Bayesian inference of haematopoietic stem/progenitor cell differentiation phenotypic manifolds and their bifurcation points using Gaussian processes and Gibbs sampling

2026-05-26 · Source: Machine learning : nature.com subject feeds · Field: Science & Research — Life Sciences & Biology, Mathematics & Computational Sciences · Depth: Expert, short

Summary

BAGEL, a novel statistical model, offers new insights into cell differentiation by modeling it as a continuous process using a robust Bayesian inference approach. This model also incorporates a powerful projection method, enabling the visualization and comparison of similarities and differences within and between species' single-cell gene expression datasets. Although the initial focus is on haematopoiesis, BAGEL is broadly applicable to various single-cell gene expression datasets. Its ability to harness the collective power of multiple datasets is significant, promising to accelerate and enhance the understanding of complex cellular maturation processes.

Key takeaway

For research scientists studying cell differentiation, BAGEL offers a powerful new tool to analyze complex single-cell gene expression data. You should consider integrating this Bayesian inference model to visualize continuous differentiation processes and compare datasets across species. This approach can significantly deepen your understanding of cellular complexity beyond traditional methods.

Key insights

BAGEL provides a Bayesian framework for continuous cell differentiation modeling and multi-dataset visualization.

Principles

• Model differentiation as a continuous process.
• Harness collective power of multiple datasets.
• Enable intra- and inter-species comparisons.

Method

BAGEL uses a robust Bayesian inference approach with Gaussian processes and Gibbs sampling to model continuous cell differentiation and project gene expression data.

In practice

• Visualize cell differentiation trajectories.
• Investigate multi-species gene expression.
• Analyze diverse single-cell datasets.

Topics

• Bayesian Inference
• Cell Differentiation
• Single-cell Gene Expression
• Haematopoiesis
• Gaussian Processes
• Gibbs Sampling

Best for: AI Scientist, Research Scientist

Related on AIssential

• Covariate-dependent Hierarchical Dirichlet Processes — CD-HDP integrates covariates into hierarchical Bayesian nonparametrics for flexible density estimation and cluster identification.
• Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference — A new functional KL divergence estimator provides a principled way to evaluate trajectory inference under partial observability.
• Deep-learning model predicts how fruit flies form, cell by cell — A deep-learning model accurately predicts cell-by-cell development in fruit fly embryos using a novel dual-graph representation.
• Unsupervised feature selection using Bayesian Tucker decomposition — Bayesian Tucker decomposition (BTuD) offers a promising unsupervised feature selection method for diverse datasets.
• Probabilistic ML - 23 - Variational Inference — Variational inference approximates intractable posteriors by iteratively maximizing the ELBO within a tractable family of distributions.
• More Than Image Generators: A Science of Problem-Solving using Probability | Diffusion Models — Diffusion models combine deep learning with Langevin sampling to generate images by iteratively following noisy gradients of an image's probability distribution.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine learning : nature.com subject feeds.