r1 G3687.1_r1 G3707_r1 G3713.2_r1 G3713.3_r1 G3713.4_r1 G3724_r1 G3729_r1 G3734.1_r1 G3735.1_r1 G3735.2_r1 G3750.1_r1 G3750.2_r1 G3750.3_r1 G3752_r1 G3758_r1 G3764_r1 G3765.2_r1 G3769.1_r1 G3769.2_r1 G3769.3_r1 G3769.4_r1 G3770.1_r1 G3770.2_r1 G3771_r1 G3782_r1 G3786_r1 G3787_r1 G3788_r1 G3789.1_r1 G3795_r1 G3796_r1 G3798_r1 G3799_r1 G3800_r1 G3805.1_r1 G3805.2_r1 G3807_r1 G3808_r1 G3809_r1 G3810.1_r1 G3810.2_r1 G3814_r1 G3816_r1 G3817_r1 G3818_r1 G3819_r1 G3820_r1 G3821_r1 G3822_r1 G3823_r1 G3825.1_r1 G3825.2_r1 G3826_r1 G3827_r1 G3829_r1 G3831_r1 G3834_r1 G3838_r1 G3840_r1 G3841_r1 G3845_r1 G3846_r1 G3848_r1 G3850_r1 G3851_r1 G3856.1_r1 G3856.3_r1 G3857_r1 NM042.1_r1 NM042.2_r1 NM042.3_r1
+do
+for directory in /idi/sabeti-scratch/kandersen/analysis/140726_ebola3
+do
+for in_directory in $directory/_bams
+do
+bsub -n 4 -R "span[hosts=1]" -q week -R "rusage[mem=8]" -o $directory/_logs/$sample.log.bsub.txt -P sabeti_align -J $sample.vp1 "mkdir $directory/_pileup/vp/$sample && /gsap/garage-viral/viral/analysis/xyang/programs/VariantCaller/bin/variant_caller -i $in_directory/$sample.realigned.bam -ig 6 -o $directory/_pileup/vp/$sample"
+done
+done
+done
+
+#output files from this step at: /idi/sabeti-data/kandersen/analysis/140726_ebola3/_pileup/vp
+#example output file: “EBOV-EM096-SL-2014.var.raw.txt”
+
+
+2. Remap iSNV calls to consistent reference coordinates
+
+#remap all variant calls to same library
+for i in *.var.raw.txt; do j=${i%%-SL-2014*.var.raw.txt}; k=${j##EBOV-}; echo $k;  /seq/viral/analysis/xyang/scripts/align2ref.pl -ref /idi/sabeti-data/rsealfon/viruses/ebolavirus/new_seqs/EBOV_SL_Guinea.fasta.aln.firstseq -seq  /idi/sabeti-scratch/kandersen/analysis/140726_ebola3/_refs/$k"_r1.fasta" -oprefix $i.mapped -vc $i; done 
+
+#complete directory of remap script: /seq/viral/analysis/xyang/scripts/align2ref.pl
+
+
+3. Filter iSNV calls
+
+#filter
+for i in *var.raw.txt.mapped.ref.vc.txt ;do perl ../vphaser2_calls/filter_read_bias.pl $i > $i.filtered; echo $i; done
+
+#the filtering parameters are hard-coded
+#complete directory of filtering script: /idi/sabeti-data/rsealfon/viruses/ebolavirus/iSNV_combined/vphaser2_calls/filter_read_bias.pl
+#script also attached
+
+
+4. Remap the file names
+
+#remap names
+for i in *.filtered; do j=${i%%-SL-2014.var.raw.txt.mapped.ref.vc.txt.filtered}; k=${j##EBOV-}; mv $i "EBOV_2014_"$k.var.raw.txt.mapped.ref.vc.txt.filtered; done
+
+
+5. Combine all of the different samples sequenced in the same library prep
+
+#navigate to folder containing all the .var.raw.txt.mapped.ref.vc.txt.filtered files from step 4
+#run attached python script: concat_samples_NXT1.py
+
+#repeat for validation set, using concat_samples_NXT2.py (this is the same file as _NXT1.py but saves results with a different name
+
+# ‘patients_all.txt’ is just a file listing all the patient names in that sequencing batch
+
+#output files (2) from this step: “vphaser_iSNVs_combined_NXT1.txt” and “vphaser_iSNVs_combined_NXT2.txt”
+
+
+
+6. Apply frequency filter (code not included)
+
+#apply only to original set (NXT1), not validation set (NXT2)
+#remove all rows from “vphaser_iSNVs_combined_NXT1.txt” where the value in the “freq” column is <0.5
+
+#output file from this step: “vphaser_iSNVs_combined_NXT1_freq.txt”
+
+
+7. Validate calls from NXT1 with validation set (NXT2)
+
+#run attached python script: nextera_validation
+#argument 1 = “vphaser_iSNVs_combined_NXT1_freq.txt”
+#argument 2 = “vphaser_iSNVs_combined_NXT2.txt”
+
+#output file from this step: “vphaser_iSNVs_combined_NXT1_freq_validated.txt”
+#final list of iSNV calls