DeCure's autonomous Cancer AI scientist is researching a drug-repurposing hypothesis for melanoma — screening already-approved drugs against its 45-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease moduleMelanoma maps to a 45-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
Structures already discussed alongside melanoma in the retrieved literature, rendered from public PubChem SMILES. Which drugs appear here reflects the evidence found, not a ranked prediction.
Molecular view
Crystal structure of EphA4 kinase domain — Dasatinib has a real, experimentally solved structure in complex with this target (PDB 2Y6O, 1.543 Å). This is the drug's own deposited structure, not a prediction, and confirms it is a structurally characterised molecule rather than an untested guess.
Loading structure…
helix sheet 1n1drag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 2Y6O · 1.543 Å · ligand Dasatinib (1N1). Experimental structure, not a prediction.
What the evidence adds up to
A retrospective analysis of 287 patients with unresectable stage III or IV melanoma treated between 2013 and 2019 found median overall survival from the start of first-line treatment was 14.9 months and median progression-free survival was 6.7 months. Among patients receiving first-line immunotherapy (pembrolizumab, nivolumab, or ipilimumab), median overall survival was 19.2 months; for those receiving targeted therapy (vemurafenib with or without cobimetinib, or dabrafenib with or without trametinib), it was 12.6 months; and for chemotherapy, 15.9 months. Normal LDH levels, absence of brain metastases, good performance status (ECOG 0), and objective response to treatment were strong predictors of longer overall survival. Brain metastases were present in 22% of patients, and a BRAF mutation was detected in 55%.
A separate study of 400 patients compared factors associated with receiving pembrolizumab versus ipilimumab plus nivolumab. Patients with poorer performance status (ECOG 2–4 versus 0–1) were significantly more likely to receive pembrolizumab (odds ratio 6.6), as were those with PD-L1 positive tumours (odds ratio 4.5) or BRAF wild-type tumours (odds ratio 2.2). The authors note that outcome comparisons between these treatments should account for such selection biases.
A 2024 review states that while immune checkpoint inhibitors and targeted therapies have transformed the management of advanced cutaneous melanoma, there remains a critical need for novel therapies, particularly for stages resistant to current options. The review does not provide new survival or response data. A registry-based time series study from Germany reports that improved survival at the population level has been observed since the introduction of immunotherapies and targeted agents in 2011, but the abstract does not give specific survival figures.
What is still missing are prospective trials that directly compare sequences of immunotherapy and targeted therapy in unselected patient populations, as well as studies designed to overcome resistance in the substantial proportion of patients who do not respond or relapse. Funding for such trials and for biomarker-driven patient stratification remains inadequate.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
British Journal of Cancer · 2014 · 15 citations · open access
Potent anti-tumour activity of a novel conditionally replicating adenovirus for melanoma via inhibition of migration and invasion
AbstractBACKGROUND: Conditionally replicating adenoviruses (CRAds) represent a novel class of oncological therapeutic agents. One strategy to ensure tumour targeting is to place the essential viral genes under the control of tumour-specific promoters. Ki67 has been selected as a cancer gene therapy target, as it is expressed in most malignant cells but is barely detectable in most normal cells. This study aimed to investigate the effects of a Ki67 promoter-controlled CRAd (Ki67-ZD55-IL-24) on the proliferation and apoptosis of melanoma cells. METHODS: Melanoma cells were independently treated with Ki67-ZD55-IL-24, ZD55-IL-24, Ki67-ZD55, and ZD55-EGFP. The cytotoxic potential of each treatment was assessed using cell viability measurements. Cell migration and invasion were assayed using cell migration and invasion assays. Apoptosis was assayed using the annexin V-FITC assay, western blotting, reverse transcriptase PCR (RT-PCR), haematoxylin and eosin (H&E) staining, and the TUNEL assay. RESULTS: Our results showed that Ki67-ZD55-IL-24 had significantly enhanced anti-tumour activity as it more effectively induced apoptosis in melanoma cells than the other agents. Ki67-ZD55-IL-24 also caused the most significant inhibition of cell migration and invasion of melanoma cells. Furthermore, apoptosis was induced more effectively in melanoma xenografts in nude mice. CONCLUSIONS: This strategy holds promising potential for the further development of an effective approach to treat malignant melanoma.
Współczesna Onkologia · 2020 · 11 citations · open access
Real-world treatment practice in patients with advanced melanoma
AbstractINTRODUCTION: The treatment outcomes of patients with advanced/metastatic melanoma were poor before the use of new therapeutic options. MATERIAL AND METHODS: A retrospective analysis was conducted among 287 patients with unresectable stage III and stage IV melanoma treated at the Maria Sklodowska-Curie National Research Institute of Oncology Cracow Branch, from 2013 to 2019. All enrolled patients were treated with immunotherapy (IT; consisting of pembrolizumab/nivolumab, or ipilimumab) or target therapy (TT; consisting of vemurafenib ±cobimetinib or dabrafenib ±trametinib) in at least one treatment line. RESULTS: mutation was detected in 152 (55%) patients. In general, the majority of patients (92%) were in very good or good condition (Eastern Cooperative Oncology Group [ECOG] 0 or 1). Brain metastasis was detected in 64 (22%) patients. Median OS and PFS in the experimental group from the beginning of the first-line treatment were 14.9 and 6.7 months, respectively. Across the study population, as a first-line treatment patients received IT, TT as well as CHT, and the median OS was 19.2, 12.6 and 15.9 months, respectively. Multivariate analysis confirmed that normal LDH levels, no brain metastases, ECOG 0, and objective response to the treatment were strong predictors of longer OS. For PFS, absence of brain metastases, ECOG 0, and treatment response were found to be predictive factors on multivariate analysis. CONCLUSIONS: The administration of new therapies for the treatment of patients with advanced/disseminated melanoma significantly prolonged survival in this group of patients. Nevertheless, further studies should be conducted to assess the effectiveness of various sequences of treatment.
Frontiers in Oncology · 2022 · 10 citations · open access
Case report: complete remission with crizotinib in ROS1 fusion-positive sinonasal mucosal melanoma
AbstractIntroduction: Sinonasal mucosal melanoma (SNMM) originates from melanocytes. Currently, the main treatment methods, including surgery, radiotherapy and chemotherapy, have little effect on the recurrence and metastasis of SNMM. However, targeted therapy may be a breakthrough in treating SNMM. Methods: A SNMM patient with ROS1 fusion received 250mg Crizotinib capsule (2 times a day, 1 tablet each time) therapy. Results: The patient achieved partial remission after 4 months of treatment and complete remission after 8 months of treatment. Conclusion: Our findings suggest that crizotinib can be an option to improve overall survival and quality of life of patients with metastatic ROS1-fusion SNMM. We believe that our report will provide insights for the application of crizotini in the treatment of melanoma.
Unaddressed Challenges in the Treatment of Cutaneous Melanoma?
AbstractBackground and Objectives: While the management of noninvasive cutaneous melanoma (CM) is typically limited to a secondary excision to reduce recurrence risk and periodic follow-up, treating patients with advanced melanoma presents ongoing challenges. Materials and Methods: This review provides a comprehensive examination of both established and emerging pharmacologic strategies for advanced CM management, offering an up-to-date insight into the current therapeutic milieu. The dynamic landscape of advanced CM treatment is explored, highlighting the efficacy of immune checkpoint inhibitors and targeted therapies, either in monotherapy or combination regimens. Additionally, ongoing investigations into novel treatment modalities are thoroughly discussed, reflecting the evolving nature of melanoma management. Results: The therapeutic landscape for melanoma management is undergoing significant transformation. Although various treatment modalities exist, there remains a critical need for novel therapies, particularly for certain stages of melanoma or cases resistant to current options. Conclusions: Consequently, further studies are warranted to identify new treatment avenues and optimize the utilization of existing drugs.
Factors Associated with Immunotherapy Selection in Patients with Advanced Melanoma
AbstractAIM: To explore factors associated with pembrolizumab (PEMBRO) versus ipilimumab + nivolumab (IPI+NIVO) selection in advanced melanoma. MATERIALS & METHODS: Total of 12 academic and satellite clinics contributed to this study. Descriptive and logistic regression analyses were conducted to explore associations between clinical characteristics and treatment choice. Results: Total of 400 patients were included: 200 PEMBRO and 200 IPI+NIVO. Patients were significantly more likely to receive PEMBRO versus IPI+NIVO if they had poorer Eastern Cooperative Oncology Group score, 2-4 versus 0-1 (odds ratio [OR]: 6.6; 95% CI: 3.0-14.7), if they were PD-L1 positive (OR: 4.5; 95% CI: 1.9-10.4) or had BRAF wild-type tumor (OR: 2.2; 95% CI: 1.4-3.6). CONCLUSION: Patient factors are significantly associated with treatment selection in advanced melanoma. Outcomes comparisons should take this into consideration.
A phase II trial of dasatinib in patients with unresectable locally advanced or stage IV mucosal, acral, and vulvovaginal melanomas: A trial of the ECOG-ACRIN Cancer Research Group (E2607).
Abstract9501 Background: Pre-clinical studies report a critical role of c-KIT mutations in some mucosal, acral, solar, and vulvovaginal melanomas. Clinical trials of KIT-directed therapy with imatinib and sunitinib demonstrated activity in these subtypes. Unlike other TKIs, dasatinib has activity in melanoma cell lines with the most common KIT mutation at exon 11L576P. E2607 assessed the efficacy of dasatinib in treatment-naïve or previously-treated patients (pts) with unresectable melanoma of these subtypes. Methods: Pts were assigned to receive dasatinib 70 mg PO twice daily with adjustment for toxicity. The primary objective for this two-stage phase II trial was response rate (RR: RECIST). Stage I was open to KIT mutated (KIT+) and wild-type (KIT-) tumors with mucosal, acral, and solar melanomas (n = 57). Depending upon the interim analysis, stage II would be for pts with KIT+ (n = 30) tumors; to enrich for KIT+, vulvovaginal was added and solar melanomas removed. Secondary objectives included progression-free survival (PFS), overall survival (OS), and safety. Results: From May 2009 to Dec 2010, 57 pts were accrued to stage I. These data were presented at ASCO 2012. Three pts had KIT+ tumors, with 13.2+ months (mo) as the longest OS. Stage II opened in Nov 2011, accrued 24 pts with KIT+ tumors, and closed in Dec 2015 due to slow accrual. Six pts had mucosal (25%), 9 acral (37.5%), and 9 vulvovaginal melanomas (37.5%). As of Jan 2016, 16/24 have progressed (median PFS: 4.0 mo, 95% CI: 1.3-25.0) and 14/24 died (median OS: 12.3 mo, 4.5-29.7). Among 10 surviving pts, median follow-up is 15.2 mo (0.5-36.1 mo). Of 17 pts from stage II with mature response data, 4 had partial response (PR: 23.5%), 6 stable disease (35%), 5 progression (29.5%), and 2 were unevaluable (12%). Grade III (11/23: 48%) treatment-related toxicities were fatigue, (5 pts), anemia (3 pts) and dyspnea (2 pts). One pt had grade IV dyspnea. Conclusions: E2607 is closed to accrual, and finalized results, including type of KIT mutation and durations of disease control from stages I and II will be presented. Among pts with these KIT+ melanoma subtypes, dasatinib is an active agent. Clinical trial information: NCT00700882.
German Medical Science (German Research Foundation) · 2024 · 0 citations · open access
Improved Melanoma Survival in Germany: A Registry-Based Time Series Study
AbstractIntroduction: Since 2011, new treatment options specifically for prognostically unfavorable cutaneous melanoma are available, such as immunotherapies and targeted agents. Randomized controlled trials report improvements in survival, but it is unclear if beneficial effects are also appearing on the population-level. [for full text, please go to the a.m. URL]
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.
