Show simple item record

dc.contributor.author
Manica, Matteo
dc.contributor.author
Mathis, Roland
dc.contributor.author
Cadow, Joris
dc.contributor.author
Rodríguez Martínez, María
dc.date.accessioned
2020-09-10T08:44:22Z
dc.date.available
2020-07-30T07:19:45Z
dc.date.available
2020-09-10T08:44:22Z
dc.date.issued
2019-04
dc.identifier.issn
2522-5839
dc.identifier.other
10.1038/s42256-019-0036-1
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/429154
dc.description.abstract
The number of biomedical publications has grown steadily in recent years. However, most biomedical facts are not readily available, but buried in the form of unstructured text. Here we present INtERAcT, an unsupervised method to extract interactions from a corpus of biomedical articles. INtERAcT exploits a vector representation of words, computed on a corpus of domain-specific knowledge, and implements a new metric that estimates an interaction score between two molecules in the space where the corresponding words are embedded. We use INtERAcT to reconstruct the molecular pathways of 10 different cancer types using corpora of disease-specific articles, considering the STRING database as a benchmark. Our metric outperforms currently adopted approaches and it is highly robust to parameter choices, leading to the identification of known molecular interactions in all studied cancer types. Furthermore, our approach does not require text annotation, manual curation or the definition of semantic rules based on expert knowledge, and can therefore be efficiently applied to different scientific domains.
en_US
dc.language.iso
en
en_US
dc.publisher
Nature Publishing Group
en_US
dc.title
Context-specific interaction networks from vector representation of words
en_US
dc.type
Journal Article
dc.date.published
2019-04-09
ethz.journal.title
Nature Machine Intelligence
ethz.journal.volume
1
en_US
ethz.journal.issue
4
en_US
ethz.journal.abbreviated
Nat Mach Intell
ethz.pages.start
181
en_US
ethz.pages.end
190
en_US
ethz.grant
PERSONALIZED ENGINE FOR CANCER INTEGRATIVE STUDY AND EVALUATION, a tool for cancer patient risk-stratification and pers. drug selection through multi-omic data integration.
en_US
ethz.identifier.scopus
ethz.publication.place
London
en_US
ethz.publication.status
published
en_US
ethz.grant.agreementno
668858
ethz.grant.fundername
SBFI
ethz.grant.funderDoi
10.13039/501100007352
ethz.grant.program
H2020
ethz.date.deposited
2020-07-30T07:19:54Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2020-09-10T08:44:33Z
ethz.rosetta.lastUpdated
2022-03-29T03:05:50Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Context-specific%20interaction%20networks%20from%20vector%20representation%20of%20words&rft.jtitle=Nature%20Machine%20Intelligence&rft.date=2019-04&rft.volume=1&rft.issue=4&rft.spage=181&rft.epage=190&rft.issn=2522-5839&rft.au=Manica,%20Matteo&Mathis,%20Roland&Cadow,%20Joris&Rodr%C3%ADguez%20Mart%C3%ADnez,%20Mar%C3%ADa&rft.genre=article&rft_id=info:doi/10.1038/s42256-019-0036-1&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record