fix handling of dominant / recessive

pgscatalog_utils/scorefile/qc.py

@@ -137,11 +137,11 @@ def assign_effect_type(
 ) -> typing.Generator[ScoreVariant, None, None]:
     for variant in variants:
         match (variant.is_recessive, variant.is_dominant):
-            case (None, None) | ("FALSE", "FALSE"):
+            case (None, None) | (False, False):
                 pass  # default value is additive, pass to break match and yield
-            case ("FALSE", "TRUE"):
+            case (False, True):
                 variant.effect_type = EffectType.DOMINANT
-            case ("TRUE", "FALSE"):
+            case (True, False):
                 variant.effect_type = EffectType.RECESSIVE
             case _:
                 logger.critical(f"Bad effect type setting: {variant}")

pgscatalog_utils/scorefile/scorevariant.py

@@ -106,8 +106,14 @@ def __init__(
 
         self.hm_inferOtherAllele: Optional[str] = hm_inferOtherAllele
         self.hm_source: Optional[str] = hm_source
-        self.is_dominant: Optional[bool] = is_dominant
-        self.is_recessive: Optional[bool] = is_recessive
+
+        self.is_dominant: Optional[bool] = (
+            is_dominant == "True" if is_dominant is not None else None
+        )
+        self.is_recessive: Optional[bool] = (
+            is_recessive == "True" if is_recessive is not None else None
+        )
+
         self.hm_rsID: Optional[str] = hm_rsID
         self.hm_match_chr: Optional[str] = hm_match_chr
         self.hm_match_pos: Optional[str] = hm_match_pos

tests/data/combine/PGS000802_hmPOS_GRCh37.txt

@@ -0,0 +1,39 @@
+###PGS CATALOG SCORING FILE - see https://www.pgscatalog.org/downloads/#dl_ftp_scoring for additional information
+#format_version=2.0
+##POLYGENIC SCORE (PGS) INFORMATION
+#pgs_id=PGS000802
+#pgs_name=CRC_19
+#trait_reported=Colorectal cancer
+#trait_mapped=colorectal cancer
+#trait_efo=EFO_0005842
+#genome_build=NR
+#variants_number=19
+#weight_type=NR
+##SOURCE INFORMATION
+#pgp_id=PGP000191
+#citation=He CY et al. Genomics (2021). doi:10.1016/j.ygeno.2021.01.025
+##HARMONIZATION DETAILS
+#HmPOS_build=GRCh37
+#HmPOS_date=2022-07-28
+#HmPOS_match_chr={"True": null, "False": null}
+#HmPOS_match_pos={"True": null, "False": null}
+rsID	chr_name	chr_position	effect_allele	other_allele	effect_weight	allelefrequency_effect	is_dominant	is_recessive	locus_name	hm_source	hm_rsID	hm_chr	hm_pos	hm_inferOtherAllele
+rs10936599	3	170974795	T	C	0.123	0.377	True	False	MYNN	ENSEMBL	rs10936599	3	169492101	
+rs6061231	20	60390312	A	C	0.491	0.892	False	True	LOC100128184, RPS21	ENSEMBL	rs6061231	20	60956917	
+rs10774214	12	4238613	C	T	0.122	0.637	True	False	LOC100129645, CCND2	ENSEMBL	rs10774214	12	4368352	
+rs10795668	10	8741225	A	G	0.147	0.61	True	False	LOC338591, LOC389936	ENSEMBL	rs10795668	10	8701219	
+rs11903757	2	192295449	T	C	0.185	0.925	False	True	LOC100132133, hCG_2045843	ENSEMBL	rs11903757	2	192587204	
+rs12603526	17	747343	T	C	0.142	0.695	False	True	NXN	ENSEMBL	rs12603526	17	800593	
+rs1321311	6	36730878	G	T	0.135	0.876	True	False	SFRS3, LOC389386	ENSEMBL	rs1321311	6	36622900	
+rs2423279	20	7760350	T	C	0.193	0.715	False	True	FUSIP1P2	ENSEMBL	rs2423279	20	7812350	
+rs3802842	11	110676919	A	C	0.177	0.663	True	False	LOC120376	ENSEMBL	rs3802842	11	111171709	
+rs4813802	20	6647595	T	G	0.189	0.816	False	True	LOC728383	ENSEMBL	rs4813802	20	6699595	
+rs6469656	8	117716969	G	A	0.204	0.627	False	True	TRPS1, EIF3H	ENSEMBL	rs6469656	8	117647788	
+rs647161	5	134526991	C	A	0.277	0.663	False	True	LOC389328, H2AFY	ENSEMBL	rs647161	5	134499092	
+rs704017	10	80489138	A	G	0.123	0.644	True	False	LOC100132987, ZMIZ1	ENSEMBL	rs704017	10	80819132	
+rs7315438	12	114375786	C	T	0.146	0.388	True	False	TBX3, LOC100129020	ENSEMBL	rs7315438	12	115891403	
+rs10411210	19	38224140	C	T	0.232	0.836	False	False	RHPN2	ENSEMBL	rs10411210	19	33532300	
+rs12953717	18	44707927	T	C	0.157	0.789	False	False	SMAD7	ENSEMBL	rs12953717	18	46453929	
+rs16969681	15	30780403	T	C	0.175	0.583	False	False	C15orf45, GREM1	ENSEMBL	rs16969681	15	32993111	
+rs1801133	1	11778965	A	G	0.16	0.592	False	False	MTHFR	ENSEMBL	rs1801133	1	11856378	
+rs6983267	8	128482487	G	T	0.217	0.376	False	False	FAM84B, POU5F1P1	ENSEMBL	rs6983267	8	128413305