Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks
Visualization algorithms are fundamental tools for interpreting single-cell data. However, standard methods, such as t-stochastic neighbor embedding (t-SNE), are not scalable to datasets with millions of cells and the resulting visualizations cannot be generalized to analyze new datasets. Here we in...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Cell Press
2019
|
| Online Access: | https://hdl.handle.net/1721.1/122802 |
| _version_ | 1811085433928417280 |
|---|---|
| author | Cho, Hyunghoon Berger Leighton, Bonnie Peng, Jian |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Cho, Hyunghoon Berger Leighton, Bonnie Peng, Jian |
| author_sort | Cho, Hyunghoon |
| collection | MIT |
| description | Visualization algorithms are fundamental tools for interpreting single-cell data. However, standard methods, such as t-stochastic neighbor embedding (t-SNE), are not scalable to datasets with millions of cells and the resulting visualizations cannot be generalized to analyze new datasets. Here we introduce net-SNE, a generalizable visualization approach that trains a neural network to learn a mapping function from high-dimensional single-cell gene-expression profiles to a low-dimensional visualization. We benchmark net-SNE on 13 different datasets, and show that it achieves visualization quality and clustering accuracy comparable with t-SNE. Additionally we show that the mapping function learned by net-SNE can accurately position entire new subtypes of cells from previously unseen datasets and can also be used to reduce the runtime of visualizing 1.3 million cells by 36-fold (from 1.5 days to an hour). Our work provides a framework for bootstrapping single-cell analysis from existing datasets. Researchers are applying single-cell RNA sequencing to increasingly large numbers of cells in diverse tissues and organisms. We introduce a data visualization tool, named net-SNE, which trains a neural network to embed single cells in 2D or 3D. Unlike previous approaches, our method allows new cells to be mapped onto existing visualizations, facilitating knowledge transfer across different datasets. Our method also vastly reduces the runtime of visualizing large datasets containing millions of cells. Keywords: data visualization; neural network; single-cell RNA sequencing |
| first_indexed | 2024-09-23T13:09:31Z |
| format | Article |
| id | mit-1721.1/122802 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:09:31Z |
| publishDate | 2019 |
| publisher | Cell Press |
| record_format | dspace |
| spelling | mit-1721.1/1228022022-09-28T12:19:28Z Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks Cho, Hyunghoon Berger Leighton, Bonnie Peng, Jian Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Mathematics Visualization algorithms are fundamental tools for interpreting single-cell data. However, standard methods, such as t-stochastic neighbor embedding (t-SNE), are not scalable to datasets with millions of cells and the resulting visualizations cannot be generalized to analyze new datasets. Here we introduce net-SNE, a generalizable visualization approach that trains a neural network to learn a mapping function from high-dimensional single-cell gene-expression profiles to a low-dimensional visualization. We benchmark net-SNE on 13 different datasets, and show that it achieves visualization quality and clustering accuracy comparable with t-SNE. Additionally we show that the mapping function learned by net-SNE can accurately position entire new subtypes of cells from previously unseen datasets and can also be used to reduce the runtime of visualizing 1.3 million cells by 36-fold (from 1.5 days to an hour). Our work provides a framework for bootstrapping single-cell analysis from existing datasets. Researchers are applying single-cell RNA sequencing to increasingly large numbers of cells in diverse tissues and organisms. We introduce a data visualization tool, named net-SNE, which trains a neural network to embed single cells in 2D or 3D. Unlike previous approaches, our method allows new cells to be mapped onto existing visualizations, facilitating knowledge transfer across different datasets. Our method also vastly reduces the runtime of visualizing large datasets containing millions of cells. Keywords: data visualization; neural network; single-cell RNA sequencing National Institutes of Health (U.S.) (Grant R01GM081871) 2019-11-08T13:33:04Z 2019-11-08T13:33:04Z 2018-08 2019-11-07T18:42:47Z Article http://purl.org/eprint/type/JournalArticle 2405-4712 https://hdl.handle.net/1721.1/122802 Cho, Hyunghoon, et al. "Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks." Cell Systems 7, 2 (August 2018): 185–191 © 2018 Elsevier en http://dx.doi.org/10.1103/10.1016/j.cels.2018.05.017 Cell Systems Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Cell Press PMC |
| spellingShingle | Cho, Hyunghoon Berger Leighton, Bonnie Peng, Jian Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks |
| title | Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks |
| title_full | Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks |
| title_fullStr | Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks |
| title_full_unstemmed | Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks |
| title_short | Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks |
| title_sort | generalizable and scalable visualization of single cell data using neural networks |
| url | https://hdl.handle.net/1721.1/122802 |
| work_keys_str_mv | AT chohyunghoon generalizableandscalablevisualizationofsinglecelldatausingneuralnetworks AT bergerleightonbonnie generalizableandscalablevisualizationofsinglecelldatausingneuralnetworks AT pengjian generalizableandscalablevisualizationofsinglecelldatausingneuralnetworks |