xianglin226/Benchmarking-Single-Cell-Perturbation
Public
Star 历史趋势
数据来源: GitHub API · 生成自 Stargazers.cn
README.md

Many perturbation models are coming out!

Models developed for genetic/chemical perturbation data

NameYearJournal/Conf.Title
Rachel et al2018Pacific Symposium on Biocomputing 2018Cell-specific prediction and application of drug-induced gene expression profiles
scGEN2019Nature MethodscGen predicts single-cell perturbation responses
DTD2019The World Wide Web Conference, 2019Modeling Relational Drug-Target-Disease Interactions via Tensor Factorization with Multiple Web Sources
CPA2021Molecular system biologyPredicting cellular responses to complex perturbations in high‐throughput screens
CellBox2021Cell systemsCellBox: Interpretable Machine Learning for Perturbation Biology with Application to the Design of Cancer Combination Therapy
CellDrift2022BIBCellDrift: inferring perturbation responses in temporally sampled single-cell data
MultiCPA2022MultiCPA: Multimodal Compositional Perturbation Autoencoder
PerturbNet2022PerturbNet predicts single-cell responses to unseen chemical and genetic perturbations
scINSIGHT2022Genome biologyscINSIGHT for interpreting single-cell gene expression from biologically heterogeneous data
scpregan2022BioinformaticsscPreGAN, a deep generative model for predicting the response of single-cell expression to perturbation
Gears2023Nature BiotechPredicting transcriptional outcomes of novel multigene perturbations with GEARS
cycleCDR2023Interpretable Modeling of Single-cell perturbation Responses to Novel Drugs Using Cycle Consistence Learning
scVIDR2023PatternsGenerative modeling of single-cell gene expression for dose-dependent chemical perturbations
Unagi2023Unagi: Deep Generative Model for Deciphering Cellular Dynamics and In-Silico Drug Discovery in Complex Diseases
CINEMA-OT2023Nature MethodCausal identification of single-cell experimental perturbation effects with CINEMA-OT
ChemCPA2023NeurIPS 2022Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution
DREEP2023BMC MedicinePredicting drug response from single-cell expression profiles of tumours
ontoVAE2023BioinformaticsBiologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations
scDiff2023A GENERAL SINGLE-CELL ANALYSIS FRAMEWORK VIA CONDITIONAL DIFFUSION GENERATIVE MODELS
ContrastiveVI2023Nature MethodIsolating salient variations of interest in single-cell data with contrastiveVI
sVAE2023PMLRLearning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling
CellOT2023Nature MethodLearning single-cell perturbation responses using neural optimal transport
MOASL2023Computers in Biology and MedicineMOASL: Predicting drug mechanism of actions through similarity learning with transcriptomic signature
samsVAE2024Advances in Neural Information Processing SystemsModelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
Biolord2024Nature BiotechDisentanglement of single-cell data with biolord
PDGrapher2024Nature Biomedical EngineeringCombinatorial prediction of therapeutic perturbations using causally-inspired neural networks
TAT2024Journal of Chemical Information and ModelingCompound Activity Prediction with Dose-Dependent Transcriptomic Profiles and Deep Learning
scVAE2024A Supervised Contrastive Framework for Learning Disentangled Representations of Cell Perturbation Data
Cell PaintingCNN2024NCLearning representations for image-based profiling of perturbations
scDisInFact2024NCscDisInFact: disentangled learning for integration and prediction of multi-batch multi-condition single-cell RNA-sequencing data
CellCap2024Modeling interpretable correspondence between cell state and perturbation response with CellCap
CODEX2024BioinformaticsCODEX: COunterfactual Deep learning for the in silico EXploration of cancer cell line perturbations
scFM2024PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction
STAMP2024NCSToward subtask-decomposition-based learning and benchmarking for predicting genetic perturbation outcomes and beyond
PrePR-CT2024PrePR-CT: Predicting Perturbation Responses in Unseen Cell Types Using Cell-Type-Specific Graphs
PRnet2024NCPredicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery
TranSiGen2024NCDeep representation learning of chemical-induced transcriptional profile for phenotype-based drug discovery
BioDiscoveryAgent2024BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments
DRSPRING2024Computers in Biology and MedicineDRSPRING: Graph convolutional network (GCN)-Based drug synergy prediction utilizing drug-induced gene expression profile
PertKGE2024Identify compound-protein interaction with knowledge graph embedding of perturbation transcriptomics
scRank2024Cell Reports MedicinescRank infers drug-responsive cell types from untreated scRNA-seq data using a target-perturbed gene regulatory network
CellFlow2025CellFlow enables generative single-cell phenotype modeling with flow matching
IMPA2025NCPredicting cell morphological responses to perturbations using generative modeling
PS2025Nature Cell BiologyDecoding heterogeneous single-cell perturbation responses
TRADE2025Nature GeneticsTranscriptome-wide analysis of differential expression in perturbation atlases
UNAGI2025Nature Biomedical EngineeringA deep generative model for deciphering cellular dynamics and in silico drug discovery in complex diseases
STATE2025Predicting cellular responses to perturbation across diverse contexts with State
scAgent2025scAgents:AMulti-AgentFramework forFullyAutonomousEnd-to-EndSingle-Cell PerturbationAnalysis
CONCERT2025CONCERT predicts niche-aware perturbation responses in spatial transcriptomics
Cradle-VAE2025AAAI Conference on AICradle-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement
Pertpy2025NMPertpy: an end-to-end framework for perturbation analysis
Scouter2025NCSScouter predicts transcriptional responses to genetic perturbations with large language model embeddings
PertAdapt2025PertAdapt: Unlocking Single-Cell Foundation Models for Genetic Perturbation Prediction via Condition-Sensitive Adaptation
CausalGRN2025CausalGRN: deciphering causal gene regulatory networks from single-cell CRISPR screens
Systema2025Nature BiotechnologySystema: a framework for evaluating genetic perturbation response prediction beyond systematic variation
Stack2026Stack: In-Context Learning of Single-Cell Biology
AlphaCell2026Towards building a World Model to simulate perturbation-induced cellular dynamics by AlphaCell
XPert2026NMIModelling drug-induced cellular perturbation responses with a biologically informed dual-branch transformer
PrePR-CT2026NMIPredicting and interpreting cell-type-specific drug responses in the small-data regime using inductive priors
SequenTx2026NMIReinforcement learning-based design of sequential drug treatment targeting the evolving tumour landscape with SequenTx
TxPert2026NBTTxPert: using multiple knowledge graphs for prediction of transcriptomic perturbation effects
scPert2026A Multi-modal LLM-Knowledge Fusion Framework for Predicting Single-cell Genetic Perturbation Effects
X-Cell2026X-Cell: Scaling Causal Perturbation Prediction Across Diverse Cellular Contexts via Diffusion Language Models
RegVelo2026CellRegVelo: Gene-regulatory-informed dynamics of single cells
UniPert-G2CP2026CellUniPert-G2CP bridges genetic and chemical screens from molecular representation to phenotype modeling

Review

|2026|Nature Reviews Genetics| Interpretation, extrapolation and perturbation of single cells

Benchmark and Challenges

|2025|BMC genomics| Benchmarking foundation cell models for post-perturbation RNA-seq prediction
|2025| NM | Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines
|2025| Communications Biology | A large-scale benchmark for network inference from single-cell perturbation data
|2025| Bioinformatics | Simple controls exceed best deep learning algorithms and reveal foundation model effectiveness for predicting genetic perturbations
|2026|NeurIPS| PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis

Perturbation Datasets

SC-perturb
C-MAP
PerturbBase
PerturDB
Tahoe-100M
Multiome Perturb-seq (paper)
Multiome: CRISPRmap (paper)
Spatial: Perturb-Fish (paper)
Spatial: PerturbView (paper)
Spatial: Perturb-map (paper)
Spatial: Perturb-DBiT (paper - NBT)
Spatial: Spatial-perturb-seq (paper)
Spatial: NIS-seq (paper)
Spatial: PERTURB-CAST (paper)
Spatial: SPAC-seq(paper)

List of scFM

These tables will be periodically updated.

We will build APIs for some of these models on TDC for benchmarking.

Find single-cell data from CZI database

FastPert

A tool to quickly check:

Questions, ideas, comments, ...

Please contact Xiang Lin (xiang_lin@hms.harvard.edu).

Citation is appeciated

@misc{pertogether2025,
title = {PerTogether: A tool for perturbation research and modeling},
author = {Xiang Lin, Zhenxing Li, Chenyi Li, Hengyu Zhang},
year = {2025},
url = {https://github.com/xianglin226/Benchmarking-Single-Cell-Perturbation/},
note = {Version 1.0}
}

关于 About

Single-Cell (Perturbation) Model Library
autoencoderscounterfactual-inferencedisentanglementdrugdrug-discoverydrug-repurposingllmperturbationssingle-cell

语言 Languages

Python100.0%

提交活跃度 Commit Activity

代码提交热力图
过去 52 周的开发活跃度
34
Total Commits
峰值: 11次/周
Less
More

核心贡献者 Contributors