Loading…

PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences

Increasing evidence has proved that miRNA plays a significant role in biological progress. In order to understand the etiology and mechanisms of various diseases, it is necessary to identify the essential miRNAs. However, it is time-consuming and expensive to identify essential miRNAs by using tradi...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in medicine 2022-11, Vol.9, p.1015278-1015278
Main Authors: Yan, Cheng, Ding, Changsong, Duan, Guihua
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c442t-c8aa01004e9b7c7f4b1b6723fb85013c6450ea3159f43c264d3dac1509671b223
cites cdi_FETCH-LOGICAL-c442t-c8aa01004e9b7c7f4b1b6723fb85013c6450ea3159f43c264d3dac1509671b223
container_end_page 1015278
container_issue
container_start_page 1015278
container_title Frontiers in medicine
container_volume 9
creator Yan, Cheng
Ding, Changsong
Duan, Guihua
description Increasing evidence has proved that miRNA plays a significant role in biological progress. In order to understand the etiology and mechanisms of various diseases, it is necessary to identify the essential miRNAs. However, it is time-consuming and expensive to identify essential miRNAs by using traditional biological experiments. It is critical to develop computational methods to predict potential essential miRNAs. In this study, we provided a new computational method (called PMMS) to identify essential miRNAs by using multi-head self-attention and sequences. First, PMMS computes the statistic and structure features and extracts the static feature by concatenating them. Second, PMMS extracts the deep learning original feature (BiLSTM-based feature) by using bi-directional long short-term memory (BiLSTM) and pre-miRNA sequences. In addition, we further obtained the multi-head self-attention feature (MS-based feature) based on BiLSTM-based feature and multi-head self-attention mechanism. By considering the importance of the subsequence of pre-miRNA to the static feature of miRNA, we obtained the deep learning final feature (WA-based feature) based on the weighted attention mechanism. Finally, we concatenated WA-based feature and static feature as an input to the multilayer perceptron) model to predict essential miRNAs. We conducted five-fold cross-validation to evaluate the prediction performance of PMMS. The areas under the ROC curves (AUC), the F1-score, and accuracy (ACC) are used as performance metrics. From the experimental results, PMMS obtained best prediction performances (AUC: 0.9556, F1-score: 0.9030, and ACC: 0.9097). It also outperformed other compared methods. The experimental results also illustrated that PMMS is an effective method to identify essential miRNA.
doi_str_mv 10.3389/fmed.2022.1015278
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_583535f999fa429ca99734621765ba4b</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_583535f999fa429ca99734621765ba4b</doaj_id><sourcerecordid>2747008242</sourcerecordid><originalsourceid>FETCH-LOGICAL-c442t-c8aa01004e9b7c7f4b1b6723fb85013c6450ea3159f43c264d3dac1509671b223</originalsourceid><addsrcrecordid>eNpVkV1rFTEQhhdRsLT9Ad7tpTd7TCbJJvFCKEVrodXiB3ghhEl2ck7KftRkj-C_d7fnIPZqhnmHZz7eqnrF2UYIY9_EgboNMIANZ1yBNs-qEwDbNkaZH8__y19W56XcM8a4ACW5OKl-3t3efn1b32XqUpjTuK2pFBrnhH09pC-fLkrtsVBXT2M97Ps5NTvCri7Uxwbnee1cFQo7HFMZahxX8deexkDlrHoRsS90foyn1fcP779dfmxuPl9dX17cNEFKmJtgEBlnTJL1OugoPfetBhG9UcumoZWKEQqubJQiQCs70WHgitlWcw8gTqvrA7eb8N495DRg_uMmTO6xMOWtwzyn0JNTRiihorU2ogQb0FotZAtct8qj9Avr3YH1sPfLW8NyYcb-CfSpMqad206_ndVcGGAL4PURkKflD2V2QyqB-h5HmvbFgZaaMQNy3ZsfWkOeSskU_43hzK3OutVZtzrrjs6Kv4RWl0Y</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2747008242</pqid></control><display><type>article</type><title>PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences</title><source>PubMed Central</source><creator>Yan, Cheng ; Ding, Changsong ; Duan, Guihua</creator><creatorcontrib>Yan, Cheng ; Ding, Changsong ; Duan, Guihua</creatorcontrib><description>Increasing evidence has proved that miRNA plays a significant role in biological progress. In order to understand the etiology and mechanisms of various diseases, it is necessary to identify the essential miRNAs. However, it is time-consuming and expensive to identify essential miRNAs by using traditional biological experiments. It is critical to develop computational methods to predict potential essential miRNAs. In this study, we provided a new computational method (called PMMS) to identify essential miRNAs by using multi-head self-attention and sequences. First, PMMS computes the statistic and structure features and extracts the static feature by concatenating them. Second, PMMS extracts the deep learning original feature (BiLSTM-based feature) by using bi-directional long short-term memory (BiLSTM) and pre-miRNA sequences. In addition, we further obtained the multi-head self-attention feature (MS-based feature) based on BiLSTM-based feature and multi-head self-attention mechanism. By considering the importance of the subsequence of pre-miRNA to the static feature of miRNA, we obtained the deep learning final feature (WA-based feature) based on the weighted attention mechanism. Finally, we concatenated WA-based feature and static feature as an input to the multilayer perceptron) model to predict essential miRNAs. We conducted five-fold cross-validation to evaluate the prediction performance of PMMS. The areas under the ROC curves (AUC), the F1-score, and accuracy (ACC) are used as performance metrics. From the experimental results, PMMS obtained best prediction performances (AUC: 0.9556, F1-score: 0.9030, and ACC: 0.9097). It also outperformed other compared methods. The experimental results also illustrated that PMMS is an effective method to identify essential miRNA.</description><identifier>ISSN: 2296-858X</identifier><identifier>EISSN: 2296-858X</identifier><identifier>DOI: 10.3389/fmed.2022.1015278</identifier><language>eng</language><publisher>Frontiers Media S.A</publisher><subject>bi-directional long short-term memory ; deep learning ; essential miRNA ; Medicine ; microRNA ; multi-head self-attention mechanism</subject><ispartof>Frontiers in medicine, 2022-11, Vol.9, p.1015278-1015278</ispartof><rights>Copyright © 2022 Yan, Ding and Duan. 2022 Yan, Ding and Duan</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c442t-c8aa01004e9b7c7f4b1b6723fb85013c6450ea3159f43c264d3dac1509671b223</citedby><cites>FETCH-LOGICAL-c442t-c8aa01004e9b7c7f4b1b6723fb85013c6450ea3159f43c264d3dac1509671b223</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9713820/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9713820/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,881,27903,27904,53769,53771</link.rule.ids></links><search><creatorcontrib>Yan, Cheng</creatorcontrib><creatorcontrib>Ding, Changsong</creatorcontrib><creatorcontrib>Duan, Guihua</creatorcontrib><title>PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences</title><title>Frontiers in medicine</title><description>Increasing evidence has proved that miRNA plays a significant role in biological progress. In order to understand the etiology and mechanisms of various diseases, it is necessary to identify the essential miRNAs. However, it is time-consuming and expensive to identify essential miRNAs by using traditional biological experiments. It is critical to develop computational methods to predict potential essential miRNAs. In this study, we provided a new computational method (called PMMS) to identify essential miRNAs by using multi-head self-attention and sequences. First, PMMS computes the statistic and structure features and extracts the static feature by concatenating them. Second, PMMS extracts the deep learning original feature (BiLSTM-based feature) by using bi-directional long short-term memory (BiLSTM) and pre-miRNA sequences. In addition, we further obtained the multi-head self-attention feature (MS-based feature) based on BiLSTM-based feature and multi-head self-attention mechanism. By considering the importance of the subsequence of pre-miRNA to the static feature of miRNA, we obtained the deep learning final feature (WA-based feature) based on the weighted attention mechanism. Finally, we concatenated WA-based feature and static feature as an input to the multilayer perceptron) model to predict essential miRNAs. We conducted five-fold cross-validation to evaluate the prediction performance of PMMS. The areas under the ROC curves (AUC), the F1-score, and accuracy (ACC) are used as performance metrics. From the experimental results, PMMS obtained best prediction performances (AUC: 0.9556, F1-score: 0.9030, and ACC: 0.9097). It also outperformed other compared methods. The experimental results also illustrated that PMMS is an effective method to identify essential miRNA.</description><subject>bi-directional long short-term memory</subject><subject>deep learning</subject><subject>essential miRNA</subject><subject>Medicine</subject><subject>microRNA</subject><subject>multi-head self-attention mechanism</subject><issn>2296-858X</issn><issn>2296-858X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNpVkV1rFTEQhhdRsLT9Ad7tpTd7TCbJJvFCKEVrodXiB3ghhEl2ck7KftRkj-C_d7fnIPZqhnmHZz7eqnrF2UYIY9_EgboNMIANZ1yBNs-qEwDbNkaZH8__y19W56XcM8a4ACW5OKl-3t3efn1b32XqUpjTuK2pFBrnhH09pC-fLkrtsVBXT2M97Ps5NTvCri7Uxwbnee1cFQo7HFMZahxX8deexkDlrHoRsS90foyn1fcP779dfmxuPl9dX17cNEFKmJtgEBlnTJL1OugoPfetBhG9UcumoZWKEQqubJQiQCs70WHgitlWcw8gTqvrA7eb8N495DRg_uMmTO6xMOWtwzyn0JNTRiihorU2ogQb0FotZAtct8qj9Avr3YH1sPfLW8NyYcb-CfSpMqad206_ndVcGGAL4PURkKflD2V2QyqB-h5HmvbFgZaaMQNy3ZsfWkOeSskU_43hzK3OutVZtzrrjs6Kv4RWl0Y</recordid><startdate>20221117</startdate><enddate>20221117</enddate><creator>Yan, Cheng</creator><creator>Ding, Changsong</creator><creator>Duan, Guihua</creator><general>Frontiers Media S.A</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope></search><sort><creationdate>20221117</creationdate><title>PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences</title><author>Yan, Cheng ; Ding, Changsong ; Duan, Guihua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c442t-c8aa01004e9b7c7f4b1b6723fb85013c6450ea3159f43c264d3dac1509671b223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>bi-directional long short-term memory</topic><topic>deep learning</topic><topic>essential miRNA</topic><topic>Medicine</topic><topic>microRNA</topic><topic>multi-head self-attention mechanism</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yan, Cheng</creatorcontrib><creatorcontrib>Ding, Changsong</creatorcontrib><creatorcontrib>Duan, Guihua</creatorcontrib><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Frontiers in medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yan, Cheng</au><au>Ding, Changsong</au><au>Duan, Guihua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences</atitle><jtitle>Frontiers in medicine</jtitle><date>2022-11-17</date><risdate>2022</risdate><volume>9</volume><spage>1015278</spage><epage>1015278</epage><pages>1015278-1015278</pages><issn>2296-858X</issn><eissn>2296-858X</eissn><abstract>Increasing evidence has proved that miRNA plays a significant role in biological progress. In order to understand the etiology and mechanisms of various diseases, it is necessary to identify the essential miRNAs. However, it is time-consuming and expensive to identify essential miRNAs by using traditional biological experiments. It is critical to develop computational methods to predict potential essential miRNAs. In this study, we provided a new computational method (called PMMS) to identify essential miRNAs by using multi-head self-attention and sequences. First, PMMS computes the statistic and structure features and extracts the static feature by concatenating them. Second, PMMS extracts the deep learning original feature (BiLSTM-based feature) by using bi-directional long short-term memory (BiLSTM) and pre-miRNA sequences. In addition, we further obtained the multi-head self-attention feature (MS-based feature) based on BiLSTM-based feature and multi-head self-attention mechanism. By considering the importance of the subsequence of pre-miRNA to the static feature of miRNA, we obtained the deep learning final feature (WA-based feature) based on the weighted attention mechanism. Finally, we concatenated WA-based feature and static feature as an input to the multilayer perceptron) model to predict essential miRNAs. We conducted five-fold cross-validation to evaluate the prediction performance of PMMS. The areas under the ROC curves (AUC), the F1-score, and accuracy (ACC) are used as performance metrics. From the experimental results, PMMS obtained best prediction performances (AUC: 0.9556, F1-score: 0.9030, and ACC: 0.9097). It also outperformed other compared methods. The experimental results also illustrated that PMMS is an effective method to identify essential miRNA.</abstract><pub>Frontiers Media S.A</pub><doi>10.3389/fmed.2022.1015278</doi><tpages>1</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2296-858X
ispartof Frontiers in medicine, 2022-11, Vol.9, p.1015278-1015278
issn 2296-858X
2296-858X
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_583535f999fa429ca99734621765ba4b
source PubMed Central
subjects bi-directional long short-term memory
deep learning
essential miRNA
Medicine
microRNA
multi-head self-attention mechanism
title PMMS: Predicting essential miRNAs based on multi-head self-attention mechanism and sequences
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T21%3A21%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=PMMS:%20Predicting%20essential%20miRNAs%20based%20on%20multi-head%20self-attention%20mechanism%20and%20sequences&rft.jtitle=Frontiers%20in%20medicine&rft.au=Yan,%20Cheng&rft.date=2022-11-17&rft.volume=9&rft.spage=1015278&rft.epage=1015278&rft.pages=1015278-1015278&rft.issn=2296-858X&rft.eissn=2296-858X&rft_id=info:doi/10.3389/fmed.2022.1015278&rft_dat=%3Cproquest_doaj_%3E2747008242%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c442t-c8aa01004e9b7c7f4b1b6723fb85013c6450ea3159f43c264d3dac1509671b223%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2747008242&rft_id=info:pmid/&rfr_iscdi=true