Finalist
Faith Ogundimu
Diffuse midline glioma is a paediatric brainstem cancer that is almost uniformly fatal: about ninety percent of children die within two years, and the first systemic drug, approved in 2025, does not cure.
Core trick
Couples a regulatory-activity score, the disrupted motif, and a confidence flag into one agent call, promoting variants only when evidence agrees.
Description
Diffuse midline glioma is a paediatric brainstem cancer that is almost uniformly fatal: about ninety percent of children die within two years, and the first systemic drug, approved in 2025, does not cure. Its biology is largely non-coding, which is exactly where variant prediction is least trustworthy.
NCypher is a triage layer, not another predictor. In the matched fetal-OPC cell context it couples a regulatory-activity score, the mechanism (the motif and the exact base that breaks), and an honest confidence flag into one agent call, promoting a variant only when independent lines of evidence agree.
Across 10,869 somatic non-coding variants from an H3 K27M cohort it returns a two-sided finding, not a manufactured driver: somatic mutation does not drive the super-enhancers this tumour depends on, yet those enhancers sit on markedly more conserved OPC regulatory sequence (matched-permutation p<0.001), with NPAS3 leading the shortlist.
The engine is validated where it should work (progenitor caQTLs, AUROC 0.69) and honest where it should not. Six independent stress tests, each re-derived by a separate reviewer agent, harden it. NCypher ships as a rich MCP tool, an Agent Skill with a built-in sceptic, a reproducibility gate, and a downloadable regulatory map.
README excerpt
<p align="center"> <img src="assets/ncypher-logo.png" width="460" alt="NCypher, decode the non-coding"> </p> <p align="center"><i>decode the non-coding</i></p> <p align="center"> A calibrated, honest, context-specific engine for triaging <b>non-coding regulatory variants</b> in paediatric<br> <b>diffuse midline glioma</b>, delivered as a rich MCP tool and an Agent Skill for Claude Science. </p> <p align="center"> <b>Built with Claude: Life Sciences</b> · Researcher track · Apache-2.0 </p> <p align="center"> <a href="https://faith-ogun.github.io/ncypher/"><b>◆ Explore the live dashboard →</b></a> </p> <p align="center"> <a href="https://youtu.be/0EQfVwYXFG8"><b>▶ Watch the 3-minute demo</b></a> · <a href="notebooks/reproduce.ipynb">Reproduce the finding</a> · <a href="regulatory_map/">The regulatory map</a> </p> <p align="center"> <a href="https://github.com/faith-ogun/ncypher/actions/workflows/reproducibility.yml"><img src="https://github.com/faith-ogun/ncypher/actions/workflows/reproducibility.yml/badge.svg" alt="reproducibility"></a> </p> --- ## What is this, in plain terms? Most of the genome does not code for protein. The other ~98% *regulates*: it is the switches and dials that decide which genes turn on, in which cell, and by how much. When one of those switches is mutated the effect is real, but it is invisible to the tools built for protein-coding genes. **Diff