Systematic biomarker discovery for triple-negative breast cancer.

TNBC isn't one disease — but it's still targeted like one.

Triple-negative breast cancer (TNBC) is not one disease. Lehmann's 2011 classification split TNBC into distinct molecular subtypes — basal-like, mesenchymal, luminal androgen receptor, and others — each with different biology and different drug sensitivities. Despite that, candidate biomarker and targeting studies are still mostly done one gene, one paper, one lab at a time, without systematically checking whether a target behaves consistently across subtypes before it gets built into a therapeutic strategy.

Test it against real data before it becomes a strategy.

Cleavr tests candidate TNBC biomarkers against public, patient-level sequencing data — starting with TCGA — broken out by molecular subtype, and cross-checks every claim against the primary literature before it's published. Every number is independently re-derived from raw source files in a second pass, not computed once and trusted. Null results get reported exactly as directly as positive ones.

One case study live. Independently verified, start to finish.

Milestones, as they happen.

• 2026-07-08Screening pipeline shipped. The GNRHR analysis is now a reusable, gene-agnostic pipeline: candidates sourced systematically (Open Targets), tested for subtype- and survival-association with Benjamini–Hochberg correction applied across every gene tested together, and cross-referenced against known druggability (ChEMBL) and existing TNBC-specific literature coverage (PubMed). Run against a 15-gene candidate set as a first test — results are internal for now, pending the same cross-cohort verification Case Study 01 went through before anything gets published as a finding.
• 2026-07-08Cleavr goes public. Site live on GitHub Pages — full methodology, code, and data open for review.
• 2026-07-07Case Study 01 published. GNRHR expression tested across TNBC molecular subtypes using TCGA data (n=116), independently re-derived and literature-checked.

From one gene to a real discovery pipeline.

• Cross-cohort validation — check findings against a second dataset (METABRIC) so results don't rest on one cohort.
• Literature cross-referencing, deeper — current pipeline checks how much TNBC-specific coverage a gene already has; next step is surfacing the actual relevant papers per candidate, not just a count.
• Queryable biomarker index — one place to check any gene's subtype-level expression and survival association, not a one-off write-up per gene.