Prima Mente Unlocks Early-Stage Alzheimer’s Diagnostics with Epigenome Model
•February 17, 2026
0
Why It Matters
Early, non‑invasive detection can shrink diagnostic delays and guide therapeutic interventions, reshaping neurodegenerative care and reducing NHS waiting lists.
Key Takeaways
- •Pleiades detects early Alzheimer’s with 89% accuracy
- •Accuracy climbs to 97% with pTau‑217 integration
- •Model trained on 1.9 trillion epigenetic tokens
- •Runs on NVIDIA DGX Cloud Lepton AI platform
- •Deployed in UK’s 15‑site SANDBOX clinical study
Pulse Analysis
Diagnosing Alzheimer’s and related neurodegenerative disorders has long relied on neuroimaging, cognitive testing, and, in rare cases, invasive brain biopsies—methods that are costly, time‑consuming, and often detect disease after irreversible damage has occurred. Recent advances in liquid biopsy technology have opened a pathway to capture disease signals from circulating cell‑free DNA, yet interpreting these fragments requires sophisticated computational tools. Prima Mente’s Pleiades model leverages the dynamic nature of the epigenome, using DNA methylation patterns as a real‑time readout of neuronal and immune cell health, thereby shifting the diagnostic paradigm from static snapshots to continuous molecular monitoring.
The core of Pleiades is a 7‑billion‑parameter foundation model trained on 1.9 trillion tokens of methylation and genomic data, enabling it to pinpoint the tissue origin of cfDNA fragments with unprecedented precision. In validation cohorts the system identified early‑stage Alzheimer’s and Parkinson’s with 89 % sensitivity, a figure that rose to 97 % when combined with established protein biomarkers such as pTau‑217. By enriching disease‑specific cfDNA signals up to twenty‑fold, the model can detect rare pathological signatures from minimal blood volumes, offering a scalable, non‑invasive alternative to current diagnostic standards.
Prima Mente’s partnership with NVIDIA’s DGX Cloud Lepton platform underscores the growing convergence of high‑performance AI infrastructure and biomedical research. The ongoing SANDBOX study across fifteen UK sites demonstrates real‑world feasibility and promises to alleviate NHS waiting lists by triaging patients more efficiently. Looking ahead, the company intends to broaden the platform to proteomics, transcriptomics, and longitudinal multi‑omics datasets, positioning Pleiades as a versatile diagnostic engine for multiple disease areas by 2026. Such a move could accelerate drug development pipelines, attract venture capital, and set new regulatory benchmarks for AI‑driven precision medicine.
Prima Mente Unlocks Early-Stage Alzheimer’s Diagnostics with Epigenome Model
AI biology company, Prima Mente, is on a mission to tackle one of the greatest challenges in medicine, uncovering the molecular basis of neurodegenerative conditions. These aging-related diseases are characterized by subtle changes in gene regulation, cellular identity, immune signaling, and more that begin decades before symptoms emerge.
While much progress in therapeutics has focused on designing new protein structures or analyzing fixed genome sequences, Prima Mente seeks to establish a new paradigm for precision diagnostics that uses AI to understand the dynamic epigenome, where aging biology happens in real-time.
“Imaging and cognitive scores don’t necessarily tell you how to intervene or change the path of disease,” said Hannah Madan, PhD, co-founder at Prima Mente, in an interview with GEN Edge. “This is what epigenetics can start to unravel.”
The company’s AI model, Pleiades, analyzes DNA methylation changes in cell-free DNA (cfDNA) derived from patient blood samples to diagnose neurodegenerative disease. The method presents an appealing alternative to invasive and costly brain biopsies, which are the current diagnostic standard.
Strikingly, Pleiades demonstrated an 89% success rate for detecting early-stage Alzheimer’s and Parkinson’s in real-world clinical cohorts. That rate subsequently increased to 97% when the model was integrated with leading neurodegenerative protein biomarkers, such as pTau-217.
Prima Mente is an NVIDIA Inception member and has partnered with NVIDIA Cloud Partner, Nebius, to leverage the DGX Cloud Lepton AI platform to train and develop Pleiades. The company, whose name translates to “first mind” and signals the approach of breaking down problems to first principles, was founded in 2022 and currently hosts over two dozen employees based across London, San Francisco, and Dubai.
“The hypothesis we had from the beginning was that bigger models would help understand complex biology over time, which requires both compute and the ‘know-how’ for building these models,” said Madan, when describing the motivation for the Nvidia and Nebius collaboration.
Pleiades is currently deployed in a live clinical study, called SANDBOX, across 15 sites in the U.K. The model will support the classification and stratification of patients with suspected neurodegenerative conditions to improve clinical outcomes and manage waiting lists in the U.K. National Health Service. Designing therapeutics in-house is also on Prima Mente’s horizon.
In the fragment
Pleiades is a 7 billion parameter epigenetic foundation model trained using 1.9 trillion tokens of epigenetic data representing human methylation and genomic sequences. Data was sourced from genomic and cfDNA across multiple cell types and sequenced with methods that preserve cytosine methylation state.
By training on tissue-specific information, the model can accurately pinpoint cfDNA cell type of origin, identifying both brain components (neurons and microglia) and immune components (T-cells and B-cells), as predictors of Alzheimer’s disease. The team is building a virtual cell model, named Parthenon, to discover novel therapeutic targets for microglia-related cells.
Notably, Pleiades demonstrated that cfDNA fragmentation patterns can act as a novel class of biomarkers for Alzheimer’s detection. These fragments reflect biological processes such as epigenetic state, nucleosome positioning, and mechanism of cell death.
Results show that Pleiades can reconstruct cell-free DNA fragments with 83% per-nucleotide accuracy and a 91% match to original methylation patterns. Additionally, the model enriches signals from specific cell types in the blood by up to 20-fold to enable the detection of rare disease signatures from limited material.
Looking ahead, Madan said Prima Mente aims to expand the model beyond epigenomics to proteomics, transcriptomics, and more clinical data. To support this goal, the company is currently conducting longitudinal studies that include both blood samples and brain tissue.
Madan also emphasizes that the platform is generalizable and will be applied to more disease areas in 2026.
The post Prima Mente Unlocks Early-Stage Alzheimer’s Diagnostics with Epigenome Model appeared first on GEN - Genetic Engineering and Biotechnology News.
0
Comments
Want to join the conversation?
Loading comments...