Add a population clustering fraction cutoff argument (#39)

* Add population cutoff parameter * Clean MIPWrangler scripts * Update changelog
bailey-lab · May 9, 2022 · 25ef3b9 · 25ef3b9
1 parent 4376805
commit 25ef3b9
Show file tree

Hide file tree

Showing 10 changed files with 72 additions and 44 deletions.
diff --git a/MIPTools.def b/MIPTools.def
@@ -307,6 +307,8 @@ From: amd64/ubuntu:20.04
         echo "  -c    Number of available processors to use. Default: 1."
         echo "  -e    Required. A unique ID given to each sequencing run by"
         echo "        the user."
+        echo "  -f    The population fraction cutoff used by MIPWrangler."
+        echo "        Default: 0.005."
         echo "  -h    Print the help page."
         echo "  -k    Keep intermediate files generated by MIPWrangler."
         echo "  -l    Required. File providing a list of samples with "
@@ -354,12 +356,14 @@ From: amd64/ubuntu:20.04
     min_capture_length="none"
     stitch_options="none"
     keep_files=""
+    population_fraction_cutoff=0.005
 
     # Parse options
-    while getopts "c:e:hkl:m:n:p:s:w:x:" opt; do
+    while getopts "c:e:f:hkl:m:n:p:s:w:x:" opt; do
         case ${opt} in
             c) cpu_count=${OPTARG} ;;
             e) experiment_id=${OPTARG} ;;
+            f) population_fraction_cutoff=${OPTARG} ;;
             h) help
                exit 1 ;;
             k) keep_files=-k ;;
@@ -394,7 +398,7 @@ From: amd64/ubuntu:20.04
     -c ${cpu_count} -e ${experiment_id} ${keep_files} \
     -l /opt/analysis/${sample_list} -m ${min_capture_length} \
     -n ${server_number} -p ${probe_sets} -s ${sample_sets} \
-    -w ${cluster_script} -x ${stitch_options}
+    -w ${cluster_script} -x ${stitch_options} -f ${population_fraction_cutoff}
 
     # Run wrangler scripts.
     # The dot space is used to let the sourced script modify the current

diff --git a/base_resources/MIPWrangler_scripts/runMIPWranglerCurrent.sh b/base_resources/MIPWrangler_scripts/runMIPWranglerCurrent.sh
@@ -1,11 +1,18 @@
 #!/usr/bin/env bash
-if [[ $# -ne 2 ]]; then
-    echo "Illegal number of parameters, needs 2 argument, 1) name of mip server number, 2) num of threads to use"
-    exit
+
+if [[ $# -ne 3 ]]; then
+    msg="Illegal number of parameters. Needs three arguments:\n"
+    msg="${msg}1) The name of the MIP server number\n"
+    msg="${msg}2) The number of threads to use\n"
+    msg="${msg}3) The population clustering fraction cutoff."
+    echo ${msg} >&2
+    exit 2
 fi
 
+# Correct barcodes
 MIPWrangler mipBarcodeCorrectionMultiple                --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipBarcodeCorrecting_run1 --allowableErrors 6
 MIPWrangler mipCorrectForContamWithSameBarcodesMultiple --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipCorrectForContamWithSameBarcodes_run1
+
+# Cluster barcodes and MIPs
 MIPWrangler mipClusteringMultiple                       --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipClustering_run1 --par /opt/resources/clustering_pars/illumina_collapseHomoploymers.pars.txt --countEndGaps
-MIPWrangler mipPopulationClusteringMultiple             --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipPopClustering_run1 --cutoff 0 --countEndGaps
-#nohup MIPWrangler mav			                        --masterDir $(realpath ./)  --numThreads $2 --port $((10000+$1)) --name mip$1  &
+MIPWrangler mipPopulationClusteringMultiple             --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipPopClustering_run1 --cutoff 0 --countEndGaps --fraccutoff $3
diff --git a/base_resources/MIPWrangler_scripts/runMIPWranglerNoCutoffCurrent.sh b/base_resources/MIPWrangler_scripts/runMIPWranglerNoCutoffCurrent.sh
diff --git a/base_resources/MIPWrangler_scripts/runMIPWranglerSwga.sh b/base_resources/MIPWrangler_scripts/runMIPWranglerSwga.sh
@@ -1,11 +1,18 @@
 #!/usr/bin/env bash
-if [[ $# -ne 2 ]]; then
-    echo "Illegal number of parameters, needs 2 argument, 1) name of mip server number, 2) num of threads to use"
-    exit
+
+if [[ $# -ne 3 ]]; then
+    msg="Illegal number of parameters. Needs three arguments:\n"
+    msg="${msg}1) The name of the MIP server number\n"
+    msg="${msg}2) The number of threads to use\n"
+    msg="${msg}3) The population clustering fraction cutoff."
+    echo ${msg} >&2
+    exit 2
 fi
 
+# Correct barcodes
 MIPWrangler mipBarcodeCorrectionMultiple                --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipBarcodeCorrecting_run1 --allowableErrors 6
 MIPWrangler mipCorrectForContamWithSameBarcodesMultiple --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipCorrectForContamWithSameBarcodes_run1
+
+# Cluster barcodes and MIPs
 MIPWrangler mipClusteringMultiple                       --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipClustering_run1 --par /opt/resources/clustering_pars/illumina_swga.pars.txt --countEndGaps
 MIPWrangler mipPopulationClusteringMultiple             --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipPopClustering_run1 --cutoff 0 --countEndGaps
-#nohup MIPWrangler mav			                        --masterDir $(realpath ./)  --numThreads $2 --port $((10000+$1)) --name mip$1  &
diff --git a/base_resources/MIPWrangler_scripts/runMIPWranglerSwgaPop.sh b/base_resources/MIPWrangler_scripts/runMIPWranglerSwgaPop.sh
@@ -1,11 +1,18 @@
 #!/usr/bin/env bash
-if [[ $# -ne 2 ]]; then
-    echo "Illegal number of parameters, needs 2 argument, 1) name of mip server number, 2) num of threads to use"
-    exit
+
+if [[ $# -ne 3 ]]; then
+    msg="Illegal number of parameters. Needs three arguments:\n"
+    msg="${msg}1) The name of the MIP server number\n"
+    msg="${msg}2) The number of threads to use\n"
+    msg="${msg}3) The population clustering fraction cutoff."
+    echo ${msg} >&2
+    exit 2
 fi
 
+# Correct barcodes
 MIPWrangler mipBarcodeCorrectionMultiple                --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipBarcodeCorrecting_run1 --allowableErrors 6
 MIPWrangler mipCorrectForContamWithSameBarcodesMultiple --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipCorrectForContamWithSameBarcodes_run1
+
+# Cluster barcodes and MIPs
 MIPWrangler mipClusteringMultiple                       --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipClustering_run1 --par /opt/resources/clustering_pars/illumina_swga_pop.pars.txt --countEndGaps
 MIPWrangler mipPopulationClusteringMultiple             --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipPopClustering_run1 --cutoff 0 --countEndGaps
-#nohup MIPWrangler mav			                        --masterDir $(realpath ./)  --numThreads $2 --port $((10000+$1)) --name mip$1  &
diff --git a/bin/runMIPWranglerCurrent.sh b/bin/runMIPWranglerCurrent.sh
@@ -1,11 +1,18 @@
 #!/usr/bin/env bash
-if [[ $# -ne 2 ]]; then
-    echo "Illegal number of parameters. Needs 2 arguments: 1) name of mip server number, 2) num of threads to use." >&2
+
+if [[ $# -ne 3 ]]; then
+    msg="Illegal number of parameters. Needs three arguments:\n"
+    msg="${msg}1) The name of the MIP server number\n"
+    msg="${msg}2) The number of threads to use\n"
+    msg="${msg}3) The population clustering fraction cutoff."
+    echo ${msg} >&2
     exit 2
 fi
 
+# Correct barcodes
 MIPWrangler mipBarcodeCorrectionMultiple                --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipBarcodeCorrecting_run1 --allowableErrors 6
 MIPWrangler mipCorrectForContamWithSameBarcodesMultiple --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipCorrectForContamWithSameBarcodes_run1
+
+# Cluster barcodes and MIPs
 MIPWrangler mipClusteringMultiple                       --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipClustering_run1 --par /opt/resources/clustering_pars/illumina_collapseHomoploymers.pars.txt --countEndGaps
-MIPWrangler mipPopulationClusteringMultiple             --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipPopClustering_run1 --cutoff 0 --countEndGaps
-#nohup MIPWrangler mav			                        --masterDir $(realpath ./)  --numThreads $2 --port $((10000+$1)) --name mip$1  &
+MIPWrangler mipPopulationClusteringMultiple             --masterDir $(realpath ./)  --numThreads $2 --overWriteDirs --overWriteLog --logFile mipPopClustering_run1 --cutoff 0 --countEndGaps --fraccutoff $3
diff --git a/bin/runMIPWranglerNoCutoffCurrent.sh b/bin/runMIPWranglerNoCutoffCurrent.sh
diff --git a/docs/CHANGELOG.rst b/docs/CHANGELOG.rst
@@ -8,10 +8,12 @@ MIPTools (development version)
 New Features
 ------------
 
+-  Add an additional argument to the ``wrangler`` app to control the population
+   clustering fraction cutoff defined by :github:repo:`MIPWrangler
+   <bailey-lab/MIPWrangler>` (:github:user:`arisp99`, :github:pull:`39`).
 -  Add the capability to freeze software version numbers when building the
    container. Additionally, the version number for key software tools has been
-   fixed (:github:user:`arisp99`,
-   :github:pull:`32`).
+   fixed (:github:user:`arisp99`, :github:pull:`32`).
 -  Install :github:repo:`mipscripts <bailey-lab/mipscripts>`, which contains
    additional tools for analysis pipelines.
 -  Perform additional argument parsing to ensure arguments are formatted

diff --git a/docs/app-reference/wrangler-app.rst b/docs/app-reference/wrangler-app.rst
@@ -29,6 +29,7 @@ Options
 
 	# Optional
 	-c    Number of available processors to use.
+	-f    Population fraction cutoff used by MIPWrangler.
 	-h    Print the help page.
 	-k    Keep intermediate files generated by MIPWrangler.
 	-m    Minimum capture length for stitching excluding probe arms.
@@ -44,6 +45,7 @@ Defaults
 
 	# Optional
 	-c    Default: 1
+	-f    Default: 0.005
 	-k    Default: false
 	-m    Default: 100
 	-n    Default: 1

diff --git a/src/generate_wrangler_scripts.py b/src/generate_wrangler_scripts.py
@@ -106,6 +106,13 @@
     help="Minimum capture length for stitching, excluding probe arms.",
     type=int,
 )
+parser.add_argument(
+    "-f",
+    "--population-fraction-cutoff",
+    help="Population clustering fraction cutoff.",
+    default=0.005,
+    type=float,
+)
 
 # Parse arguments from command line
 args = vars(parser.parse_args())
@@ -312,7 +319,14 @@
 )
 wrangler_commands = [
     ["cd", "analysis"],
-    ["nohup", "bash", cluster_script, str(server_num), str(cpu_count)],
+    [
+        "nohup",
+        "bash",
+        cluster_script,
+        str(server_num),
+        str(cpu_count),
+        str(args["population_fraction_cutoff"]),
+    ],
     ["mv", os.path.join(analysis_dir, "analysis/logs"), analysis_dir],
     ["mv", os.path.join(analysis_dir, "analysis/scripts"), analysis_dir],
     ["mv", os.path.join(analysis_dir, "analysis/resources"), analysis_dir],