{ "version": "https://jsonfeed.org/version/1", "title": "Jianghui Xiong", "icon": "https://avatars.micro.blog/avatars/2026/34/1954144.jpg", "home_page_url": "https://en.xiongjianghui.com/", "feed_url": "https://en.xiongjianghui.com/feed.json", "items": [ { "id": "http://xiongj.micro.blog/2026/09/20/your-disease-risk-isnt-a.html", "content_html": "

Your disease risk isn’t a number — it’s a slope. Reserves fall across five lines for years before diagnosis: phenotypic warning, organ function, metabolic stability, immune repair, hallmarks. Manage the slope, not the score.

\n

I’m rarely on LinkedIn — email: jianghui@deepome.com

\n\"\"\n", "date_published": "2026-09-20T15:58:37+08:00", "url": "https://en.xiongjianghui.com/2026/09/20/your-disease-risk-isnt-a.html" }, { "id": "http://xiongj.micro.blog/2026/09/16/a-steerable-model-must-answer.html", "content_html": "

A steerable model must answer counterfactuals: what transition would this module have made without the intervention? That question separates a world model from a black box: www.preprints.org/manuscrip…

\n

I’m rarely on LinkedIn — email: jianghui@deepome.com

\n\"\"\n", "date_published": "2026-09-16T18:35:18+08:00", "url": "https://en.xiongjianghui.com/2026/09/16/a-steerable-model-must-answer.html" }, { "id": "http://xiongj.micro.blog/2026/09/15/two-patients-the-same-symptom.html", "content_html": "

Two patients, the same symptom score, different mIC states — the same intervention, different outcomes. Why N-of-1 medicine needs a state layer, not just risk scores: www.preprints.org/manuscrip…\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n\"\"\n", "date_published": "2026-09-15T05:46:57+08:00", "url": "https://en.xiongjianghui.com/2026/09/15/two-patients-the-same-symptom.html" }, { "id": "http://xiongj.micro.blog/2026/09/15/mic-modulelevel-intrinsic-capability-our.html", "content_html": "

mIC = module-level intrinsic capability: our proposed state format for biomedical world models. One vector per module; an intervention is defined by the transition it induces: www.preprints.org/manuscrip…\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n\"\"\n", "date_published": "2026-09-15T00:06:13+08:00", "url": "https://en.xiongjianghui.com/2026/09/15/mic-modulelevel-intrinsic-capability-our.html" }, { "id": "http://xiongj.micro.blog/2026/09/14/we-want-to-steer-a.html", "content_html": "

We want to steer a body, not just predict it — but most medical AI only forecasts. A model must clear five checkpoints to steer; miss one and it is just a predictor: www.preprints.org/manuscrip…\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n\"\"\n", "date_published": "2026-09-14T22:15:43+08:00", "url": "https://en.xiongjianghui.com/2026/09/14/we-want-to-steer-a.html" }, { "id": "http://xiongj.micro.blog/2026/09/14/we-want-a-map-honest.html", "content_html": "

We want a map honest enough to show its own blank spots. A third of our 332 modules have no known intervention. We publish the gaps and take nominations: steeramed.com/en/bench/…\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n", "date_published": "2026-09-14T20:39:26+08:00", "url": "https://en.xiongjianghui.com/2026/09/14/we-want-a-map-honest.html" }, { "id": "http://xiongj.micro.blog/2026/09/11/we-believe-a-model-that.html", "content_html": "

We believe a model that can’t say where it fails isn’t science. Ours, published first: hold out one disease, and performance drops to a coin flip — on the landing page, not in an appendix: steeramed.com/en/bench/\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n", "date_published": "2026-09-11T22:25:27+08:00", "url": "https://en.xiongjianghui.com/2026/09/11/we-believe-a-model-that.html" }, { "id": "http://xiongj.micro.blog/2026/09/11/we-believe-more-data-is.html", "content_html": "

We believe more data is not more medicine. We tested the full marker atlas against a small curated panel — the atlas won outright in only 9 of 23 diseases. Pick modules, not markers: steeramed.com/en/bench/\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n", "date_published": "2026-09-11T17:57:40+08:00", "url": "https://en.xiongjianghui.com/2026/09/11/we-believe-more-data-is.html" }, { "id": "http://xiongj.micro.blog/2026/09/10/our-one-question-can-human.html", "content_html": "

Our one question: can human health be steered, not just predicted? Three preprints — what a steerable model must have, one person’s evidence chain, and an open benchmark with failure modes first: steeramed.com/en/bench/\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n\"\"\n", "date_published": "2026-09-10T22:28:41+08:00", "url": "https://en.xiongjianghui.com/2026/09/10/our-one-question-can-human.html" }, { "id": "http://xiongj.micro.blog/2026/09/07/an-ai-agent-proposed-and.html", "content_html": "

An AI agent proposed and refined aging modules under a frozen protocol. Of 7 concepts, 2 reach nominal significance (ECM stiffening +0.031, TRM efferocytosis +0.021); none survive FDR. Replay is public: steeramed.com/en/bench/…\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n", "date_published": "2026-09-07T17:06:33+08:00", "url": "https://en.xiongjianghui.com/2026/09/07/an-ai-agent-proposed-and.html" }, { "id": "http://xiongj.micro.blog/2026/09/06/our-claim-capability-modules-are.html", "content_html": "

Our claim: 332 capability modules are the right unit for steering human health. Any such claim has to lose somewhere. Next three posts: where a 117-axis panel beats the atlas, where we drop to chance, and which axes have no handle.> I’m rarely on LinkedIn — email: jianghui@deepome.com

\n", "date_published": "2026-09-06T22:46:56+08:00", "url": "https://en.xiongjianghui.com/2026/09/06/our-claim-capability-modules-are.html" }, { "id": "http://xiongj.micro.blog/2026/09/06/put-a-human-on-mars.html", "content_html": "

Put a human on Mars, Europa, Kepler-22b — which capability reserves get remodeled first? A pure test of deduction: no new data, only whether the reasoning survives published biology. Which reserve would you bet breaks first?\nI’m rarely on LinkedIn — email: jianghui@deepome.com

\n", "date_published": "2026-09-06T21:46:54+08:00", "url": "https://en.xiongjianghui.com/2026/09/06/put-a-human-on-mars.html" }, { "id": "http://xiongj.micro.blog/2026/08/29/which-representation-ranks-repurposing-drugs.html", "content_html": "

Which representation ranks repurposing drugs best? It depends on the disease: Hallmarks won cancer (recall@20 0.900), food-as-medicine won depression, TCM won sedatives; the full atlas was strictly best in only 9 of 23: https://www.preprints.org/manuscript/202608.0998/v1

\n\"\"\n", "date_published": "2026-08-29T14:44:43+08:00", "url": "https://en.xiongjianghui.com/2026/08/29/which-representation-ranks-repurposing-drugs.html" }, { "id": "http://xiongj.micro.blog/2026/08/28/everyone-is-building-virtual-cells.html", "content_html": "

Everyone is building virtual cells. We’re after the missing layer between cell and patient — emergence, pathway compensation, and whether this person responds to this intervention. The figure contrasts the two: https://steeramed.com/en/

\n\"\"\n", "date_published": "2026-08-28T21:22:58+08:00", "url": "https://en.xiongjianghui.com/2026/08/28/everyone-is-building-virtual-cells.html" }, { "id": "http://xiongj.micro.blog/2026/08/28/we-built-steeramed-bench-to.html", "content_html": "

We built SteeraMed Bench to answer one question: can an AI-generated “aging module” actually predict drug effects? The setup: 332 modules × 1,916 repurposing drugs × 23 disease categories, one frozen protocol for everyone. The diagram shows the instrument: https://steeramed.com/en/bench/

\n\"\"\n", "date_published": "2026-08-28T18:11:18+08:00", "url": "https://en.xiongjianghui.com/2026/08/28/we-built-steeramed-bench-to.html" }, { "id": "http://xiongj.micro.blog/2026/08/28/our-new-preprint-maps-human.html", "content_html": "

Our new preprint maps human health as 332 capability modules — 117 nutrient, 105 food-medicine, 72 aging-hallmark, 38 syndrome axes. Figure 1 shows how the atlas and its frozen evaluation protocol fit together: https://www.preprints.org/manuscript/202608.0998/v1

\n\"\"\n", "date_published": "2026-08-28T13:08:28+08:00", "url": "https://en.xiongjianghui.com/2026/08/28/our-new-preprint-maps-human.html" }, { "id": "http://xiongj.micro.blog/2026/08/28/the-ai-virtual-cell-is.html", "content_html": "

The AI virtual cell is fashionable. But a patient is not a bigger cell — between them sit emergent transitions, pathway compensation, heterogeneity. Missing is not a larger model but another scale of map, plus action semantics and a retest loop a virtual cell doesn’t have.

\n", "date_published": "2026-08-28T09:19:09+08:00", "url": "https://en.xiongjianghui.com/2026/08/28/the-ai-virtual-cell-is.html" }, { "id": "http://xiongj.micro.blog/2026/08/27/biomedical-knowledge-lives-in-three.html", "content_html": "

Biomedical knowledge lives in three forms: travelogues (reviews), museums (databases), maps (computable knowledge). Astronomy has star catalogs, chemistry the periodic table. Biology has the largest data output in science — and still no coordinate system of its own.

\n", "date_published": "2026-08-27T18:39:15+08:00", "url": "https://en.xiongjianghui.com/2026/08/27/biomedical-knowledge-lives-in-three.html" }, { "id": "http://xiongj.micro.blog/2026/08/27/our-starting-axiom-a-body.html", "content_html": "

Our starting axiom: a body is a set of capabilities for adapting to its environment. Not a gene list, not a network diagram. Everything downstream — capability axes, response mapping, module panels — is deduced from that one sentence, then tested.

\n", "date_published": "2026-08-27T12:25:20+08:00", "url": "https://en.xiongjianghui.com/2026/08/27/our-starting-axiom-a-body.html" }, { "id": "http://xiongj.micro.blog/2026/08/27/systems-biology-tells-us-how.html", "content_html": "

Systems biology tells us how a living system runs. A world model tells us how it moves under an action. A steerable model asks a third question: how does the rider get there without breaking the horse? Not a rebrand — a different task.

\n", "date_published": "2026-08-27T08:13:52+08:00", "url": "https://en.xiongjianghui.com/2026/08/27/systems-biology-tells-us-how.html" }, { "id": "http://xiongj.micro.blog/2026/08/27/two-hundred-years-of-biomedicine.html", "content_html": "

Two hundred years of biomedicine ran on induction: collect data, find patterns, explain. AI is usually deployed to make that loop faster. We are trying the other direction — deduce from first principles, then let data refute it: https://steerable.world

\n", "date_published": "2026-08-27T00:26:09+08:00", "url": "https://en.xiongjianghui.com/2026/08/27/two-hundred-years-of-biomedicine.html" }, { "id": "http://xiongj.micro.blog/2026/08/26/steeramed-bench-module-axes-drugbank.html", "content_html": "

SteeraMed Bench: 332 module axes, 1,916 DrugBank small molecules, 5 disease tasks, 23 ATC-derived categories. Versioned snapshots, published failure modes, open nominations: steeramed.com/en/bench/

\n", "date_published": "2026-08-26T11:54:42+08:00", "url": "https://en.xiongjianghui.com/2026/08/26/steeramed-bench-module-axes-drugbank.html" }, { "id": "http://xiongj.micro.blog/2026/08/25/why-modules-one-gene-is.html", "content_html": "

Why modules: one gene is too small a unit to steer a body, a whole transcriptome too large to act on. Our atlas has 332 axes — 117 nutrient targets, 105 food-medicine compounds, 72 extended aging hallmarks, 38 syndrome proxies from Chinese medicine.

\n", "date_published": "2026-08-25T10:13:18+08:00", "url": "https://en.xiongjianghui.com/2026/08/25/why-modules-one-gene-is.html" }, { "id": "http://xiongj.micro.blog/2026/08/24/most-aiforbiology-work-asks-what.html", "content_html": "

Most AI-for-biology work asks what will happen. We ask a narrower question: which knob, turned how far, moves a person — and what measurement would show it. Prediction without a handle is not yet medicine.

\n", "date_published": "2026-08-24T22:35:09+08:00", "url": "https://en.xiongjianghui.com/2026/08/24/most-aiforbiology-work-asks-what.html" }, { "id": "http://xiongj.micro.blog/2026/08/24/new-blog-notes-on-steerable.html", "content_html": "

New blog: notes on steerable biology — what can actually be changed in a human body, and how we would know it moved. Method notes, failure boundaries, and open problems from building SteeraMed Bench: steeramed.com/en/bench/

\n", "date_published": "2026-08-24T21:20:00+08:00", "url": "https://en.xiongjianghui.com/2026/08/24/new-blog-notes-on-steerable.html" } ] }