refactor general scripts for Bowtie2 and update

Fix straggling updates including ones from EpitopeID switch to Bowtie2 for the aligner
- refactor update_tagDB.sh utility generate Bowtie2 indexes
- update dependency notes in all of identify-*.sh scripts
- minor fix to identify-Strain.sh report name generation
- adjust genome index file check in identify-Epitope.sh for Bowtie2-named index files
- update gitignore with Bowtie2 index filenames
- update paper README with extra dependencies

Author: owlang

.gitignore

@@ -5,9 +5,21 @@ EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.ann
 EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.bwt
 EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.pac
 EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.sa
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.1.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.2.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.3.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.4.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.rev.1.bt2
+EpitopeID/sacCer3_EpiID/FASTA_genome/genome.fa.rev.2.bt2
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.amb
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.ann
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.bwt
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.pac
 EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.sa
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.1.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.2.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.3.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.4.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.rev.1.bt2
+EpitopeID/hg19_EpiID/FASTA_genome/genome.fa.rev.2.bt2

DeletionID/identify-Deletion.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # Required software:
-# python v2.15 with scipy
+# python3 with scipy
 
 usage()
 {

EpitopeID/identify-Epitope.sh

@@ -5,7 +5,7 @@
 # samtools v1.7+
 # bedtools v2.26+
 # perl5
-# python v2.15 with scipy
+# python3 with scipy
 # GNU grep (BSD grep on MacOSX is >10X slower)
 
 # Unused Software (no-longer required)
@@ -73,15 +73,15 @@ fi
 
 # Check if ALL_TAG.fa aligner index exists, creates if it doesn't
 #if [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.amb ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.ann ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.bwt ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.pac ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.sa ]; then
-if [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.1.bt2 ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.rev.1.bt2 ]; then
+if [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.1.bt2 ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.2.bt2 ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.3.bt2 ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.4.bt2 ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.rev.1.bt2 ] || [ ! -f $DATABASE/FASTA_tag/ALL_TAG.fa.rev.2.bt2 ]; then
 	echo "Building TAG index..."
 	#bwa index $DATABASE/FASTA_tag/ALL_TAG.fa
 	bowtie2-build $DATABASE/FASTA_tag/ALL_TAG.fa $DATABASE/FASTA_tag/ALL_TAG.fa
 fi
 
 # Check if genome.fa aligner index exists, creates if it doesn't
 #if [ ! -f $DATABASE/FASTA_genome/genome.fa.amb ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.ann ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.bwt ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.pac ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.sa ]; then
-if [ ! -f $DATABASE/FASTA_genome/genome.fa.1.bt2 ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.rev.1.bt2 ]; then
+if [ ! -f $DATABASE/FASTA_genome/genome.fa.1.bt2 ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.2.bt2 ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.3.bt2 ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.4.bt2 ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.rev.1.bt2 ] || [ ! -f $DATABASE/FASTA_genome/genome.fa.rev.2.bt2 ]; then
 	echo "Building ORF index..."
 	#bwa index $DATABASE/FASTA_genome/genome.fa
 	bowtie2-build $DATABASE/FASTA_genome/genome.fa $DATABASE/FASTA_genome/genome.fa

EpitopeID/utility_scripts/update_tagDB.sh

@@ -4,13 +4,11 @@
 # and creates a bwa index. The resulting files should be moved into the appropriate /pwd/tag_FASTA/ folder
 
 # Required software:
-# BWA v0.7.14+
+# Bowtie2 v2.2.5+ 
 
 # Remove existing master tag file and bwa indexes if they exist
 rm -f ALL_TAG.fa*
 # Concatenate various posible FASTA files into master index
 cat *.fa *.fna *.ffn *.fasta > ALL_TAG.fa
-# BWA index command
-bwa index ALL_TAG.fa
-
-
+# Bowtie2 index command
+bowtie2-build ALL_TAG.fa ALL_TAG.fa

StrainID/identify-Strain.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # Required software:
-# python v2.15 with pysam
+# python3 with pysam
 
 usage()
 {
@@ -55,7 +55,7 @@ cd $INPUT
 for BAM in *.bam
 do
 
-	SAMPLE=`basename $BAM`
+	SAMPLE=`basename $BAM ".bam"`
 	echo $SAMPLE
 
 	if [[ $SEED -eq "" ]]; then

paper/README.md

@@ -23,7 +23,11 @@ paper
 
 These scripts were built to run on a linux server with a PBS job scheduler set up and some of the dependencies installed using some environmental modules and a conda environment for remaining dependencies. You may need to modify these scripts to account for different server setup and configurations.
 
-See the [GenoPipe documentation](https://pughlab.mbg.cornell.edu/GenoPipe-docs/) for a list of dependencies needed to run these publication-associated scripts. In addition to these dependencies, you will also need to instal [seqtk](https://github.com/lh3/seqtk).
+See the [GenoPipe documentation](https://pughlab.mbg.cornell.edu/GenoPipe-docs/) for a list of dependencies needed to run these publication-associated scripts. In addition to these dependencies, you will also need to install the following:
+
+* [seqtk](https://github.com/lh3/seqtk).
+* sra-toolkit (fastq-dump)
+* wget
 
 ## setup.sh
 Runs the scripts to download and format the yeast and human genomes and other reference files for aligning the data