Predicting cross-tissue hormone-gene relations using balanced word embeddings
Inter-organ/inter-tissue communication is central to multi-cellular organisms including humans, and mapping inter-tissue interactions can advance system-level whole-body modeling efforts. Large volumes of biomedical literature have fostered studies that map within-tissue or tissue-agnostic interacti...
Gespeichert in:
Veröffentlicht in: | Bioinformatics (Oxford, England) England), 2022-10, Vol.38 (20), p.4771-4781 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 4781 |
---|---|
container_issue | 20 |
container_start_page | 4771 |
container_title | Bioinformatics (Oxford, England) |
container_volume | 38 |
creator | Jadhav, Aditya Kumar, Tarun Raghavendra, Mohit Loganathan, Tamizhini Narayanan, Manikandan |
description | Inter-organ/inter-tissue communication is central to multi-cellular organisms including humans, and mapping inter-tissue interactions can advance system-level whole-body modeling efforts. Large volumes of biomedical literature have fostered studies that map within-tissue or tissue-agnostic interactions, but literature-mining studies that infer inter-tissue relations, such as between hormones and genes are solely missing.
We present a first study to predict from biomedical literature the hormone-gene associations mediating inter-tissue signaling in the human body. Our BioEmbedS* models use neural network-based Biomedical word Embeddings with a Support Vector Machine classifier to predict if a hormone-gene pair is associated or not, and whether an associated gene is involved in the hormone's production or response. Model training relies on our unified dataset Hormone-Gene version 1 of ground-truth associations between genes and endocrine hormones, which we compiled and carefully balanced in the embedded space to handle data disparities, such as between poorly- versus well-studied hormones. Our BioEmbedS model recapitulates known gene mediators of tissue-tissue signaling with 70.4% accuracy; predicts novel inter-tissue communication genes in humans, which are enriched for hormone-related disorders; and generalizes well to mouse, thereby holding promise for its extension to other multi-cellular organisms as well.
Freely available at https://cross-tissue-signaling.herokuapp.com are our model predictions & datasets; https://github.com/BIRDSgroup/BioEmbedS has all relevant code.
Supplementary data are available at Bioinformatics online. |
doi_str_mv | 10.1093/bioinformatics/btac578 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9563690</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2706181185</sourcerecordid><originalsourceid>FETCH-LOGICAL-c414t-96f73d812526e4e311f78d3fae4934796acbdd8e950e45db54bf6b310bc2bab43</originalsourceid><addsrcrecordid>eNpVUctOwzAQtBAISuEXqhy5hNrxI8kFCSFeUhEc4Gz5sWmNkhjsBMTf49JSwWlXu7OzuzMIzQg-J7imc-286xsfOjU4E-d6UIaX1R6aECrKnFWE7O9yTI_QcYyvGGOOuThER1SkvOL1BD08BbDODK5fZib4GPPBxThCtkrcvod8CT1kAdq0x_cxG-MaqVWregM2-_TBZtBpsDbV4wk6aFQb4XQbp-jl5vr56i5fPN7eX10ucsMIG_JaNCW1FSl4IYABJaQpK0sbBaymrKyFMtraCmqOgXGrOdON0JRgbQqtNKNTdLHhfRt1B9ZAPwTVyrfgOhW-pFdO_u_0biWX_kPWXFBR40RwtiUI_n2EOMjORQNtegv8GGVRYkGSiBVPULGB_sgToNmtIViuvZD_vZBbL9Lg7O-Ru7Ff8ek3vOWOgA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2706181185</pqid></control><display><type>article</type><title>Predicting cross-tissue hormone-gene relations using balanced word embeddings</title><source>MEDLINE</source><source>Oxford Journals Open Access Collection</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Alma/SFX Local Collection</source><creator>Jadhav, Aditya ; Kumar, Tarun ; Raghavendra, Mohit ; Loganathan, Tamizhini ; Narayanan, Manikandan</creator><contributor>Wren, Jonathan</contributor><creatorcontrib>Jadhav, Aditya ; Kumar, Tarun ; Raghavendra, Mohit ; Loganathan, Tamizhini ; Narayanan, Manikandan ; Wren, Jonathan</creatorcontrib><description>Inter-organ/inter-tissue communication is central to multi-cellular organisms including humans, and mapping inter-tissue interactions can advance system-level whole-body modeling efforts. Large volumes of biomedical literature have fostered studies that map within-tissue or tissue-agnostic interactions, but literature-mining studies that infer inter-tissue relations, such as between hormones and genes are solely missing.
We present a first study to predict from biomedical literature the hormone-gene associations mediating inter-tissue signaling in the human body. Our BioEmbedS* models use neural network-based Biomedical word Embeddings with a Support Vector Machine classifier to predict if a hormone-gene pair is associated or not, and whether an associated gene is involved in the hormone's production or response. Model training relies on our unified dataset Hormone-Gene version 1 of ground-truth associations between genes and endocrine hormones, which we compiled and carefully balanced in the embedded space to handle data disparities, such as between poorly- versus well-studied hormones. Our BioEmbedS model recapitulates known gene mediators of tissue-tissue signaling with 70.4% accuracy; predicts novel inter-tissue communication genes in humans, which are enriched for hormone-related disorders; and generalizes well to mouse, thereby holding promise for its extension to other multi-cellular organisms as well.
Freely available at https://cross-tissue-signaling.herokuapp.com are our model predictions & datasets; https://github.com/BIRDSgroup/BioEmbedS has all relevant code.
Supplementary data are available at Bioinformatics online.</description><identifier>ISSN: 1367-4803</identifier><identifier>EISSN: 1367-4811</identifier><identifier>DOI: 10.1093/bioinformatics/btac578</identifier><identifier>PMID: 36000859</identifier><language>eng</language><publisher>England: Oxford University Press</publisher><subject>Animals ; Hormones ; Humans ; Mice ; Neural Networks, Computer ; Original Papers</subject><ispartof>Bioinformatics (Oxford, England), 2022-10, Vol.38 (20), p.4771-4781</ispartof><rights>The Author(s) 2022. Published by Oxford University Press.</rights><rights>The Author(s) 2022. Published by Oxford University Press. 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c414t-96f73d812526e4e311f78d3fae4934796acbdd8e950e45db54bf6b310bc2bab43</citedby><cites>FETCH-LOGICAL-c414t-96f73d812526e4e311f78d3fae4934796acbdd8e950e45db54bf6b310bc2bab43</cites><orcidid>0000-0002-8490-4087</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/PMC9563690/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9563690/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/36000859$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><contributor>Wren, Jonathan</contributor><creatorcontrib>Jadhav, Aditya</creatorcontrib><creatorcontrib>Kumar, Tarun</creatorcontrib><creatorcontrib>Raghavendra, Mohit</creatorcontrib><creatorcontrib>Loganathan, Tamizhini</creatorcontrib><creatorcontrib>Narayanan, Manikandan</creatorcontrib><title>Predicting cross-tissue hormone-gene relations using balanced word embeddings</title><title>Bioinformatics (Oxford, England)</title><addtitle>Bioinformatics</addtitle><description>Inter-organ/inter-tissue communication is central to multi-cellular organisms including humans, and mapping inter-tissue interactions can advance system-level whole-body modeling efforts. Large volumes of biomedical literature have fostered studies that map within-tissue or tissue-agnostic interactions, but literature-mining studies that infer inter-tissue relations, such as between hormones and genes are solely missing.
We present a first study to predict from biomedical literature the hormone-gene associations mediating inter-tissue signaling in the human body. Our BioEmbedS* models use neural network-based Biomedical word Embeddings with a Support Vector Machine classifier to predict if a hormone-gene pair is associated or not, and whether an associated gene is involved in the hormone's production or response. Model training relies on our unified dataset Hormone-Gene version 1 of ground-truth associations between genes and endocrine hormones, which we compiled and carefully balanced in the embedded space to handle data disparities, such as between poorly- versus well-studied hormones. Our BioEmbedS model recapitulates known gene mediators of tissue-tissue signaling with 70.4% accuracy; predicts novel inter-tissue communication genes in humans, which are enriched for hormone-related disorders; and generalizes well to mouse, thereby holding promise for its extension to other multi-cellular organisms as well.
Freely available at https://cross-tissue-signaling.herokuapp.com are our model predictions & datasets; https://github.com/BIRDSgroup/BioEmbedS has all relevant code.
Supplementary data are available at Bioinformatics online.</description><subject>Animals</subject><subject>Hormones</subject><subject>Humans</subject><subject>Mice</subject><subject>Neural Networks, Computer</subject><subject>Original Papers</subject><issn>1367-4803</issn><issn>1367-4811</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNpVUctOwzAQtBAISuEXqhy5hNrxI8kFCSFeUhEc4Gz5sWmNkhjsBMTf49JSwWlXu7OzuzMIzQg-J7imc-286xsfOjU4E-d6UIaX1R6aECrKnFWE7O9yTI_QcYyvGGOOuThER1SkvOL1BD08BbDODK5fZib4GPPBxThCtkrcvod8CT1kAdq0x_cxG-MaqVWregM2-_TBZtBpsDbV4wk6aFQb4XQbp-jl5vr56i5fPN7eX10ucsMIG_JaNCW1FSl4IYABJaQpK0sbBaymrKyFMtraCmqOgXGrOdON0JRgbQqtNKNTdLHhfRt1B9ZAPwTVyrfgOhW-pFdO_u_0biWX_kPWXFBR40RwtiUI_n2EOMjORQNtegv8GGVRYkGSiBVPULGB_sgToNmtIViuvZD_vZBbL9Lg7O-Ru7Ff8ek3vOWOgA</recordid><startdate>20221014</startdate><enddate>20221014</enddate><creator>Jadhav, Aditya</creator><creator>Kumar, Tarun</creator><creator>Raghavendra, Mohit</creator><creator>Loganathan, Tamizhini</creator><creator>Narayanan, Manikandan</creator><general>Oxford University Press</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-8490-4087</orcidid></search><sort><creationdate>20221014</creationdate><title>Predicting cross-tissue hormone-gene relations using balanced word embeddings</title><author>Jadhav, Aditya ; Kumar, Tarun ; Raghavendra, Mohit ; Loganathan, Tamizhini ; Narayanan, Manikandan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c414t-96f73d812526e4e311f78d3fae4934796acbdd8e950e45db54bf6b310bc2bab43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Animals</topic><topic>Hormones</topic><topic>Humans</topic><topic>Mice</topic><topic>Neural Networks, Computer</topic><topic>Original Papers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jadhav, Aditya</creatorcontrib><creatorcontrib>Kumar, Tarun</creatorcontrib><creatorcontrib>Raghavendra, Mohit</creatorcontrib><creatorcontrib>Loganathan, Tamizhini</creatorcontrib><creatorcontrib>Narayanan, Manikandan</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Bioinformatics (Oxford, England)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jadhav, Aditya</au><au>Kumar, Tarun</au><au>Raghavendra, Mohit</au><au>Loganathan, Tamizhini</au><au>Narayanan, Manikandan</au><au>Wren, Jonathan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting cross-tissue hormone-gene relations using balanced word embeddings</atitle><jtitle>Bioinformatics (Oxford, England)</jtitle><addtitle>Bioinformatics</addtitle><date>2022-10-14</date><risdate>2022</risdate><volume>38</volume><issue>20</issue><spage>4771</spage><epage>4781</epage><pages>4771-4781</pages><issn>1367-4803</issn><eissn>1367-4811</eissn><abstract>Inter-organ/inter-tissue communication is central to multi-cellular organisms including humans, and mapping inter-tissue interactions can advance system-level whole-body modeling efforts. Large volumes of biomedical literature have fostered studies that map within-tissue or tissue-agnostic interactions, but literature-mining studies that infer inter-tissue relations, such as between hormones and genes are solely missing.
We present a first study to predict from biomedical literature the hormone-gene associations mediating inter-tissue signaling in the human body. Our BioEmbedS* models use neural network-based Biomedical word Embeddings with a Support Vector Machine classifier to predict if a hormone-gene pair is associated or not, and whether an associated gene is involved in the hormone's production or response. Model training relies on our unified dataset Hormone-Gene version 1 of ground-truth associations between genes and endocrine hormones, which we compiled and carefully balanced in the embedded space to handle data disparities, such as between poorly- versus well-studied hormones. Our BioEmbedS model recapitulates known gene mediators of tissue-tissue signaling with 70.4% accuracy; predicts novel inter-tissue communication genes in humans, which are enriched for hormone-related disorders; and generalizes well to mouse, thereby holding promise for its extension to other multi-cellular organisms as well.
Freely available at https://cross-tissue-signaling.herokuapp.com are our model predictions & datasets; https://github.com/BIRDSgroup/BioEmbedS has all relevant code.
Supplementary data are available at Bioinformatics online.</abstract><cop>England</cop><pub>Oxford University Press</pub><pmid>36000859</pmid><doi>10.1093/bioinformatics/btac578</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-8490-4087</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1367-4803 |
ispartof | Bioinformatics (Oxford, England), 2022-10, Vol.38 (20), p.4771-4781 |
issn | 1367-4803 1367-4811 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9563690 |
source | MEDLINE; Oxford Journals Open Access Collection; EZB-FREE-00999 freely available EZB journals; PubMed Central; Alma/SFX Local Collection |
subjects | Animals Hormones Humans Mice Neural Networks, Computer Original Papers |
title | Predicting cross-tissue hormone-gene relations using balanced word embeddings |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T01%3A52%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predicting%20cross-tissue%20hormone-gene%20relations%20using%20balanced%20word%20embeddings&rft.jtitle=Bioinformatics%20(Oxford,%20England)&rft.au=Jadhav,%20Aditya&rft.date=2022-10-14&rft.volume=38&rft.issue=20&rft.spage=4771&rft.epage=4781&rft.pages=4771-4781&rft.issn=1367-4803&rft.eissn=1367-4811&rft_id=info:doi/10.1093/bioinformatics/btac578&rft_dat=%3Cproquest_pubme%3E2706181185%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2706181185&rft_id=info:pmid/36000859&rfr_iscdi=true |