Table 1 Pathogenic TRs used in training/LOOCV and testing datasets. RExPRT ensemble classification, as well as both SVM and XGB scores are provided for each pathogenic TR. Additionally, information is provided for each locus including associated disease, motif, the gene region in which the TR is located, age-of-onset, inheritance pattern of the associated disease, whether a motif change is required to pathogenic, and whether the motif was uniquely represented among other pathogenic TRs in the training dataset
From: RExPRT: a machine learning tool to predict pathogenicity of tandem repeat loci
Gene | Disease | Age of onset | Motif | Gene region | Inheritance | Motif change | Unique motif | SVM score | XGB score | RExPRT classification | Dataset |
|---|---|---|---|---|---|---|---|---|---|---|---|
AFF2 | Fragile X syndrome, FRAXE type | 2–10 years | CCG | 5′UTR | X-Linked | No | No | 0.99 | 0.91 | Pathogenic | Training |
AFF3 | Intellectual disability associated with fragile site FRA2A | 0–7 years | CGG | Intron | Dominant | No | No | 0.98 | 0.64 | Pathogenic | Testing |
AR | Spinal and bulbar muscular atrophy, Kennedy disease | 20–49 years | CAG | Exon | X-Linked | No | No | 0.97 | 1.00 | Pathogenic | Training |
ARX | Early infantile epileptic encephalopathy | < 1 year | GCG | Exon | X-Linked | No | No | 0.99 | 0.97 | Pathogenic | Training |
ARX | Partington syndrome | 1–3 years | GCN | Exon | X-Linked | No | No | 0.98 | 0.99 | Pathogenic | Testing |
ATN1 | Dentatorubral-pallidoluysian atrophy | 1–72 years | CAG | Exon | Dominant | No | No | 0.97 | 0.99 | Pathogenic | Training |
ATXN1 | Spinocerebellar ataxia type 1 | 13–60 years | CAG | Exon | Dominant | No | No | 0.97 | 0.99 | Pathogenic | Training |
ATXN10 | Spinocerebellar ataxia type 10 | 12–48 years | ATTCT | Intron | Dominant | No | Yes | 0.00 | 0.00 | Benign | Training |
ATXN2 | Spinocerebellar ataxia type 2 | 25–50 years | CAG | Exon | Dominant | No | No | 0.87 | 1.00 | Pathogenic | Training |
ATXN3 | Spinocerebellar ataxia type 3, Machado-Joseph disease | 10–50 years | CAG | Exon | Dominant | No | No | 0.63 | 1.00 | Pathogenic | Training |
ATXN7 | Spinocerebellar ataxia type 7 | 0–50 years | CAG | Exon | Dominant | No | No | 1.00 | 1.00 | Pathogenic | Training |
ATXN8OS | Spinocerebellar ataxia type 8 | 1–73 years | CTG | 3′UTR | Dominant | No | No | 0.99 | 0.90 | Pathogenic | Training |
BEAN1 | Spinocerebellar ataxia type 31 | 20–72 years | TGGAA | Intron | Dominant | Yes | Yes | 0.51 | 0.04 | Pathogenic | Training |
C9orf72 | Amyotrophic lateral sclerosis, frontotemporal dementia | 27–85 years | GGGGCC | Intron | Dominant | No | Yes | 0.90 | 0.94 | Pathogenic | Training |
CACNA1A | Spinocerebellar ataxia type 6 | 19–73 years | CAG | Exon | Dominant | No | No | 0.92 | 1.00 | Pathogenic | Training |
CBL2 | Jacobsen syndrome, fragile site FRAX11B | < 1 year | CGG | 5′UTR | Dominant | No | No | 0.98 | 0.98 | Pathogenic | Testing |
CNBP | Myotonic dystrophy type 2 | 30–40 years | CCTG | Intron | Dominant | No | Yes | 0.07 | 0.00 | Benign | Training |
COMP | Multiple epiphyseal dysplasia | 13 years | GTC | Exon | Dominant | No | Yes | 0.96 | 1.00 | Pathogenic | Testing |
CSTB | Myoclonic epilepsy of Unverricht and Lundborg | 6–15 years | CCCCGCCCCGCG | 5′UTR | Recessive | No | Yes | 0.83 | 0.52 | Pathogenic | Training |
DAB1 | Spinocerebellar ataxia type 37 | 18–64 years | TTTCA | Intron | Dominant | Yes | No | 0.00 | 0.53 | Pathogenic | Training |
DIP2B | Intellectual developmental disorder, FRA12A type | 1 year | CGG | 5′UTR | X-Linked | No | No | 0.97 | 1.00 | Pathogenic | Testing |
DMPK | Myotonic dystrophy type 1 | 0–70 years | CTG | 3′UTR | Dominant | No | No | 0.76 | 0.98 | Pathogenic | Training |
FGF14 | Spinocerebellar ataxia 27B | 46–77 years | GAA | Intron | Dominant | No | No | 0.02 | 0.00 | Benign | Testing |
FMR1 | Fragile X syndrome | 2–65 years | CGG | 5′UTR | X-Linked | No | No | 0.97 | 0.99 | Pathogenic | Training |
FOXL2 | Blepharophimosis, epicanthus inversus, and pitosis | < 1 year | GCC | Exon | Dominant | No | No | 0.99 | 0.99 | Pathogenic | Training |
FXN | Friedrich ataxia | 5–25 years | GAA | Intron | Recessive | No | Yes | 0.00 | 0.01 | Benign | Training |
GIPC1 | Oculopharyngodistal myopathy | 10–29 years | CGG | 5′UTR | Dominant | No | No | 0.95 | 0.99 | Pathogenic | Training |
GLS | Glutaminase deficiency | 0–1 years | GCA | 5′UTR | Recessive | No | No | 0.93 | 1.00 | Pathogenic | Training |
HOXA13 | Hand-foot-genital syndrome 1 | < 1 year | GCN | Exon | Dominant | No | No | 0.97 | 1.0 | Pathogenic | Testing |
HOXA13 | Hand-foot-genital syndrome 2 | < 1 year | GCG | Exon | Dominant | No | No | 1.00 | 0.99 | Pathogenic | Training |
HOXA13 | Hand-foot-genital syndrome 3 | < 1 year | GCN | Exon | Dominant | No | No | 1.00 | 0.99 | Pathogenic | Testing |
HOXD13 | Syndactyly | < 1 year | GCG | Exon | Dominant | No | No | 0.83 | 1.00 | Pathogenic | Training |
HTT | Huntington disease | 10–70 years | CAG | Exon | Dominant | No | No | 0.97 | 1.00 | Pathogenic | Training |
JPH3 | Huntington disease-like 2 | 12–66 years | CTG | 3′UTR | Dominant | No | No | 0.56 | 0.62 | Pathogenic | Training |
LRP12 | Oculopharyngodistal myopathy type 1 | 7–50 years | CGG | 5′UTR | Dominant | No | No | 0.98 | 0.99 | Pathogenic | Training |
MARCHF6 | Familial adult myoclonic epilepsy type 3 | 10–40 years | TTTCA | Intron | Dominant | Yes | No | 0.00 | 0.01 | Benign | Testing |
NIPA1 | Amyotrophic lateral sclerosis | 19–66 years | GCG | Exon | Dominant | No | No | 0.98 | 1.0 | Pathogenic | Testing |
NOP56 | Spinocerebellar ataxia type 36 | 48–57 years | GGCCTG | Intron | Dominant | No | Yes | 0.67 | 0.66 | Pathogenic | Training |
NOTCH2NLC | Neuronal intranuclear inclusion disease | 16–76 years | GGC | 5′UTR | Dominant | No | No | 0.88 | 0.71 | Pathogenic | Training |
NUTMB-AS1 | Oculopharyngeal myopathy with leukoencephalopathy 1 | 15–40 years | GGC | Exon | Dominant | No | No | 0.83 | 0.04 | Pathogenic | Testing |
PABPN1 | Oculopharyngeal muscular dystrophy | 26–65 years | GCG | Exon | Dominant | No | No | 0.90 | 0.80 | Pathogenic | Training |
PHOX2B | Congenital central hypoventilation syndrome | 0–20 years | GCN | Exon | Dominant | No | No | 0.71 | 0.99 | Pathogenic | Training |
PPP2R2B | Spinocerebellar ataxia type 12 | 8–55 years | CAG | 5′UTR | Dominant | No | No | 0.87 | 1.00 | Pathogenic | Training |
PRDM12 | Hereditary sensory and autonomic neuropathy type VIII | < 1 year | GCC | Exon | Recessive | No | No | 0.98 | 0.98 | Pathogenic | Testing |
RAPGEF2 | Familial adult myoclonic epilepsy type 7 | 18–37 years | TTTCA | Intron | Dominant | Yes | No | 0.02 | 0.03 | Benign | Testing |
RFC1 | Cerebellar ataxia, neuropathy, and vestibular areflexia syndrome | 33–71 years | AAGGG | Intron | Recessive | Yes | Yes | 0.01 | 0.00 | Benign | Training |
RILPL1 | Oculopharyngodistal myopathy type 4 | 14–27 years | CGG | 5′UTR | Dominant | No | No | 0.48 | 0.72 | Pathogenic | Testing |
RUNX2 | Cleidocranial dysplasia | < 1 year | GCN | Exon | Dominant | No | No | 1.00 | 0.99 | Pathogenic | Training |
SAMD12 | Familial adult myoclonic epilepsy type 1 | 18–50 years | TTTCA | Intron | Dominant | Yes | No | 0.94 | 0.00 | Pathogenic | Training |
SOX3 | X-linked mental retardation | 0–9 years | GCC | Exon | X-Linked | No | No | 0.95 | 0.98 | Pathogenic | Training |
STARD7 | Familial adult myoclonic epilepsy type 2 | 5–60 years | TTTCA | Intron | Dominant | Yes | No | 0.05 | 0.49 | Benign | Testing |
TBP | Spinocerebellar ataxia type 17 | 3–55 years | CAG | Exon | Dominant | No | No | 0.98 | 1.00 | Pathogenic | Training |
TBX1 | Tetralogy of Fallot | < 1 year | GCN | Exon | Dominant | No | No | 0.96 | 0.99 | Pathogenic | Testing |
TCF4 | Fuchs endothelial corneal dystrophy 3 | 32–70 years | CTG | Intron | Dominant | No | No | 0.62 | 0.96 | Pathogenic | Training |
THAP11 | Spinocerebellar ataxia | 4–51 years | CAG | Exon | Dominant | No | No | 0.96 | 0.99 | Pathogenic | Testing |
TNRC6A | Familial adult myoclonic epilepsy type 6 | 20–70 years | TTTCA | Intron | Dominant | Yes | No | 0.00 | 0.02 | Benign | Testing |
XYLT1 | Baratela-Scott syndrome | < 1 year | GGC | 5′UTR | Recessive | No | No | 0.99 | 0.04 | Pathogenic | Training |
YEATS2 | Familial adult myoclonic epilepsy type 4 | 10–33 years | TTTCA | Intron | Dominant | Yes | No | 0.02 | 0.63 | Pathogenic | Testing |
ZIC2 | Holoprosencephaly-5 | < 1 year | GCN | Exon | Dominant | No | No | 0.98 | 1.00 | Pathogenic | Training |
ZIC3 | X-linked VACTERL syndrome | < 1 year | GCN | Exon | X-Linked | No | No | 0.97 | 0.98 | Pathogenic | Testing |
ZNF713 | Autism spectrum disorder associated with fragile site FRA7A | Early | CGG | 5′UTR | Dominant | No | No | 0.97 | 0.99 | Pathogenic | Testing |