The Cerelume platform

From a faint methylation pattern to an interpretable tumour profile.

The product is a liquid biopsy: a targeted assay on a few dozen CpG sites, not whole-genome sequencing. MethyGlio combines atlas-scale methylation data, a hierarchical Transformer model and feature-level interpretation in one pathway.1

Blood drawcfDNA methylationTargeted assayGliomaIDH-mutant1p/19qGradeMolecular class
01

Blood sample

cfDNA carries tumour-specific methylation fragments, but they are only a small fraction of the total.

02

Targeted assay

A panel of a few dozen CpG sites, chosen because the model relies on them and they survive in serum.

03

Hierarchical read

MethyGlio resolves tumour status, CNS origin, entity, glioma subtype, grade and molecular class in sequence.

04

Interpretable result

Glioma present or absent, likely subtype, grade signal, IDH and 1p/19q status, a confidence score and the sites behind the call.

AI-led biomarker discovery

Very little of the cfDNA in blood comes from a brain tumour, and tumour DNA is detectable in fewer than half of primary brain tumours.2,3 A glioma liquid biopsy only works if it measures exactly the right sites, and AI is how those sites are found.4,5

  1. Learn

    A hierarchical Transformer is trained on 15,606 methylation profiles across the 57,425 CpG sites shared by every array generation.

  2. Explain

    Integrated Gradients attributes each classification to the specific CpG sites that drive it, so the model shows its evidence.

  3. Select

    Only the sites that also survive in serum are kept, confirmed at single-locus resolution in matched serum and tumour. The result is a panel of a few dozen biomarkers, including novel proprietary ones.

Intended uses, in order of launch

Each use answers a question that today requires tissue.

How the science works
  1. First

    Molecular classification when tissue is unavailable or non-diagnostic.

  2. Second

    Monitoring for progression, transformation and treatment resistance.

  3. Third

    Triage of symptomatic patients and high-risk groups, and later an add-on to multi-cancer panels through partnership.

Collaborate with Cerelume

Help bring a clearer signal to brain tumour care.

Start a conversation

References

  1. 1Maimaiti A, et al. MethyGlio: cfDNA methylation and liquid biopsy for glioma classification. Manuscript under journal review. Data on file, Cerelume; 2026.
  2. 2Bettegowda C, et al. Detection of Circulating Tumor DNA in Early- and Late-Stage Human Malignancies. Sci Transl Med. 2014;6. doi:10.1126/scitranslmed.3007094
  3. 3Otsuji R, et al. Liquid Biopsy for Glioma Using Cell-Free DNA in Cerebrospinal Fluid. Cancers. 2024;16:1009. doi:10.3390/cancers16051009
  4. 4Sundararajan M, Taly A, Yan Q. Axiomatic attribution for deep networks. Proceedings of the 34th International Conference on Machine Learning. PMLR. 2017;70:3319-3328. arXiv:1703.01365
  5. 5Maimaiti A. MethyGlio: a 15,606-sample methylation atlas supporting six clinically aligned decisions. Invited oral presentation, MAP Congress 2026, London; 10 to 11 September 2026.

Platform performance and biomarker selection are from the MethyGlio manuscript, which is under journal review. The liquid biopsy is at proof-of-concept stage and is not validated for clinical use.