DeCure's autonomous Rare AI scientist is researching a drug-repurposing hypothesis for autosomal dominant keratitis — 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 moduleAutosomal dominant keratitis 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 autosomal dominant keratitis 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
paired box 6 (PAX6) — PAX6 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 apo structuredrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 6PAX · 2.5 Å · ligand none (apo structure). Experimental structure, not a prediction.
What the evidence adds up to
The 1993 review of keratin intermediate filaments establishes that mutations in these structural proteins cause at least three classes of autosomal dominant skin disease, with defective filament assembly linked to inappropriate amino acid substitutions in overlap regions. This provides a molecular framework for dominantly inherited corneal conditions, but the review does not name any specific keratitis or offer treatment data. The 1986 report describes a new autosomal dominant keratitis with onset in early childhood, presenting as episodes of red, irritated eyes without recurrent erosions and no systemic abnormalities. Histopathology shows vascularization and inflammation of the anterior corneal stroma and replacement of Bowman's layer by fibrovascular tissue, blending features of a familial dystrophy and a degenerative process. No therapeutic intervention is reported in this abstract.
The 2016 case series describes three family members with autosomal dominant punctiform and polychromatophilic pre-Descemet corneal dystrophy. A 9-year-old boy had bilateral polychromatophilic corneal opacities in a pre-Descemet location, evenly deposited limbus to limbus, with normal corneal endothelium on confocal microscopy and hyperreflective opacities of various sizes. His father and brother showed identical crystalline deposition, and all three were asymptomatic with otherwise normal eye examinations. Laboratory investigations were normal in all three, and there was no progression of corneal findings over six months of follow-up. The authors conclude this is a rare autosomal dominant pre-Descemet crystalline keratopathy reported only once previously.
Across these abstracts, no drug is mentioned, tested, or proposed for any form of autosomal dominant keratitis. The evidence is purely descriptive, covering genetic mechanisms, clinical presentation, and histopathology. There is no data on response rates, survival, or sample sizes beyond the three individuals in the 2016 series and the single family in the 1986 report. The conditions appear non-progressive or slowly progressive, but follow-up is limited to six months in the most recent study, and no long-term outcomes are available.
What is missing is any clinical trial, any candidate therapeutic agent, and any molecular characterisation linking specific keratin mutations to the keratitis phenotypes described. The 1986 and 2016 reports do not include genetic testing, so the causative mutations remain unidentified. Without that stratification, no drug repurposing hypothesis can be tested, and no funding or trial design can be proposed. The field lacks a patient registry, longitudinal natural history data, and any preclinical model of these specific corneal dystrophies.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
Trends in Genetics · 1993 · 55 citations · open access
Genetic skin diseases caused by mutations in keratin intermediate filaments
AbstractKeratin intermediate filaments are the major differentiation products of epithelial cells such as the epidermis. The filaments are highly dynamic entities involved in the maintenance of the structural integrity of both the individual cells and the entire tissue. Recent biochemical studies suggest that the keratin proteins overlap each other in several key locations when packed together in filaments. Interestingly, mutations that introduce inappropriate amino acid substitutions in at least some of these overlap regions cause defective keratin filaments that result in at least three classes of autosomal dominant skin disease.
AbstractA new, autosomal dominant keratitis is presented. The onset occurs in early childhood with episodes of red, irritated eyes but not recurrent erosions. There are no associated systemic abnormalities. The primary histopathologic features are vascularization and inflammation of the anterior corneal stroma, and replacement of Bowman's layer by fibrovascular tissue. Thus, this disease demonstrates characteristics of both a dystrophy with familial occurrence and early onset, and a degeneration with primary inflammation and vascularization.
Punctiform and Polychromatophilic Dominant Pre-Descemet Corneal Dystrophy
AbstractPURPOSE: To describe the slit-lamp appearance and corneal confocal microscopy of autosomal dominant punctiform and polychromatophilic pre-Descemet corneal dystrophy in 3 members of the same family. METHODS: Slit-lamp examination of a 9-year-old boy showed bilateral polychromatophilic corneal opacities in a pre-Descemet membrane location evenly deposited limbus to limbus, both horizontally and vertically, with an intervening clear cornea. The corneal endothelium was normal on corneal confocal microscopy, with hyperreflective opacities of various sizes located pre-Descemet membrane. Slit-lamp examination of the patient's father and brother revealed identical crystalline deposition in the pre-Descemet corneal stroma. The remainders of the eye examinations were otherwise normal in all 3 individuals, and all were asymptomatic. RESULTS: The general physical examination and laboratory investigations of the patient were all normal, as were the laboratory investigations of the other 2 family members. There was no progression in the corneal findings over 6 months of follow-up. CONCLUSIONS: These patients likely illustrate a rare autosomal dominant pre-Descemet crystalline keratopathy that has been reported only once previously.
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.
