Add haploid mode

KewinOgink · Dec 22, 2019 · e40b714 · e40b714
1 parent 21ed5de
commit e40b714
Show file tree

Hide file tree

Showing 3 changed files with 29 additions and 0 deletions.
diff --git a/clair/callVarBam.py b/clair/callVarBam.py
@@ -87,6 +87,7 @@ def Run(args):
     stop_consider_left_edge = command_option_from(args.stop_consider_left_edge, 'stop_consider_left_edge')
     log_path = command_option_from(args.log_path, 'log_path', option_value=args.log_path)
     pysam_for_all_indel_bases = command_option_from(args.pysam_for_all_indel_bases, 'pysam_for_all_indel_bases')
+    haploid_mode = command_option_from(args.haploid_mode, 'haploid_mode')
     debug = command_option_from(args.debug, 'debug')
     qual = command_option_from(args.qual, 'qual', option_value=args.qual)
     fast_plotting = command_option_from(args.fast_plotting, 'fast_plotting')
@@ -161,6 +162,7 @@ def Run(args):
         CommandOption('threads', numCpus),
         CommandOption('ref_fn', ref_fn),
         pysam_for_all_indel_bases,
+        haploid_mode,
         qual,
         debug
     ]
@@ -293,6 +295,9 @@ def main():
     parser.add_argument('--pysam_for_all_indel_bases', action='store_true',
                         help="Always using pysam for outputting indel bases, optional")
 
+    parser.add_argument('--haploid_mode', action='store_true',
+                        help="call haploid instead of diploid")
+
     parser.add_argument('--activation_only', action='store_true',
                         help="Output activation only, no prediction")
     parser.add_argument('--max_plot', type=int, default=10,

diff --git a/clair/callVarBamParallel.py b/clair/callVarBamParallel.py
@@ -45,6 +45,7 @@ def Run(args):
     stop_consider_left_edge = command_option_from(args.stop_consider_left_edge, 'stop_consider_left_edge')
     log_path = command_option_from(args.log_path, 'log_path', option_value=args.log_path)
     pysam_for_all_indel_bases = command_option_from(args.pysam_for_all_indel_bases, 'pysam_for_all_indel_bases')
+    haploid_mode = command_option_from(args.haploid_mode, 'haploid_mode')
     debug = command_option_from(args.debug, 'debug')
     qual = command_option_from(args.qual, 'qual', option_value=args.qual)
     fast_plotting = command_option_from(args.fast_plotting, 'fast_plotting')
@@ -67,6 +68,7 @@ def Run(args):
         stop_consider_left_edge,
         debug,
         pysam_for_all_indel_bases,
+        haploid_mode,
     ]
 
     activation_only_command_options = [
@@ -174,6 +176,9 @@ def main():
     parser.add_argument('--pysam_for_all_indel_bases', action='store_true',
                         help="Always using pysam for outputting indel bases, optional")
 
+    parser.add_argument('--haploid_mode', action='store_true',
+                        help="call haploid instead of diploid")
+
     parser.add_argument('--activation_only', action='store_true',
                         help="Output activation only, no prediction")
     parser.add_argument('--max_plot', type=int, default=10,

diff --git a/clair/call_var.py b/clair/call_var.py
@@ -34,6 +34,7 @@
 OutputConfig = namedtuple('OutputConfig', [
     'is_show_reference',
     'is_debug',
+    'is_haploid_mode_enabled',
     'quality_score_for_pass',
 ])
 OutputUtilities = namedtuple('OutputUtilities', [
@@ -663,6 +664,7 @@ def output_from(
     genotype_probabilities,
     variant_length_probabilities_1,
     variant_length_probabilities_2,
+    output_config,
     output_utilities,
 ):
     insertion_bases_using, deletion_bases_using, insertion_bases_using_pysam_using = (
@@ -723,6 +725,18 @@ def output_from(
         is_hetero_DelDel = maximum_probability in hetero_DelDel_probabilities
         is_insertion_and_deletion = maximum_probability in hetero_InsDel_probabilities
 
+
+        if output_config.is_haploid_mode_enabled:
+            if (
+                is_hetero_SNP or is_hetero_ACGT_Ins or is_hetero_InsIns or
+                is_hetero_ACGT_Del or is_hetero_DelDel or is_insertion_and_deletion
+            ):
+                return (
+                    (True, False, False, False, False, False, False, False, False, False),
+                    (reference_base_ACGT, reference_base_ACGT)
+                )
+
+
         if is_homo_SNP:
             base1, base2 = homo_SNP_bases_from(gt21_probabilities)
             reference_base = reference_sequence[tensor_position_center]
@@ -977,6 +991,7 @@ def batch_output(mini_batch, batch_Y, output_config, output_utilities):
             genotype_probabilities,
             variant_length_probabilities_1,
             variant_length_probabilities_2,
+            output_config,
             output_utilities,
         )
 
@@ -1150,6 +1165,7 @@ def call_variants(args, m):
     output_config = OutputConfig(
         is_show_reference=args.showRef,
         is_debug=args.debug,
+        is_haploid_mode_enabled=args.haploid_mode,
         quality_score_for_pass=args.qual,
     )
     output_utilities = output_utilties_from(
@@ -1266,6 +1282,9 @@ def main():
     parser.add_argument('--pysam_for_all_indel_bases', action='store_true',
                         help="Always using pysam for outputting indel bases, optional")
 
+    parser.add_argument('--haploid_mode', action='store_true',
+                        help="call haploid instead of diploid")
+
     args = parser.parse_args()
 
     if len(sys.argv[1:]) == 0: