AI for Science · AI for Biology · AI for Drug Development

A causal virtual cell — the chain of thought for drug development.

ChronoCell-WM brings frontier AI to the heart of biology: a virtual cell that does not just predict endpoints, but simulates the regulatory path that produced them — built by a UC San Diego collaboration spanning single-cell biology, generative world models, controllable reasoning, and production-grade ML systems.

  • AI for Science
  • AI for Biology
  • AI for Drug Development
  • Four labsBiology · world model · reasoning · systems
  • UC San DiegoMulti-department collaboration
  • Minute-scaleSingle-cell temporal resolution
  • Open scienceData, models, benchmarks, APIs

Vision · AI for Science

A virtual cell that
can answer counterfactuals.

We believe the next frontier of AI for Science is not predicting labels — it is simulating the causal processes that produce them. Modern single-cell genomics tells us what cells become after a perturbation, but not how they got there. ChronoCell-WM closes that gap.

Given an initial cell state and an intervention program — a gene, a drug, a cytokine, a combination, a schedule — the model simulates the regulatory trajectory step by step, producing endpoint predictions with the mechanistic path that produced them.

“If a cell starts in state S₀ — what happens under A, under B, under A+B, under A→B, or under B→A?”

Why it matters · AI for Drug Development

Drug development is a trajectory problem
solved with snapshot data.

~90%

of drug candidates fail in the clinic — often from resistance, scheduling, or kinetic toxicity that endpoint data cannot reveal.

$2B+

average cost to bring a therapy to market — much of it lost discovering causal mechanisms only after late-stage failures.

104+

combinatorial intervention programs (doses, orders, schedules) per disease — exhaustive wet-lab screening is intractable.

Endpoint-only view — what most perturbation atlases provide today. Two snapshots, no path.
Causal trajectory view — what ChronoCell-WM provides. Minute-scale waypoints reveal mechanism, timing, and branching.

The gap

Static data, dynamic biology

Today's perturbation atlases measure cells at fixed endpoints. The transient regulatory states that drive commitment, resistance, and combination effects are structurally invisible.

The opportunity

Causal trajectories, not labels

A virtual cell that simulates how regulatory states evolve under intervention — not just where they end up — could replace much of the discovery search with in silico hypothesis generation.

The unlock

Time-resolved single-cell data

Recent advances in minute-scale single-cell profiling now make causal regulatory dynamics directly observable — providing the missing supervision for true world-model learning.

The approach · AI for Biology

Four converging research programs.
One causal virtual cell.

ChronoCell-WM is uniquely positioned because it brings together four research programs that rarely live in the same team — each already validated through public technologies, peer-reviewed publications, and open-source releases. Together they cover the full stack required to move biology from endpoint observation to in silico simulation.

  1. I

    Temporal single-cell biology

    Wang Lab · ChronoSeq platform & regulatory inference

    Minute-scale genome-wide single-cell profiling that reveals how regulatory states evolve under intervention — the missing causal substrate that endpoint atlases cannot provide.

  2. II

    Controllable, plausible reasoning

    Q-Lab · Constrained generation & diverse paths

    Energy-based constraints, diverse-path search, and uncertainty calibration that keep long-horizon rollouts on the biological manifold — making the virtual cell interpretable and falsifiable.

  3. III

    Generative world models

    MixLab · Action-conditioned simulation & reasoning

    Frontier-scale world models that represent state, action, and transition — proven on video, language, and reasoning tasks, now extended to cellular dynamics and counterfactual rollouts.

  4. IV

    ML systems at production scale

    PICASSO Lab · Branching workloads & efficient inference

    Production-grade compiler, scheduling, and caching infrastructure validated on the largest open models — the systems substrate that makes counterfactual rollout at biological scale tractable.

From Endpoint snapshots Where cells land
Through Causal world model How cells move
To Predicted trajectories Mechanism, timing, uncertainty
Impact In silico discovery Combinations · schedules · drivers

The team

Four labs. One full stack.

ChronoCell-WM requires capabilities that rarely live in one team: minute-scale single-cell biology, world modeling at frontier scale, constrained reasoning, and production-grade ML systems. The four collaborating labs at UC San Diego cover every layer — with an existing track record of co-authorship.

Wei Wang

I — Temporal single-cell biology

Wei Wang

Professor, Chemistry & Biochemistry · UC San Diego

Wang is an internationally recognized leader in regulatory genomics and single-cell biology. His lab developed ChronoSeq — the technology that pushed single-cell transcriptomics to minute-scale temporal resolution — and has built directed transcription-factor atlases validated by CRISPR perturbation (Nature, 2026). Decades of expertise in regulatory network inference and experimental validation anchor the project's biological foundation.

wanglab.ucsd.edu →

Lianhui Qin

II — Controllable, plausible reasoning

Lianhui Qin

Assistant Professor, CSE · UC San Diego · Q-Lab

Qin's research focuses on controllable, constrained, and diffusion-enhanced reasoning. Her work develops methods for generating diverse yet scientifically plausible reasoning trajectories under explicit constraints. In ChronoCell-WM, this expertise provides the foundation for constraint-aware cellular simulation, enabling biologically consistent and interpretable long-horizon rollouts under complex perturbations and uncertainty.

lianhui.ucsd.edu →

Zhiting Hu

III — Generative world models

Zhiting Hu

Assistant Professor, HDSI & CSE · UC San Diego · MixLab

Hu pioneers general-purpose world models for machine reasoning. His group built Pandora (action-conditioned video world model trained on 1000+ H100s), RAP (reasoning as planning with a world model), and the widely adopted LLM Reasoners library. His framework for action-conditioned counterfactual simulation maps directly onto cellular dynamics.

zhiting.ucsd.edu →

Yufei Ding

IV — ML systems at production scale

Yufei Ding

Professor, CSE · UC San Diego · PICASSO Lab

Ding builds the systems substrate beneath frontier-scale ML — WLB-LLM (OSDI '25, validated in production on the largest open models), FastTree (MLSys '25), KVFlow (NeurIPS '25), and others. Her work delivers order-of-magnitude gains in training and inference throughput for branching, heterogeneous workloads.

yufeiding.ucsd.edu →

This is not a new collaboration. Wang & Hu have co-authored four papers; Wang & Qin have three active projects together; Qin & Hu share five co-authored publications across NeurIPS, EMNLP, and ACL; Qin & Ding co-authored a NeurIPS '25 paper. The team has access to UC San Diego's SDSC GPU clusters and dedicated experimental core facilities — the project is execution-ready from day one.

Direction

From seed dataset
to a discovery engine.

Three phases, each with a public release. Every phase is designed to be falsifiable — we will know, at each step, whether the model is learning real biology or memorizing labels.

  1. Phase I · Foundation

    Establishing the causal substrate

    Public release: seed dataset & first model

    • Generate the first dense-time perturbation atlas
    • Train an initial regulatory-transition world model
    • Validate against known transcription-factor directionality
  2. Phase II · Extension

    Combinations, schedules, and constraints

    Public release: expanded atlas & rollout model

    • Expand coverage of cell contexts and intervention programs
    • Extend to combinatorial and sequential interventions
    • Integrate constrained reasoning & uncertainty calibration
  3. Phase III · Platform

    Open discovery engine

    Public release: full atlas, APIs, benchmarks

    • Release final dataset, model family, and distilled open variants
    • Deploy public APIs, notebooks, tutorials, and leaderboards
    • Prospective wet-lab validation against standard screening

Impact

A force multiplier for predictive biology — open by design.

ChronoCell-WM is built to be released. Every dataset, model, benchmark, and API will be open — lowering the barrier to virtual-cell simulation for labs without large screening infrastructure and unlocking the latent value of every existing endpoint atlas in the field.

For under-resourced institutions and labs in low- and middle-income countries, this means access to causal in silico simulation without multi-million-dollar sequencing budgets. For the field at large, it means a new evaluation standard and a compounding network effect: every new perturbation dataset becomes more causally valuable because the transition operator exists.

Interested in collaborating, contributing data, or learning more? Reach the team →