Troubleshooting

bioforensics · Oct 23, 2023 · 090edff · 090edff
1 parent 66a3321
commit 090edff
Show file tree

Hide file tree

Showing 15 changed files with 592 additions and 950,376 deletions.
diff --git a/dbbuild/build-summary.txt b/dbbuild/build-summary.txt
@@ -1,34 +1,5 @@
 swapping out rs74812635 for rs602427
 swapping out rs75324027 for rs602875
-swapping out rs74812635 for rs602427
-swapping out rs75324027 for rs602875
-swapping out rs281863504 for rs71542446
-swapping out rs281863503 for rs41270931
-swapping out rs281863502 for rs28724261
-swapping out rs281863499 for rs71542447
-swapping out rs281863486 for rs2854267
-swapping out rs281863485 for rs9274216
-swapping out rs281863467 for rs201930518
-swapping out rs281863466 for rs17613599
-swapping out rs281863464 for rs71542448
-swapping out rs281863463 for rs9274217
-swapping out rs281863439 for rs58770498
-swapping out rs281863431 for rs17613606
-swapping out rs281863430 for rs9274218
-swapping out rs281863427 for rs115495316
-swapping out rs281863426 for rs9274219
-swapping out rs281863425 for rs9274220
-swapping out rs281863414 for rs2856703
-swapping out rs281863406 for rs41270932
-swapping out rs281863401 for rs9274222
-swapping out rs281863398 for rs72844333
-swapping out rs281863397 for rs200098349
-swapping out rs281863382 for rs74222206
-swapping out rs281863375 for rs9274225
-swapping out rs281863371 for rs41270933
-swapping out rs281863364 for rs17613629
-swapping out rs281863363 for rs17613636
-swapping out rs281863357 for rs9274227
 swapping out rs281863504 for rs71542446
 swapping out rs281863503 for rs41270931
 swapping out rs281863502 for rs28724261
@@ -57,46 +28,12 @@ swapping out rs281863364 for rs17613629
 swapping out rs281863363 for rs17613636
 swapping out rs281863357 for rs9274227
 swapping out rs561074738 for rs9348865
-swapping out rs561074738 for rs9348865
 swapping out rs115980227 for rs80319605
-swapping out rs115980227 for rs80319605
-swapping out rs536547537 for rs80087112
 swapping out rs536547537 for rs80087112
 swapping out rs74898010 for rs73151289
 swapping out rs28970291 for rs4076758
 swapping out rs72629020 for rs36190610
-swapping out rs74898010 for rs73151289
-swapping out rs28970291 for rs4076758
-swapping out rs72629020 for rs36190610
 swapping out rs10546081 for rs9657920
-swapping out rs10546081 for rs9657920
-swapping out rs281863504 for rs71542446
-swapping out rs281863503 for rs41270931
-swapping out rs281863502 for rs28724261
-swapping out rs281863499 for rs71542447
-swapping out rs281863486 for rs2854267
-swapping out rs281863485 for rs9274216
-swapping out rs281863467 for rs201930518
-swapping out rs281863466 for rs17613599
-swapping out rs281863464 for rs71542448
-swapping out rs281863463 for rs9274217
-swapping out rs281863439 for rs58770498
-swapping out rs281863431 for rs17613606
-swapping out rs281863430 for rs9274218
-swapping out rs281863427 for rs115495316
-swapping out rs281863426 for rs9274219
-swapping out rs281863425 for rs9274220
-swapping out rs281863414 for rs2856703
-swapping out rs281863406 for rs41270932
-swapping out rs281863401 for rs9274222
-swapping out rs281863398 for rs72844333
-swapping out rs281863397 for rs200098349
-swapping out rs281863382 for rs74222206
-swapping out rs281863375 for rs9274225
-swapping out rs281863371 for rs41270933
-swapping out rs281863364 for rs17613629
-swapping out rs281863363 for rs17613636
-swapping out rs281863357 for rs9274227
 swapping out rs281863504 for rs71542446
 swapping out rs281863503 for rs41270931
 swapping out rs281863502 for rs28724261
@@ -125,8 +62,6 @@ swapping out rs281863364 for rs17613629
 swapping out rs281863363 for rs17613636
 swapping out rs281863357 for rs9274227
 swapping out rs115980227 for rs80319605
-swapping out rs115980227 for rs80319605
-swapping out rs536547537 for rs80087112
 swapping out rs536547537 for rs80087112
 swapping out rs281863504 for rs71542446
 swapping out rs281863503 for rs41270931
@@ -143,28 +78,9 @@ swapping out rs281863431 for rs17613606
 swapping out rs281863430 for rs9274218
 swapping out rs281863427 for rs115495316
 swapping out rs281863426 for rs9274219
-swapping out rs281863504 for rs71542446
-swapping out rs281863503 for rs41270931
-swapping out rs281863502 for rs28724261
-swapping out rs281863499 for rs71542447
-swapping out rs281863486 for rs2854267
-swapping out rs281863485 for rs9274216
-swapping out rs281863467 for rs201930518
-swapping out rs281863466 for rs17613599
-swapping out rs281863464 for rs71542448
-swapping out rs281863463 for rs9274217
-swapping out rs281863439 for rs58770498
-swapping out rs281863431 for rs17613606
-swapping out rs281863430 for rs9274218
-swapping out rs281863427 for rs115495316
-swapping out rs281863426 for rs9274219
-swapping out rs576530137 for rs281864341
-swapping out rs530460066 for rs281864275
 swapping out rs576530137 for rs281864341
 swapping out rs530460066 for rs281864275
 swapping out rs573533995 for rs12222263
-swapping out rs573533995 for rs12222263
-swapping out rs536547537 for rs80087112
 swapping out rs536547537 for rs80087112
 Merging 'mh01SCUZJ-0109666' --> 'mh01SCUZJ-0109665'
 Merging 'mh01WL-082' --> 'mh01WL-020'
@@ -3118,7 +3034,6 @@ Marker mh11KK-040 as defined in Staadig2021 was defined previously and is redund
   - 59 marker definitions based on 658 SNPs
 [Byrska-Bishop2022]
   - 31 population samples
-  - frequencies for 59232 distinct haplotypes in 31 populations; 856064 total frequencies
 [Fan2022]
   - 22 marker definitions based on 338 SNPs and 25 indels
 [Yu2022G1]

diff --git a/dbbuild/frequency.csv.gz b/dbbuild/frequency.csv.gz
diff --git a/dbbuild/lib/marker.py b/dbbuild/lib/marker.py
@@ -13,6 +13,7 @@
 from .variant import VariantList
 from itertools import chain
 import pandas as pd
+import sys
 
 
 class InvalidMarkerNameError(ValueError):
@@ -225,9 +226,14 @@ def __init__(self, name, chrom, rsids, index, xrefs=None, source=None):
 
     def resolve(self):
         for refr in ("GRCh37", "GRCh38"):
-            for position in self.index.resolve(self.rsids, refr, strict=True):
-                self.positions[refr].append(position)
-            self.positions[refr].sort()
+            positions = sorted(self.index.resolve(self.rsids, refr, strict=True))
+            coords = [pos for pos, rsid in positions]
+            rsids = [rsid for pos, rsid in positions]  # Possibly updated from refsnp-merged
+            self.positions[refr] = coords
+            self.rsids = rsids
+            if len(set(coords)) < len(coords):
+                coordstring = '\n'.join([str(c) for c in rsids])
+                raise ValueError(f"issue resolving RSID coordinates for {self.name}: {coordstring}")
 
     @property
     def numvars(self):

diff --git a/dbbuild/lib/variant.py b/dbbuild/lib/variant.py
@@ -145,7 +145,7 @@ def resolve(self, rsids, refr, strict=False):
                 print(f"swapping out {rsid} for {self.merged_rsids[rsid]}")
                 rsid = self.merged_rsids[rsid]
             if rsid in self.coords_by_rsid[refr]:
-                yield self.coords_by_rsid[refr][rsid]
+                yield self.coords_by_rsid[refr][rsid], rsid
             elif strict is True:
                 raise ValueError(f"no {refr} coordinate for {rsid}")