The University of Southampton
University of Southampton Institutional Repository

Transfer learning efficiently maps bone marrow cell types from mouse to human using single-cell RNA sequencing

Transfer learning efficiently maps bone marrow cell types from mouse to human using single-cell RNA sequencing
Transfer learning efficiently maps bone marrow cell types from mouse to human using single-cell RNA sequencing
Biomedical research often involves conducting experiments on model organisms in the anticipation that the biology learnt will transfer to humans. Previous comparative studies of mouse and human tissues were limited by the use of bulk-cell material. Here we show that transfer learning—the branch of machine learning that concerns passing information from one domain to another—can be used to efficiently map bone marrow biology between species, using data obtained from single-cell RNA sequencing. We first trained a multiclass logistic regression model to recognize different cell types in mouse bone marrow achieving equivalent performance to more complex artificial neural networks. Furthermore, it was able to identify individual human bone marrow cells with 83% overall accuracy. However, some human cell types were not easily identified, indicating important differences in biology. When re-training the mouse classifier using data from human, less than 10 human cells of a given type were needed to accurately learn its representation. In some cases, human cell identities could be inferred directly from the mouse classifier via zero-shot learning. These results show how simple machine learning models can be used to reconstruct complex biology from limited data, with broad implications for biomedical research.
2399-3642
Stumpf, Patrick Simon
3aa7f861-0629-4a6c-a7be-3afd99e11314
Du, Xin
9629013b-b962-4a81-bf18-7797d581fdd8
Imanishi, Haruka
2e00ec02-0937-4cad-8bde-7302ec0b982e
Kunisaki, Yuya
c9875902-7b58-4017-93fe-b5814c1aae96
Semba, Yuichiro
55f97152-ff8b-47de-893f-80bf7d7dfc33
Noble, Timothy
e0aa0d7d-ba1b-4f2e-9acf-41f9b030081a
Smith, Rosanna
1fe5586f-92e9-4658-bd55-cd3eaa176b66
Rose-Zerilli, Matthew
29603401-e310-4054-b818-8a542c361b9a
West, Jonathan
f1c2e060-16c3-44c0-af70-242a1c58b968
Oreffo, Richard
ff9fff72-6855-4d0f-bfb2-311d0e8f3778
Farrahi, Katayoun
bc848b9c-fc32-475c-b241-f6ade8babacb
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Akashi, Koichi
c76de2d9-ffa4-4dbd-b63d-a6f27d63b270
Arai, Fumio
55b7859b-98f0-450a-b355-74e1f1e1945d
Macarthur, Benjamin
2c0476e7-5d3e-4064-81bb-104e8e88bb6b
Stumpf, Patrick Simon
3aa7f861-0629-4a6c-a7be-3afd99e11314
Du, Xin
9629013b-b962-4a81-bf18-7797d581fdd8
Imanishi, Haruka
2e00ec02-0937-4cad-8bde-7302ec0b982e
Kunisaki, Yuya
c9875902-7b58-4017-93fe-b5814c1aae96
Semba, Yuichiro
55f97152-ff8b-47de-893f-80bf7d7dfc33
Noble, Timothy
e0aa0d7d-ba1b-4f2e-9acf-41f9b030081a
Smith, Rosanna
1fe5586f-92e9-4658-bd55-cd3eaa176b66
Rose-Zerilli, Matthew
29603401-e310-4054-b818-8a542c361b9a
West, Jonathan
f1c2e060-16c3-44c0-af70-242a1c58b968
Oreffo, Richard
ff9fff72-6855-4d0f-bfb2-311d0e8f3778
Farrahi, Katayoun
bc848b9c-fc32-475c-b241-f6ade8babacb
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Akashi, Koichi
c76de2d9-ffa4-4dbd-b63d-a6f27d63b270
Arai, Fumio
55b7859b-98f0-450a-b355-74e1f1e1945d
Macarthur, Benjamin
2c0476e7-5d3e-4064-81bb-104e8e88bb6b

Stumpf, Patrick Simon, Du, Xin, Imanishi, Haruka, Kunisaki, Yuya, Semba, Yuichiro, Noble, Timothy, Smith, Rosanna, Rose-Zerilli, Matthew, West, Jonathan, Oreffo, Richard, Farrahi, Katayoun, Niranjan, Mahesan, Akashi, Koichi, Arai, Fumio and Macarthur, Benjamin (2020) Transfer learning efficiently maps bone marrow cell types from mouse to human using single-cell RNA sequencing. Communications Biology, 3 (1), [736]. (doi:10.1038/s42003-020-01463-6).

Record type: Article

Abstract

Biomedical research often involves conducting experiments on model organisms in the anticipation that the biology learnt will transfer to humans. Previous comparative studies of mouse and human tissues were limited by the use of bulk-cell material. Here we show that transfer learning—the branch of machine learning that concerns passing information from one domain to another—can be used to efficiently map bone marrow biology between species, using data obtained from single-cell RNA sequencing. We first trained a multiclass logistic regression model to recognize different cell types in mouse bone marrow achieving equivalent performance to more complex artificial neural networks. Furthermore, it was able to identify individual human bone marrow cells with 83% overall accuracy. However, some human cell types were not easily identified, indicating important differences in biology. When re-training the mouse classifier using data from human, less than 10 human cells of a given type were needed to accurately learn its representation. In some cases, human cell identities could be inferred directly from the mouse classifier via zero-shot learning. These results show how simple machine learning models can be used to reconstruct complex biology from limited data, with broad implications for biomedical research.

Text
TL paper - Accepted Manuscript
Download (13MB)

More information

Accepted/In Press date: 30 October 2020
Published date: 4 December 2020

Identifiers

Local EPrints ID: 445275
URI: http://eprints.soton.ac.uk/id/eprint/445275
ISSN: 2399-3642
PURE UUID: 8a8cf6c0-02fb-4627-a895-97f573ec41d2
ORCID for Jonathan West: ORCID iD orcid.org/0000-0002-5709-6790
ORCID for Richard Oreffo: ORCID iD orcid.org/0000-0001-5995-6726

Catalogue record

Date deposited: 30 Nov 2020 17:31
Last modified: 06 Jan 2021 17:47

Export record

Altmetrics

Contributors

Author: Patrick Simon Stumpf
Author: Xin Du
Author: Haruka Imanishi
Author: Yuya Kunisaki
Author: Yuichiro Semba
Author: Timothy Noble
Author: Rosanna Smith
Author: Matthew Rose-Zerilli
Author: Jonathan West ORCID iD
Author: Richard Oreffo ORCID iD
Author: Katayoun Farrahi
Author: Mahesan Niranjan
Author: Koichi Akashi
Author: Fumio Arai

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×