Text mining-based word representations for biomedical data analysis and protein-protein interaction networks in machine learning tasks

Biomedical and life science literature is an essential way to publish experimental results. With the rapid growth of the number of new publications, the amount of scientific knowledge represented in free text is increasing remarkably. There has been much interest in developing techniques that can ex...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PloS one 2021-10, Vol.16 (10), p.e0258623-e0258623
Hauptverfasser: Alachram, Halima, Chereda, Hryhorii, Beißbarth, Tim, Wingender, Edgar, Stegmaier, Philip
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page e0258623
container_issue 10
container_start_page e0258623
container_title PloS one
container_volume 16
creator Alachram, Halima
Chereda, Hryhorii
Beißbarth, Tim
Wingender, Edgar
Stegmaier, Philip
description Biomedical and life science literature is an essential way to publish experimental results. With the rapid growth of the number of new publications, the amount of scientific knowledge represented in free text is increasing remarkably. There has been much interest in developing techniques that can extract this knowledge and make it accessible to aid scientists in discovering new relationships between biological entities and answering biological questions. Making use of the word2vec approach, we generated word vector representations based on a corpus consisting of over 16 million PubMed abstracts. We developed a text mining pipeline to produce word2vec embeddings with different properties and performed validation experiments to assess their utility for biomedical analysis. An important pre-processing step consisted in the substitution of synonymous terms by their preferred terms in biomedical databases. Furthermore, we extracted gene-gene networks from two embedding versions and used them as prior knowledge to train Graph-Convolutional Neural Networks (CNNs) on large breast cancer gene expression data and on other cancer datasets. Performances of resulting models were compared to Graph-CNNs trained with protein-protein interaction (PPI) networks or with networks derived using other word embedding algorithms. We also assessed the effect of corpus size on the variability of word representations. Finally, we created a web service with a graphical and a RESTful interface to extract and explore relations between biomedical terms using annotated embeddings. Comparisons to biological databases showed that relations between entities such as known PPIs, signaling pathways and cellular functions, or narrower disease ontology groups correlated with higher cosine similarity. Graph-CNNs trained with word2vec-embedding-derived networks performed sufficiently good for the metastatic event prediction tasks compared to other networks. Such performance was good enough to validate the utility of our generated word embeddings in constructing biological networks. Word representations as produced by text mining algorithms like word2vec, therefore are able to capture biologically meaningful relations between entities. Our generated embeddings are publicly available at
doi_str_mv 10.1371/journal.pone.0258623
format Article
fullrecord <record><control><sourceid>gale_plos_</sourceid><recordid>TN_cdi_plos_journals_2582406916</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A679077331</galeid><doaj_id>oai_doaj_org_article_72ddc5ce3d944699be3e4b096cf57a7a</doaj_id><sourcerecordid>A679077331</sourcerecordid><originalsourceid>FETCH-LOGICAL-c735t-f321fff9eefc513b2e818e95b59402a73787e61de482f9854ec4ed11725fe1203</originalsourceid><addsrcrecordid>eNqNk9-K1DAUxoso7rr6BoIBQfSiY5M0bXMjLIt_BhYWdPU2pOnJTGbbZDZJ1X0Bn9t0p8pW9kJykXDyO99JPs7Jsue4WGFa47c7N3or-9XeWVgVhDUVoQ-yY8wpyStS0Id3zkfZkxB2RcFoU1WPsyNaVowSUh5nvy7hZ0SDscZu8lYG6NAP5zvkYe8hgI0yGmcD0s6j1rgBOqNkjzoZJZKp_E0wIR06tPcugrH5vCNjI3ippmxkISbRq5CCaJBqayygHqSfiqIow1V4mj3Ssg_wbN5Psq8f3l-efcrPLz6uz07Pc1VTFnNNCdZacwCtGKYtgQY3wFnLeFkQWdO6qaHCHZQN0bxhJagSOoxrwjTgZMRJ9uKgu-9dELOFQST3SFlUHFeJWB-Izsmd2HszSH8jnDTiNuD8RkgfjepB1KTrFFNAO16WFectUCjbgldKs1rWMmm9m6uNbXJOJTu97BeiyxtrtmLjvouGYV4ymgRezwLeXY8QohhMUND30oIbD-9uCt5UOKEv_0Hv_91MbWT6gLHapbpqEhWnVc2LuqZ00lrdQ6XVwWBU6jdtUnyR8GaRkJiY-mojxxDE-svn_2cvvi3ZV3fYLcg-boPrx9ueXILlAVTeheBB_zUZF2Ialz9uiGlcxDwu9DdlpQkb</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2582406916</pqid></control><display><type>article</type><title>Text mining-based word representations for biomedical data analysis and protein-protein interaction networks in machine learning tasks</title><source>DOAJ Directory of Open Access Journals</source><source>Public Library of Science (PLoS) Journals Open Access</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Free Full-Text Journals in Chemistry</source><creator>Alachram, Halima ; Chereda, Hryhorii ; Beißbarth, Tim ; Wingender, Edgar ; Stegmaier, Philip</creator><contributor>Le, Khanh N.Q.</contributor><creatorcontrib>Alachram, Halima ; Chereda, Hryhorii ; Beißbarth, Tim ; Wingender, Edgar ; Stegmaier, Philip ; Le, Khanh N.Q.</creatorcontrib><description>Biomedical and life science literature is an essential way to publish experimental results. With the rapid growth of the number of new publications, the amount of scientific knowledge represented in free text is increasing remarkably. There has been much interest in developing techniques that can extract this knowledge and make it accessible to aid scientists in discovering new relationships between biological entities and answering biological questions. Making use of the word2vec approach, we generated word vector representations based on a corpus consisting of over 16 million PubMed abstracts. We developed a text mining pipeline to produce word2vec embeddings with different properties and performed validation experiments to assess their utility for biomedical analysis. An important pre-processing step consisted in the substitution of synonymous terms by their preferred terms in biomedical databases. Furthermore, we extracted gene-gene networks from two embedding versions and used them as prior knowledge to train Graph-Convolutional Neural Networks (CNNs) on large breast cancer gene expression data and on other cancer datasets. Performances of resulting models were compared to Graph-CNNs trained with protein-protein interaction (PPI) networks or with networks derived using other word embedding algorithms. We also assessed the effect of corpus size on the variability of word representations. Finally, we created a web service with a graphical and a RESTful interface to extract and explore relations between biomedical terms using annotated embeddings. Comparisons to biological databases showed that relations between entities such as known PPIs, signaling pathways and cellular functions, or narrower disease ontology groups correlated with higher cosine similarity. Graph-CNNs trained with word2vec-embedding-derived networks performed sufficiently good for the metastatic event prediction tasks compared to other networks. Such performance was good enough to validate the utility of our generated word embeddings in constructing biological networks. Word representations as produced by text mining algorithms like word2vec, therefore are able to capture biologically meaningful relations between entities. Our generated embeddings are publicly available at</description><identifier>ISSN: 1932-6203</identifier><identifier>EISSN: 1932-6203</identifier><identifier>DOI: 10.1371/journal.pone.0258623</identifier><identifier>PMID: 34653224</identifier><language>eng</language><publisher>San Francisco: Public Library of Science</publisher><subject>Algorithms ; Analysis ; Artificial neural networks ; Bioinformatics ; Biology and Life Sciences ; Biomedical data ; Biomedical research ; Breast cancer ; Cognitive tasks ; Computational linguistics ; Computer and Information Sciences ; Data analysis ; Data collection ; Data mining ; Data processing ; Datasets ; Embedding ; Gene expression ; Information management ; Knowledge ; Knowledge representation ; Language processing ; Learning algorithms ; Machine learning ; Medicine and Health Sciences ; Metastases ; Natural language ; Natural language interfaces ; Neural networks ; Physical Sciences ; Protein interaction ; Protein-protein interactions ; Proteins ; Scientific papers ; Semantics ; Trigonometric functions ; Web services</subject><ispartof>PloS one, 2021-10, Vol.16 (10), p.e0258623-e0258623</ispartof><rights>COPYRIGHT 2021 Public Library of Science</rights><rights>2021 Alachram et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 Alachram et al 2021 Alachram et al</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c735t-f321fff9eefc513b2e818e95b59402a73787e61de482f9854ec4ed11725fe1203</citedby><cites>FETCH-LOGICAL-c735t-f321fff9eefc513b2e818e95b59402a73787e61de482f9854ec4ed11725fe1203</cites><orcidid>0000-0002-4567-0775</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8519453/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8519453/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,864,885,2102,2928,23866,27924,27925,53791,53793,79600,79601</link.rule.ids></links><search><contributor>Le, Khanh N.Q.</contributor><creatorcontrib>Alachram, Halima</creatorcontrib><creatorcontrib>Chereda, Hryhorii</creatorcontrib><creatorcontrib>Beißbarth, Tim</creatorcontrib><creatorcontrib>Wingender, Edgar</creatorcontrib><creatorcontrib>Stegmaier, Philip</creatorcontrib><title>Text mining-based word representations for biomedical data analysis and protein-protein interaction networks in machine learning tasks</title><title>PloS one</title><description>Biomedical and life science literature is an essential way to publish experimental results. With the rapid growth of the number of new publications, the amount of scientific knowledge represented in free text is increasing remarkably. There has been much interest in developing techniques that can extract this knowledge and make it accessible to aid scientists in discovering new relationships between biological entities and answering biological questions. Making use of the word2vec approach, we generated word vector representations based on a corpus consisting of over 16 million PubMed abstracts. We developed a text mining pipeline to produce word2vec embeddings with different properties and performed validation experiments to assess their utility for biomedical analysis. An important pre-processing step consisted in the substitution of synonymous terms by their preferred terms in biomedical databases. Furthermore, we extracted gene-gene networks from two embedding versions and used them as prior knowledge to train Graph-Convolutional Neural Networks (CNNs) on large breast cancer gene expression data and on other cancer datasets. Performances of resulting models were compared to Graph-CNNs trained with protein-protein interaction (PPI) networks or with networks derived using other word embedding algorithms. We also assessed the effect of corpus size on the variability of word representations. Finally, we created a web service with a graphical and a RESTful interface to extract and explore relations between biomedical terms using annotated embeddings. Comparisons to biological databases showed that relations between entities such as known PPIs, signaling pathways and cellular functions, or narrower disease ontology groups correlated with higher cosine similarity. Graph-CNNs trained with word2vec-embedding-derived networks performed sufficiently good for the metastatic event prediction tasks compared to other networks. Such performance was good enough to validate the utility of our generated word embeddings in constructing biological networks. Word representations as produced by text mining algorithms like word2vec, therefore are able to capture biologically meaningful relations between entities. Our generated embeddings are publicly available at</description><subject>Algorithms</subject><subject>Analysis</subject><subject>Artificial neural networks</subject><subject>Bioinformatics</subject><subject>Biology and Life Sciences</subject><subject>Biomedical data</subject><subject>Biomedical research</subject><subject>Breast cancer</subject><subject>Cognitive tasks</subject><subject>Computational linguistics</subject><subject>Computer and Information Sciences</subject><subject>Data analysis</subject><subject>Data collection</subject><subject>Data mining</subject><subject>Data processing</subject><subject>Datasets</subject><subject>Embedding</subject><subject>Gene expression</subject><subject>Information management</subject><subject>Knowledge</subject><subject>Knowledge representation</subject><subject>Language processing</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Medicine and Health Sciences</subject><subject>Metastases</subject><subject>Natural language</subject><subject>Natural language interfaces</subject><subject>Neural networks</subject><subject>Physical Sciences</subject><subject>Protein interaction</subject><subject>Protein-protein interactions</subject><subject>Proteins</subject><subject>Scientific papers</subject><subject>Semantics</subject><subject>Trigonometric functions</subject><subject>Web services</subject><issn>1932-6203</issn><issn>1932-6203</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><sourceid>DOA</sourceid><recordid>eNqNk9-K1DAUxoso7rr6BoIBQfSiY5M0bXMjLIt_BhYWdPU2pOnJTGbbZDZJ1X0Bn9t0p8pW9kJykXDyO99JPs7Jsue4WGFa47c7N3or-9XeWVgVhDUVoQ-yY8wpyStS0Id3zkfZkxB2RcFoU1WPsyNaVowSUh5nvy7hZ0SDscZu8lYG6NAP5zvkYe8hgI0yGmcD0s6j1rgBOqNkjzoZJZKp_E0wIR06tPcugrH5vCNjI3ippmxkISbRq5CCaJBqayygHqSfiqIow1V4mj3Ssg_wbN5Psq8f3l-efcrPLz6uz07Pc1VTFnNNCdZacwCtGKYtgQY3wFnLeFkQWdO6qaHCHZQN0bxhJagSOoxrwjTgZMRJ9uKgu-9dELOFQST3SFlUHFeJWB-Izsmd2HszSH8jnDTiNuD8RkgfjepB1KTrFFNAO16WFectUCjbgldKs1rWMmm9m6uNbXJOJTu97BeiyxtrtmLjvouGYV4ymgRezwLeXY8QohhMUND30oIbD-9uCt5UOKEv_0Hv_91MbWT6gLHapbpqEhWnVc2LuqZ00lrdQ6XVwWBU6jdtUnyR8GaRkJiY-mojxxDE-svn_2cvvi3ZV3fYLcg-boPrx9ueXILlAVTeheBB_zUZF2Ialz9uiGlcxDwu9DdlpQkb</recordid><startdate>20211015</startdate><enddate>20211015</enddate><creator>Alachram, Halima</creator><creator>Chereda, Hryhorii</creator><creator>Beißbarth, Tim</creator><creator>Wingender, Edgar</creator><creator>Stegmaier, Philip</creator><general>Public Library of Science</general><general>Public Library of Science (PLoS)</general><scope>AAYXX</scope><scope>CITATION</scope><scope>IOV</scope><scope>ISR</scope><scope>3V.</scope><scope>7QG</scope><scope>7QL</scope><scope>7QO</scope><scope>7RV</scope><scope>7SN</scope><scope>7SS</scope><scope>7T5</scope><scope>7TG</scope><scope>7TM</scope><scope>7U9</scope><scope>7X2</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</scope><scope>8C1</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>H94</scope><scope>HCIFZ</scope><scope>K9.</scope><scope>KB.</scope><scope>KB0</scope><scope>KL.</scope><scope>L6V</scope><scope>LK8</scope><scope>M0K</scope><scope>M0S</scope><scope>M1P</scope><scope>M7N</scope><scope>M7P</scope><scope>M7S</scope><scope>NAPCQ</scope><scope>P5Z</scope><scope>P62</scope><scope>P64</scope><scope>PATMY</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>PYCSY</scope><scope>RC3</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-4567-0775</orcidid></search><sort><creationdate>20211015</creationdate><title>Text mining-based word representations for biomedical data analysis and protein-protein interaction networks in machine learning tasks</title><author>Alachram, Halima ; Chereda, Hryhorii ; Beißbarth, Tim ; Wingender, Edgar ; Stegmaier, Philip</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c735t-f321fff9eefc513b2e818e95b59402a73787e61de482f9854ec4ed11725fe1203</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Analysis</topic><topic>Artificial neural networks</topic><topic>Bioinformatics</topic><topic>Biology and Life Sciences</topic><topic>Biomedical data</topic><topic>Biomedical research</topic><topic>Breast cancer</topic><topic>Cognitive tasks</topic><topic>Computational linguistics</topic><topic>Computer and Information Sciences</topic><topic>Data analysis</topic><topic>Data collection</topic><topic>Data mining</topic><topic>Data processing</topic><topic>Datasets</topic><topic>Embedding</topic><topic>Gene expression</topic><topic>Information management</topic><topic>Knowledge</topic><topic>Knowledge representation</topic><topic>Language processing</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Medicine and Health Sciences</topic><topic>Metastases</topic><topic>Natural language</topic><topic>Natural language interfaces</topic><topic>Neural networks</topic><topic>Physical Sciences</topic><topic>Protein interaction</topic><topic>Protein-protein interactions</topic><topic>Proteins</topic><topic>Scientific papers</topic><topic>Semantics</topic><topic>Trigonometric functions</topic><topic>Web services</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Alachram, Halima</creatorcontrib><creatorcontrib>Chereda, Hryhorii</creatorcontrib><creatorcontrib>Beißbarth, Tim</creatorcontrib><creatorcontrib>Wingender, Edgar</creatorcontrib><creatorcontrib>Stegmaier, Philip</creatorcontrib><collection>CrossRef</collection><collection>Gale In Context: Opposing Viewpoints</collection><collection>Gale In Context: Science</collection><collection>ProQuest Central (Corporate)</collection><collection>Animal Behavior Abstracts</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Biotechnology Research Abstracts</collection><collection>Nursing &amp; Allied Health Database</collection><collection>Ecology Abstracts</collection><collection>Entomology Abstracts (Full archive)</collection><collection>Immunology Abstracts</collection><collection>Meteorological &amp; Geoastrophysical Abstracts</collection><collection>Nucleic Acids Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Agricultural Science Collection</collection><collection>Health &amp; Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Public Health Database</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>Agricultural &amp; Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Materials Science Database</collection><collection>Nursing &amp; Allied Health Database (Alumni Edition)</collection><collection>Meteorological &amp; Geoastrophysical Abstracts - Academic</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest Biological Science Collection</collection><collection>Agricultural Science Database</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Algology Mycology and Protozoology Abstracts (Microbiology C)</collection><collection>Biological Science Database</collection><collection>Engineering Database</collection><collection>Nursing &amp; Allied Health Premium</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Environmental Science Database</collection><collection>Materials Science Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>Environmental Science Collection</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>PloS one</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Alachram, Halima</au><au>Chereda, Hryhorii</au><au>Beißbarth, Tim</au><au>Wingender, Edgar</au><au>Stegmaier, Philip</au><au>Le, Khanh N.Q.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Text mining-based word representations for biomedical data analysis and protein-protein interaction networks in machine learning tasks</atitle><jtitle>PloS one</jtitle><date>2021-10-15</date><risdate>2021</risdate><volume>16</volume><issue>10</issue><spage>e0258623</spage><epage>e0258623</epage><pages>e0258623-e0258623</pages><issn>1932-6203</issn><eissn>1932-6203</eissn><abstract>Biomedical and life science literature is an essential way to publish experimental results. With the rapid growth of the number of new publications, the amount of scientific knowledge represented in free text is increasing remarkably. There has been much interest in developing techniques that can extract this knowledge and make it accessible to aid scientists in discovering new relationships between biological entities and answering biological questions. Making use of the word2vec approach, we generated word vector representations based on a corpus consisting of over 16 million PubMed abstracts. We developed a text mining pipeline to produce word2vec embeddings with different properties and performed validation experiments to assess their utility for biomedical analysis. An important pre-processing step consisted in the substitution of synonymous terms by their preferred terms in biomedical databases. Furthermore, we extracted gene-gene networks from two embedding versions and used them as prior knowledge to train Graph-Convolutional Neural Networks (CNNs) on large breast cancer gene expression data and on other cancer datasets. Performances of resulting models were compared to Graph-CNNs trained with protein-protein interaction (PPI) networks or with networks derived using other word embedding algorithms. We also assessed the effect of corpus size on the variability of word representations. Finally, we created a web service with a graphical and a RESTful interface to extract and explore relations between biomedical terms using annotated embeddings. Comparisons to biological databases showed that relations between entities such as known PPIs, signaling pathways and cellular functions, or narrower disease ontology groups correlated with higher cosine similarity. Graph-CNNs trained with word2vec-embedding-derived networks performed sufficiently good for the metastatic event prediction tasks compared to other networks. Such performance was good enough to validate the utility of our generated word embeddings in constructing biological networks. Word representations as produced by text mining algorithms like word2vec, therefore are able to capture biologically meaningful relations between entities. Our generated embeddings are publicly available at</abstract><cop>San Francisco</cop><pub>Public Library of Science</pub><pmid>34653224</pmid><doi>10.1371/journal.pone.0258623</doi><tpages>e0258623</tpages><orcidid>https://orcid.org/0000-0002-4567-0775</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1932-6203
ispartof PloS one, 2021-10, Vol.16 (10), p.e0258623-e0258623
issn 1932-6203
1932-6203
language eng
recordid cdi_plos_journals_2582406916
source DOAJ Directory of Open Access Journals; Public Library of Science (PLoS) Journals Open Access; EZB-FREE-00999 freely available EZB journals; PubMed Central; Free Full-Text Journals in Chemistry
subjects Algorithms
Analysis
Artificial neural networks
Bioinformatics
Biology and Life Sciences
Biomedical data
Biomedical research
Breast cancer
Cognitive tasks
Computational linguistics
Computer and Information Sciences
Data analysis
Data collection
Data mining
Data processing
Datasets
Embedding
Gene expression
Information management
Knowledge
Knowledge representation
Language processing
Learning algorithms
Machine learning
Medicine and Health Sciences
Metastases
Natural language
Natural language interfaces
Neural networks
Physical Sciences
Protein interaction
Protein-protein interactions
Proteins
Scientific papers
Semantics
Trigonometric functions
Web services
title Text mining-based word representations for biomedical data analysis and protein-protein interaction networks in machine learning tasks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T13%3A24%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_plos_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Text%20mining-based%20word%20representations%20for%20biomedical%20data%20analysis%20and%20protein-protein%20interaction%20networks%20in%20machine%20learning%20tasks&rft.jtitle=PloS%20one&rft.au=Alachram,%20Halima&rft.date=2021-10-15&rft.volume=16&rft.issue=10&rft.spage=e0258623&rft.epage=e0258623&rft.pages=e0258623-e0258623&rft.issn=1932-6203&rft.eissn=1932-6203&rft_id=info:doi/10.1371/journal.pone.0258623&rft_dat=%3Cgale_plos_%3EA679077331%3C/gale_plos_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2582406916&rft_id=info:pmid/34653224&rft_galeid=A679077331&rft_doaj_id=oai_doaj_org_article_72ddc5ce3d944699be3e4b096cf57a7a&rfr_iscdi=true