Orchestrated Biosciences
Tumor mutational burden (TMB) is our best predictor of immune checkpoint blockade (ICB) response, yet it's only modestly accurate (AUC ~0.6) and reads DNA alone.
Core trick
Runs leave-one-cohort-out tests on RNA splicing, editing, and transposable-element features against TMB, then reframes response as survival using subclonal mutation burden.
Description
Tumor mutational burden (TMB) is our best predictor of immune checkpoint blockade (ICB) response, yet it's only modestly accurate (AUC ~0.6) and reads DNA alone. I asked whether a tumor's RNA adds independent signal. I built a cohort-scale pipeline for non-reference RNA features (alternative splicing, intron retention, RNA editing, transposable-element activation, fusion transcripts) across five melanoma ICB cohorts, and ran the Evo2 genomic foundation model on novel splice junctions. Using strict leave-one-cohort-out testing, nothing in the RNA layer beat plain TMB — and I found why: every RNA signal was a proxy for how inflamed the tumor already was, and that proxy flips sign between cohorts, which may explain why so many RNA biomarkers fail to replicate. Reframing from response to survival surfaced the real result: subclonal mutation burden — a measure of how disordered a tumor's evolution is — predicted worse overall survival across three cohorts (HR 1.49, p=0.0004), separable from both TMB and immune state. The takeaway: how many mutations a tumor carries shapes whether it responds; how disordered its evolution is shapes how long the patient lives. A rigorously reported negative plus a novel, cross-cohort survival signal — and an honest account of where the signal actually lives.
README excerpt
# evolutionary-rna-state **Reconstructing a latent evolutionary RNA-state of tumors from bulk RNA-seq to organize immune checkpoint blockade (ICB) response.**  *Early driver mutations set a tumor's trajectory; downstream RNA-processing phenotypes are manifestations of one latent state **S** that shapes antigenicity and immunotherapy response. Illustrations: [NIH BioArt](https://bioart.niaid.nih.gov) (NIAID Visual & Medical Arts).* ## Thesis Early driver mutations set a tumor's evolutionary trajectory. As the tumor evolves, genomic instability, epigenetic remodeling, RNA-processing dysregulation, and immune selection combine to produce coordinated transcriptomic abnormalities — alternative splicing, intron retention, RNA editing, transposable-element (TE) activation, fusion transcripts, and cryptic/non-canonical ORFs. **Core reframing:** these are not independent biomarkers but downstream manifestations of a single latent *evolutionary RNA-state* **S**. That state — not any one biomarker — ultimately shapes tumor antigenicity and response to ICB. Clinical response is one noisy *observable* of where a tumor sits on its trajectory, not the latent variable itself. ## Falsifiable claims 1. **Co-variation (internal).** The RNA phenotypes above share