SSteeraMed

DeepoMe · SteeraMed Research Portal

A Steerable Biomedical World Model

A world model first — and a suite of tools built on it. The physician sets the direction; the model navigates: we encode aging, disease, and intervention as computable networks, so every individualized decision follows a traceable evidence chain.

Three-Layer Stack

Bench · InfrastructureMap · EngineeringN-of-1 · Application

Infrastructure → Engineering → Application · One shared evidence substrate

Content on this site is for research reference only and does not constitute medical advice.

Research Landscape

One steerable framework, a growing suite of modules — from a blood/saliva readout to good healthspan practice.

Steerability Framework

The founding framework paper: aging, disease, and intervention encoded as one steerable, computable network.

For Pharma

Drug repurposing, run on virtual patients first

The same human-scale representations serve two audiences: longevity medicine navigates them in the landscape above; the pharmaceutical industry runs drug-repurposing screening on them. VPR appears on both sides.

VPR — Virtual Patient Repurposing

Paper 3: human-scale representations for virtual patients, built through drug repurposing — 332 module maps × 1,916 small molecules × 5 chronic-disease tasks. The full dataset is open on this site's Bench.

SteeraMed Map — Industrial Workflow

The industrial research workflow on the navigation map: disease reclassification → patient stratification → drug repurposing → target discovery. It outputs candidate hypotheses, not causally validated conclusions.

How the pieces fit — Capomics: the mother science running through every SteeraMed module, with module-level intrinsic capacity (mIC) as the shared measurement language. DeepKang (the DeepoMe institutional channel): follow-up retesting and efficacy-mechanism record services that work alongside the SteeraMed map, while the academic system stays open and neutral.

Four Tracks within the Landscape

From Infrastructure to Application

Four tracks on one shared evidence substrate: Bench quantifies capability under a frozen protocol, RootMap maps conditional dependencies between aging hallmarks and organ aging, Map turns validated capability into navigation workflows, and N-of-1 lands it in individualized intervention reasoning.

Infrastructure

Bench Module Benchmark

A shared coordinate system for AI-generated biological maps.

Why

AI can generate "aging modules," but without a unified benchmark no one can say which is better. Drug repurposing needs a reproducible, comparable, human-scale testbed.

What

An evaluation infrastructure of 332 modules × 1,916 small molecules × 5 chronic-disease tasks (extended to 23 disease categories): a frozen protocol guarantees reproducibility; the online demo replays the paper's propose–score–reflect–refine agent loop; all data and code open-sourced.

Where

A self-learning agent: the module atlas grows with the literature instead of relying on manual curation. Core finding — no single biological map is universally optimal; different diseases need different module combinations.

Science

RootMap Conditional Dependency Atlas

Which maintenance states shape how our organs age?

Why

PPI networks tell us which molecules are connected — not which maintenance processes sit upstream of which organ functions. Hallmark catalogs are lists, not relations. Longevity-medicine practice needs to know what to measure and what to follow up.

What

From blood DNA methylation: a module-level intrinsic-capacity score (mIC) for every gene module in every sample; Δz comparisons of organ-module–age associations between hallmark-module groups — with every claim passing a four-check protocol (multiple-testing correction, random-direction nulls, age-proxy check, random gene-set controls).

Where

Toward a third cohort and cross-modal readouts (protein clocks, imaging), calibration studies, and an interactive RootMap tool offered as a research preview through steeramed.com.

Engineering

Map: State–Intervention Navigation

Evidence should not be scattered across thousands of papers — it should grow into a navigable map.

Why

Physicians and researchers need navigation from individual state to intervention options, not yet another pile of literature. Evidence must be organized, versioned, and traceable.

What

Engineering Bench-validated capability into a versioned, evidence-aware navigation map: personal state projection for individuals; an industrial research workflow (disease reclassification → patient stratification → drug repurposing → target discovery) for pharma and R&D teams.

Where

To become the computable data substrate of longevity medicine — clinical communication and industrial R&D sharing one map, one evidence chain.

Application

N-of-1 Individualized Reasoning

Longevity interventions are N-of-1 trials — population averages cannot answer "will this work for me?"

Why

Multimorbidity among adults 65+ reaches 42.4%; the one-disease-one-model paradigm has failed. Each aging trajectory is unique and demands counterfactual reasoning about this individual.

What

DNA methylation reads individual state; the DNet dependency network (108 terms, 1,121 edges) bridges Western and Chinese medicine; PPI networks link drug targets — converging into a four-layer evidence chain (state → steering alignment → mechanism → confidence), translated into a three-panel clinical view.

Where

From retrospective validation (four-disease drug screening; RA Recall@10 = 51.7%, 5.8× random baseline) toward a prospective precision-intervention loop: target engagement → clinical biomarker response → individualized prescriptions.