Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

VCWorld: A Biological World Model for Virtual Cell Simulation

arXiv 25.12 2025 48 method, system, application

TLDR

VCWorld is a white-box biological world model using LLMs and structured knowledge for interpretable virtual cell simulation and drug response prediction.

Reasoning

The paper presents a novel approach combining biological knowledge with LLMs to create an interpretable, data-efficient simulator, achieving state-of-the-art results on drug perturbation benchmarks. However, its scope is limited to cellular biology, and it does not address general world modeling or interactive/video domains, which reduces relevance for some keywords.

Read-first score

Read-first score 48, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 24.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%
60

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,dataset

Reproducibility 25%
46

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=dataset,reproduce

Topical relevance 42%
34.3

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 400.

Keyword Scores

world model
8
world simulator
7
world dynamics prediction
5
generative world model
3
interactive world model
1
video world model
0
model-based reinforcement learning world model
0

Deep Analysis

Innovations

  • Integrates structured biological knowledge with iterative reasoning capabilities of large language models to instantiate a biological world model
  • White-box simulator that generates interpretable, stepwise predictions alongside explicit mechanistic hypotheses
  • Data-efficient manner to reproduce perturbation-induced signaling cascades

Methodology

VCWorld is a cell-level white-box simulator that integrates structured biological knowledge with the iterative reasoning capabilities of large language models. It operates in a data-efficient manner to reproduce perturbation-induced signaling cascades and generates interpretable, stepwise predictions.

Key Results

In drug perturbation benchmarks, VCWorld achieves state-of-the-art predictive performance, and the inferred mechanistic pathways are consistent with publicly available biological evidence.

Tags