CoChat

Exploring Single-Cell Data with Deep Multitasking Neural Networks

Open access
Amodio, Matthew, van Dijk, David, Srinivasan, Krishnan, Chen, William S, Mohsen, Hussein, Moon, Kevin R., Campbell, Allison, Zhao, Yujiao, Wang, Xiaomei, Venkataswamy, Manjunatha, Desai, Anita, Ravi, V., Kumar, Priti, Montgomery, Ruth, Wolf, Guy, Krishnaswamy, Smita · 2017 · bioRxiv (Cold Spring Harbor Laboratory)

Preprint — published as 10.1038/s41592-019-0576-7 · Paper page

PreprintCited by 45

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

Biomedical researchers are generating high-throughput, high-dimensional single-cell data at a staggering rate. As costs of data generation decrease, experimental design is moving towards measurement of many different single-cell samples in the same dataset. These samples can correspond to different patients, conditions, or treatments. While scalability of methods to datasets of these sizes is a challenge on its own, dealing with large-scale experimental design presents a whole new set of problems, including batch effects and sample comparison issues. Currently, there are no computational tools that can both handle large amounts of data in a scalable manner (many cells) and at the same time deal with many samples (many patients or conditions). Moreover, data analysis currently involves the use of different tools that each operate on their own data representation, not guaranteeing a synchronized analysis pipeline. For instance, data visualization methods can be disjoint and mismatched with the clustering method. For this purpose, we present SAUCIE, a deep neural network that leverages the high degree of parallelization and scalability offered by neural networks, as well as the deep representation of data that can be learned by them to perform many single-cell data analysis tasks, all on a unified representation. A well-known limitation of neural networks is their interpretability. Our key contribution here are newly formulated regularizations (penalties) that render features learned in hidden layers of the neural network interpretable. When large multi-patient datasets are fed into SAUCIE, the various hidden layers contain denoised and batch-corrected data, a low dimensional visualization, unsupervised clustering, as well as other information that can be used to explore the data. We show this capability by analyzing a newly generated 180-sample dataset consisting of T cells from dengue patients in India, measured with mass cytometry. We show that SAUCIE, for the first time, can batch correct and process this 11-million cell data to identify cluster-based signatures of acute dengue infection and create a patient manifold, stratifying immune response to dengue on the basis of single-cell measurements.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/237065

Cites

14 of 14 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 49

  1. 2017, “Unsupervised extraction of stable expression signatures from public compendia with an ensemble of neural networks,”, Cell systems, 5, 63, 10.1016/j.cels.2017.06.003 · DOI · Paper page
  2. G. P. Way and C. S. Greene , “Extracting a biologically relevant latent space from cancer transcriptomes with variational autoencoders,” bioRxiv, p. 174474, 2017.
  3. 10.1038/nmeth.3547 · DOI · Paper page
  4. 10.1109/TPAMI.2013.50 · DOI · Paper page
  5. P. Vincent , H. Larochelle , Y. Bengio , and P.-A. Manzagol , “Extracting and composing robust features with denoising autoencoders,” in ICML, 2008. · DOI · Paper page
  6. 10.1126/science.1127647 · DOI · Paper page
  7. J. Tan , M. Ung , C. Cheng , and C. S. Greene , “Unsupervised feature construction and knowledge extraction from genome-wide assays of breast cancer with denoising autoencoders,” in Pacific Symposium on Biocomputing Co-Chairs, pp. 132–143, World Scientific, 2014. · DOI · Paper page
  8. 10.1128/msystems.00025-15 · DOI · Paper page
  9. H. Chen , J. Shen , L. Wang , and J. Song , “Leveraging stacked denoising autoencoder in prediction of pathogen-host protein-protein interactions,” in Big Data (BigData Congress), 2017 IEEE International Congress on, pp. 368–375, IEEE, 2017. · DOI
  10. 2016, “Learning a hierarchical representation of the yeast transcriptomic machinery using an autoencoder model,”, BMC bioinformatics, 17, S9
  11. 10.1016/j.acha.2006.04.006 · DOI · Paper page
  12. D. van Dijk , J. Nainys , R. Sharma , P. Kathail , A. J. Carr , K. R. Moon , L. Mazutis , G. Wolf , S. Krishnaswamy , and D. Pe’er , “Magic: A diffusion-based imputation method reveals gene-gene interactions in single-cell rna-sequencing data,” BioRxiv, p. 111591, 2017.
  13. P. Vincent , H. Larochelle , Y. Bengio , and P.-A. Manzagol , “Extracting and composing robust features with denoising autoencoders,” in Proceedings of the 25th international conference on Machine learning, pp. 1096–1103, ACM, 2008.
  14. K. R. Moon , J. Stanley , D. Burkhardt , D. van Dijk , G. Wolf , and S. Krishnaswamy , “Manifold learning-based methods for analyzing single-cell rna-sequencing data,” Current Opinion in Systems Biology, 2017. · DOI
  15. M. Courbariaux , Y. Bengio , and J.-P. David , “Binaryconnect: Training deep neural networks with binary weights during propagations,” in Advances in neural information processing systems, pp. 3123–3131, 2015.
  16. 10.1093/bioinformatics/btx196 · DOI · Paper page
  17. 10.1016/j.cell.2017.04.016 · DOI · Paper page
  18. 10.1016/j.stem.2015.01.015 · DOI · Paper page
  19. 10.1016/j.cell.2015.11.013 · DOI · Paper page
  20. 10.1126/science.aaa1934 · DOI · Paper page
  21. 2011, “Scikit-learn: Machine learning in Python,”, Journal of Machine Learning Research, 12, 2825
  22. A. Butler and R. Satija , “Integrated analysis of single cell transcriptomic data across conditions, technologies, and species,” bioRxiv, p. 164889, 2017.
  23. M. Buttner , Z. Miao , A. Wolf , S. A. Teichmann , and F. J. Theis , “Assessment of batch-correction methods for scrna-seq data with a new test metric,” bioRxiv, p. 200345, 2017.
  24. 2002, “Iterative procrustes alignment with the em algorithm,”, Image and Vision Computing, 20, 377, 10.1016/S0262-8856(02)00010-0 · DOI
  25. K. Lui , G. W. Ding , R. Huang , and R. McCann , “Dimensionality reduction has quantifiable imperfections: Two geometric bounds,” in Advances in Neural Information Processing Systems, pp. 8461–8471, 2018.
  26. 10.1016/j.cell.2017.06.010 · DOI · Paper page
  27. 10.1126/science.aan6836 · DOI · Paper page
  28. C.-Y. Tsai , K. H. Liong , M. G. Gunalan , N. Li , D. S. L. Lim , D. A. Fisher , P. A. MacAry , Y. S. Leo , S.-C. Wong , K. J. Puan , et al., “Type i ifns and il-18 regulate the antiviral response of primary human γ δ t cells against dendritic cells infected with dengue virus,” The Journal of Immunology, p. 1303343, 2015.
  29. 2015, “gd t lymphocytes in the diagnosis of human t cell receptor immunodeficiencies,”, Frontiers in immunology, 6, 20
  30. 10.1146/annurev-immunol-032713-120216 · DOI · Paper page
  31. 2017, “Human zika infection induces a reduction of ifn-γ producing cd4 t-cells and a parallel expansion of effector vδ2 t-cells,”, Scientific reports, 7, 6313, 10.1038/s41598-017-06536-x · DOI
  32. 10.1084/jem.173.2.503 · doi:10.1084/jem.173.2.503
  33. 10.1016/j.cell.2015.05.047 · DOI · Paper page
  34. 2008, “Visualizing data using t-sne,”, Journal of Machine Learning Research, 9, 2579
  35. 10.1126/science.290.5500.2323 · DOI · Paper page
  36. B. Nadler , S. Lafon , I. Kevrekidis , and R. R. Coifman , “Diffusion maps, spectral clustering and eigenfunctions of fokker-planck operators,” in Advances in neural information processing systems, pp. 955–962, 2006.
  37. K. R. Moon , D. van Dijk , Z. Wang , W. Chen , M. J. Hirn , R. R. Coifman , N. B. Ivanova , G. Wolf , and S. Krishnaswamy , “Phate: A dimensionality reduction method for visualizing trajectory structures in high-dimensional biological data,” bioRxiv, p. 120378, 2017.
  38. 2006, “Diffusion maps and coarse-graining: A unified framework for dimensionality reduction, graph partitioning, and data set parameterization,”, IEEE transactions on pattern analysis and machine intelligence, 28, 1393, 10.1109/TPAMI.2006.184 · DOI · Paper page
  39. 2012, “Hierarchical data organization, clustering and denoising via localized diffusion folders,”, Applied and Computational Harmonic Analysis, 33, 1, 10.1016/j.acha.2011.09.002 · DOI
  40. 2012, “Coarse-grained localized diffusion,”, Applied and Computational Harmonic Analysis, 33, 388, 10.1016/j.acha.2012.02.004 · DOI
  41. 2016, “Diffusion pseudotime robustly reconstructs lineage branching,”, Nature methods, 13, 845, 10.1038/nmeth.3971 · DOI · Paper page
  42. 10.1073/pnas.1307298110 · DOI
  43. 2014, “What regularized auto-encoders learn from the data-generating distribution,”, The Journal of Machine Learning Research, 15, 3563
  44. G. K. Dziugaite , D. M. Roy , and Z. Ghahramani , “Training generative neural networks via maximum mean discrepancy optimization,” in UAI, 2015.
  45. D. Arpit , Y. Zhou , H. Q. Ngo , and V. Govindaraju , “Why regularized auto-encoders learn sparse representation?,” in ICML, 2016.
  46. X. Glorot , A. Bordes , and Y. Bengio , “Deep sparse rectifier neural networks,” in AISTATS, 2011.
  47. H. Wang , Z. Hu , and Y. Zhao , “Kernel principal component analysis for large scale data set,” in International Conference on Intelligent Computing, pp. 745–756, Springer, 2006. · doi:10.1007/11816157_91
  48. 2017, “The natural killer cell response to west nile virus in young and old individuals with or without a prior history of infection,”, PloS one, 12, e0172625, 10.1371/journal.pone.0172625 · DOI
  49. 10.1016/j.jim.2014.10.010 · DOI

Cited by

See all 45

Metadata

Authors
Amodio, M., van Dijk, D., Srinivasan, K., Chen, W. S., Mohsen, H., Moon, K. R., Campbell, A., Zhao, Y., Wang, X., Venkataswamy, M., Desai, A., Ravi, V., Kumar, P., Montgomery, R., Wolf, G., & Krishnaswamy, S.
Venue
bioRxiv (Cold Spring Harbor Laboratory)
Publisher
openRxiv
Published
2017-12-19
OpenAlex
W2784595248
Cited by
45
References
14
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

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.