Squidiff: predicting cellular development and responses to perturbations using a diffusion model
Siyu He1,2,3, Yuefei Zhu1, Daniel Naveed Tavakol1
1Department of Biomedical Engineering, Columbia University, New York, NY, USA.
Nature Methods
|November 3, 2025
Summary
Squidiff, a new diffusion model, predicts cell transcriptomic changes during differentiation, gene perturbation, and drug responses. This tool aids in understanding cell fate and disease mechanisms.
Area of Science:
- Computational Biology
- Genomics
- Systems Biology
Background:
- Single-cell sequencing reveals cellular heterogeneity and responses to stimuli.
- Mapping transcriptomic changes and disease mechanisms across cell types is challenging.
Purpose of the Study:
- Introduce Squidiff, a diffusion model-based generative framework.
- Predict transcriptomic changes in diverse cell types under various environmental conditions.
- Facilitate in silico screening and hypothesis generation for cell fate decisions.
Main Methods:
- Utilized a diffusion model-based generative framework (Squidiff).
- Integrated continuous denoising and semantic feature learning.
- Applied the model to cell differentiation, gene perturbation, and drug response prediction.
Main Results:
- Demonstrated Squidiff's robustness across multiple biological scenarios.
- Successfully modeled blood vessel organoid development and cellular responses to stimuli.
- Enabled prediction of high-resolution transcriptomic landscapes over time and conditions.
Conclusions:
- Squidiff enables in silico screening of molecular landscapes and cellular state transitions.
- Facilitates rapid hypothesis generation for biological research.
- Provides insights into the regulatory principles governing cell fate decisions.
Related Concept Videos
01:24Protein Diffusion in the Membrane
5.4K
Proteins show rotational as well as lateral diffusion across the membrane. The lateral diffusion of proteins was confirmed through the cell fusion experiment where mouse and human cells were fused, resulting in hybrid cells. When the human and mouse cells fused, the specific membrane proteins on human and mouse cells were marked with the red and green-fluorescent markers, respectively. Initially, the red and green fluorescence was located on the respective hemisphere of the cell. As time...
5.4K
02:36Cells Coordinate Growth and Proliferation
5.0K
Cell size is a significant factor impacting cellular design, function, and fitness. There exists some internal coordination by which cells double their masses before division, thus, achieving homeostasis. Coordination between cell growth and proliferation depends on the checkpoints in between cell cycle phases. Loss of coordination or failure in the checkpoint mechanism can drive the cell to uncontrolled growth and loss of cellular function. Like dividing cells that coordinate cellular growth,...
5.0K
01:22Diversity in Cell Signaling Responses
7.7K
The physiological function of a cell and cellular communication are outcomes of a range of extrinsic signals, intracellular signaling pathways, and cellular responses. No two cell types express the same repertoire of signaling components. Receptors are highly selective for their cognate ligands, but once activated, they can alter multiple cellular processes such as DNA transcription, protein synthesis, and metabolic activity.
Graded and Abrupt Responses
Some signaling systems generate...
Graded and Abrupt Responses
Some signaling systems generate...
7.7K
00:57Physiological Pharmacokinetic Models: Blood Flow-Limited Versus Diffusion-Limited Models
326
Physiological pharmacokinetic models, often called flow-limited or perfusion models, typically assume a swift drug distribution between tissue and venous blood, creating a rapid drug equilibrium. This premise is based on the idea that drug diffusion is extremely fast, and the cell membrane presents no barrier to drug permeation. In this scenario, where no drug binding occurs, the drug concentration in the tissue equals that of the venous blood leaving the tissue. This greatly simplifies the...
326