organization update

HPC_analysis/output/Popgen/angsd/all/README

@@ -0,0 +1,10 @@
+# sign into a node
+ssh himem04
+
+# load 
+module load bio/pcangsd
+
+# source activate as guided when loading 
+
+# call pcangd.py to create .cov files 
+pcangsd.py -plink all_final -e 2 -threads 64 -o ./pcangsd/all_final_pcangsd

HPC_analysis/scripts/lcWGS/F0_Broodstock_angsd_dupscoord.sh → HPC_analysis/scripts/lcWGS/F0_all_juveniles_OM_angsd_dupsquery.sh

@@ -1,29 +1,22 @@
 #!/bin/bash
-#SBATCH --job-name="F0B_angsd_run_dupscoord"
+#SBATCH --job-name="angsdF0alljuvOM"
 #SBATCH -t 500:00:00
 #SBATCH --mail-type=ALL
-#SBATCH --mem=160GB
+#SBATCH --mem=180GB
+#SBATCH -c 20
 #SBATCH -p medmem
 #SBATCH [email protected]
-#SBATCH --output=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_Broodstock/coord_dups/"%x_out.%j"
-#SBATCH --error=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_Broodstock/coord_dups/"%x_err.%j"
+#SBATCH --output=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_all_juveniles/"%x_out.%j"
+#SBATCH --error=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_all_juveniles/"%x_err.%j"
 
 # Set-up
 
-
 # output dir
 mkdir -p angsd/output
 
-
 ## load module
-module load bio/angsd/0.933
-module load bio/samtools/1.15.1
-
-#IDS=('F1_Broodstock' 'F1_Juveniles' 'F2_Juveniles' 'F2_Broodstock' 'F3_Juveniles') # loop strings
-
-## loop vars by treatment (for loop #2)
-#TREATMENT_ALL=('LOWpCO2' 'MODpCO2' 'HIGHpCO2') # a list of the common str on file names and outputs in the for loop below
-
+module load bio/angsd/0.940
+module load bio/samtools/1.19
 
 ## dir shortcuts
 DATDIR=~/Airradians_lcWGS/snakemake_pipeline/angsd/data # Path to generation and life stage bam files
@@ -57,15 +50,14 @@ MINMAF=0.05 # Minimum minor allele frequency filter
 # objective to input a strata / metadta to identify treatments associated with ids downstream..
 
 
-mkdir -p $OUTDIR/F0_Broodstock # make director for ansd output files
-mkdir -p $OUTDIR/FO_Broodstock/coord_dups
+mkdir -p $OUTDIR/all_juveniles # make director for ansd output files
 
 # nav to dir
-cd $DATDIR/F0_Broodstock/merged_bams/coord_dups_removed # NAV TO THE REMOVED DUPLICATES BY QUERYNAME!
-ls ./*.bam | sort | uniq > ./merged_bamlist.txt # create a list of all bam files in merged_bams
+cd $DATDIR/Master_query_dups_removed # NAV TO THE REMOVED DUPLICATES BY QUERYNAME!
+#ls *.bam | sort | uniq > ./merged_bamlist.txt # create a list of all bam files in merged_bams
 
 # cal number of indiv
-nIND=$(wc -l $DATDIR/F0_Broodstock/merged_bams/coord_dups_removed/merged_bamlist.txt | awk '{print $1}') # call and count lines of the bamlist with delimiter id
+nIND=$(wc -l $DATDIR/Master_query_dups_removed/F0_all_juveniles_OM_bamlist.txt | awk '{print $1}') # call and count lines of the bamlist with delimiter id
 minIND=$(echo "(${nIND} * 0.95)" | bc) # min individual is 90% of the total count
 minINDRd=$(printf "%.0f" ${minIND}) # round that
 
@@ -74,11 +66,11 @@ MINDP=$(echo "(${minINDRd} * 5)" | bc) # min coverage of 5X accoutning for the m
 MAXDP=$(echo "(${minINDRd} * 20)" | bc) # max coverage of 20X accounting for the minimum num of individual for genotype calls as 90% and assuming per indiv per loci
 
 # call unique outbase
-OUTBASE='F0Broodstock_doMaf'$DOMAF'_minMaf'$MINMAF'_majorminor'$DOMAJORMINOR'_minind'$minINDRd'_minD5x'$MINDP'_maxD20x'$MAXDP'minDind'$SETMINDEPTHIND'_maxDind'$SETMAXDEPTHIND'_minq'$MINQ'_minmapQ' # Build base name of output files
+OUTBASE='F0_OM_all_juveniles_doMaf'$DOMAF'_minMaf'$MINMAF'_majorminor'$DOMAJORMINOR'_minind'$minINDRd'_minD5x'$MINDP'_maxD20x'$MAXDP'minDind'$SETMINDEPTHIND'_maxDind'$SETMAXDEPTHIND'_minq'$MINQ'_minmapQ' # Build base name of output files
 
 # run angsd
-angsd -b $DATDIR/F0_Broodstock/merged_bams/coord_dups_removed/merged_bamlist.txt \
-    -ref $REFDIR/Argopecten_irradians_irradians_genome.fasta \
+angsd -b $DATDIR/Master_query_dups_removed/F0_all_juveniles_OM_bamlist.txt \
+    -ref $REFDIR/GCA_041381155.1_Ai_NY_genomic.fna \
     -GL $GENOLIKE \
     -doGlf $DOGLF \
     -doMaf $DOMAF \
@@ -103,11 +95,11 @@ angsd -b $DATDIR/F0_Broodstock/merged_bams/coord_dups_removed/merged_bamlist.txt
     -minMapQ $MINMAPQ \
     -minMaf $MINMAF \
     -SNP_pval 1e-6 \
-    -P -20 \
+    -P 2 \
     -remove_bads 1 \
     -only_proper_pairs 1 \
     -uniqueOnly 1 \
     -C 50 \
-    -out $OUTDIR/F0_Broodstock/coord_dups/$OUTBASE \
-    >& $OUTDIR/F0_Broodstock/coord_dups/$OUTBASE'.log';
+    -out $OUTDIR/F0_all_juveniles/$OUTBASE \
+    >& $OUTDIR/F0_all_juveniles/$OUTBASE'.log';
 #done

HPC_analysis/scripts/lcWGS/F0_Broodstock_angsd_dupsquery.sh → HPC_analysis/scripts/lcWGS/F0_all_juveniles_angsd_dupsquery.sh

@@ -1,29 +1,22 @@
 #!/bin/bash
-#SBATCH --job-name="F0B_angsd_run_dupsquery"
+#SBATCH --job-name="angsdF0alljuv"
 #SBATCH -t 500:00:00
 #SBATCH --mail-type=ALL
-#SBATCH --mem=160GB
+#SBATCH --mem=180GB
+#SBATCH -c 20
 #SBATCH -p medmem
 #SBATCH [email protected]
-#SBATCH --output=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_Broodstock/query_dups/"%x_out.%j"
-#SBATCH --error=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_Broodstock/query_dups/"%x_err.%j"
+#SBATCH --output=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_all_juveniles/"%x_out.%j"
+#SBATCH --error=./Airradians_lcWGS/snakemake_pipeline/angsd/output/F0_all_juveniles/"%x_err.%j"
 
 # Set-up
 
-
 # output dir
 mkdir -p angsd/output
 
-
 ## load module
-module load bio/angsd/0.933
-module load bio/samtools/1.15.1
-
-#IDS=('F1_Broodstock' 'F1_Juveniles' 'F2_Juveniles' 'F2_Broodstock' 'F3_Juveniles') # loop strings
-
-## loop vars by treatment (for loop #2)
-#TREATMENT_ALL=('LOWpCO2' 'MODpCO2' 'HIGHpCO2') # a list of the common str on file names and outputs in the for loop below
-
+module load bio/angsd/0.940
+module load bio/samtools/1.19
 
 ## dir shortcuts
 DATDIR=~/Airradians_lcWGS/snakemake_pipeline/angsd/data # Path to generation and life stage bam files
@@ -57,15 +50,14 @@ MINMAF=0.05 # Minimum minor allele frequency filter
 # objective to input a strata / metadta to identify treatments associated with ids downstream..
 
 
-mkdir -p $OUTDIR/F0_Broodstock # make director for ansd output files
-mkdir -p $OUTDIR/FO_Broodstock/query_dups
+mkdir -p $OUTDIR/all_juveniles # make director for ansd output files
 
 # nav to dir
-cd $DATDIR/F0_Broodstock/merged_bams/query_dups_removed # NAV TO THE REMOVED DUPLICATES BY QUERYNAME!
-ls ./*.bam | sort | uniq > ./merged_bamlist.txt # create a list of all bam files in merged_bams
+cd $DATDIR/Master_query_dups_removed # NAV TO THE REMOVED DUPLICATES BY QUERYNAME!
+#ls *.bam | sort | uniq > ./merged_bamlist.txt # create a list of all bam files in merged_bams
 
 # cal number of indiv
-nIND=$(wc -l $DATDIR/F0_Broodstock/merged_bams/query_dups_removed/merged_bamlist.txt | awk '{print $1}') # call and count lines of the bamlist with delimiter id
+nIND=$(wc -l $DATDIR/Master_query_dups_removed/F0_all_juveniles_bamlist.txt | awk '{print $1}') # call and count lines of the bamlist with delimiter id
 minIND=$(echo "(${nIND} * 0.95)" | bc) # min individual is 90% of the total count
 minINDRd=$(printf "%.0f" ${minIND}) # round that
 
@@ -74,11 +66,11 @@ MINDP=$(echo "(${minINDRd} * 5)" | bc) # min coverage of 5X accoutning for the m
 MAXDP=$(echo "(${minINDRd} * 20)" | bc) # max coverage of 20X accounting for the minimum num of individual for genotype calls as 90% and assuming per indiv per loci
 
 # call unique outbase
-OUTBASE='F0Broodstock_doMaf'$DOMAF'_minMaf'$MINMAF'_majorminor'$DOMAJORMINOR'_minind'$minINDRd'_minD5x'$MINDP'_maxD20x'$MAXDP'minDind'$SETMINDEPTHIND'_maxDind'$SETMAXDEPTHIND'_minq'$MINQ'_minmapQ' # Build base name of output files
+OUTBASE='F0_all_juveniles_doMaf'$DOMAF'_minMaf'$MINMAF'_majorminor'$DOMAJORMINOR'_minind'$minINDRd'_minD5x'$MINDP'_maxD20x'$MAXDP'minDind'$SETMINDEPTHIND'_maxDind'$SETMAXDEPTHIND'_minq'$MINQ'_minmapQ' # Build base name of output files
 
 # run angsd
-angsd -b $DATDIR/F0_Broodstock/merged_bams/query_dups_removed/merged_bamlist.txt \
-    -ref $REFDIR/Argopecten_irradians_irradians_genome.fasta \
+angsd -b $DATDIR/Master_query_dups_removed/F0_all_juveniles_bamlist.txt \
+    -ref $REFDIR/GCA_041381155.1_Ai_NY_genomic.fna \
     -GL $GENOLIKE \
     -doGlf $DOGLF \
     -doMaf $DOMAF \
@@ -103,11 +95,11 @@ angsd -b $DATDIR/F0_Broodstock/merged_bams/query_dups_removed/merged_bamlist.txt
     -minMapQ $MINMAPQ \
     -minMaf $MINMAF \
     -SNP_pval 1e-6 \
-    -P -20 \
+    -P 20 \
     -remove_bads 1 \
     -only_proper_pairs 1 \
     -uniqueOnly 1 \
     -C 50 \
-    -out $OUTDIR/F0_Broodstock/query_dups/$OUTBASE \
-    >& $OUTDIR/F0_Broodstock/query_dups/$OUTBASE'.log';
+    -out $OUTDIR/F0_all_juveniles/$OUTBASE \
+    >& $OUTDIR/F0_all_juveniles/$OUTBASE'.log';
 #done