DeCure's autonomous Rare AI scientist is researching a drug-repurposing hypothesis for Angelman syndrome — screening already-approved drugs against its 13-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease moduleAngelman syndrome maps to a 13-gene Open Targets module — the target space DeCure's AI scientist screens approved drugs against.
DeCure.ai methodSignature reversal (LINCS) plus network proximity (STRING) rank already-approved drugs likely to perturb this module — the same engine that produces DeCure.ai's repurposing hypotheses.
Repurposing thesisScreening approved medicines against this disease module, then publishing the evidence for the strongest candidate. Known pharmacology and human exposure data make the first question sharper — they do not establish safety or efficacy in a new indication.
Research record
01
ResearchComing soon
Candidate research + dossier — target rationale, drug-repurposing thesis and evidence pack.proof: Published dossier + on-chain hash
02
ValidationComing soon
In-vitro biological validation at a contract research org (CRO).proof: CRO contract + in-vitro report
03
Peer review & paperComing soon
Peer-reviewed paper published open-access (preprint + journal).proof: DOI + open-access link + on-chain hash
Current lead
No approved-drug candidate for angelman syndrome is corroborated in the literature DeepSearch retrieved. Some conditions are managed with non-pharmacological care — a device, surgery or physical therapy — rather than a medicine; that may be the case here, or the literature we found may simply be too sparse yet to support a drug-repurposing angle.
Molecular view
methyl-CpG binding protein 2 (MECP2) — MECP2 is one of the genes genetically linked to this disease in Open Targets — shown as context, not as a drug target we're pursuing: no approved-drug candidate for this disease is yet corroborated in the literature we found.
Loading structure…
helix sheet unxdrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 6OGK · 1.65 Å · ligand UNKNOWN ATOM OR ION (UNX). Experimental structure, not a prediction.
What the evidence adds up to
In a phase 2 randomised trial (STARS, 2020), 88 adolescents and adults with Angelman syndrome were assigned to placebo, gaboxadol 15 mg once daily, or gaboxadol 10 mg morning plus 15 mg evening for 12 weeks. Of 87 who received at least one dose, 78 completed the study. Adverse events were mostly mild or moderate; no life-threatening events occurred. On a prespecified exploratory analysis using an adapted Clinical Global Impression–Improvement scale, the once-daily gaboxadol group showed improvement compared with placebo (p = 0.0006). The authors state the drug was generally well tolerated and that further studies are warranted.
A 2005 review of Angelman syndrome describes its prevalence as 1 in 10,000 to 1 in 20,000. The syndrome presents in infancy with global developmental delay, microcephaly, seizures, or an ataxic/hypotonic cerebral palsy. Diagnosis becomes clearer after age one or two, when speech does not develop, walking is impaired by severe ataxia, and seizures occur. EEG findings can be diagnostic: high-voltage slow waves at 4–6 cycles per second, 2–3 c/s slow activity in runs, and spikes or sharp waves posteriorly provoked by eye closure. The genetic cause involves the UBE3A gene on chromosome 15; microdeletions are most common and carry a less than 1% recurrence risk, while UBE3A mutations carry a 50% recurrence risk. In 10–15% of cases genetic confirmation is not possible.
A 2025 case report describes an 11-year-old girl with Angelman syndrome who developed severe drowsiness and limb weakness after receiving a combination of levetiracetam, clobazam, clonazepam, and sodium valproate. A clinical pharmacist identified clonazepam as highly relevant to the adverse effects. After the medical team adjusted the medications, the patient’s symptoms improved and she was discharged.
What is still missing: the phase 2 gaboxadol trial was exploratory and not designed to establish efficacy; no phase 3 data are available. The case report is a single observation, not a controlled study. No trial has yet demonstrated a disease-modifying effect in Angelman syndrome, and the heterogeneity of genetic subtypes and symptom severity makes patient stratification a persistent challenge. Funding for adequately powered, long-term trials remains limited.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
Neurology · 2020 · 28 citations · open access
The STARS Phase 2 Study
Abstract<h3>Objective</h3> To evaluate safety and tolerability and exploratory efficacy end points for gaboxadol (OV101) compared with placebo in individuals with Angelman syndrome (AS). <h3>Methods</h3> Gaboxadol is a highly selective orthosteric agonist that activates δ-subunit–containing extrasynaptic γ-aminobutyric acid type A (GABA<sub>A</sub>) receptors. In a multicenter, double-blind, placebo-controlled, parallel-group trial, adolescent and adult individuals with a molecular diagnosis of AS were randomized (1:1:1) to 1 of 3 dosing regimens for a duration of 12 weeks: placebo morning dose and gaboxadol 15 mg evening dose (qd), gaboxadol 10 mg morning dose and 15 mg evening dose (bid), or placebo morning and evening dose. Safety and tolerability were monitored throughout the study. Prespecified exploratory efficacy end points included adapted Clinical Global Impression–Severity and Clinical Global Impression–Improvement (CGI-I) scales, which documented the clinical severity at baseline and change after treatment, respectively. <h3>Results</h3> Eighty-eight individuals were randomized. Of 87 individuals (aged 13–45 years) who received at least 1 dose of study drug, 78 (90%) completed the study. Most adverse events (AEs) were mild to moderate, and no life-threatening AEs were reported. Efficacy of gaboxadol, as measured by CGI-I improvement in an exploratory analysis, was observed in gaboxadol qd vs placebo (<i>p</i> = 0.0006). <h3>Conclusion</h3> After 12 weeks of treatment, gaboxadol was found to be generally well-tolerated with a favorable safety profile. The efficacy as measured by the AS-adapted CGI-I scale warrants further studies. <h3>Clinicaltrials.gov Identifier</h3> NCT02996305. <h3>Classification of Evidence</h3> This study provides Class I evidence that, for individuals with AS, gaboxadol is generally safe and well-tolerated.
AbstractThe neurological and diagnostic aspects of Angelman syndrome (AS) are reviewed by a geneticist at the University of Florida, Gainesville, FL. The prevalence of AS is 1/10,000 to 1/20,000. The syndrome presents in infancy with global developmental delay, microcephaly, seizures or an ataxic/hypotonic form of cerebral palsy. The facial features and general physical examination are generally normal, although a protruding tongue, strabismus, brisk deep tendon reflexes, and a happy demeanor may be present. Hypopigmentation in infants with AS due to deletion of the P pigment gene but may be overlooked. The diagnosis becomes more evident after 1 or 2 years of age, when speech does not develop, walking is impaired by severe ataxia, and seizures occur. The EEG findings can be diagnostic, with high voltage slow waves at 4-6 c/s throughout the record, 2-3 c/s slow activity in runs, especially anteriorly, and spikes or sharp waves posteriorly, provoked by eye-closure. The diagnosis is usually obvious clinically after 3 years of age and is sometimes first suggested by the parents. Behavior is often outgoing, hyperactive, hyperexcitable with excessive laughing, grabbing to engage siblings, putting objects in the mouth, and drooling. These characteristics without signs of degeneration and associated with microcephaly, seizures, and ataxia are classical. Maternally derived chromosome 15 was implicated in 1980, with microdeletion of 15qll.2-15ql3. Subsequently, the ubiquitin ligase gene, UBE3A, located at 15ql 1.2, was identified as the AS gene, and 4 genetic mechanisms were involved, microdeletions being most common. The type of genetic mechanism was correlated with the severity of AS, patients with large chromosome deletions having a greater risk of seizures, microcephaly, and hypopigmentation of skin, eye and hair. The distinct behavioral syndrome and seizure patterns are related to the effects of UBE3A occurring during neuronal development. DNA methylation testing of blood is a sensitive and specific screening for 3 of the 4 genetic mechanisms. Chromosome 15 FISH analysis is necessary to distinguish which mechanism is involved. In 10-15% of cases genetic test confirmation is not possible. Genetic counseling should be offered to families of AS patients since UBE3A mutations carry a 50% recurrence risk, while common deletion cases have <1% recurrence risk. (Williams CA.
Serican Journal of Medicine · 2025 · 0 citations · open access
A possible drug interaction between sodium valproate and clonazepam resulting in severe drowsiness and limb weakness：A case report and literature review
AbstractThe treatment process of an 11-year-old girl diagnosed with Angelman syndrome, who experienced severe drowsiness and limb weakness following the combination of sodium valproate and clonazepam, is analyzed herein. Initially, the patient was prescribed levetiracetam, clobazam, clonazepam, and sodium valproate. However, she subsequently developed significant lethargy and weakness in her limbs. Upon her admission, the clinical pharmacist take medication reconciliation the following day, identifying clonazepam as a highly relevant factor in her condition. The medical team collaboratively adjusted the inappropriate medications. Ultimately, the patient's symptoms improved, leading to her discharge.
Disease module: DeepOracle (Open Targets). Structures: RDKit from PubChem SMILES. Literature: retrieved by DeepSearch across 234,678,978 indexed works (targeted per-candidate search), resolved on OpenAlex.
DeCure is a research and publication project, not medical advice and not a treatment. "DeCure for X" describes a research goal, not a claim that a cure exists. Backing a cure is a contribution to fund the research — it is not an investment, and confers no yield, royalty, equity or IP ownership. Papers are published open-access by the DeCure.ai DAO.
