add with lit check

data/STRchive-loci.json

@@ -681,7 +681,7 @@
   "mechanism": "GoF",
   "mechanism_detail": "Polyglutamine expansion leading to gain of function; aggregated and mislocalized proteins in neurons [@pmid:36169768; @genereviews:NBK1196].",
   "source": [],
-  "details": "Benign alleles range from 11-44 repeats [@pmid:37906407], with intermediate alleles (45-59) associated with incomplete penetrance and non-classic phenotypes [@genereviews:NBK1196]. The threshold between incomplete and full penetrance is unclear, but presumed to occur at ~60 repeats [@genereviews:NBK1196; @pmid:37906407]. The interruption CAA has been observed [@pmid:35245110]; AAG is present in hg38 reference sequence.",
+  "details": "Benign alleles range from 11-44 repeats [@pmid:37906407], with intermediate alleles (45-59) associated with incomplete penetrance and non-classic phenotypes [@genereviews:NBK1196]. The threshold between incomplete and full penetrance is unclear, but presumed to occur at ~60 repeats [@genereviews:NBK1196; @pmid:37906407]. The interruption CAA has been observed [@pmid:35245110]; AAG is present in hg38 reference sequence. The APOE ε4 allele appears to act as a disease modifier [@pmid:39731318]; GLS expansions may also function as disease modifiers [@pmid: 39699045].",
   "omim": ["109150"],
   "prevalence": "2.1/100000",
   "prevalence_details": "1-5/100,000 [@pmid:29100084]. Most prevalent SCA subtype [@genereviews:NBK557816]. Found worldwide across ancestries/ethnicities [@genereviews:NBK1196].",
@@ -925,7 +925,7 @@
   "intermediate_min": 24.0,
   "intermediate_max": 60.0,
   "pathogenic_min": 251.0,
-  "pathogenic_max": 4000.0,
+  "pathogenic_max": 4088.0,
   "ref_copies": 10.8,
   "motif_len": 6,
   "age_onset": "Typical: 50-64; Range: 20-91 [@genereviews:NBK268647].",
@@ -937,7 +937,7 @@
   "mechanism": "Ambiguous",
   "mechanism_detail": "The HRE forms DNA and RNA G-quadruplexes with distinct structures and promotes RNA/DNA hybrids (R-loops). The structural polymorphism causes a repeat length-dependent accumulation of transcripts aborted in the HRE region [@omim:105500]. Addiitonal mechanisms theorized include protein loss of function and RNA gain of function [@pmid:37847372].",
   "source": [],
-  "details": "FTD and ALS form a clinical spectrum [@pmid:37388914; @pmid:22406228]. The clinical ranges of the C9orf72 locus remain ambiguous [@stripy:C9ORF72]: most healthy controls have alleles up to 24 repeats [@pmid:28319737] yet 24-30 repeats are associated with ALS [@pmid:31315673] and while 60 repeats is frequently used as a threshold for uncertain alleles, the exact threshold of pathogenicity remains unclear [@genereviews:NBK268647; @pmid:38099605]. Repeat of 80 motifs and lower appear to have delayed onset for any phenotype [@pmid:28319737]. >250 repeats are associated with a full FTD/ALS disease state [@pmid:31048495], but pathogenic alleles can range from 30 to more than 4000 repeats [@pmid:38099605]. Penetrance appears to also be age-dependent, with environmental factors and specific phenotypes associated with sex and age at onset [@pmid:28522837].",
+  "details": "FTD and ALS form a clinical spectrum [@pmid:37388914; @pmid:22406228]. The clinical ranges of the C9orf72 locus remain ambiguous [@stripy:C9ORF72]: most healthy controls have alleles up to 24 repeats [@pmid:28319737] yet 24-30 repeats are associated with ALS [@pmid:31315673] and while 60 repeats is frequently used as a threshold for uncertain alleles, the exact threshold of pathogenicity remains unclear [@genereviews:NBK268647; @pmid:38099605]. Repeat of 80 motifs and lower appear to have delayed onset for any phenotype [@pmid:28319737]. >250 repeats are associated with a full FTD/ALS disease state [@pmid:31048495], but pathogenic alleles can range from 30 to more than 4000 repeats [@pmid:38099605; @pmid:39709476]. Penetrance appears to also be age-dependent, with environmental factors and specific phenotypes associated with sex and age at onset [@pmid:28522837]. Methylation appears to increase with expansion length and age [@pmid:39709476].",
   "omim": ["105500"],
   "prevalence": null,
   "prevalence_details": "The expansion of a hexanucleotide repeat GGGGCC in C9orf72 is the most common known cause of ALS accounting for ~ 40% familial cases and ~ 7% sporadic cases in the European population; overall ALS incidence is 1-2/100,000 person-years, point prevalence is 3-5/100,000 (Europe/US); lifetime risk is 1 in 300 [@pmid:31315673]. Related individuals to patients with C9orf72-ALS appear at an increased risk of disease regardless of carrier status [@pmid:38149039; @pmid:39315390]. C9orf72-FTD is estimated to be 0.04-134:100,000 [@genereviews:NBK268647], and by our estimates 0.65-1.56/100,000 for C9orf72-ALS. The expansion has been found across ethnicities/ancestries, with population-dependent prevalence, highest in those with northern European ancestry [@genereviews:NBK268647].",
@@ -1099,8 +1099,8 @@
   "disease_id": "DM2",
   "gene_strand": "-",
   "reference_motif_reference_orientation": ["CAGG"],
-  "pathogenic_motif_reference_orientation": ["CAGG"],
-  "pathogenic_motif_gene_orientation": ["CCTG"],
+  "pathogenic_motif_reference_orientation": ["CAGG", "CAGA"],
+  "pathogenic_motif_gene_orientation": ["CCTG", "TCTG"],
   "benign_motif_reference_orientation": [],
   "benign_motif_gene_orientation": [],
   "unknown_motif_reference_orientation": [],
@@ -1129,7 +1129,7 @@
   "mechanism": "GoF",
   "mechanism_detail": "Aberrant splicing, RAN translation [@pmid:22140091; @pmid:38467784].",
   "source": [],
-  "details": "Detailed overview of disease locus through 2024 by Rimoldi et al [@pmid:39643839]. ≤30 uninterrupted CCTG repeats or 11-26 CCTG repeats with GCTC/TCTG interruptions are considered benign; 27-29 repeats with interruptions have currently unknown significance, ~30-~54 repeats are considered premutations, ~55-74 repeats are premutations with possible reduced penetrance, and >74 repeat alleles are considered pathogenic [@genereviews:NBK1466]. Penetrance is age-dependent and approaches 100%. Locus structure is (TG)n(TCTG)n(CCTG)n. CCTG expansion causes DM2 but the other repeat units are also variable. Interruptions include GCTG/TCTG/GGCT [@pmid:35245110].",
+  "details": "Detailed overview of disease locus through 2024 by Rimoldi et al [@pmid:39643839]. ≤30 uninterrupted CCTG repeats or 11-26 CCTG repeats with GCTC/TCTG interruptions are considered benign; 27-29 repeats with interruptions have currently unknown significance, ~30-~54 repeats are considered premutations, ~55-74 repeats are premutations with possible reduced penetrance, and >74 repeat alleles are considered pathogenic [@genereviews:NBK1466]. Penetrance is age-dependent and approaches 100%. Locus structure is (TG)n(TCTG)n(CCTG)n. CCTG expansion causes DM2 but the other repeat units are also variable. Interruptions include GCTG/TCTG/GGCT [@pmid:35245110; @pmid:39703464].",
   "omim": ["602668"],
   "prevalence": "2.29/100000",
   "prevalence_details": "2.29/100,000 [@pmid:35483324]; population specific prevalence [@genereviews:NBK1466]. Most cases have European ancestry, but disease has been reported worldwide [@genereviews:NBK1466].",
@@ -1513,7 +1513,7 @@
   "mechanism": "GoF",
   "mechanism_detail": "RNA gain-of-function: RNA gelation leading to misregulation of alternative splicing [@pmid:36169768].",
   "source": [],
-  "details": "Overview of disease locus through 2024, including largest pathogenic allele of 4,000, described in Rimoldi et al review [@pmid:39643839]. Intermediate alleles (35-49) associated with premutation [@genereviews:NBK1165]. 3%-8% of DM1 expansions contain variant repeats such as CCG and CGG, associated with later onset and milder phenotype [@pmid:32851192]. In another study, interruptions of the CTG repeat with CCG, GGC, CTC or CAG motifs are estimated to occur in 3-11% of DM1 patients [@pmid:35741732].",
+  "details": "Overview of disease locus through 2024, including largest pathogenic allele of 4,000, described in Rimoldi et al review [@pmid:39643839]. Intermediate alleles (35-49) associated with premutation [@genereviews:NBK1165]. 3%-8% of DM1 expansions contain interrupting variant repeats such as CCG and CGG, associated with later onset and milder phenotype; the variant repeat GCGGCA has also been reported [@pmid:32851192; @doi:10.1016/j.mcp.2024.102005]. In another study, interruptions of the CTG repeat with CCG, GGC, CTC or CAG motifs are estimated to occur in 3-11% of DM1 patients [@pmid:35741732]. Expansions within gene ZNF850 may function as DM1 modifiers [@doi:10.1093/hmg/ddae186].",
   "omim": ["160900"],
   "prevalence": "9.27/100000",
   "prevalence_details": "5-20/100,000 [@genereviews:NBK1165]. 0.5-18.1/100,000 [@pmid:29100084]; 6.5/100,000 [@pmid:31159885]. 9.27 cases (95% CI: 4.73-15.21) per 100,000, ranging from 0.37 to 36.29 cases per 100,000 [@pmid:35483324]. Found across ethnicities/ancestries, with population-dependent prevalence [@genereviews:NBK1165].",
@@ -4012,7 +4012,7 @@
   "details": "Most controls have <40 repeats while majority of patients have >50 repeats; penetrance is <100%, as unaffected individuals have been documented with >80 repeats and alleles of affected individuals range from 12-2600 [@genereviews:NBK535148; @pmid:25168903]. Expansions are causative in approximately 70% of disease cases [@genereviews:NBK535148].",
   "omim": ["613267"],
   "prevalence": "4.5/100",
-  "prevalence_details": "~4/100 (over 40) [@omim:613267]; 5/100 [@pmid:20825314]. Predominantly in women (~75%) [@pmid:16769829]. Although studies on the prevalence of FECD worldwide are limited, the disorder is thought to be more common in Eurasian populations [@pmid:26401622], with its corneal manifestations documented in 11% of females and 7% of males in Reykjavik, Iceland, 8.5 % of Singapore Chinese, and 5.5% of Japanese [@pmid:25722209]. Uncommon/rare in Saudi Arabia, Singaporean Chinese, and Japan [@orphanet:98974].",
+  "prevalence_details": "~4/100 (over 40) [@omim:613267]; 5/100 [@pmid:20825314]. Predominantly in women (~75%) [@pmid:16769829]. In one study of two cohorts (Dallas Heart Study and 1000 Genomes Project), expanded allele carrier rates were 3.1% (African American), 8.1% (European American), and 3.3% (Latinos)in DHS, and 2.7% (AFR), 9.5% (EUR), 5.2% (East Asians), 7.2% (South Asians), and 5.2% (admixed Americans) in 1KGP [@pmid:39669694]. The highest carrier prevalence (12.1%–12.5%) occurred in EUR and admixed American subpopulations, while rates were 0%–1.9% in West Africans vs 6.2% in a Kenyan subpopulation.",
   "stripy": ["TCF4"],
   "gnomad": ["TCF4"],
   "genereviews": ["NBK535148"],
@@ -4670,4 +4670,4 @@
   "disease_tags": [],
   "references": ["pmid:38714868", "pmid:38714869", "omim:609893"],
   "additional_literature": []
-}]
+}]