cluster snps to process reference once

calico · Sep 11, 2023 · 4799a4e · 4799a4e
1 parent dd1250d
commit 4799a4e
Show file tree

Hide file tree

Showing 4 changed files with 400 additions and 152 deletions.
diff --git a/src/baskerville/scripts/hound_snp.py b/src/baskerville/scripts/hound_snp.py
@@ -17,7 +17,7 @@
 import pdb
 import pickle
 import os
-from baskerville.snps import calculate_sad
+from baskerville.snps import score_snps
 
 """
 hound_snp.py
@@ -31,6 +31,13 @@
 def main():
     usage = "usage: %prog [options] <params_file> <model_file> <vcf_file>"
     parser = OptionParser(usage)
+    parser.add_option(
+        "-c",
+        dest="cluster_snps_pct",
+        default=0,
+        type="float",
+        help="Cluster SNPs within a %% of the seq length to make a single ref pred [Default: %default]",
+    )
     parser.add_option(
         "-f",
         dest="genome_fasta",
@@ -66,8 +73,8 @@ def main():
     )
     parser.add_option(
         "--stats",
-        dest="sad_stats",
-        default="SAD",
+        dest="snp_stats",
+        default="logSAD",
         help="Comma-separated list of stats to save. [Default: %default]",
     )
     parser.add_option(
@@ -129,17 +136,20 @@ def main():
     else:
         parser.error("Must provide parameters and model files and QTL VCF file")
 
+    if options.targets_file is None:
+        parser.error("Must provide targets file")
+
     if not os.path.isdir(options.out_dir):
         os.mkdir(options.out_dir)
 
     options.shifts = [int(shift) for shift in options.shifts.split(",")]
-    options.sad_stats = options.sad_stats.split(",")
+    options.snp_stats = options.snp_stats.split(",")
 
     # calculate SAD scores:
     if options.processes is not None:
-        calculate_sad(params_file, model_file, vcf_file, worker_index, options)
+        score_snps(params_file, model_file, vcf_file, worker_index, options)
     else:
-        calculate_sad(params_file, model_file, vcf_file, 0, options)
+        score_snps(params_file, model_file, vcf_file, 0, options)
 
 
 ################################################################################

diff --git a/src/baskerville/scripts/hound_snp_slurm.py b/src/baskerville/scripts/hound_snp_slurm.py
@@ -41,6 +41,13 @@ def main():
     parser = OptionParser(usage)
 
     # snp
+    parser.add_option(
+        "-c",
+        dest="cluster_snps_pct",
+        default=0,
+        type="float",
+        help="Cluster SNPs within a %% of the seq length to make a single ref pred [Default: %default]",
+    )
     parser.add_option(
         "-f",
         dest="genome_fasta",
@@ -69,8 +76,8 @@ def main():
     )
     parser.add_option(
         "--stats",
-        dest="sad_stats",
-        default="SAD",
+        dest="snp_stats",
+        default="logSAD",
         help="Comma-separated list of stats to save. [Default: %default]",
     )
     parser.add_option(
@@ -80,12 +87,19 @@ def main():
         type="str",
         help="File specifying target indexes and labels in table format",
     )
+    parser.add_option(
+        "-u",
+        dest="untransform_old",
+        default=False,
+        action="store_true",
+        help="Untransform old models [Default: %default]",
+    )
 
     # multi
     parser.add_option(
         "-e",
         dest="conda_env",
-        default="tf210",
+        default="tf12",
         help="Anaconda environment [Default: %default]",
     )
     parser.add_option(