Learning interpretable cellular responses to complex perturbations in high-throughput screens
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Recent advances in multiplexed single-cell transcriptomics experiments are facilitating the high-throughput study of drug and genetic perturbations. However, an exhaustive exploration of the combinatorial perturbation space is experimentally unfeasible, so computational methods are needed to predict, interpret, and prioritize perturbations. Here, we present the compositional perturbation autoencoder (CPA), which combines the interpretability of linear models with the flexibility of deep-learning approaches for single-cell response modeling. CPA encodes and learns transcriptional drug responses across different cell type, dose, and drug combinations. The model produces easy-to-interpret embeddings for drugs and cell types, which enables drug similarity analysis and predictions for unseen dosage and drug combinations. We show that CPA accurately models single-cell perturbations across compounds, doses, species, and time. We further demonstrate that CPA predicts combinatorial genetic interactions of several types, implying that it captures features that distinguish different interaction programs. Finally, we demonstrate that CPA can generate in-silico 5,329 missing genetic combination perturbations (97.6% of all possibilities) with diverse genetic interactions. We envision our model will facilitate efficient experimental design and hypothesis generation by enabling in-silico response prediction at the single-cell level, and thus accelerate therapeutic applications using single-cell technologies.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471
Deep generative modeling for single-cell transcriptomics
Lopez, R., Regier, J., Cole, M. B., Jordan, M. I., & Yosef, N. (2018) · Nature Methods · doi:10.1038/s41592-018-0229-2 · Cited by 2,530 · cited 1×
“336 Although we opted to implement a deterministic autoencoder scheme, extensions towards variational 337 models[17, 23], as well as cost functions other than mean squared error[22] are straightforward.”
MethodDixit, A., Parnas, O., Li, B., Chen, J., Fulco, C. P., Jerby-Arnon, L., Marjanovic, N. D., Dionne, D., Burks, T., Raychowdhury, R., et al. (2016) · Cell · doi:10.1016/j.cell.2016.11.038 · Cited by 1,863 · cited 4×
“Linear models[12, 21] do not suffer from these scalability issues, but have limited predictive 45 power and are unable to capture nonlinear cell-type specific responses.”
BackgroundInfluentialPooled CRISPR screening with single-cell transcriptome readout.
Datlinger, P., Rendeiro, A. F., Schmidl, C., Krausgruber, T., Traxler, P., Klughammer, J., Schuster, L. C., Kuchler, A., Alpar, D., & Bock, C. (2017) · Nature Methods · doi:10.1038/nmeth.4177 · Cited by 1,096
Construction of a human cell landscape at single-cell level
Han, X., Zhou, Z., Fei, L., Sun, H., Wang, R., Chen, Y., Chen, H., Wang, J., Tang, H., Ge, W., et al. (2020) · Nature · doi:10.1038/s41586-020-2157-4 · Cited by 1,087
Combinatorial drug therapy for cancer in the post-genomic era
Al-Lazikani, B., Banerji, U., & Workman, P. (2012) · Nature Biotechnology · doi:10.1038/nbt.2284 · Cited by 1,070
Massively multiplex chemical transcriptomics at single-cell resolution
Srivatsan, S. R., McFaline-Figueroa, J. L., Ramani, V., Saunders, L., Cao, J., Packer, J., Pliner, H. A., Jackson, D. L., Daza, R. M., Christiansen, L., et al. (2020) · Science · doi:10.1126/science.aax6234 · Cited by 401
Papalexi, E., Mimitou, E. P., Butler, A. W., Foster, S., Bracken, B., Mauck, W. M., Wessels, H.-H., Hao, Y., Yeung, B. Z., Smibert, P., et al. (2021) · Nature Genetics · doi:10.1038/s41588-021-00778-2 · Cited by 237 · cited 3×
“be extended to include other modalities, for example via multimodal single-cell CRISPR[41, 42] 347 combined scRNA- and ATAC-seq[43, 44] and CUT&Tag[45, 46].”
BackgroundFröhlich, F., Kessler, T., Weindl, D., Shadrin, A., Schmiester, L., Hache, H., Muradyan, A., Schütte, M., Lim, J.-H., Heinig, M., et al. (2018) · Cell Systems · doi:10.1016/j.cels.2018.10.013 · Cited by 143 · cited 1×
“The first approach leverages mechanistic modeling [18, 19] to predict cell 41 viability[19] or the abundance of a few selected proteins[18].”
BackgroundSelf-citationConditional out-of-distribution generation for unpaired data using transfer VAE
Lotfollahi, M., Naghipourfar, M., Theis, F. J., & Wolf, F. A. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa800 · Cited by 130 · cited 4×
“Recently, DL methods have been used to model gene 47 expression latent spaces from scRNA-seq data [22–25], and describe and predict single-cell responses 48 [16, 17, 20, 26].”
BackgroundMethodInfluentialSelf-citation
Research works printed but not linked: 38
- Pisco, A. O. et al A single cell transcriptomic atlas characterizes aging tissues in the mouse. BioRxiv 661728 (2019).
- Domcke, S. et al A human cell atlas of fetal chromatin accessibility. Science 370 (2020). · DOI · Paper page
- 10.1126/science.aax4438 · DOI · Paper page
- 2020, Single-cell genomic approaches for developing the next generation of immunotherapies, Nature medicine, 26, 171, 10.1038/s41591-019-0736-4 · DOI
- 2019, Multi-seq: sample multiplexing for single-cell rna sequencing using lipid-tagged indices, Nature methods, 16, 619, 10.1038/s41592-019-0433-8 · DOI · Paper page
- 2020, Highly multiplexed single-cell rna-seq by dna oligonucleotide tagging of cellular proteins, Nature Biotechnology, 38, 35, 10.1038/s41587-019-0372-z · DOI · Paper page
- 2020, Targeted pharmacological therapy restores β-cell function for diabetes remission, Nature Metabolism, 2, 192, 10.1038/s42255-020-0171-3 · DOI · Paper page
- 10.1186/s13059-015-0866-z · DOI · Paper page
- 2017, The human cell atlas: from vision to reality, Nature News, 550, 451, 10.1038/550451a · DOI · Paper page
- 2018, Gene expression variability across cells and species shapes innate immunity, Nature, 563, 197, 10.1038/s41586-018-0657-2 · DOI · Paper page
- 2019, scgen predicts single-cell perturbation responses, Nature methods, 16, 715, 10.1038/s41592-019-0494-8 · DOI · Paper page
- 2021, Cellbox: Interpretable machine learning for perturbation biology with application to the design of cancer combination therapy, Cell Systems, 12, 128, 10.1016/j.cels.2020.11.013 · DOI · Paper page
- 2019, Dr.VAE: improving drug response prediction via modeling of drug perturbation effects, Bioinformatics, 35, 3743, 10.1093/bioinformatics/btz158 · DOI · Paper page
- 2019, Single-cell rna-seq denoising using a deep count autoencoder, Nature communications, 10, 1
- Lotfollahi, M. et al Query to reference single-cell integration with transfer learning. bioRxiv (2020). · DOI · Paper page
- 2020, Enhancing scientific discoveries in molecular biology with deep generative models, Molecular Systems Biology, 16, e9198, 10.15252/msb.20199198 · DOI · Paper page
- 2020, Style transfer with variational autoencoders is a promising approach to rna-seq data harmonization and analysis, Bioinformatics, 36, 5076, 10.1093/bioinformatics/btaa624 · DOI · Paper page
- 2015, Learning structured output representation using deep conditional generative models, Advances in neural information processing systems, 28, 3483
- McInnes, L. , Healy, J. & Melville, J. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018). · DOI · Paper page
- Van der Maaten, L. & Hinton, G. Visualizing data using t-sne. Journal of machine learning research 9(2008).
- 2013, Distributed representations of words and phrases and their compositionality, arXiv preprint
- Lample, G. et al Fader networks: Manipulating images by sliding attributes. In Advances in neural information processing systems, 5967–5976 (2017).
- 2015, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv preprint
- Goodfellow, I. , Bengio, Y. , Courville, A. & Bengio, Y. Deep learning, vol. 1 (MIT press Cambridge, 2016).
- 10.1126/science.aax6234 · DOI · Paper page
- 10.1126/science.aax6234 · DOI · Paper page
- 2019, Systems pharmacogenomic landscape of drug similarities from lincs data: drug association networks, Scientific reports, 9, 1
- 2019, Nature Communications, 10, 2674
- 2020, Machine learning approaches to drug response prediction: challenges and recent progress, npj Precision Oncology, 4, 19, 10.1038/s41698-020-0122-1 · DOI · Paper page
- 10.1038/nrd2683 · DOI · Paper page
- Frangieh, C. J. et al Multimodal pooled perturb-cite-seq screens in patient models define mechanisms of cancer immune evasion. Nature genetics 1–10 (2021). · DOI
- 2019, High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell, Nature biotechnology, 37, 1452, 10.1038/s41587-019-0290-0 · DOI · Paper page
- 10.1038/s41467-018-03661-7 · DOI · Paper page
- 2019, Cut&tag for efficient epigenomic profiling of small samples and single cells, Nature communications, 10, 1
- 2020, Single-cell and spatial transcriptomics reveal somitogenesis in gastruloids, Nature, 582, 405, 10.1038/s41586-020-2024-3 · DOI · Paper page
- 10.1126/science.aaw1219 · DOI · Paper page
- 2019, Deep learning in chemistry, Journal of chemical information and modeling, 59, 2545, 10.1021/acs.jcim.9b00266 · DOI · Paper page
- 10.1186/s13059-017-1381-1 · DOI · Paper page
Cited by
scGPT: Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AI
Cui, H., Wang, C., Maan, H., Pang, K., Luo, F., & Wang, B. (2023) · doi:10.1101/2023.04.30.538439 · Cited by 1,694
“We conducted a performance comparison between scGPT and two other recent methods, GEARS [38] and CPA [39].”
BackgroundMethodInfluentialBest practices for single-cell analysis across modalities
Heumos, L., Schaar, A. C., Lance, C., Litinetskaya, A., Drost, F., Zappia, L., Lücken, M. D., Strobl, D. C., Henao, J., Curion, F., et al. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-023-00586-w · Cited by 1,051
“3).”
Self-citationLarge-scale foundation model on single-cell transcriptomics
Hao, M., Gong, J., Zeng, X., Liu, C., Guo, Y., Cheng, X., Wang, T., Ma, J., Zhang, X., & Song, L. (2024) · Nature Methods · doi:10.1038/s41592-024-02305-7 · Cited by 628
“Using Perturb-seq 51,52 data resources to train models for modeling cellular response to perturbations is a key task of computational biology 53–55 .”
Mapping single-cell data to reference atlases by transfer learning
Lotfollahi, M., Naghipourfar, M., Luecken, M. D., Khajavi, M., Büttner, M., Wagenstetter, M., Avsec, Ž., Gayoso, A., Yosef, N., Interlandi, M., et al. (2022) · Nature Biotechnology · doi:10.1038/s41587-021-01001-7 · Cited by 602
“Incorporating additional covariates as conditional neurons in the reference model will allow modeling of treatment response with a certain perturbation or drug 63,64 .”
MethodSelf-citationRational combinations of targeted cancer therapies: background, advances and challenges
Jin, H., Wang, L., & Bernards, R. (2023) · Nature Reviews Drug Discovery · doi:10.1038/s41573-022-00615-z · Cited by 503
Metadata
- Authors
- Lotfollahi, M., Susmelj, A. K., De Donno, C., Ji, Y., Ibarra, I. L., Wolf, F. A., Yakubova, N., Theis, F. J., & Lopez-Paz, D.
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2021-04-15
- OpenAlex
- W3153727370
- Cited by
- 48
- References
- 11
- Type
- posted content
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning interpretable cellular responses to complex perturbations in high-throughput screens. https://app.cochat.ai/papers/10.1101/2021.04.14.439903
- The paper
- Lotfollahi, M., Susmelj, A. K., De Donno, C., Ji, Y., Ibarra, I. L., Wolf, F. A., Yakubova, N., Theis, F. J., & Lopez-Paz, D. (2021). Learning interpretable cellular responses to complex perturbations in high-throughput screens. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.1101/2021.04.14.439903
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.