DeCure's autonomous Cancer AI scientist is researching a drug-repurposing hypothesis for spindle cell intraocular melanoma — screening already-approved drugs against its 37-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease moduleSpindle cell intraocular melanoma maps to a 37-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 spindle cell intraocular melanoma 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
protein tyrosine phosphatase receptor type D (PTPRD) — PTPRD 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 flcdrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 2YD6 · 1.35 Å · ligand CITRATE ANION (FLC). Experimental structure, not a prediction.
What the evidence adds up to
In a 2008 retrospective review of 81 metastatic spindle cell melanoma specimens from 67 patients, the classic cytologic features of conventional melanoma were noted infrequently. Nine percent of cases showed none of those classic characteristics. Spindle cells displayed a wide range of atypia, from deceptively bland cells to those indistinguishable from high-grade sarcomas. When compared with the primary tumour or other metastases from the same patient, a cell type discrepancy was found in 20% of cases, where the previous counterpart had been epithelioid. Spindle cells also tended to lose immunoexpression of melanoma markers.
A 2015 immunohistochemical and genetic study of 58 spindle cell melanomas divided into six morphological groups found that all tumours expressed S100, SOX10, KBA.62, nestin, and cyclin D1. HMB45 and Melan A expression was diffuse and marked in nodular and superficial spreading groups, but only scattered in sarcomatoid and mixed desmoplastic melanomas, and absent in pure desmoplastic melanomas. BRAF V600E expression was detected in 14% of cases (2 nodular, 1 superficial spreading) and correlated with the presence of mutation. An NRAS mutation was found in 1 nodular spindle cell melanoma. Desmoplastic melanomas did not harbour either mutation.
A 2019 phase II single-arm trial tested neoadjuvant intravitreal ranibizumab (0.5 mg in 0.05 ml, six injections over six months) in seven patients with primary ocular melanoma requiring radical surgery due to tumour size. No patient achieved a complete or partial response at any visit. All required enucleation. Histopathology showed mixed cell melanoma in 5 of 7 (71%) and spindle cell morphology in 2 of 7 (29%). Loss of chromosome 3 was found in 5 of 7 (71%). The trial was terminated early because alternative treatments were clearly superior for local tumour control. The authors concluded that intravitreal anti-VEGF agents may have a role as adjuncts for radiation retinopathy after radiotherapy, not as primary treatment.
What remains missing is any trial that tests a drug specifically in the spindle cell variant of intraocular melanoma, rather than in uveal melanoma generally. The 2019 ranibizumab trial failed to shrink any tumour, and the genetic and immunohistochemical data from 2015 show that spindle cell melanomas are heterogeneous, with variable marker expression and infrequent BRAF mutations. No study has yet stratified patients by spindle cell morphology to test a targeted agent or immunotherapy in that subgroup. Funding for such a trial, and a design that accounts for the rarity and heterogeneity of the disease, are still absent.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
Cancer · 2008 · 43 citations · open access
Diagnostic challenges of metastatic spindle cell melanoma on fine-needle aspiration specimens
AbstractBACKGROUND: Spindle cell melanoma is a morphologic variant of melanoma that can be difficult to diagnose on specimens obtained via fine-needle aspiration (FNA). Published cytology studies concerning this entity were based for the most part on small series. In the current study, a large series of metastatic spindle cell melanoma is described and the diagnostic pitfalls present in FNA samples addressed. METHODS: The authors retrospectively reviewed the cytologic features of 81 metastatic spindle cell melanoma specimens obtained from 67 patients. Corresponding primary tumors or metastatic tumors taken elsewhere from the same patient were also evaluated. RESULTS: The cytologic smears were mostly cellular and comprised of predominantly spindle tumor cells that frequently formed cohesive fascicles or whorls intermingled with scattered epithelioid tumor cells. The classic cytologic characteristics of conventional melanoma (predominantly dyshesive cellular distribution, cytoplasmic melanin pigments, intranuclear pseudoinclusions, macronucleoli, and binucleation or multinucleation) were noted infrequently or, if present, were more readily found in coexisting epithelioid cells. Remarkably, 9% of the cases failed to demonstrate any of the above classic characteristics. In addition, spindle cells demonstrated a wide range of cytologic atypia, from deceptively bland cells resembling reactive fibroblasts to those indistinguishable from pleomorphic high-grade sarcomatous neoplasms. When the morphologic features were compared with those of the primary tumor or metastatic melanoma taken elsewhere from the same patient, cell type discrepancy was found in 20% of the cases in that the previous counterparts demonstrated the epithelioid cell type. Spindle cells also tended to lose immunoexpression of melanoma markers. CONCLUSIONS: Spindle cell melanoma infrequently demonstrates the diagnostic cytologic features and immunoreactivity of conventional melanoma. Varying degrees of cytologic atypia and possible cell type differences from the primary counterpart or metastatic melanoma occurring elsewhere are additional sources of diagnostic challenges, especially in the metastatic setting. Familiarity with cytologic features, combined with clinical and immunoperoxidase findings, is required to avoid misinterpretation.
Journal of Surgical Oncology · 1989 · 22 citations
Ocular melanoma in alberta: A 38 year review pointing to the importance of tumor size and tumor histology as predictors of survival
AbstractA large number of cases of ocular melanoma have been entered in The Provincial Cancer Registry of Alberta over the past 40 years. This study was undertaken in order to describe further the natural history of this disease and derive management recommendations for use at the provincial level. A retrospective chart review was carried out on all cases of ocular melanoma registered through The Alberta Provincial Cancer Registry between 1949 and 1987. Two hundred fifty-one cases were identified: 143 were males and 108 were females. The mean age of the patients at diagnosis was 60. The majority of the melanomas arose from the choroid of the eye (82%) with the remainder arising from the iris, conjunctiva and ciliary body, respectively. According to the Callender classification for ocular melanomas, the majority of the melanomas were of the spindle cell type (53%), the others being either mixed cell (23%), epithelioid (8%), or fascicular (1%). Survival rates differed depending on the cell type. Spindle cell tumors demonstrated a mean survival time of 5.2 years; epithelioid tumors 4.8 years and the mixed cell tumors appeared to be the most aggressive with a mean survival time of 2.7 years after diagnosis. The majority of deaths from ocular melanoma occurred within 5 years of diagnosis, although 14% of patients in this review presented with metastases more than 10 years after diagnosis. Some of the cases of ocular melanoma could be classified pathologically as small, medium, or large. Patients with large ocular melanomas had a 5 year survival rate of 33% compared to 70% and 66% for patients with small and medium sized tumors. Of note, 43% of patients with large ocular melanomas who were dead from their disease within 5 years of diagnosis were also found to have mixed cell tumors. These findings call for a longer follow-up period for ocular melanomas and point to the importance of cell type and tumor size as predictors of survival and as guides in planning prophylactic therapeutic interventions.
Neoadjuvant intravitreal ranibizumab treatment in high-risk ocular melanoma patients: a two-stage single-centre phase II single-arm study
AbstractDespite an established history of intraocular antivascular endothelial growth factor (anti-VEGF) agents therapy in a variety of ocular pathologies as well as other cancer forms, use in the primary treatment of uveal melanoma has not been well assessed. This was a two-stage therapeutic and exploratory phase II, non-randomised, single centre trial involving intraocular treatment with 0.5 mg in 0.05 ml of ranibizumab via six intravitreous injections over 6 months in patients with primary ocular melanoma that otherwise required radical surgery because of tumour size. Seven patients were recruited with a median age of 66 years. At baseline, the longest basal diameter was 15.1 mm (mean, range 10-20.4 mm) with a height measured by ultrasonography of 9.2 mm (mean, range 6.6-12.7 mm). No patients achieved complete or partial response at any visit. All required enucleation. Histopathological analysis revealed mixed cell melanoma in 5/7 (71%) and spindle cell morphology in 2/7 (29%) with ciliary body involvement in 4/7 (57%) and the presence of closed loops also in 4/7 (57%). Genetic analysis demonstrated loss of chromosome 3 in 5/7 (71%) but abnormalities in chromosome 1,6 or 8 in all cases. Our study was terminated early as alternative treatments were clearly superior for local tumour control. There continues to be a role of intravitreal anti-VEGF for the treatment of the sequelae of local radiotherapy in the form of radiation retinopathy and so these agents may be used as adjuncts in the treatment of uveal melanoma rather than as a primary treatment.
Russian Journal of Archive of Pathology · 2015 · 3 citations
Immunohistochemical and genetic profiles of melanomas with spindle cell morphology
AbstractOBJECTIVE: to comparatively study the immunohistochemical profile and to analyze mutations in the BRAF and N-RAS genes. MATERIAL AND METHODS: The spindle cell melanomas taken from the Institute's archives were divided into 6 groups according to the results of clinical and morphological analyses and follow-up studies. Immunohistochemical examination was conducted in 58 cases, including 19 nodular spindle cell melanomas, 10 superficial spreading melanomas, 4 combined melanomas, 8 sarcoma- toid melanomas, 13 mixed desmoplastic melanomas, and 4 pure desmoplastic melanomas. RESULTS: All tumors of the spectrum in question expressed S100, SOX10, KBA.62, nestin, and cyclin D1. The rate of positive staining was 80% for MITF, 69% for PNL2, 61% for HMB45, 58% for Melan A, 36% for CD117, and 35% for SMA. The expression of HMB45 and Melan A was diffuse and marked in the groups of nodular and superficial spreading melanomas; sarcomatoid and mixed desmoplastic melanomas showed only scattered stained cells; pure desmoplastic melanomas were negative to these markers. SMA immunoexpression was observed in only sarcomatoid and desmoplastic types. Dual S100 staining showed a separate actin-positive myofibroblast-like population disappearing in more cellular zones. EMA, claudin 1, and DOG1 were negative in all cases. BRAFV expression was detected in 14% (in 2 nodular and 1 superficial spreading melanomas) and correlated with the presence of mutation. NRAS mutation was found in 1 nodular spindle cell melanoma. Desmoplastic melanomas did not harbor the above mutations. CONCLUSION: This study indicates the variant heterogeneity of spindle cell melanomas, as confirmed by clinical, morphological, immunohistochemical, and molecular examinations. The findings may be useful in the differential diagnosis of these tumors.
Metastatic spindle cell melanoma on cytology – a diagnostic challenge
AbstractSpindle cell melanoma is a rare variant of malignant melanoma. The diagnosis on fine needle aspiration cytology can be challenging. An accurate cytological diagnosis is important owing to the prognostic and therapeutic implications. It also directs staging, treatment and prognosis. Spindle cell melanoma may mimic other spindle cell lesions because Due to the lack of characteristic features of conventional melanoma, spindle cell melanoma can be often mistake for various other spindle cell lesions. Fine needle aspiration cytology is often used to document recurrent or metastatic disease and thus plays a very important role. We present a case of a 61year old male with spindle cell melanoma.
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.
