Initial commit

skills/phylo_from_buscos/templates/pbs/02_compleasm_first.job

@@ -0,0 +1,27 @@
+#!/bin/bash
+#PBS -N compleasm_first
+#PBS -l nodes=1:ppn=TOTAL_THREADS  # Replace with total available CPUs (e.g., 64)
+#PBS -l mem=384gb  # Adjust based on ppn × 6GB
+#PBS -l walltime=24:00:00
+
+cd $PBS_O_WORKDIR
+source ~/.bashrc
+conda activate phylo
+
+mkdir -p logs
+mkdir -p 01_busco_results
+
+# Process FIRST genome only (downloads lineage database)
+first_genome=$(head -n 1 genome_list.txt)
+genome_name=$(basename ${first_genome} .fasta)
+echo "Processing first genome: ${genome_name} with $PBS_NUM_PPN threads..."
+echo "This will download the BUSCO lineage database for subsequent runs."
+
+compleasm run \
+  -a ${first_genome} \
+  -o 01_busco_results/${genome_name}_compleasm \
+  -l LINEAGE \
+  -t $PBS_NUM_PPN
+
+echo "First genome complete! Lineage database is now cached."
+echo "Submit the parallel job for remaining genomes: qsub run_compleasm_parallel.job"

skills/phylo_from_buscos/templates/pbs/02_compleasm_parallel.job

@@ -0,0 +1,24 @@
+#!/bin/bash
+#PBS -N compleasm_parallel
+#PBS -t 2-NUM_GENOMES  # Start from genome 2 (first genome already processed)
+#PBS -l nodes=1:ppn=THREADS_PER_JOB  # e.g., 16 for 64-core system
+#PBS -l mem=96gb  # Adjust based on ppn × 6GB
+#PBS -l walltime=48:00:00
+
+cd $PBS_O_WORKDIR
+source ~/.bashrc
+conda activate phylo
+
+mkdir -p 01_busco_results
+
+# Get genome for this array task
+genome=$(sed -n "${PBS_ARRAYID}p" genome_list.txt)
+genome_name=$(basename ${genome} .fasta)
+
+echo "Processing ${genome_name} with $PBS_NUM_PPN threads..."
+
+compleasm run \
+  -a ${genome} \
+  -o 01_busco_results/${genome_name}_compleasm \
+  -l LINEAGE \
+  -t $PBS_NUM_PPN

skills/phylo_from_buscos/templates/pbs/08a_partition_search.job

@@ -0,0 +1,22 @@
+#!/bin/bash
+#PBS -N iqtree_partition
+#PBS -l nodes=1:ppn=18
+#PBS -l mem=72gb
+#PBS -l walltime=72:00:00
+
+cd $PBS_O_WORKDIR/06_concatenation
+source ~/.bashrc
+conda activate phylo
+
+iqtree \
+  -s FcC_supermatrix.fas \
+  -spp partition_def.txt \
+  -nt 18 \
+  -safe \
+  -pre partition_search \
+  -m TESTMERGEONLY \
+  -mset MODEL_SET \
+  -msub nuclear \
+  -rcluster 10 \
+  -bb 1000 \
+  -alrt 1000

skills/phylo_from_buscos/templates/pbs/08c_gene_trees_array.job

@@ -0,0 +1,26 @@
+#!/bin/bash
+#PBS -N iqtree_genes
+#PBS -t 1-NUM_LOCI
+#PBS -l nodes=1:ppn=1
+#PBS -l mem=4gb
+#PBS -l walltime=2:00:00
+
+cd $PBS_O_WORKDIR/trimmed_aa
+source ~/.bashrc
+conda activate phylo
+
+# Create list of alignments if not present
+if [ ! -f locus_alignments.txt ]; then
+    ls *_trimmed.fas > locus_alignments.txt
+fi
+
+locus=$(sed -n "${PBS_ARRAYID}p" locus_alignments.txt)
+
+iqtree \
+  -s ${locus} \
+  -m MFP \
+  -bb 1000 \
+  -bnni \
+  -czb \
+  -pre $(basename ${locus} _trimmed.fas) \
+  -nt 1