Jan lit update

CITATION.cff

@@ -1,6 +1,6 @@
 title: STRchive
-version: 2.14.0
-date-released: "2025-11-10"
+version: 2.15.0
+date-released: "2026-1-21"
 url: https://github.com/dashnowlab/STRchive
 authors:
   - family-names: Dashnow

data/STRchive-loci.json

@@ -900,7 +900,7 @@
   "stop_t2t": 27584155,
   "disease": "Frontotemporal dementia (FTD) and/or amyotrophic lateral sclerosis (ALS)",
   "inheritance": ["AD"],
-  "disease_description": "Pure frontotemporal dementia, pure amyotrophic lateral sclerosis or combination of the two [@pmid:39349043]. Nominal associations with risk of Parkinson's has also been reported [@pmid:41074692].",
+  "disease_description": "Pure frontotemporal dementia, pure amyotrophic lateral sclerosis or combination of the two [@pmid:39349043]. Nominal associations with risk of Parkinson's have also been reported [@pmid:41074692].",
   "hpo_terms": null,
   "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].",
@@ -909,7 +909,7 @@
   "age_onset_max": 91.0,
   "typ_age_onset_min": 50.0,
   "typ_age_onset_max": 64.0,
-  "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].",
+  "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]. Repeats 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].",
   "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]. Multiple cell types in the prefrontal cortex, including oligodendrocytes, microglia, astrocytes, and neurons, appear impacted during pathogenesis [@pmid:39999167].",
   "year": "2011 [@pmid:21944778]",
@@ -962,7 +962,7 @@
   "stop_t2t": 13333176,
   "disease": "Spinocerebellar ataxia type 6",
   "inheritance": ["AD"],
-  "disease_description": "Spinocerebellar ataxia type 6 (SCA6) is the most common subtype of autosomal dominant cerebellar ataxia type III (ADCA type III) characterized by late-onset and slowly progressive gait ataxia and other cerebellar signs such as impaired muscle coordination and nystagmus [@mondo:0008457].",
+  "disease_description": "Spinocerebellar ataxia type 6 (SCA6) is the most common subtype of autosomal dominant cerebellar ataxia type III (ADCA type III) characterized by late-onset and slowly progressive gait ataxia and other cerebellar signs such as impaired muscle coordination and nystagmus [@mondo:0008457]. Ao, et al. has proposed that this expansion may have effects on chronotype, differing by sex and menopausal status, as well as depresssion severity [@pmid:41358280].",
   "hpo_terms": null,
   "prevalence": "2.65/100000",
   "prevalence_details": "13-15% of global SCA prevalence, estimated to be 0.02-31/100,000 [@genereviews:NBK1140; @pmid:29100084]: resultant estimate is 0.3-5/100,000. Found across ethnicities/ancestries, with population-dependent prevalence [@genereviews:NBK1140].",
@@ -1223,7 +1223,7 @@
   "stop_hg19": 45196360,
   "start_t2t": 42132054,
   "stop_t2t": 42132091,
-  "disease": "Progressive Myoclonic Epilepsy Type 1 (EPM1) Unverricht-Lundborg Disease (ULD)",
+  "disease": "Progressive Myoclonic Epilepsy Type 1 (EPM1), a.k.a Unverricht-Lundborg Disease (ULD)",
   "inheritance": ["AR"],
   "disease_description": "Unverricht-Lundborg disease (ULD) is a rare progressive myoclonic epilepsy disorder characterized by action- and stimulus-sensitive myoclonus, and tonic-clonic seizures with ataxia, but with only a mild cognitive decline over time [@mondo:0009698].",
   "hpo_terms": null,
@@ -1626,7 +1626,7 @@
   "age_onset_max": 87.0,
   "typ_age_onset_min": 42.0,
   "typ_age_onset_max": 70.0,
-  "details": "Higher repeat size is associated with earlier age of onset [@pmid:39263992]. The 250-300 repeats range is linked to incomplete penetrance and >300 repeats with complete penetrance in some studies and resources [@genereviews:NBK599589; @pmid:37399286; @pmid:39227614]. However, our thresholds are taken from suggestions made by Mohren et al upon evaluation of 169 cases and 802 controls; the authors propose lower thresholds based on pathogenic cases of shorter pure repeats [@pmid:39227614]. Additionally, this study suggests that benign motifs may disrupt the formation of secondary structures in DNA/RNA, leading to reduced pathogenicity. The affect of interruptions on penetrance and onset has been shown in patients, with uninterrupted expansions apparently necessary for disease [@pmid:40007153]. Variation in flanking regions appear to correlate with repeat size [@pmid:39227614; @pmid:38937606]. Intermediate alleles make pose as susceptibility factors or be associated with a phenotypic spectrum (multiple system atrophy) [@pmid:39227614; @pmid:39604554].",
+  "details": "Higher repeat size is associated with earlier age of onset [@pmid:39263992]. The 250-300 repeats range is linked to incomplete penetrance and >300 repeats with complete penetrance in some studies and resources [@genereviews:NBK599589; @pmid:37399286; @pmid:39227614]. However, our thresholds are taken from suggestions made by Mohren et al upon evaluation of 169 cases and 802 controls; the authors propose lower thresholds based on pathogenic cases of shorter pure repeats [@pmid:39227614]. Additionally, this study suggests that benign motifs may disrupt the formation of secondary structures in DNA/RNA, leading to reduced pathogenicity. The affect of interruptions on penetrance and onset has been shown in patients, with uninterrupted expansions apparently necessary for disease [@pmid:40007153]. Variation in flanking regions appear to correlate with repeat size [@pmid:39227614; @pmid:38937606]. Intermediate alleles make pose as susceptibility factors or be associated with a phenotypic spectrum (multiple system atrophy) [@pmid:39227614; @pmid:39604554]. Finally, a complex (TTC/TGC) ≥300 repeat expansion has been associated as a risk factor for Parkinson's disease [@pmid:41327893; @pmid:41277530].",
   "mechanism": "LoF",
   "mechanism_detail": "Reduced transcript 2 [@pmid:36516086].",
   "year": "2023 [@pmid:36493768]",

data/catalogs/STRchive-disease-loci.T2T-chm13.general.bed

@@ -62,7 +62,7 @@ chr19	18921630	18921645	EDM1-PSACH_COMP	COMP	GTC	GTC	6	AD	Multiple epiphyseal dy
 chr19	48597739	48597756	DM1_DMPK	DMPK	CAG	CAG	50	AD	Myotonic dystrophy type 1
 chr20	2683189	2683230	SCA36_NOP56	NOP56	GGCCTG	GGCCTG	650	AD	Spinocerebellar ataxia type 36
 chr20	4738633	4738705	CJD_PRNP	PRNP	GGTGGTGGCTGGGGGCAGCCTCAT	CCTCATGGTGGTGGCTGGGGGCAG	5	AD	Creutzfeldt-Jakob disease
-chr21	42132054	42132091	EPM1_CSTB	CSTB	CGCGGGGCGGGG	CGCGGGGCGGGG	30	AR	Progressive Myoclonic Epilepsy Type 1 (EPM1) Unverricht-Lundborg Disease (ULD)
+chr21	42132054	42132091	EPM1_CSTB	CSTB	CGCGGGGCGGGG	CGCGGGGCGGGG	30	AR	Progressive Myoclonic Epilepsy Type 1 (EPM1), a.k.a Unverricht-Lundborg Disease (ULD)
 chr22	20143615	20143660	TOF_TBX1	TBX1	GCN	GCN	25	AD	Tetralogy of Fallot
 chr22	46280059	46280134	SCA10_ATXN10	ATXN10	ATTCT	ATTCT	800	AD	Spinocerebellar ataxia type 10
 chrX	24597766	24597802	PRTS_ARX	ARX	NGC	NGC	20	XR	Partington syndrome

data/catalogs/STRchive-disease-loci.hg19.general.bed

@@ -62,7 +62,7 @@ chr19	18896844	18896860	EDM1-PSACH_COMP	COMP	GTC	GTC	6	AD	Multiple epiphyseal dy
 chr19	46273462	46273524	DM1_DMPK	DMPK	CAG	CAG	50	AD	Myotonic dystrophy type 1
 chr20	2633378	2633403	SCA36_NOP56	NOP56	GGCCTG	GGCCTG	650	AD	Spinocerebellar ataxia type 36
 chr20	4680043	4680139	CJD_PRNP	PRNP	GGTGGTGGCTGGGGGCAGCCTCAT	CCTCATGGTGGTGGCTGGGGGCAG	5	AD	Creutzfeldt-Jakob disease
-chr21	45196323	45196360	EPM1_CSTB	CSTB	CGCGGGGCGGGG	CGCGGGGCGGGG	30	AR	Progressive Myoclonic Epilepsy Type 1 (EPM1) Unverricht-Lundborg Disease (ULD)
+chr21	45196323	45196360	EPM1_CSTB	CSTB	CGCGGGGCGGGG	CGCGGGGCGGGG	30	AR	Progressive Myoclonic Epilepsy Type 1 (EPM1), a.k.a Unverricht-Lundborg Disease (ULD)
 chr22	19754285	19754330	TOF_TBX1	TBX1	GCN	GCN	25	AD	Tetralogy of Fallot
 chr22	46191234	46191304	SCA10_ATXN10	ATXN10	ATTCT	ATTCT	800	AD	Spinocerebellar ataxia type 10
 chrX	25031646	25031682	PRTS_ARX	ARX	NGC	NGC	20	XR	Partington syndrome

data/catalogs/STRchive-disease-loci.hg38.general.bed

@@ -62,7 +62,7 @@ chr19	18786034	18786050	EDM1-PSACH_COMP	COMP	GTC	GTC	6	AD	Multiple epiphyseal dy
 chr19	45770204	45770266	DM1_DMPK	DMPK	CAG	CAG	50	AD	Myotonic dystrophy type 1
 chr20	2652732	2652757	SCA36_NOP56	NOP56	GGCCTG	GGCCTG	650	AD	Spinocerebellar ataxia type 36
 chr20	4699397	4699493	CJD_PRNP	PRNP	GGTGGTGGCTGGGGGCAGCCTCAT	CCTCATGGTGGTGGCTGGGGGCAG	5	AD	Creutzfeldt-Jakob disease
-chr21	43776442	43776479	EPM1_CSTB	CSTB	CGCGGGGCGGGG	CGCGGGGCGGGG	30	AR	Progressive Myoclonic Epilepsy Type 1 (EPM1) Unverricht-Lundborg Disease (ULD)
+chr21	43776442	43776479	EPM1_CSTB	CSTB	CGCGGGGCGGGG	CGCGGGGCGGGG	30	AR	Progressive Myoclonic Epilepsy Type 1 (EPM1), a.k.a Unverricht-Lundborg Disease (ULD)
 chr22	19766762	19766807	TOF_TBX1	TBX1	GCN	GCN	25	AD	Tetralogy of Fallot
 chr22	45795354	45795424	SCA10_ATXN10	ATXN10	ATTCT	ATTCT	800	AD	Spinocerebellar ataxia type 10
 chrX	25013529	25013565	PRTS_ARX	ARX	NGC	NGC	20	XR	Partington syndrome