DeCure's autonomous Neuro AI scientist is researching a drug-repurposing hypothesis for seizures, benign familial infantile, 5 — screening already-approved drugs against its 2-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease moduleSeizures, benign familial infantile, 5 maps to a 2-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 seizures, benign familial infantile, 5 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
sodium voltage-gated channel alpha subunit 8 (SCN8A) — SCN8A 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 3beta,14beta,17beta,25rdrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 25II · 2.5 Å · ligand (3beta,14beta,17beta,25R)-3-[4-methoxy-3-(methoxymethyl)butoxy]spirost-5-en (9Z9). Experimental structure, not a prediction.
What the evidence adds up to
Benign familial neonatal seizures are autosomal dominant disorders in most families, but a 1991 report of a consanguineous sibship describes an autosomal recessive form that did not show tight linkage to the chromosome 20q locus, confirming genetic heterogeneity. The self-limited familial epilepsies of neonates and infants are characterised by focal motor seizures that remit during infancy or early childhood, with no neurodevelopmental complications; a positive family history is typical but incomplete penetrance and de novo mutations occur. The 2021 overview lists KCNQ2, KCNQ3, ARX, STXBP1, SLC25A22, CDKL5, KCNT1, SCN2A and SCN8A among genes implicated in neonatal epilepsies, and mentions new possible therapeutic strategies without providing specific outcome data.
A 2025 case report of DEPDC5-related familial focal epilepsy with variable foci-1 describes a 12-month-old male whose focal seizures progressed to generalised tonic-clonic seizures within one year. Levetiracetam did not control the seizures; sodium valproate provided partial response. The child’s mother and grandmother had epilepsy, MRI was normal, and whole-exome sequencing revealed a heterozygous pathogenic variant in exon 26 of DEPDC5. This single case shows that DEPDC5 mutations can present in infancy with drug-resistant seizures that are only partially responsive to valproate, but no larger series or controlled data are available.
No abstract reports a specific drug that reliably stops seizures in benign familial neonatal epilepsy type 5 or any other genetic subtype. The 2025 case is the only one that names a drug and its effect, and that effect is partial. What is missing are prospective trials that stratify patients by genotype, funding for multicentre registries that track seizure remission and drug response in each genetic subgroup, and any randomised evidence for sodium valproate, levetiracetam, or other agents in these specific monogenic disorders.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
Brain Sciences · 2021 · 38 citations · open access
Neonatal Seizures: An Overview of Genetic Causes and Treatment Options
AbstractSeizures are the most frequent neurological clinical symptoms of the central nervous system (CNS) during the neonatal period. Neonatal seizures may be ascribed to an acute event or symptomatic conditions determined by genetic, metabolic or structural causes, outlining the so-called ‘Neonatal Epilepsies’. To date, three main groups of neonatal epilepsies are recognised during the neonatal period: benign familial neonatal epilepsy (BFNE), early myoclonic encephalopathy (EME) and ‘Ohtahara syndrome’ (OS). Recent advances showed the role of several genes in the pathogenesis of these conditions, such as KCNQ2, KCNQ3, ARX, STXBP1, SLC25A22, CDKL5, KCNT1, SCN2A and SCN8A. Herein, we reviewed the current knowledge regarding the pathogenic variants most frequently associated with neonatal seizures, which should be considered when approaching newborns affected by these disorders. In addition, we considered the new possible therapeutic strategies reported in these conditions.
Epileptic Disorders · 2023 · 21 citations · open access
ILAE Genetic Literacy Series: Self‐limited familial epilepsy syndromes with onset in neonatal age and infancy
AbstractThe self-limited (familial) epilepsies with onset in neonates or infants, formerly called benign familial neonatal and/or infantile epilepsies, are autosomal dominant disorders characterized by neonatal- or infantile-onset focal motor seizures and the absence of neurodevelopmental complications. Seizures tend to remit during infancy or early childhood and are therefore called "self-limited". A positive family history for epilepsy usually suggests the genetic etiology, but incomplete penetrance and de novo inheritance occur. Here, we review the phenotypic spectrum and the genetic architecture of self-limited (familial) epilepsies with onset in neonates or infants. Using an illustrative case study, we describe important clues in recognition of these syndromes, diagnostic steps including genetic testing, management, and genetic counseling.
An autosomal recessive form of benign familial neonatal seizures
AbstractWe present a consanguineous sibship with benign familial neonatal seizures. The mode of transmission of the disorder in this family seems to be autosomal recessive, which is contrary to the usual autosomal dominant type. Linkage analysis failed to show tight linkage between the disease locus and the autosomal dominant locus assigned to chromosome 20q. We thus conclude that benign familial neonatal seizures is a genetically heterogeneous type of epilepsy.
DEPDC5-Related Familial Focal Epilepsy With Variable Foci-1: A Report of a Rare Case
AbstractFamilial focal epilepsy with variable foci-1 (FFEVF1) is a genetic epilepsy syndrome associated with a pathogenic mutation in the DEPDC5 gene. It has autosomal dominant inheritance, along with incomplete penetrance and a variable phenotype. We present a case of focal seizures that progressed to generalized tonic-clonic seizures within the span of one year in a 12-month-old male child. A family history of epilepsy was present in the mother and grandmother of the child. Generalized epilepsy was observed in the initial EEG, while the MRI of the brain was unremarkable. Levetiracetam was unable to control the seizures; however, they were partially responsive to sodium valproate, which was prescribed later. A heterozygous pathogenic variant was revealed in exon 26 during whole-exome sequencing of the DEPDC5 gene. Family history and genetic testing can play crucial roles in pediatric epilepsy diagnosis, particularly when lab investigations and neuroimaging are normal, as showcased in this case.
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.
