Cargando…
Correcting nuisance variation using Wasserstein distance
Profiling cellular phenotypes from microscopic imaging can provide meaningful biological information resulting from various factors affecting the cells. One motivating application is drug development: morphological cell features can be captured from images, from which similarities between different...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7050548/ https://www.ncbi.nlm.nih.gov/pubmed/32161688 http://dx.doi.org/10.7717/peerj.8594 |
_version_ | 1783502630917505024 |
---|---|
author | Tabak, Gil Fan, Minjie Yang, Samuel Hoyer, Stephan Davis, Geoffrey |
author_facet | Tabak, Gil Fan, Minjie Yang, Samuel Hoyer, Stephan Davis, Geoffrey |
author_sort | Tabak, Gil |
collection | PubMed |
description | Profiling cellular phenotypes from microscopic imaging can provide meaningful biological information resulting from various factors affecting the cells. One motivating application is drug development: morphological cell features can be captured from images, from which similarities between different drug compounds applied at different doses can be quantified. The general approach is to find a function mapping the images to an embedding space of manageable dimensionality whose geometry captures relevant features of the input images. An important known issue for such methods is separating relevant biological signal from nuisance variation. For example, the embedding vectors tend to be more correlated for cells that were cultured and imaged during the same week than for those from different weeks, despite having identical drug compounds applied in both cases. In this case, the particular batch in which a set of experiments were conducted constitutes the domain of the data; an ideal set of image embeddings should contain only the relevant biological information (e.g., drug effects). We develop a general framework for adjusting the image embeddings in order to “forget” domain-specific information while preserving relevant biological information. To achieve this, we minimize a loss function based on distances between marginal distributions (such as the Wasserstein distance) of embeddings across domains for each replicated treatment. For the dataset we present results with, the only replicated treatment happens to be the negative control treatment, for which we do not expect any treatment-induced cell morphology changes. We find that for our transformed embeddings (i) the underlying geometric structure is not only preserved but the embeddings also carry improved biological signal; and (ii) less domain-specific information is present. |
format | Online Article Text |
id | pubmed-7050548 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | PeerJ Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-70505482020-03-11 Correcting nuisance variation using Wasserstein distance Tabak, Gil Fan, Minjie Yang, Samuel Hoyer, Stephan Davis, Geoffrey PeerJ Bioinformatics Profiling cellular phenotypes from microscopic imaging can provide meaningful biological information resulting from various factors affecting the cells. One motivating application is drug development: morphological cell features can be captured from images, from which similarities between different drug compounds applied at different doses can be quantified. The general approach is to find a function mapping the images to an embedding space of manageable dimensionality whose geometry captures relevant features of the input images. An important known issue for such methods is separating relevant biological signal from nuisance variation. For example, the embedding vectors tend to be more correlated for cells that were cultured and imaged during the same week than for those from different weeks, despite having identical drug compounds applied in both cases. In this case, the particular batch in which a set of experiments were conducted constitutes the domain of the data; an ideal set of image embeddings should contain only the relevant biological information (e.g., drug effects). We develop a general framework for adjusting the image embeddings in order to “forget” domain-specific information while preserving relevant biological information. To achieve this, we minimize a loss function based on distances between marginal distributions (such as the Wasserstein distance) of embeddings across domains for each replicated treatment. For the dataset we present results with, the only replicated treatment happens to be the negative control treatment, for which we do not expect any treatment-induced cell morphology changes. We find that for our transformed embeddings (i) the underlying geometric structure is not only preserved but the embeddings also carry improved biological signal; and (ii) less domain-specific information is present. PeerJ Inc. 2020-02-28 /pmc/articles/PMC7050548/ /pubmed/32161688 http://dx.doi.org/10.7717/peerj.8594 Text en © 2020 Tabak et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. |
spellingShingle | Bioinformatics Tabak, Gil Fan, Minjie Yang, Samuel Hoyer, Stephan Davis, Geoffrey Correcting nuisance variation using Wasserstein distance |
title | Correcting nuisance variation using Wasserstein distance |
title_full | Correcting nuisance variation using Wasserstein distance |
title_fullStr | Correcting nuisance variation using Wasserstein distance |
title_full_unstemmed | Correcting nuisance variation using Wasserstein distance |
title_short | Correcting nuisance variation using Wasserstein distance |
title_sort | correcting nuisance variation using wasserstein distance |
topic | Bioinformatics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7050548/ https://www.ncbi.nlm.nih.gov/pubmed/32161688 http://dx.doi.org/10.7717/peerj.8594 |
work_keys_str_mv | AT tabakgil correctingnuisancevariationusingwassersteindistance AT fanminjie correctingnuisancevariationusingwassersteindistance AT yangsamuel correctingnuisancevariationusingwassersteindistance AT hoyerstephan correctingnuisancevariationusingwassersteindistance AT davisgeoffrey correctingnuisancevariationusingwassersteindistance |