Cargando…
Digging deep into Golgi phenotypic diversity with unsupervised machine learning
The synthesis of glycans and the sorting of proteins are critical functions of the Golgi apparatus and depend on its highly complex and compartmentalized architecture. High-content image analysis coupled to RNA interference screening offers opportunities to explore this organelle organization and th...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The American Society for Cell Biology
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5706995/ https://www.ncbi.nlm.nih.gov/pubmed/29021342 http://dx.doi.org/10.1091/mbc.E17-06-0379 |
_version_ | 1783282331498315776 |
---|---|
author | Hussain, Shaista Le Guezennec, Xavier Yi, Wang Dong, Huang Chia, Joanne Yiping, Ke Khoon, Lee Kee Bard, Frédéric |
author_facet | Hussain, Shaista Le Guezennec, Xavier Yi, Wang Dong, Huang Chia, Joanne Yiping, Ke Khoon, Lee Kee Bard, Frédéric |
author_sort | Hussain, Shaista |
collection | PubMed |
description | The synthesis of glycans and the sorting of proteins are critical functions of the Golgi apparatus and depend on its highly complex and compartmentalized architecture. High-content image analysis coupled to RNA interference screening offers opportunities to explore this organelle organization and the gene network underlying it. To date, image-based Golgi screens have based on a single parameter or supervised analysis with predefined Golgi structural classes. Here, we report the use of multiparametric data extracted from a single marker and a computational unsupervised analysis framework to explore Golgi phenotypic diversity more extensively. In contrast with the three visually definable phenotypes, our framework reproducibly identified 10 Golgi phenotypes. They were used to quantify and stratify phenotypic similarities among genetic perturbations. The derived phenotypic network partially overlaps previously reported protein–protein interactions as well as suggesting novel functional interactions. Our workflow suggests the existence of multiple stable Golgi organizational states and provides a proof of concept for the classification of drugs and genes using fine-grained phenotypic information. |
format | Online Article Text |
id | pubmed-5706995 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | The American Society for Cell Biology |
record_format | MEDLINE/PubMed |
spelling | pubmed-57069952018-02-16 Digging deep into Golgi phenotypic diversity with unsupervised machine learning Hussain, Shaista Le Guezennec, Xavier Yi, Wang Dong, Huang Chia, Joanne Yiping, Ke Khoon, Lee Kee Bard, Frédéric Mol Biol Cell Articles The synthesis of glycans and the sorting of proteins are critical functions of the Golgi apparatus and depend on its highly complex and compartmentalized architecture. High-content image analysis coupled to RNA interference screening offers opportunities to explore this organelle organization and the gene network underlying it. To date, image-based Golgi screens have based on a single parameter or supervised analysis with predefined Golgi structural classes. Here, we report the use of multiparametric data extracted from a single marker and a computational unsupervised analysis framework to explore Golgi phenotypic diversity more extensively. In contrast with the three visually definable phenotypes, our framework reproducibly identified 10 Golgi phenotypes. They were used to quantify and stratify phenotypic similarities among genetic perturbations. The derived phenotypic network partially overlaps previously reported protein–protein interactions as well as suggesting novel functional interactions. Our workflow suggests the existence of multiple stable Golgi organizational states and provides a proof of concept for the classification of drugs and genes using fine-grained phenotypic information. The American Society for Cell Biology 2017-12-01 /pmc/articles/PMC5706995/ /pubmed/29021342 http://dx.doi.org/10.1091/mbc.E17-06-0379 Text en © 2017 Hussain, Le Guezennec, et al. This article is distributed by The American Society for Cell Biology under license from the author(s). Two months after publication it is available to the public under an Attribution–Noncommercial–Share Alike 3.0 Unported Creative Commons License (http://creativecommons.org/licenses/by-nc-sa/3.0). “ASCB®,” “The American Society for Cell Biology®,” and “Molecular Biology of the Cell®” are registered trademarks of The American Society for Cell Biology. |
spellingShingle | Articles Hussain, Shaista Le Guezennec, Xavier Yi, Wang Dong, Huang Chia, Joanne Yiping, Ke Khoon, Lee Kee Bard, Frédéric Digging deep into Golgi phenotypic diversity with unsupervised machine learning |
title | Digging deep into Golgi phenotypic diversity with unsupervised machine learning |
title_full | Digging deep into Golgi phenotypic diversity with unsupervised machine learning |
title_fullStr | Digging deep into Golgi phenotypic diversity with unsupervised machine learning |
title_full_unstemmed | Digging deep into Golgi phenotypic diversity with unsupervised machine learning |
title_short | Digging deep into Golgi phenotypic diversity with unsupervised machine learning |
title_sort | digging deep into golgi phenotypic diversity with unsupervised machine learning |
topic | Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5706995/ https://www.ncbi.nlm.nih.gov/pubmed/29021342 http://dx.doi.org/10.1091/mbc.E17-06-0379 |
work_keys_str_mv | AT hussainshaista diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning AT leguezennecxavier diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning AT yiwang diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning AT donghuang diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning AT chiajoanne diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning AT yipingke diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning AT khoonleekee diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning AT bardfrederic diggingdeepintogolgiphenotypicdiversitywithunsupervisedmachinelearning |