Single-cell research, publications, and software

Zeyu Fu 付泽宇

Ph.D. Candidate · Single-Cell Computational Biology · Machine Learning

I build machine learning methods for single-cell genomics, including interpretable representation learning, graph attention, neural ODEs, reinforcement learning, and structured latent generation for cell-state dynamics and trajectory analysis.

Open SCPortal View Publications Browse Software

ORCID GitHub Profile Profile README Scopus WoS fuzeyu99@126.com

10 peer-reviewed papers highlighted on this homepage

10 published software projects with code or package distribution

6 public sites and tools linked from this homepage

At a glance

Single-cell machine learning, publications, and tools.

Representation learning, dynamics, publications, and released software in one quick view.

Representation learning

Variational, graph, and hyperbolic methods for single-cell structure and phenotype analysis.

Dynamic systems and decision-making

Neural ODE and reinforcement learning work for developmental dynamics and intervention questions.

Released papers and software

Publications, packages, benchmark sites, and companion pages tied to the published work.

Publication highlights Software & tools

Start here

Choose the page that fits the task

Use SCPortal for broad browsing, benchmark pages for detailed comparisons, and project pages for methods, datasets, or companion materials.

See all tools

Broad browse Portal

SCPortal

Browse datasets, benchmarks, models, and linked tools from one overview.

Open SCPortal →

Focused analysis Tool

mRNA Intersection

Interactive mRNA intersection analysis and visualization.

Launch →

Benchmark detail Benchmark

LAIOR Benchmarks

Compare benchmark models, datasets, and metrics on dedicated reference pages.

Open LAIOR Benchmarks →

Project materials Project

iAODE Pages

Datasets, explorer pages, and project materials for the iAODE work.

Open iAODE Pages →

Dataset records Benchmark

scCCVGBen

Browse 200 single-cell benchmark datasets with per-dataset metadata cards.

Open scCCVGBen →

Method notes Companion

GAHIB

Method notes, dataset metadata, benchmark definitions, and code links for GAHIB.

Open GAHIB →

Suggested route

Start broad, then open the detail you need

A simple path from the homepage overview to broader browsing and then benchmark-specific detail.

Overview Browse Compare

Homepage: overview

Research themes, publication highlights, profile links, and released tools in one place.

SCPortal: browse the catalog

Compare datasets, models, benchmarks, and related tools across the public work.

Open SCPortal → 03

LAIOR: compare benchmarks

Model, dataset, and metric pages when you need benchmark-specific detail.

Open benchmarks →

About

Single-cell method development across Python/deep learning, R/statistical analysis, and code-backed paper releases.

See public tools

I develop machine learning methods for single-cell sequencing data (scRNA-seq and scATAC-seq), using Python-first deep learning, R/statistical analysis, and reproducible software to connect representation learning, trajectory dynamics, generative modeling, and interpretable cell-fate analysis.

Single-Cell GenomicsPython / PyTorchR StatisticsVAE / GNN / ODEContrastive LearningDiffusion LatentsHyperbolic GeometryReproducible Releases

Available here

Modeling layer

VAE-family models, graph attention/GNNs, neural ODE/SDE ideas, reinforcement learning, contrastive learning, diffusion-style latent generation, and hyperbolic geometry.

Analysis and build layer

Python/PyTorch for modeling, R/statistics for biological analysis where useful, and web/release tooling for packages, benchmarks, and paper companion pages.

Mass-vibing workflow

Claude Code, Codex, Grok Build, Antigravity, and OpenCode are orchestrated with the oh-my-* harness series for paper code, pages, benchmarks, and reproducible tooling.

Profiles and identifiers

GitHub, ORCID, Scopus, and Web of Science records for code, citations, and authorship tracking.

Research focus

Three recurring themes across the work

A compact map of the modeling directions connecting publications, software, and public tools.

Match focus to software

Interpretable representation learning

VAE-family models, geometry-aware latent spaces, and stable embeddings designed for clearer clustering, visualization, and biological interpretation.

iVAE LiVAE CCVGAE

Dynamics and continuum modeling

Neural ODE and graph-enhanced methods for developmental trajectories, chromatin accessibility continua, and fate-transition structure in single-cell systems.

iAODE GNODEVAE CODE

Contrastive, generative, and decision-aware analysis

Contrastive coupling, structured latent generation, reinforcement learning, and downstream utilities for branching, lineage focus, and biological workflow support.

MCCVAE CLOP-DiT scRL scFocus mRNA Intersection

Publications

^# Equal contribution * Corresponding author 10 peer-reviewed papers

Islands and bridges: Momentum contrastive coupling unifies discrete and continuous structure in single-cell omics

Fu, Z.^#,*, Chen, C.^#, Zhang, K. · Biomedical Signal Processing and Control 122, 110376 · 2026

DOI ScienceDirect Code Site

CCVGAE: A centroid-coupled variational graph attention autoencoder for stable and interpretable single-cell representation learning

Fu, Z.^#,*, Liu, Y.^#, Wang, J., Wang, S. · Array 30, 100808 · 2026

DOI ScienceDirect Code

CLOP-DiT: Structured-metadata-conditioned single-cell latent generation via contrastive language-omics pretraining and Diffusion Transformers

Fu, Z.^#,*, Liu, Y.^#, Wang, J., Wang, S. · Array 100934, in press · 2026

DOI ScienceDirect Code

iVAE: An Interpretable Representation Learning Framework Enhancing Clustering Performance for Single-Cell Data

Fu, Z.^#,*, Chen, C.^#, Wang, S. et al. · BMC Biology 23, 213 · 2025

DOI PubMed Code PyPI

iAODE for Benchmarking and Continuum Modeling of Single-Cell Chromatin Accessibility

Fu, Z.^#,*, Chen, C.^#, Wang, S. et al. · Communications Biology · 2026

DOI PubMed Code PyPI

Correlated Latent Space Learning for Structural Differentiation Modeling in Single Cell RNA Data

Fu, Z.^#,*, Chen, C.^# · Computers in Biology and Medicine 198(A), 111115 · 2025

DOI PubMed Code PyPI

GNODEVAE: A Graph-Based ODE-VAE Enhances Clustering for Single-Cell Data

Fu, Z.^#,*, Chen, C.^#, Wang, S. et al. · BMC Genomics 26, 767 · 2025

DOI PubMed Code PyPI

scFocus: Detecting Branching Probabilities in Single-cell Data with SAC

Chen, C.^#, Fu, Z.^#,*, Yang, J. et al. · Computational and Structural Biotechnology Journal 27, 2243–2263 · 2025

DOI PubMed Code PyPI

Lorentz-Regularized Interpretable VAE for Multi-Scale Single-Cell Transcriptomic and Epigenomic Embeddings

Fu, Z.^#,*, Fu, J.^#, Chen, C.^# et al. · Frontiers in Genetics 16, 1713727 · 2026

DOI PubMed Code PyPI

scRL: Utilizing Reinforcement Learning to Evaluate Fate Decisions in Single-Cell Data

Fu, Z.^#, Chen, C.^#, Wang, S. et al. · Biology 14(6), 679 · 2025

DOI PubMed Code PyPI

Open-Source Software

10 published tools and code releases (7 on PyPI)

MCCVAE

BSPC · 2026

Momentum contrastive coupling for discrete and continuous structure in single-cell omics.

CCVGAE

Array · 2026

Centroid-coupled graph attention VAE for stable, interpretable single-cell embeddings.

CLOP-DiT

Array · 2026

Structured metadata-conditioned latent generation via language-omics pretraining and DiT.

iAODE

pip install iaode

Neural ODE-VAE for scATAC-seq benchmarking and continuum modeling.

iVAE

pip install iVAE

Interpretable VAE enhancing clustering for single-cell data.

LiVAE

pip install livae

Lorentz-regularized VAE for transcriptomic and epigenomic embeddings.

GNODEVAE

pip install gnodevae

Graph ODE-VAE with GNN-enhanced clustering and dynamics.

scRL

pip install scrl-fatedecision

RL for evaluating cell fate decisions in single-cell data.

scFocus

pip install scfocus

SAC-based branching probability detection for lineage focusing.

CODE

pip install scCODE

Correlated latent space learning for single-cell RNA continuum modeling.

Released tools

Explore the public tools

Public pages for browsing datasets, checking benchmarks, reading companion materials, and using focused utilities.

Browse Benchmarks Utilities

Start here

SCPortal Portal

Portal

Browse datasets, benchmarks, models, and linked tools from one overview.

Open SCPortal →

mRNA Intersection Utility

Utility

Interactive mRNA intersection analysis and visualization.

Launch →

Benchmark and companion pages

LAIOR Benchmarks

Benchmark

Benchmark Pages

Benchmark site for model, dataset, and metric detail when the question is benchmark-specific.

Open LAIOR Benchmarks →

iAODE Pages

Project

Project Materials

Project materials, datasets, and explorer pages for the iAODE work.

Open iAODE Pages →

scCCVGBen

Benchmark

Dataset Viewer

Benchmark viewer for 200 single-cell datasets with per-dataset metadata cards.

Open scCCVGBen →

GAHIB

Companion

Companion Notes

Method notes, dataset metadata, benchmark definitions, and code links.

Open GAHIB →

AI Usage & Stats

Live AI interaction statistics for the mass-vibing workflow behind these paper releases, benchmarks, and pages.

Tokscale AI Profile

Track the AI-assisted build loop across Claude Code, Codex, Grok Build, Antigravity, and OpenCode, coordinated by the oh-my-* harness series.

View Full Stats →

Contact

For collaborations, code, profiles, and public research references.