DeCure's autonomous Rare AI scientist is researching a drug-repurposing hypothesis for Stevens-Johnson syndrome — screening already-approved drugs against its 8-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease moduleStevens-Johnson syndrome maps to a 8-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 stevens-johnson 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
IKAROS family zinc finger 1 (IKZF1) — IKZF1 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 3-chloro-4-methylphenyldrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 9Q2D · 2.94 Å · ligand 1-(3-chloro-4-methylphenyl)-3-({2-[(3S)-2,6-dioxopiperidin-3-yl]-1-oxo-2,3-dihydro-1H-isoindol-5-yl}methyl)urea (85C). Experimental structure, not a prediction.
What the evidence adds up to
A retrospective review of 78 cases admitted to Siriraj Hospital in Thailand between 1981 and 1990 identified 58 cases of Stevens-Johnson syndrome and 20 cases of toxic epidermal necrolysis. A culprit drug was determined in 60 patients (77%). The mean time from first drug administration to onset was 6.8 days, with longer incubation periods observed for thiacetazone (10.5 days), phenytoin (12 days), and carbamazepine (11.3 days). The most common culprit drugs were antibiotics (32 cases, including penicillin, sulfonamides, tetracycline, and erythromycin), anticonvulsants (nine cases), and antitubercular drugs (eight cases, all thiacetazone). The most frequent underlying diseases were infections (52.7%), pulmonary tuberculosis (10.8%), and seizures (8.1%). The total mortality rate was 14%; 5% for Stevens-Johnson syndrome and 40% for toxic epidermal necrolysis. Mortality was not affected by the type of drug responsible.
Two case reports from 2015 and 2017, with identical text, describe Stevens-Johnson syndrome as a very rare, immune complex mediated hypersensitivity reaction. They state that the most common triggers are drugs, followed by infection, and that 25-50% of cases are idiopathic. The reports focus on the medicolegal consequences of death from the condition, including physician responsibility and potential criminal consequences, but provide no new clinical data on treatment or outcomes.
No drug repurposing data, no interventional trials, and no evidence of any drug being tested for treatment or prevention of Stevens-Johnson syndrome are present in these abstracts. What is missing is any prospective trial design, any biomarker or genetic stratification (beyond a mention of HLA association in the case reports), and any funding for a controlled study of a candidate drug.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
International Journal of Dermatology · 1993 · 53 citations
STEVENS‐JOHNSON SYNDROME AND TOXIC EPIDERMAL NECROLYSIS IN THAILAND
AbstractBACKGROUND: Stevens-Johnson syndrome (SJS) and toxic epidermal necrolysis (TEN) are potentially life-threatening illnesses that have often been linked to drug exposure. METHODS: We looked retrospectively for all cases of SJS and TEN that were admitted to Siriraj Hospital between 1981 and 1990 to determine the drug etiology. RESULTS: Fifty-eight cases of SJS and 20 cases of TEN were identified. Eight patients initially had an SJS-like aspect, which subsequently evolved into TEN. A culpable drug was determined in 60 patients (77%). The mean time from first drug administration to onset of SJS or TEN was 6.8 +/- 6.5 days (range, 1 to 28 days). A longer incubation period was observed with thiacetazone (10.5 +/- 5.6 days), phenytoin (12 +/- 8.5 days), and carbamazepine (11.3 +/- 3.4 days). CONCLUSIONS: The culprit drugs included the following: antibiotics, 32 cases (penicillin, sulfonamides, tetracycline, erythromycin); anticonvulsants, nine (phenytoin, carbamazepine, barbiturates); antitubercular drugs, eight (thiacetazone); analgesics, four (acetylsalicylic acid, fenbufen); sulfonylurea, two; allopurinol, one; and others, four. The most frequent underlying diseases justifying the ingestion of one or more drugs in our patients were infections (52.7%), followed by pulmonary tuberculosis (10.8%), and by seizures (8.1%). The total mortality rate was 14%; 5% for SJS, and 40% for TEN. Mortality was not affected by the type of drug responsible.
Correction of Stevens-Jonson syndrome - an adverse event of antibiotic therapy
AbstractStevens-Johnson syndrome refers to the type B of adverse reactions to drugs according to WHO classification and is severe systemic allergic reaction of delayed type. This syndrome is a severe variant of multiform erythema in which both skin and mucous membranes symptoms are observed. In the article literature data on etiology, pathogenesis and treatment of Stevens-Johnson syndrome as well as clinical case of 24 years old woman with this syndrome are represented.
Medicolegal Consequences of Death due to Stevens Johnson Syndrome: A Case Report
AbstractConditions like Stevens Johnson syndrome are very rare and mortality arising out of it is still a rarest entity. It is immune complex mediated hypersensitivity reaction; most common factors to trigger the immunity are drugs, followed by infection with various organisms, which starts the chain of events in SJS. It sometimes associated with HLA Antigen and 25-50% cases are idiopathic. In present case an emphasis is given on progression of this life threatening condition, mode of death, responsibilities of the physician and legal as well as criminal consequences arise out of it while treating such cases.
International Journal of Forensic Science & Pathology · 2015 · 0 citations · open access
Medicolegal Consequences of Death due to Stevens Johnson Syndrome: A Case Report
AbstractConditions like Stevens Johnson syndrome are very rare and mortality arising out of it is still a rarest entity. It is immune complex mediated hypersensitivity reaction; most common factors to trigger the immunity are drugs, followed by infection with various organisms, which starts the chain of events in SJS. It sometimes associated with HLA Antigen and 25-50% cases are idiopathic.
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.
