SCA: recovering single-cell heterogeneity through information-based dimensionality reduction
Abstract Dimensionality reduction summarizes the complex transcriptomic landscape of single-cell datasets for downstream analyses. Current approaches favor large cellular populations defined by many genes, at the expense of smaller and more subtly defined populations. Here, we present...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
BioMed Central
2023
|
| Online Access: | https://hdl.handle.net/1721.1/152252 |
| _version_ | 1826192856461606912 |
|---|---|
| author | DeMeo, Benjamin Berger, Bonnie |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory DeMeo, Benjamin Berger, Bonnie |
| author_sort | DeMeo, Benjamin |
| collection | MIT |
| description | Abstract
Dimensionality reduction summarizes the complex transcriptomic landscape of single-cell datasets for downstream analyses. Current approaches favor large cellular populations defined by many genes, at the expense of smaller and more subtly defined populations. Here, we present surprisal component analysis (SCA), a technique that newly leverages the information-theoretic notion of surprisal for dimensionality reduction to promote more meaningful signal extraction. For example, SCA uncovers clinically important cytotoxic T-cell subpopulations that are indistinguishable using existing pipelines. We also demonstrate that SCA substantially improves downstream imputation. SCA’s efficient information-theoretic paradigm has broad applications to the study of complex biological tissues in health and disease. |
| first_indexed | 2024-09-23T09:29:55Z |
| format | Article |
| id | mit-1721.1/152252 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T09:29:55Z |
| publishDate | 2023 |
| publisher | BioMed Central |
| record_format | dspace |
| spelling | mit-1721.1/1522522024-01-12T21:11:37Z SCA: recovering single-cell heterogeneity through information-based dimensionality reduction DeMeo, Benjamin Berger, Bonnie Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Mathematics Abstract Dimensionality reduction summarizes the complex transcriptomic landscape of single-cell datasets for downstream analyses. Current approaches favor large cellular populations defined by many genes, at the expense of smaller and more subtly defined populations. Here, we present surprisal component analysis (SCA), a technique that newly leverages the information-theoretic notion of surprisal for dimensionality reduction to promote more meaningful signal extraction. For example, SCA uncovers clinically important cytotoxic T-cell subpopulations that are indistinguishable using existing pipelines. We also demonstrate that SCA substantially improves downstream imputation. SCA’s efficient information-theoretic paradigm has broad applications to the study of complex biological tissues in health and disease. 2023-09-22T18:47:59Z 2023-09-22T18:47:59Z 2023-08-25 2023-08-27T03:12:02Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/152252 Genome Biology. 2023 Aug 25;24(1):195 PUBLISHER_CC PUBLISHER_CC en https://doi.org/10.1186/s13059-023-02998-7 Creative Commons Attribution http://creativecommons.org/licenses/by/4.0/ BioMed Central Ltd., part of Springer Nature application/pdf BioMed Central Springer |
| spellingShingle | DeMeo, Benjamin Berger, Bonnie SCA: recovering single-cell heterogeneity through information-based dimensionality reduction |
| title | SCA: recovering single-cell heterogeneity through information-based dimensionality reduction |
| title_full | SCA: recovering single-cell heterogeneity through information-based dimensionality reduction |
| title_fullStr | SCA: recovering single-cell heterogeneity through information-based dimensionality reduction |
| title_full_unstemmed | SCA: recovering single-cell heterogeneity through information-based dimensionality reduction |
| title_short | SCA: recovering single-cell heterogeneity through information-based dimensionality reduction |
| title_sort | sca recovering single cell heterogeneity through information based dimensionality reduction |
| url | https://hdl.handle.net/1721.1/152252 |
| work_keys_str_mv | AT demeobenjamin scarecoveringsinglecellheterogeneitythroughinformationbaseddimensionalityreduction AT bergerbonnie scarecoveringsinglecellheterogeneitythroughinformationbaseddimensionalityreduction |