Merge pull request #78 from brentp/fixes

set alt clip to 0 if there is no other alt support

README.md

@@ -24,7 +24,7 @@ Requirements:
 
 ## `svtyper` vs `svtyper-sso`
 
-`svtyper` is the original implementation of the genotyping algorithm, and works with multiple samples.  `svtyper-sso` is an alternative implementation of `svtyper` that is optimized for genotyping a single sample.  `svtyper-sso` is a parallelized implementation of `svtyper` that takes advantage of multiple CPU cores via the [multiprocessing][8] module. `svtyper-sso` can offer a 2x or more speedup (depending on how many CPU cores used) in genotyping a single sample.
+`svtyper` is the original implementation of the genotyping algorithm, and works with multiple samples.  `svtyper-sso` is an alternative implementation of `svtyper` that is optimized for genotyping a single sample.  `svtyper-sso` is a parallelized implementation of `svtyper` that takes advantage of multiple CPU cores via the [multiprocessing][8] module. `svtyper-sso` can offer a 2x or more speedup (depending on how many CPU cores used) in genotyping a single sample. **_NOTE: svtyper-sso is not yet stable. There are minor logging differences between the two and svtyper-sso may exit with an error prematurely when processing CRAM files._**
 
 ## Example Usage
 

svtyper/classic.py

@@ -427,10 +427,15 @@ def sv_genotype(bam_string,
                 alt_span = 0
                 ref_span = 0
 
+            if alt_span + alt_seq == 0 and alt_clip > 0:
+                # discount any SV that's only supported by clips.
+                alt_clip = 0
+
             if ref_seq + alt_seq + ref_span + alt_span + alt_clip > 0:
                 # get bayesian classifier
                 if var.info['SVTYPE'] == "DUP": is_dup = True
                 else: is_dup = False
+
                 alt_splitters = alt_seq + alt_clip
                 QR = int(split_weight * ref_seq) + int(disc_weight * ref_span)
                 QA = int(split_weight * alt_splitters) + int(disc_weight * alt_span)
@@ -512,6 +517,10 @@ def sv_genotype(bam_string,
             var2.genotype = var.genotype
             vcf_out.write(var2.get_var_string() + '\n')
 
+    # throw warning if we've lost unpaired breakends
+    if True:
+        logging.warning('Unpaired breakends found in file. These will not be present in output.')
+
     # close the files
     vcf_in.close()
     vcf_out.close()

svtyper/singlesample.py

@@ -387,6 +387,9 @@ def tally_variant_read_fragments(split_slop, min_aligned, breakpoint, sam_fragme
     if alt_span < 0.5 and (alt_seq + alt_clip) >= 1:
         alt_span = 0
         ref_span = 0
+    if alt_span + alt_seq == 0 and alt_clip > 0:
+        # discount any SV that's only supported by clips.
+        alt_clip = 0
 
     counts = { 'ref_seq' : ref_seq, 'alt_seq' : alt_seq,
                'ref_span' : ref_span, 'alt_span' : alt_span,

svtyper/version.py

@@ -1,2 +1,2 @@
 __author__ = "Colby Chiang (colbychiang@wustl.edu)"
-__version__ = "v0.5.2"
+__version__ = "v0.6.0"

tests/data/example.gt.vcf

@@ -170,7 +170,7 @@
 2	56652247	82193	G	<DEL>	0.00	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-3645;END=56655892;STR=+-:57;IMPRECISE;CIPOS=-2,18;CIEND=0,0;EVENT=82193;SUP=57;PESUP=57;SRSUP=0;EVTYPE=PE;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/0:200:129:129:0:0.00:-0,-39,-128:128:0:58:0:0:70:0:0
 2	59623256	91676	T	<DEL>	821.08	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-7791;END=59631047;STR=+-:225;CIPOS=0,0;CIEND=0,0;EVENT=91676;SUP=225;PESUP=180;SRSUP=45;EVTYPE=PE,SR;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/1:200:129:87:41:821.08:-87,-5,-55:86:40:41:10:2:45:27:0.32
 2	61880174	92462	C	<DEL>	0.00	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-931;END=61881105;STR=+-:110;CIPOS=0,0;CIEND=0,0;EVENT=92462;SUP=110;PESUP=1;SRSUP=109;EVTYPE=PE,SR;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/0:200:130:130:0:0.00:-0,-39,-129:129:0:60:0:0:69:0:0
-2	62916470	92781	A	<DEL>	0.00	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-5164;END=62921634;STR=+-:32;CIPOS=0,0;CIEND=0,0;EVENT=92781;SUP=32;PESUP=22;SRSUP=10;EVTYPE=PE,SR;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/0:200:137:136:0:0.00:-0,-41,-135:135:0:60:0:0:75:0:0
+2	62916470	92781	A	<DEL>	0.00	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-5164;END=62921634;STR=+-:32;CIPOS=0,0;CIEND=0,0;EVENT=92781;SUP=32;PESUP=22;SRSUP=10;EVTYPE=PE,SR;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/0:200:136:136:0:0.00:-0,-41,-135:135:0:60:0:0:75:0:0
 2	64479691	93866	A	<DEL>	0.00	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-4887;END=64484578;STR=+-:15;IMPRECISE;CIPOS=-1,86;CIEND=0,0;EVENT=93866;SUP=15;PESUP=15;SRSUP=0;EVTYPE=PE;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/0:200:99:99:0:0.00:-0,-30,-98:98:0:47:0:0:51:0:0
 2	66505594	94494	T	<DEL>	842.31	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-1958;END=66507552;STR=+-:235;CIPOS=0,0;CIEND=0,0;EVENT=94494;SUP=235;PESUP=167;SRSUP=68;EVTYPE=PE,SR;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/1:200:92:53:38:842.31:-86,-2,-29:52:37:24:6:3:28:27:0.42
 2	67974877	94992	A	<DEL>	0.00	.	TOOL=LUMPY;SVTYPE=DEL;SVLEN=-201;END=67975078;STR=+-:10;CIPOS=0,0;CIEND=0,0;EVENT=94992;SUP=10;PESUP=0;SRSUP=10;EVTYPE=SR;PRIN	GT:GQ:DP:RO:AO:SQ:GL:QR:QA:RS:AS:ASC:RP:AP:AB	0/0:200:149:148:0:0.00:-0,-44,-147:147:0:71:0:0:76:0:0