DeCure's autonomous Cancer AI scientist is researching a drug-repurposing hypothesis for myeloid leukemia — screening already-approved drugs against its 44-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease moduleMyeloid leukemia maps to a 44-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 myeloid leukemia in the retrieved literature, rendered from public PubChem SMILES. Which drugs appear here reflects the evidence found, not a ranked prediction.
Molecular view
Structure of L1196M Mutant Anaplastic Lymphoma Kinase — Crizotinib has a real, experimentally solved structure in complex with this target (PDB 2YFX, 1.7 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 vghdrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 2YFX · 1.7 Å · ligand Crizotinib (VGH). Experimental structure, not a prediction.
What the evidence adds up to
A 2011 retrospective review of 84 paediatric acute myeloid leukaemia patients treated at a single centre in Saudi Arabia reported that treatment related mortality fell from 76% in patients treated between 1986 and 1995 to 11.5% in those treated between 1996 and 2011, with five-year overall survival rising from 10.5% to 56%. Within the later era, which used the same MRC AML10 protocol, the introduction of supportive care measures was associated with a drop in treatment related mortality from 48.6% to 4.7% and an improvement in overall survival from 33.3% to 56.2%. The authors concluded that supportive care, not just the chemotherapy protocol, was a significant factor in outcome.
A 2016 commentary noted that acute myeloid leukaemia is an imprecise term covering myeloid malignancies with different genetic causes and therapeutic sensitivities. It reported that targeting the MLL1 and DOT1L histone modification complexes, alone and in combination, showed activity against AML driven by a mutant NPM1 protein in several preclinical models. No human data were presented.
A 2012 review described inhibitors of anaplastic lymphoma kinase, noting that crizotinib had just been approved for ALK-positive tumours such as anaplastic large cell lymphoma and a subset of non-small cell lung cancer. The review drew a parallel with imatinib in chronic myeloid leukaemia but did not present any original data on ALK inhibitors in myeloid leukaemia. No ALK inhibitor was tested in myeloid leukaemia patients in any of these abstracts.
What is missing: prospective trials that separate the effect of supportive care from chemotherapy protocols in paediatric AML; any clinical trial of DOT1L or MLL1 inhibitors in NPM1-mutated AML; and any evidence that ALK inhibitors have activity in myeloid leukaemia. Funding for stratified trials that account for centre-specific supportive care measures would be needed to clarify whether the survival gains seen in the single-centre retrospective study are reproducible.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
Expert Opinion on Investigational Drugs · 2012 · 55 citations
Inhibitors of the anaplastic lymphoma kinase
AbstractINTRODUCTION: Anaplastic lymphoma kinase (ALK) is a receptor tyrosine kinase normally expressed in the developing nervous tissue. Genetic alterations of ALK are associated with a number of cancers, including anaplastic large cell lymphoma (ALCL) and a subset of non-small cell lung cancer (NSCLC). Standard therapies for these diseases include surgery plus unspecific cytotoxic agents, with a low therapeutic window and significant treatment-associated systemic toxicity. A few small-molecule inhibitors of ALK kinase activity have been described in the recent years, some of which are currently undergoing clinical evaluation. AREAS COVERED: Literature was searched for all ALK inhibitors that have entered clinical investigation, including published research articles and meeting abstracts. Data on pharmacokinetics, safety and efficacy of crizotinib, as well as preliminary clinical data for second-generation compounds, are reviewed. The issue of drug resistance is discussed. EXPERT OPINION: Understanding the specific genetic aberration that causes cancer development and progression allows major advances in cancer therapy. Along the same way shown by imatinib in chronic myeloid leukemia, compounds that selectively target ALK are bringing a revolution in the treatment of ALK-positive tumors. Crizotinib has just been approved, and new more potent ALK inhibitors will shortly follow. These molecules represent another excellent proof-of-principle for targeted therapy.
Treatment Related Mortality of AML Pediatric Patients in a Single Center in Saudi Arabia
AbstractAbstract Abstract 4291 Despite minimal changes in therapeutic approach, the outcome of acute myeloid leukemia (AML) in pediatric patients has improved significantly in the past two decades. Supportive care measures may have contributed to this success by reducing treatment related mortality (TRM) and thereby improving the overall survival (OS) of patients. Yet their impact on outcome remained unknown and masked under protocol effect. To assess the impact of supportive care measures on outcome, we undertook a retrospective review of all pediatric patients diagnosed with AML between 1986 and 2011and treated in our institution, the Princess Norah Oncology Center, King Abdulaziz Medical City, Jeddah. A total of 87 patients were reviewed. Of these, two patients whose parents refused treatment and one lost to follow-up were excluded. A total of 84 patients were qualified for the study. These patients were treated with two different protocols based on treatment eras. Patients diagnosed between 1986 and 1995 (era 1) were treated following AML-BFM-78 protocol while patients diagnosed between 1996 and 2011 (era 2) were treated following the MRC AML10. The cumulative TRM incidence was 76% in era1 compared to 11.5% in era 2 (P = 0.0001). This resulted in an improved 5-year OS from 10.5% in era 1 to 56% in era 2 (P = 0.007). The protocols used in both eras were different and may have improved OS. Significant difference in TRM however, suggests that other factors contributed to the improved OS. To gain further insight of the contributing factors, patients who received only MRC AML10 protocol (in era2) were partitioned into two sub-eras based on supportive care measures introduced sequentially in our institution as follows: 1996 to 2002 (era 2a) and 2003 to 2011 (era 2b).The cumulative TRM incidence was 48.6% in era 2a and 4.7% in era 2b (P = 0.001). This also resulted in an improved OS from 33.3% in era 2a to 56.2% in era 2b despite using the same protocol (P = 0.007). Our findings highlight the importance of supportive care as a significant factor in outcome of children. Comparing protocols per se masks the importance of supportive care measures in impacting outcome. We suggest devising a standardized scoring system to evaluate center-specific supportive care measures to quantify the impact of supportive care on TRM and survival outcomes while simultaneously allowing us to distinguish the effect of supportive care from that of protocol and other factors such as ethnicity. Disclosures: No relevant conflicts of interest to declare.
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.
