DeCure's autonomous Rare AI scientist is researching a drug-repurposing hypothesis for Bell's palsy — 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 moduleBell's palsy 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 bell's palsy 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
SPT3 homolog, SAGA and STAGA complex component (SUPT3H) — SUPT3H 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 ihpdrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 7KTR · 2.93 Å · ligand INOSITOL HEXAKISPHOSPHATE (IHP). Experimental structure, not a prediction.
What the evidence adds up to
Two randomised controlled trials with a total of 69 participants provide very low quality evidence on surgical decompression for Bell’s palsy. The first trial randomised 44 people to surgery or oral prednisolone; facial nerve recovery at nine months was comparable between groups, and the authors judged that statistically significant differences were unlikely. The second trial randomised 25 people to surgery or no treatment and reported no statistically significant differences. One operated participant in the first trial had 20 dB sensorineural hearing loss and persistent vertigo. Neither study blinded participants or outcome assessors, and allocation concealment was not attempted. The Cochrane review authors concluded that the evidence is insufficient to decide whether surgical intervention is beneficial or harmful, and noted that further research is unlikely because spontaneous recovery occurs in most cases.
A 2007 study of 57 patients with idiopathic peripheral facial palsy compared lesion sites determined by clinical findings with those identified by brain MRI. Clinical history placed the lesion in the infrageniculate-suprastapedial segment in 13 patients (23%), the infrastapedial-suprachordal segment in 9 (16%), and the mastoid segment in 35 (61%). No clinical findings suggested a suprageniculate lesion. On MRI, 51 of 57 patients (89%) showed abnormal enhancement of the facial nerve, with the most common area being the suprageniculate segment, including the distal intrameatal, labyrinthine and geniculate ganglion. The authors concluded that clinical history is not helpful in determining the site of a lesion in Bell’s palsy.
A 2011 Cochrane protocol for an overview of interventions for Bell’s palsy stated its aim to systematically summarise and qualitatively compare treatments, assessing differences in incomplete recovery, motor synkinesis, crocodile tears, persistent complete facial paralysis, and treatment side effects. A 2004 letter noted that most patients do well with or without treatment, that identifying who will fare poorly remains impossible, and that systematic reviews do not show statistically significant benefits for any treatment. Another 2004 letter stated that the most recent Cochrane reviews showed no treatment had yet been shown more effective than placebo, and that non-randomised studies cited as supporting combination therapy had not been included in systematic reviews.
What is still missing is a reliable way to identify the minority of patients who will not recover spontaneously, without which any trial must treat many to benefit few. No adequately powered, blinded, randomised trial of any intervention — surgical, medical, or combination — has yet shown a statistically significant benefit over placebo or no treatment. The anatomical site of the lesion, which MRI shows is most often suprageniculate, cannot be determined from clinical history, complicating any attempt to stratify patients by pathophysiology.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
Cochrane Database of Systematic Reviews · 2013 · 97 citations · open access
Surgical interventions for the early management of Bell's palsy
AbstractBACKGROUND: Bell's palsy is an acute paralysis of one side of the face of unknown aetiology. Bell's palsy should only be used as a diagnosis in the absence of all other pathology. As the proposed pathophysiology is swelling and entrapment of the nerve, some surgeons suggest surgical decompression of the nerve as a possible management option. This is an update of a review first published in 2011. OBJECTIVES: To assess the effects of surgery in the management of Bell's palsy. SEARCH METHODS: On 29 October 2012, we searched the Cochrane Neuromuscular Disease Group Specialized Register, CENTRAL (2012, Issue 10), MEDLINE (January 1966 to October 2012) and EMBASE (January 1980 to October 2012). We also handsearched selected conference abstracts for the original version of the review. SELECTION CRITERIA: We included all randomised or quasi-randomised controlled trials involving any surgical intervention for Bell's palsy. We compared surgical interventions to no treatment, sham treatment, other surgical treatments or medical treatment. DATA COLLECTION AND ANALYSIS: Two review authors independently assessed whether trials identified from the searches were eligible for inclusion. Two review authors independently assessed the risk of bias and extracted data. MAIN RESULTS: Two trials with a total of 69 participants met the inclusion criteria. The first study considered the treatment of 403 people but only included 44 participants in the surgical trial, who were randomised into surgical and non-surgical groups. However, the report did not provide information on the method of randomisation. The second study randomly allocated 25 participants into surgical or control groups using statistical charts. There was no attempt in either study to conceal allocation. Neither participants nor outcome assessors were blind to the interventions, in either study. The first study lost seven participants to follow-up and there were no losses to follow-up in the second study.Surgeons in both studies decompressed the nerves of all the surgical group participants using a retroauricular approach. The primary outcome was recovery of facial palsy at 12 months. The first study showed that the operated group and the non-operated group (who received oral prednisolone) had comparable facial nerve recovery at nine months. This study did not statistically compare the groups but the scores and size of the groups suggested that statistically significant differences are unlikely. The second study reported no statistically significant differences between the operated and control (no treatment) groups. One operated participant in the first study had 20 dB sensorineural hearing loss and persistent vertigo. We identified no new studies when we updated the searches in October 2012. AUTHORS' CONCLUSIONS: There is only very low quality evidence from randomised controlled trials and this is insufficient to decide whether surgical intervention is beneficial or harmful in the management of Bell's palsy.Further research into the role of surgical intervention is unlikely to be performed because spontaneous recovery occurs in most cases.
The usefulness of clinical findings in localising lesions in Bell's palsy: comparison with MRI
AbstractBACKGROUND: Although electrophysiological tests and brain MRI provide information about the site of the lesion in Bell's palsy, clinicians usually depend on clinical data. However, the accuracy of clinical findings in identifying lesions has never been evaluated. METHOD: A total of 57 patients with idiopathic peripheral facial palsy were included in this study. We determined the sites of the lesions based on associated symptoms and by brain MRI. We then compared the two to assess the value of clinical findings in determining lesion sites. RESULTS: Of the 57 patients, 27 were men. The mean age of all patients was 50.6+/-16.7 years. The lesion sites determined from clinical findings were as follows: the infrageniculate-suprastapedial segment, 13 (23%); the infrastapedial-suprachordal segment, 9 (16%); and the mastoid segment, 35 (61%). No sites were classified as involving the suprageniculate segment. On brain MRI, 51 (89%) of the 57 patients showed abnormal enhancement of the facial nerve, with the most common area being the suprageniculate segment, including the distal intrameatal, labyrinthine and geniculate ganglion. CONCLUSIONS: We demonstrate that clinical history is not helpful in determining the site of a lesion in Bell's palsy. The segment most frequently involved in Bell's palsy is the suprageniculate segment.
Cochrane Database of Systematic Reviews · 2011 · 6 citations
Interventions for Bell's Palsy (idiopathic facial paralysis)
AbstractThis is a protocol for a Cochrane Review (Overview). The objectives are as follows: The objective of this overview is to systematically summarise and qualitatively compare interventions for the treatment of Bell's palsy, aiming to identify the most effective treatment or treatments for this condition and to identify areas for future valuable research. We will assess whether there are differences in terms of primary (incomplete recovery) or secondary outcomes (motor synkinesis, crocodile tears, persistent complete facial paralysis, treatment side effects).
Recent developments in Bell's palsy: Authors' response
AbstractEDITOR—Most patients with Bell's palsy clearly do well with or without treatment. Outside certain patient subgroups, identifying who will fare well and who won't remains impossible. Therefore if treatment is to be given, all who are eligible for treatment must be treated for the benefit of the few. Although systematic reviews do not show statistically significant benefits, they are …
Recent developments in Bell's palsy: Trial for Bell's palsy is in progress in Scotland
AbstractEDITOR—Holland and Weiner's clinical review (albeit a traditional non-systematic, opinion based one) on the important topic of Bell's palsy is welcome,1 but we are concerned that their conclusions about treatment are simply not supported by current evidence.
The most recent Cochrane reviews show that no treatment has yet been shown to be more effective than placebo.2 3 The recent studies cited have not yet been included in the systematic reviews but since they are non-randomised, statements that combination therapy …
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.
