update to HLAminer

Ability to stream the (.sam) output of modern read  aligners, directly
into HLAminer.
Initial support for predicting HLA types from long nanopore reads such
as those from Oxford Nanopore Technologies.
Better information/sub-routine/date tracking in hlaminer

HLAminer-1.4/bin/HPRArnaseq_classI-II.sh

@@ -0,0 +1,8 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa..."
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA-I_II_CDS.fasta rd1.fq > aln_test.1.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA-I_II_CDS.fasta rd2.fq > aln_test.2.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa sampe -o 1000 ../database/HLA-I_II_CDS.fasta aln_test.1.sai aln_test.2.sai rd1.fq rd2.fq > aln.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -h ../database/HLA-I_II_CDS.fasta -s 500

HLAminer-1.4/bin/HPRArnaseq_classI-II_SE.sh

@@ -0,0 +1,7 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa..."
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA-I_II_CDS.fasta rd1.fq > aln_test.1.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa samse ../database/HLA-I_II_CDS.fasta aln_test.1.sai rd1.fq > aln.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -e 1 -h ../database/HLA-I_II_CDS.fasta -s 500

HLAminer-1.4/bin/HPRArnaseq_classI.sh

@@ -0,0 +1,16 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa v0.7.17-r1188"
+bwa aln -e 0 -o 0 ../database/HLA_ABC_CDS.fasta rd1.fq > aln_test.1.sai
+bwa aln -e 0 -o 0 ../database/HLA_ABC_CDS.fasta rd2.fq > aln_test.2.sai
+bwa sampe -o 1000 ../database/HLA_ABC_CDS.fasta aln_test.1.sai aln_test.2.sai rd1.fq rd2.fq > aln.sam
+
+#echo "Running bwa mem..."
+#/gsc/btl/linuxbrew/bin/bwa mem -a ../database_bwamem/HLA_ABC_CDS.fasta rd1.fq rd2.fq > TEST_vs_HLA.sam
+#echo "Fixing MD tag..."
+#/gsc/btl/linuxbrew/bin/samtools fillmd -S TEST_vs_HLA.sam ../database_bwamem/HLA_ABC_CDS.fasta > aln.sam
+
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -h ../database/HLA_ABC_CDS.fasta -s 500
+mv HLAminer_HPRA.csv HLAminer_HPRArun.csv
+mv HLAminer_HPRA.log HLAminer_HPRArun.log

HLAminer-1.4/bin/HPRArnaseq_classI_SE.sh

@@ -0,0 +1,7 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa..."
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA_ABC_CDS.fasta rd1.fq > aln_test.1.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa samse ../database/HLA_ABC_CDS.fasta aln_test.1.sai rd1.fq  > aln.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -e 1 -h ../database/HLA_ABC_CDS.fasta -s 500

HLAminer-1.4/bin/HPRArnaseq_pacbioSEclassI.sh

@@ -0,0 +1,14 @@
+### Run bwa or your favorite short read aligner
+#echo "Building bwa index..."
+#/gsc/btl/linuxbrew/bin/bwa index HLA_ABC_CDS.fasta
+echo "Downloading MCF-7 pacbio RNA-seq reads..."
+wget http://datasets.pacb.com.s3.amazonaws.com/2013/IsoSeqHumanMCF7Transcriptome/IsoSeq_MCF7_polished.unimapped.fasta
+echo "Running bwa mem..."
+/gsc/btl/linuxbrew/bin/bwa mem -x pacbio ../database_bwamem/HLA_ABC_CDS.fasta IsoSeq_MCF7_polished.unimapped.fasta > MCF7_vs_HLA.sam
+echo "Fixing MD tag..."
+/gsc/btl/linuxbrew/bin/samtools fillmd -S MCF7_vs_HLA.sam ../database_bwamem/HLA_ABC_CDS.fasta > MCF7_vs_HLAmd.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a MCF7_vs_HLAmd.sam -h ../database_bwamem/HLA_ABC_CDS.fasta -s 500 -q 1 -i 1 -e 1
+mv HLAminer_HPRA.csv HLAminer_HPRA_MCF-7.csv
+mv HLAminer_HPRA.log HLAminer_HPRA_MCF-7.log

HLAminer-1.4/bin/HPRAwgs_ONTclassI-IIdemo.sh

@@ -0,0 +1,10 @@
+echo "Predicting HLA from raw ONT reads for human NA19240..." 
+echo "Fetching raw ONT promethion ERR2585115 data (Yoruban individual NA19240)..."
+wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR258/005/ERR2585115/ERR2585115.fastq.gz
+echo "Fetching database for alignment..."
+wget http://www.bcgsc.ca/downloads/btl/hlaminer/GCA_000001405.15_GRCh38_genomic.chr-only-noChr6-HLA-I_II_GEN.fa.gz
+####
+echo "Running minimap2 (minimap2-2.12-r827) and HLAminer v1.4 combined ..."
+/usr/bin/time -v -o minimap_hlaminerERR2585115_GEN.time minimap2 -t 60 -ax map-ont --MD GCA_000001405.15_GRCh38_genomic.chr-only-noChr6-HLA-I_II_GEN.fa.gz ERR2585115.fastq.gz | ../bin/HLAminer.pl -h ../database/HLA-I_II_GEN.fasta -s 500 -q 1 -i 1 -p ../database/hla_nom_p.txt -a stream
+mv HLAminer_HPRA.csv HLAminer_HPRA_ERR2585115.csv
+mv HLAminer_HPRA.log HLAminer_HPRA_ERR2585115.log

HLAminer-1.4/bin/HPRAwgs_classI-II.sh

@@ -0,0 +1,8 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa..."
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA-I_II_GEN.fasta rd1.fq > aln_test.1.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA-I_II_GEN.fasta rd2.fq > aln_test.2.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa sampe -o 1000 ../database/HLA-I_II_GEN.fasta aln_test.1.sai aln_test.2.sai rd1.fq rd2.fq > aln.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -h ../database/HLA-I_II_GEN.fasta -s 500

HLAminer-1.4/bin/HPRAwgs_classI-II_SE.sh

@@ -0,0 +1,7 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa..."
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA-I_II_GEN.fasta rd1.fq > aln_test.1.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa samse ../database/HLA-I_II_GEN.fasta aln_test.1.sai rd1.fq > aln.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -e 1 -h ../database/HLA-I_II_GEN.fasta -s 500

HLAminer-1.4/bin/HPRAwgs_classI.sh

@@ -0,0 +1,8 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa..."
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA_ABC_GEN.fasta rd1.fq > aln_test.1.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA_ABC_GEN.fasta rd2.fq > aln_test.2.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa sampe -o 1000 ../database/HLA_ABC_GEN.fasta aln_test.1.sai aln_test.2.sai rd1.fq rd2.fq > aln.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -h ../database/HLA_ABC_GEN.fasta -s 500

HLAminer-1.4/bin/HPRAwgs_classI_SE.sh

@@ -0,0 +1,7 @@
+### Run bwa or your favorite short read aligner
+echo "Running bwa..."
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa aln -e 0 -o 0 ../database/HLA_ABC_GEN.fasta rd1.fq > aln_test.1.sai
+/home/pubseq/BioSw/bwa/bwa-0.5.9/bwa samse ../database/HLA_ABC_GEN.fasta aln_test.1.sai rd1.fq > aln.sam
+### Predict HLA
+echo "Predicting HLA..."
+../bin/HLAminer.pl -a aln.sam -e 1 -h ../database/HLA_ABC_GEN.fasta -s 500

HLAminer-1.4/bin/HPTASRrnaseq_classI-II.sh

@@ -0,0 +1,18 @@
+###Run TASR
+echo "Running TASR..."
+#TASR Default is -k 15 for recruiting reads. You may increase k, as long as k < L/2 where L is the minimum shotgun read length
+../bin/TASR -f patient.fof -m 20 -k 20 -s ../database/HLA-I_II_CDS.fasta -i 1 -b TASRhla -w 1
+###Restrict 200nt+ contigs
+cat TASRhla.contigs |perl -ne 'if(/size(\d+)/){if($1>=200){$flag=1;print;}else{$flag=0;}}else{print if($flag);}' > TASRhla200.contigs
+###Create a [NCBI] blastable database
+echo "Formatting blastable database..."
+../bin/formatdb -p F -i TASRhla200.contigs
+###Align HLA contigs to references
+echo "Aligning TASR contigs to HLA references..."
+../bin/parseXMLblast.pl -c ncbiBlastConfig.txt -d ../database/HLA-I_II_CDS.fasta -i TASRhla200.contigs -o 0 -a 1 > tig_vs_hla-ncbi.coord
+###Align HLA references to contigs
+echo "Aligning HLA references to TASR contigs (go have a coffee, it may take a while)..."
+../bin/parseXMLblast.pl -c ncbiBlastConfig.txt -i ../database/HLA-I_II_CDS.fasta -d TASRhla200.contigs -o 0 > hla_vs_tig-ncbi.coord
+###Predict HLA alleles
+echo "Predicting HLA alleles..."
+../bin/HLAminer.pl -b tig_vs_hla-ncbi.coord -r hla_vs_tig-ncbi.coord -c TASRhla200.contigs -h ../database/HLA-I_II_CDS.fasta

HLAminer-1.4/bin/HPTASRrnaseq_classI.sh

@@ -0,0 +1,18 @@
+###Run TASR
+echo "Running TASR..."
+#TASR Default is -k 15 for recruiting reads. You may increase k, as long as k < L/2 where L is the minimum shotgun read length
+../bin/TASR -f patient.fof -m 20 -k 20 -s ../database/HLA_ABC_CDS.fasta -i 1 -b TASRhla -w 1
+###Restrict 200nt+ contigs
+cat TASRhla.contigs |perl -ne 'if(/size(\d+)/){if($1>=200){$flag=1;print;}else{$flag=0;}}else{print if($flag);}' > TASRhla200.contigs
+###Create a [NCBI] blastable database
+echo "Formatting blastable database..."
+../bin/formatdb -p F -i TASRhla200.contigs
+###Align HLA contigs to references
+echo "Aligning TASR contigs to HLA references..."
+../bin/parseXMLblast.pl -c ncbiBlastConfigO.txt -d ../database/HLA_ABC_CDS.fasta -i TASRhla200.contigs -o 0 -a 1 > tig_vs_hla-ncbi.coord
+###Align HLA references to contigs
+echo "Aligning HLA references to TASR contigs (go have a coffee, it may take a while)..."
+../bin/parseXMLblast.pl -c ncbiBlastConfigO.txt -i ../database/HLA_ABC_CDS.fasta -d TASRhla200.contigs -o 0 > hla_vs_tig-ncbi.coord
+###Predict HLA alleles
+echo "Predicting HLA alleles..."
+../bin/HLAminer.pl -b tig_vs_hla-ncbi.coord -r hla_vs_tig-ncbi.coord -c TASRhla200.contigs -h ../database/HLA_ABC_CDS.fasta

HLAminer-1.4/bin/HPTASRwgs_classI-II.sh

@@ -0,0 +1,18 @@
+###Run TASR
+echo "Running TASR..."
+#TASR Default is -k 15 for recruiting reads. You may increase k, as long as k < L/2 where L is the minimum shotgun read length
+../bin/TASR -f patient.fof -m 20 -k 20 -s ../database/HLA-I_II_GEN.fasta -i 1 -b TASRhla -w 1
+###Restrict 200nt+ contigs
+cat TASRhla.contigs |perl -ne 'if(/size(\d+)/){if($1>=200){$flag=1;print;}else{$flag=0;}}else{print if($flag);}' > TASRhla200.contigs
+###Create a [NCBI] blastable database
+echo "Formatting blastable database..."
+../bin/formatdb -p F -i TASRhla200.contigs
+###Align contigs against database
+echo "Aligning TASR contigs to HLA references..."
+../bin/parseXMLblast.pl -c ncbiBlastConfig.txt -d ../database/HLA-I_II_GEN.fasta -i TASRhla200.contigs -o 0 -a 1 > tig_vs_hla-ncbi.coord
+###Align HLA references to contigs
+echo "Aligning HLA references to TASR contigs (go have a coffee, it may take a while)..."
+../bin/parseXMLblast.pl -c ncbiBlastConfig.txt -i ../database/HLA-I_II_GEN.fasta -d TASRhla200.contigs -o 0 > hla_vs_tig-ncbi.coord
+###Predict HLA alleles
+echo "Predicting HLA alleles..."
+../bin/HLAminer.pl -b tig_vs_hla-ncbi.coord -r hla_vs_tig-ncbi.coord -c TASRhla200.contigs -h ../database/HLA-I_II_GEN.fasta

HLAminer-1.4/bin/HPTASRwgs_classI.sh

@@ -0,0 +1,18 @@
+###Run TASR
+echo "Running TASR..."
+#TASR Default is -k 15 for recruiting reads. You may increase k, as long as k < L/2 where L is the minimum shotgun read length
+../bin/TASR -f patient.fof -m 20 -k 20 -s ../database/HLA_ABC_GEN.fasta -i 1 -b TASRhla -w 1
+###Restrict 200nt+ contigs
+cat TASRhla.contigs |perl -ne 'if(/size(\d+)/){if($1>=200){$flag=1;print;}else{$flag=0;}}else{print if($flag);}' > TASRhla200.contigs
+###Create a [NCBI] blastable database
+echo "Formatting blastable database..."
+../bin/formatdb -p F -i TASRhla200.contigs
+###Align contigs against database
+echo "Aligning TASR contigs to HLA references..."
+../bin/parseXMLblast.pl -c ncbiBlastConfig.txt -d ../database/HLA_ABC_GEN.fasta -i TASRhla200.contigs -o 0 -a 1 > tig_vs_hla-ncbi.coord
+###Align HLA references to contigs
+echo "Aligning HLA references to TASR contigs (go have a coffee, it may take a while)..."
+../bin/parseXMLblast.pl -c ncbiBlastConfig.txt -i ../database/HLA_ABC_GEN.fasta -d TASRhla200.contigs -o 0 > hla_vs_tig-ncbi.coord
+###Predict HLA alleles
+echo "Predicting HLA alleles..."
+../bin/HLAminer.pl -b tig_vs_hla-ncbi.coord -r hla_vs_tig-ncbi.coord -c TASRhla200.contigs -h ../database/HLA_ABC_GEN.fasta