Benchmarking-Single-Cell-Perturbation

KO | EN

gitlite — search

#javascript #hacktoberfest #react #ai #go #machine-learning #linux #docker #nodejs #awesome #awesome-list #pytorch #openai #ios

Benchmarking-Single-Cell-Perturbation

(★ 125)

Single-Cell (Perturbation) Model Library

Benchmarking-Single-Cell-Perturbation Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

![](https://github.com/xianglin226/Benchmarking-Single-Cell-Perturbation/blob/master/mach.jpg)
Many perturbation models are coming out!
## Models developed for genetic/chemical perturbation data  
| Name   | Year          | Journal/Conf.  | Title |
| -------|:-------------:| -----:|--------:|
| [Rachel et al](https://psb.stanford.edu/psb-online/proceedings/psb18/hodos.pdf)  |2018  |Pacific Symposium on Biocomputing 2018|Cell-specific prediction and application of drug-induced gene expression profiles  
| [scGEN](https://www.nature.com/articles/s41592-019-0494-8)|2019    |Nature Method|scGen predicts single-cell perturbation responses
| [DTD](https://dl.acm.org/doi/abs/10.1145/3308558.3313476) |2019         |The World Wide Web Conference, 2019|Modeling Relational Drug-Target-Disease Interactions via Tensor Factorization with Multiple Web Sources 
| [CPA](https://www.embopress.org/doi/full/10.15252/msb.202211517)|2021 |Molecular system biology|Predicting cellular responses to complex perturbations in high‐throughput screens 
| [CellBox](https://www.cell.com/cell-systems/pdf/S2405-4712(20)30464-6.pdf)|2021  |Cell systems|CellBox: Interpretable Machine Learning for Perturbation Biology with Application to the Design of Cancer Combination Therapy 
| [CellDrift](https://academic.oup.com/bib/article/23/5/bbac324/6673850)|2022         |BIB | CellDrift: inferring perturbation responses in temporally sampled single-cell data
| [MultiCPA](https://www.biorxiv.org/content/10.1101/2022.07.08.499049v1.abstract)|2022          || MultiCPA: Multimodal Compositional Perturbation Autoencoder
| [PerturbNet](https://www.biorxiv.org/content/10.1101/2022.07.20.500854v2.abstract)|2022          || PerturbNet predicts single-cell responses to unseen chemical and genetic perturbations
| [scINSIGHT](https://link.springer.com/article/10.1186/s13059-022-02649-33)|2022        |Genome biology |scINSIGHT for interpreting single-cell gene expression from biologically heterogeneous data
| [scpregan](https://academic.oup.com/bioinformatics/article/38/13/3377/6593485)|2022    |Bioinformatics |scPreGAN, a deep generative model for predicting the response of single-cell expression to perturbation
| [Gears](https://www.nature.com/articles/s41587-023-01905-6)|2023          |Nature Biotech| Predicting transcriptional outcomes of novel multigene perturbations with GEARS
| [cycleCDR](https://arxiv.org/abs/2311.10315)|2023          || Interpretable Modeling of Single-cell perturbation Responses to Novel Drugs Using Cycle Consistence Learning
| [scVIDR](https://www.cell.com/patterns/pdf/S2666-3899(23)00186-1.pdf)|2023          |Patterns| Generative modeling of single-cell gene expression for dose-dependent chemical perturbations
| [Unagi](https://www.researchsquare.com/article/rs-3676579/v1)|2023           ||Unagi: Deep Generative Model for Deciphering Cellular Dynamics and In-Silico Drug Discovery in Complex Diseases
| [CINEMA-OT](https://www.nature.com/articles/s41592-023-02040-5)| 2023        |Nature Method| Causal identification of single-cell experimental perturbation effects with CINEMA-OT
| [ChemCPA](https://proceedings.neurips.cc/paper_files/paper/2022/hash/aa933b5abc1be30baece1d230ec575a7-Abstract-Conference.html)|2023        |NeurIPS 2022 |Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution 
| [DREEP](https://link.springer.com/article/10.1186/s12916-023-03182-1)| 2023        |BMC Medicine|Predicting drug response from single-cell expression profiles of tumours 
| [ontoVAE](https://academic.oup.com/bioinformatics/article/39/6/btad387/7199588)|2023         |Bioinformatics|  Biologically informed variational autoencoders allow predictive modeling of genetic and drug-induced perturbations
| [scDiff](https://www.biorxiv.org/content/10.1101/2023.10.13.562243v1.abstract)| 2023         || A GENERAL SINGLE-CELL ANALYSIS FRAMEWORK VIA CONDITIONAL DIFFUSION GENERATIVE MODELS
| [ContrastiveVI](https://www.nature.com/articles/s41592-023-01955-3)| 2023         |Nature Method|Isolating salient variations of interest in single-cell data with contrastiveVI 
| [sVAE](https://proceedings.mlr.press/v213/lopez23a.html)| 2023       |PMLR | Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling
| [CellOT](https://www.nature.com/articles/s41592-023-01969-x)|2023         |Nature Method |Learning single-cell perturbation responses using neural optimal transport 
|[MOASL](https://www.sciencedirect.com/science/article/abs/pii/S0010482523013185)| 2023| Computers in Biology and Medicine | MOASL: Predicting drug mechanism of actions through similarity learning with transcriptomic signature  
| [samsVAE](https://proceedings.neurips.cc/paper_files/paper/2023/hash/0001ca33ba34ce0351e4612b744b3936-Abstract-Conference.html)| 2024       |Advances in Neural Information Processing Systems| Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder 
| [Biolord](https://www.nature.com/articles/s41587-023-02079-x)| 2024        |Nature Biotech| Disentanglement of single-cell data with biolord
| [PDGrapher](https://www.biorxiv.org/content/10.1101/2024.01.03.573985v2.abstract)|  2024 | Nature Biomedical Engineering | Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks
| [TAT](https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c01855)| 2024        |Journal of Chemical Information and Modeling| Compound Activity Prediction with Dose-Dependent Transcriptomic Profiles and Deep Learning 
| [scVAE](https://www.biorxiv.org/content/10.1101/2024.01.05.574421v1.abstract)|  2024      | | A Supervised Contrastive Framework for Learning Disentangled Representations of Cell Perturbation Data 
| [Cell PaintingCNN](https://www.nature.com/articles/s41467-024-45999-1)|2024        |NC |  Learning representations for image-based profiling of perturbations
| [scDisInFact](https://www.nature.com/articles/s41467-024-45227-w)| 2024       |NC| scDisInFact: disentangled learning for integration and prediction of multi-batch multi-condition single-cell RNA-sequencing data  
| [CellCap](https://www.biorxiv.org/content/10.1101/2024.03.14.585078v1.abstract)| 2024         || Modeling interpretable correspondence between cell state and perturbation response with CellCap
| [CODEX](https://academic.oup.com/bioinformatics/article/40/Supplement_1/i91/7700898) | 2024 | Bioinformatics | CODEX: COunterfactual Deep learning for the in silico EXploration of cancer cell line perturbations
| [scFM](https://www.biorxiv.org/content/10.1101/2024.10.02.616248v1) | 2024 |  | PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction
| [STAMP](https://www.nature.com/articles/s43588-024-00698-1) | 2024 | NCS | Toward subtask-decomposition-based learning and benchmarking for predicting genetic perturbation outcomes and beyond  
| [PrePR-CT](https://www.biorxiv.org/content/10.1101/2024.07.24.604816v1.full.pdf) |2024| |  PrePR-CT: Predicting Perturbation Responses in Unseen Cell Types Using Cell-Type-Specific Graphs  
|[PRnet](https://www.nature.com/articles/s41467-024-53457-1) |2024| NC | Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery  
|[TranSiGen](https://www.nature.com/articles/s41467-024-49620-3)|2024|NC|Deep representation learning of chemical-induced transcriptional profile for phenotype-based drug discovery  
|[BioDiscoveryAgent](https://arxiv.org/abs/2405.17631)| 2024| | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments  
|[DRSPRING](https://www.sciencedirect.com/science/article/pii/S0010482524005201)| 2024| Computers in Biology and Medicine| DRSPRING: Graph convolutional network (GCN)-Based drug synergy prediction utilizing drug-induced gene expression profile  
|[PertKGE](https://www.biorxiv.org/content/10.1101/2024.04.08.588632v1.abstract)|2024|| Identify compound-protein interaction with knowledge graph embedding of perturbation transcriptomics  
|[scRank](https://www.cell.com/cell-reports-medicine/fulltext/S2666-3791(24)00260-X)| 2024| Cell Reports Medicine | scRank infers drug-responsive cell types from untreated scRNA-seq data using a target-perturbed gene regulatory network  
|[CellFlow](https://www.biorxiv.org/content/10.1101/2025.04.11.648220v1)| 2025 | | CellFlow enables generative single-cell phenotype modeling with flow matching   
|[IMPA](https://www.nature.com/articles/s41467-024-55707-8) |2025| NC | Predicting cell morphological responses to perturbations using generative modeling  
|[PS](https://www.nature.com/articles/s41556-025-01626-9) |2025| Nature Cell Biology | Decoding heterogeneous single-cell perturbation responses  
|[TRADE](https://www.nature.com/articles/s41588-025-02169-3) |2025| Nature Genetics | Transcriptome-wide analysis of differential expression in perturbation atlases  
|[UNAGI](https://doi.org/10.1038/s41551-025-01423-7) |2025| Nature Biomedical Engineering | A deep generative model for deciphering cellular dynamics and in silico drug discovery in complex diseases    
|[STATE](https://arcinstitute.org/manuscripts/State) |2025|  | Predicting cellular responses to perturbation across diverse contexts with State   
|[scAgent](https://openreview.net/forum?id=HGJQvwGtfJ) |2025|  | scAgents:AMulti-AgentFramework forFullyAutonomousEnd-to-EndSingle-Cell PerturbationAnalysis  
|[CONCERT](https://www.biorxiv.org/content/10.1101/2025.11.08.686890v2.abstract) |2025|  | CONCERT predicts niche-aware perturbation responses in spatial transcriptomics     
|[Cradle-VAE](https://ojs.aaai.org/index.php/AAAI/article/view/33695) |2025| AAAI Conference on AI | Cradle-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement  
|[Pertpy](https://www.nature.com/articles/s41592-025-02909-7) |2025| NM | Pertpy: an end-to-end framework for perturbation analysis    
|[Scouter](https://www.nature.com/articles/s43588-025-00912-8) |2025| NCS | Scouter predicts transcriptional responses to genetic perturbations with large language model embeddings  
|[PertAdapt](https://www.biorxiv.org/content/10.1101/2025.11.21.689655v1) |2025|  | PertAdapt: Unlocking Single-Cell Foundation Models for Genetic Perturbation Prediction via Condition-Sensitive Adaptation  
|[CausalGRN](https://www.biorxiv.org/content/10.64898/2025.12.30.692369v1.abstract) |2025|  | CausalGRN: deciphering causal gene regulatory networks from single-cell CRISPR screens  
|[Systema](https://www.nature.com/articles/s41587-025-02777-8) |2025| Nature Biotechnology | Systema: a framework for evaluating genetic perturbation response prediction beyond systematic variation  
|[Stack](https://www.biorxiv.org/content/10.64898/2026.01.09.698608v1) |2026|  | Stack: In-Context Learning of Single-Cell Biology    
|[AlphaCell](https://www.biorxiv.org/content/10.64898/2026.03.02.709176v1.abstract) |2026|  | Towards building a World Model to simulate perturbation-induced cellular dynamics by AlphaCell  
|[XPert](https://www.nature.com/articles/s42256-025-01165-w) |2026| NMI | Modelling drug-induced cellular perturbation responses with a biologically informed dual-branch transformer  
|[PrePR-CT](https://www.nature.com/articles/s42256-026-01202-2) |2026| NMI | Predicting and interpreting cell-type-specific drug responses in the small-data regime using inductive priors  
|[SequenTx](https://www.nature.com/articles/s42256-026-01192-1) |2026| NMI | Reinforcement learning-based design of sequential drug treatment targeting the evolving tumour landscape with SequenTx  
|[TxPert](https://www.nature.com/articles/s41587-026-03113-4)| 2026 | NBT | TxPert: using multiple knowledge graphs for prediction of transcriptomic perturbation effects  
|[scPert](https://www.biorxiv.org/content/10.64898/2026.04.24.720560v1.abstract)| 2026 |  | A Multi-modal LLM-Knowledge Fusion Framework for Predicting Single-cell Genetic Perturbation Effects  
|[X-Cell](https://www.biorxiv.org/content/10.64898/2026.03.18.712807v1.abstract)| 2026 | | X-Cell: Scaling Causal Perturbation Prediction Across Diverse Cellular Contexts via Diffusion Language Models 
|[RegVelo](https://www.cell.com/cell/fulltext/S0092-8674(26)00457-5)| 2026 | Cell | RegVelo: Gene-regulatory-informed dynamics of single cells   
|[UniPert-G2CP](https://www.sciencedirect.com/science/article/pii/S0092867426006549)| 2026 | Cell | UniPert-G2CP bridges genetic and chemical screens from molecular representation to phenotype modeling    
## Review
|2026|Nature Reviews Genetics| [Interpretation, extrapolation and perturbation of single cells](https://www.nature.com/articles/s41576-025-00920-4)

## Benchmark and Challenges
|2025|BMC genomics| [Benchmarking foundation cell models for post-perturbation RNA-seq prediction](https://link.springer.com/article/10.1186/s12864-025-11600-2)  
|2025| NM | [Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines](https://www.nature.com/articles/s41592-025-02772-6)  
|2025| Communications Biology | [A large-scale benchmark for network inference from single-cell perturbation data](https://www.nature.com/articles/s42003-025-07764-y)  
|2025| Bioinformatics | [Simple controls exceed best deep learning algorithms and reveal foundation model effectiveness for predicting genetic perturbations](https://academic.oup.com/bioinformatics/article/41/6/btaf317/8142305)  
|2026|NeurIPS| [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://proceedings.neurips.cc/paper_files/paper/2025/file/8aee537279a66ced96319dfca3c00002-Paper-Datasets_and_Benchmarks_Track.pdf)

## Perturbation Datasets  
[SC-perturb](http://projects.sanderlab.org/scperturb/)  
[C-MAP](https://clue.io/)  
[PerturbBase](http://www.perturbase.cn/)  
[PerturDB](http://research.gzsys.org.cn/perturbdb/#/home)  
[Tahoe-100M](https://huggingface.co/datasets/tahoebio/Tahoe-100M)  
[Multiome Perturb-seq](https://www.biorxiv.org/content/10.1101/2024.07.26.605307v1.full.pdf) (paper)  
[Multiome: CRISPRmap](https://www.nature.com/articles/s41587-024-02386-x) (paper)  
[Spatial: Perturb-Fish](https://www.cell.com/cell/fulltext/S0092-8674(25)00197-7) (paper)  
[Spatial: PerturbView](https://www.nature.com/articles/s41587-024-02391-0) (paper)  
[Spatial: Perturb-map](https://www.cell.com/cell/fulltext/S0092-8674(22)00195-7?) (paper)   
[Spatial: Perturb-DBiT](https://www.nature.com/articles/s41587-026-03127-y) (paper - NBT)  
[Spatial: Spatial-perturb-seq](https://www.biorxiv.org/content/biorxiv/early/2024/12/20/2024.12.19.628843.full.pdf) (paper)  
[Spatial: NIS-seq](https://www.nature.com/articles/s41587-024-02516-5.pdf) (paper)  
[Spatial: PERTURB-CAST](https://www.nature.com/articles/s41551-025-01437-1) (paper)  
[Spatial: SPAC-seq](https://www.cell.com/cell/fulltext/S0092-8674(26)00516-7)(paper)

### List of [scFM](https://github.com/xianglin226/Benchmarking-Single-Cell-Perturbation/blob/master/scFM/README.md)  
### These tables will be periodically updated. 
### We will build APIs for some of these models on [TDC](https://tdcommons.ai/) for benchmarking. 
### Find single-cell data from [CZI](https://cellxgene.cziscience.com/) database

## FastPert  
A tool to quickly check:  
- DEGs of perturbations: [FastPert](https://benchmarking-single-cell-perturbation-cxpnztwdkmkuhrqv555ut8.streamlit.app/)  
- Enriched pathways of perturbations: [FastPert](https://benchmarking-single-cell-perturbation-h6zgs5utz5cbk9ckdavgxf.streamlit.app/)

## 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}  
}

Benchmarking-Single-Cell-Perturbation

Benchmarking-Single-Cell-Perturbation Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Benchmarking-Single-Cell-Perturbation

Benchmarking-Single-Cell-Perturbation Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README