---
title: "CycSeq: Leveraging Cyclic Data Generation for Accurate Perturbation Prediction in Single-Cell RNA-Seq"
authors:
  - "Yicheng Liu"
  - "Sai Wu"
  - "Tianyun Zhang"
  - "Chang Yao"
  - "Ning Shen"
doi: "10.24963/ijcai.2025/1031"
url: "https://ijcai.org/proceedings/2025/1031"
pdf: "https://ijcai.org/proceedings/2025/1031.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "9277-9285"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Domain-specific AI4Tech: AI4Care and AI4Health"
  - "Domain-specific AI4Tech: AI4Biotech"
  - "Domain-specific AI4Tech: AI4Medicine and AI4Drug"
  - "Emerging AI4Tech: Emerging AI4Tech areas"
---

# CycSeq: Leveraging Cyclic Data Generation for Accurate Perturbation Prediction in Single-Cell RNA-Seq

Yicheng Liu, Sai Wu, Tianyun Zhang, Chang Yao, Ning Shen

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 9277-9285. DOI: [10.24963/ijcai.2025/1031](https://doi.org/10.24963/ijcai.2025/1031)

## Abstract

Understanding and predicting the effects of cellular perturbations using single-cell sequencing technology remains a critical and challenging problem in biotechnology. In this work, we introduce CycSeq, a deep learning framework that leverages cyclic data generation and recent advances in neural architectures to predict single-cell responses under specified perturbations across multiple cell lines, while also generating the corresponding single-cell expression profiles. Specifically, CycSeq addresses the challenge of learning heterogeneous perturbation responses from unpaired single-cell gene expression data by generating pseudo-pairs through cyclic data generation. Experimental results demonstrate that CycSeq outperforms existing methods in perturbation prediction tasks, as evaluated using computational metrics such as R-squared and MAE. Furthermore, CycSeq employs a unified architecture that integrates information from multiple cell lines, enabling robust predictions even for long-tail cell lines with limited training data. The source code is publicly available at https://github.com/yczju/cycseq.