Applying Machine Learning to Predict the Exportome of Bovine and Canine Babesia Species That Cause Babesiosis

Goodswen, SJ; Kennedy, PJ; Ellis, JT

Applying Machine Learning to Predict the Exportome of Bovine and Canine Babesia Species That Cause Babesiosis

Goodswen, SJ Kennedy, PJ Ellis, JT

Permalink

Publisher:: MDPI AG
Publication Type:: Journal Article
Citation:: Pathogens, 2021, 10, (6), pp. 660-660
Issue Date:: 2021-05-27

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (1.81 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Goodswen, SJ
dc.contributor.author	Kennedy, PJ
dc.contributor.author	Ellis, JT
dc.date.accessioned	2021-06-04T01:58:27Z
dc.date.available	2021-06-04T01:58:27Z
dc.date.issued	2021-05-27
dc.identifier.citation	Pathogens, 2021, 10, (6), pp. 660-660
dc.identifier.issn	2076-0817
dc.identifier.issn	2076-0817
dc.identifier.uri	http://hdl.handle.net/10453/149410
dc.description.abstract	<jats:p>Babesia infection of red blood cells can cause a severe disease called babesiosis in susceptible hosts. Bovine babesiosis causes global economic loss to the beef and dairy cattle industries, and canine babesiosis is considered a clinically significant disease. Potential therapeutic targets against bovine and canine babesiosis include members of the exportome, i.e., those proteins exported from the parasite into the host red blood cell. We developed three machine learning-derived methods (two novel and one adapted) to predict for every known Babesia bovis, Babesia bigemina, and Babesia canis protein the probability of being an exportome member. Two well-studied apicomplexan-related species, Plasmodium falciparum and Toxoplasma gondii, with extensive experimental evidence on their exportome or excreted/secreted proteins were used as important benchmarks for the three methods. Based on 10-fold cross validation and multiple train–validation–test splits of training data, we expect that over 90% of the predicted probabilities accurately provide a secretory or non-secretory indicator. Only laboratory testing can verify that predicted high exportome membership probabilities are creditable exportome indicators. However, the presented methods at least provide those proteins most worthy of laboratory validation and will ultimately save time and money.</jats:p>
dc.language	en
dc.publisher	MDPI AG
dc.relation	http://purl.org/au-research/grants/arc/DP180102584
dc.relation.ispartof	Pathogens
dc.relation.isbasedon	10.3390/pathogens10060660
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	1107 Immunology, 1108 Medical Microbiology
dc.title	Applying Machine Learning to Predict the Exportome of Bovine and Canine Babesia Species That Cause Babesiosis
dc.type	Journal Article
utslib.citation.volume	10
utslib.for	1107 Immunology
utslib.for	1108 Medical Microbiology
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Strength - CHT - Health Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Life Sciences
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Centre for Health Technologies (CHT)
utslib.copyright.status	open_access	*
dc.date.updated	2021-06-04T01:58:25Z
pubs.issue	6
pubs.publication-status	Published online
pubs.volume	10
utslib.citation.issue	6

Abstract:

Babesia infection of red blood cells can cause a severe disease called babesiosis in susceptible hosts. Bovine babesiosis causes global economic loss to the beef and dairy cattle industries, and canine babesiosis is considered a clinically significant disease. Potential therapeutic targets against bovine and canine babesiosis include members of the exportome, i.e., those proteins exported from the parasite into the host red blood cell. We developed three machine learning-derived methods (two novel and one adapted) to predict for every known Babesia bovis, Babesia bigemina, and Babesia canis protein the probability of being an exportome member. Two well-studied apicomplexan-related species, Plasmodium falciparum and Toxoplasma gondii, with extensive experimental evidence on their exportome or excreted/secreted proteins were used as important benchmarks for the three methods. Based on 10-fold cross validation and multiple train–validation–test splits of training data, we expect that over 90% of the predicted probabilities accurately provide a secretory or non-secretory indicator. Only laboratory testing can verify that predicted high exportome membership probabilities are creditable exportome indicators. However, the presented methods at least provide those proteins most worthy of laboratory validation and will ultimately save time and money.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/149410