Merge branch 'main' of https://github.com/compbiocore/ccv_bootcamp_ph…

…ylogenetics

.gitignore

@@ -0,0 +1,2 @@
+scripts/logs
+results

scripts/00_env.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # make results folder
-mkdir -p results
+mkdir -p ../results
 
 # download singularity image
 apptainer pull ../metadata/bootcamp.sif docker://ghcr.io/compbiocore/ccv_bootcamp_phylogenetics:latest

scripts/01_iqtree_init.sh → scripts/01_init.sh

@@ -5,7 +5,8 @@
 #SBATCH -e logs/iqtree_init-%J.err
 #SBATCH -o logs/iqtree_init-%J.out
 
-WORKDIR=/oscar/data/datasci/aguang/ccv_bootcamp_phylogenetics
+#WORKDIR=/users/aguang/ccv_bootcamp_phylogenetics
+WORKDIR=~/ccv_bootcamp_phylogenetics
 
 export SINGULARITY_BINDPATH="${WORKDIR}"
 IMG=${WORKDIR}/metadata/bootcamp.sif

scripts/02_partition.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+#SBATCH -t 00:20:00
+#SBATCH --mem 4G
+#SBATCH --cpus-per-task=8
+#SBATCH -e logs/partition-%J.err
+#SBATCH -o logs/partition-%J.out
+
+WORKDIR=/users/aguang/ccv_bootcamp_phylogenetics
+
+export SINGULARITY_BINDPATH="${WORKDIR}"
+IMG=${WORKDIR}/metadata/bootcamp.sif
+
+# allows each partition to have its own model
+# -p turtle.nex to specify an edge-linked proportional partition model (Chernomor et al., 2016).
+# That means, there is one set of branch lengths.
+# But each partition can have proportionally shorter or longer tree length,
+# representing slow or fast evolutionary rate, respectively.
+
+singularity exec ${IMG} iqtree2 -s ${WORKDIR}/data/turtle.fa -p ${WORKDIR}/data/turtle.nex -B 1000 -T AUTO -pre ${WORKDIR}/results/partition

scripts/03_bestscheme_topotest.sh~

@@ -0,0 +1,28 @@
+#!/bin/bash
+#SBATCH -t 00:20:00
+#SBATCH --mem 4G
+#SBATCH --cpus-per-task=8
+#SBATCH -e logs/test-%J.err
+#SBATCH -o logs/test-%J.out
+
+WORKDIR=/users/aguang/ccv_bootcamp_phylogenetics
+
+export SINGULARITY_BINDPATH="${WORKDIR}"
+IMG=${WORKDIR}/metadata/bootcamp.sif
+
+# Runs PartitionFinder algorithm to merge partitions to reduce overfitting
+# -m MFP+MERGE performs PartitionFinder + tree reconstruction
+# -rcluster 10 reduces computations by only examining top 10% partitioning schemes using relaxed clustering
+
+singularity exec ${IMG} iqtree2 -s ${WORKDIR}/data/turtle.fa -p ${WORKDIR}/data/turtle.nex -B 1000 -T AUTO -m MFP+MERGE -rcluster 10 -pre ${WORKDIR}/results/merge
+
+# topology test
+# concatenate single + partition trees into trees file
+# -p merge.best_scheme.nex provides best partitioning scheme found from ModelFinder
+# -z turtle.trees inputs set of trees
+# -zb 10000 number of replicates for bootstrap for test
+# -au Approximately Unbiased test
+# -n 0 avoids tree search, just does testing
+
+cat ${WORKDIR}/results/turtle.treefile ${WORKDIR}/results/partition.treefile >${WORKDIR}/results/turtle.trees
+singularity exec ${IMG} iqtree2 -s ${WORKDIR}/data/turtle.fa -p ${WORKDIR}/results/merge.best_scheme.nex -z ${WORKDIR}/results/turtle.trees -zb 10000 -au -n 0 --pre ${WORKDIR}/results/topo

scripts/03_topo.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+#SBATCH -t 00:20:00
+#SBATCH --mem 4G
+#SBATCH --cpus-per-task=8
+#SBATCH -e logs/test-%J.err
+#SBATCH -o logs/test-%J.out
+
+WORKDIR=/users/aguang/ccv_bootcamp_phylogenetics
+
+export SINGULARITY_BINDPATH="${WORKDIR}"
+IMG=${WORKDIR}/metadata/bootcamp.sif
+
+# Runs PartitionFinder algorithm to merge partitions to reduce overfitting
+# -m MFP+MERGE performs PartitionFinder + tree reconstruction
+# -rcluster 10 reduces computations by only examining top 10% partitioning schemes using relaxed clustering
+
+singularity exec ${IMG} iqtree2 -s ${WORKDIR}/data/turtle.fa -p ${WORKDIR}/data/turtle.nex -B 1000 -T AUTO -m MFP+MERGE -rcluster 10 -pre ${WORKDIR}/results/merge
+
+# topology test
+# concatenate single + partition trees into trees file
+# -p merge.best_scheme.nex provides best partitioning scheme found from ModelFinder
+# -z turtle.trees inputs set of trees
+# -zb 10000 number of replicates for bootstrap for test
+# -au Approximately Unbiased test
+# -n 0 avoids tree search, just does testing
+
+cat ${WORKDIR}/results/turtle.treefile ${WORKDIR}/results/partition.treefile >${WORKDIR}/results/turtle.trees
+singularity exec ${IMG} iqtree2 -s ${WORKDIR}/data/turtle.fa -p ${WORKDIR}/results/merge.best_scheme.nex -z ${WORKDIR}/results/turtle.trees -zb 10000 -au -n 0 -pre ${WORKDIR}/results/topo