Loading…
iDTi-CSsmoteB: Identification of Drug-Target Interaction Based on Drug Chemical Structure and Protein Sequence Using XGBoost With Over-Sampling Technique SMOTE
Identifying interaction between drug and protein is a crucial challenge in drug discovery, which can lead the researchers to develop novel drug compounds or new target proteins for the existing drugs. The determination of drug-target interactions (DTIs) is an extremely time-consuming, costly, and te...
Saved in:
Published in: | IEEE access 2019, Vol.7, p.48699-48714 |
---|---|
Main Authors: | , , , , , |
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-c408t-53ecff2cf1094687e902a5b37dd2751d4650c6e3d7002c90619325f6628f5b563 |
---|---|
cites | cdi_FETCH-LOGICAL-c408t-53ecff2cf1094687e902a5b37dd2751d4650c6e3d7002c90619325f6628f5b563 |
container_end_page | 48714 |
container_issue | |
container_start_page | 48699 |
container_title | IEEE access |
container_volume | 7 |
creator | Mahmud, S. M. Hasan Chen, Wenyu Jahan, Hosney Liu, Yongsheng Sujan, Nasir Islam Ahmed, Saeed |
description | Identifying interaction between drug and protein is a crucial challenge in drug discovery, which can lead the researchers to develop novel drug compounds or new target proteins for the existing drugs. The determination of drug-target interactions (DTIs) is an extremely time-consuming, costly, and tedious task with wet-lab experiments. To date, multiple computational techniques have been presented to simplify the drug discovery process, but a huge number of interactions are still undiscovered. Furthermore, a class imbalance is a critical challenge regarding this experiment which can significantly degrade the classification accuracy that has not been effectively addressed yet. In this paper, we proposed a novel high-throughput computational model, called iDTi-CSsmoteB, for identification of DTIs based on drug chemical structures and protein sequences. More specifically, the protein sequence is extracted through position-specific scoring matrix (PSSM)-Bigram, amphiphilic pseudo amino acid composition (AM-PseAAC) and dipeptide PseAAC descriptors which represents evolutionary and sequence information. The drug chemical structure is represented as a molecular substructure fingerprint (MSF) which describes the existence of the functional fragments or groups. Finally, we used the over-sampling SMOTE technique to overcome the imbalance issue of the datasets and applied XGBoost algorithm as a classifier to predict DTIs. To evaluate the performance of iDTi-CSsmoteB, several experiments have been conducted on four benchmark datasets, namely, enzyme, ion channel, GPCR, and nuclear receptor based on fivefold cross validation. The experimental analysis exhibits that our model outperforms similar methods in terms of area under the ROC (auROC) curve. In addition, our achieved results indicate the effectiveness of the feature extraction techniques, balancing methods, and classifier for predicting the DTIs which can provide substance for new drug development. iDTi-CSsmoteB webserver is available online at http://idticssmoteb-uestc.me/ . |
doi_str_mv | 10.1109/ACCESS.2019.2910277 |
format | article |
fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2455610815</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8686077</ieee_id><doaj_id>oai_doaj_org_article_bf50c48bca5b402e82f24cb14def2c44</doaj_id><sourcerecordid>2455610815</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-53ecff2cf1094687e902a5b37dd2751d4650c6e3d7002c90619325f6628f5b563</originalsourceid><addsrcrecordid>eNpNUV1r2zAUNWOFlq6_oC-CPTuTZEm299a4WRfoyMAu7ZuQ5atEIbEySR7s1-yvTqlLmV50ufeccz9Olt0SvCAE11_ummbVtguKSb2gNcG0LD9kV5SIOi94IT7-F19mNyHscXpVSvHyKvtr7zubN204ugjLr2g9wBitsVpF60bkDLr30zbvlN9CROsxglf6tbRUAQaUgjMANTs4JtIBtdFPOk4ekBoH9NMnWTuiFn5NMGpAT8GOW_TysHQuRPRs4w5tfoPPW3U8Hc6lDvRutAmN2h-bbvUpuzDqEODm7b_Onr6tuuZ7_rh5WDd3j7lmuIo5L0AbQ7VJB2GiKqHGVPG-KIeBlpwMTHCsBRRDiTHVNRakLig3QtDK8J6L4jpbz7qDU3t58vao_B_plJWvCee3Uvlo9QFkb5IWq3qdGjBMoaKGMt0TNkCagLGk9XnWOnmXFglR7t3kxzS-pIxzQdL1eUIVM0p7F4IH896VYHk2Vs7GyrOx8s3YxLqdWRYA3hmVqARO1X8HCZ8f</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2455610815</pqid></control><display><type>article</type><title>iDTi-CSsmoteB: Identification of Drug-Target Interaction Based on Drug Chemical Structure and Protein Sequence Using XGBoost With Over-Sampling Technique SMOTE</title><source>IEEE Open Access Journals</source><creator>Mahmud, S. M. Hasan ; Chen, Wenyu ; Jahan, Hosney ; Liu, Yongsheng ; Sujan, Nasir Islam ; Ahmed, Saeed</creator><creatorcontrib>Mahmud, S. M. Hasan ; Chen, Wenyu ; Jahan, Hosney ; Liu, Yongsheng ; Sujan, Nasir Islam ; Ahmed, Saeed</creatorcontrib><description>Identifying interaction between drug and protein is a crucial challenge in drug discovery, which can lead the researchers to develop novel drug compounds or new target proteins for the existing drugs. The determination of drug-target interactions (DTIs) is an extremely time-consuming, costly, and tedious task with wet-lab experiments. To date, multiple computational techniques have been presented to simplify the drug discovery process, but a huge number of interactions are still undiscovered. Furthermore, a class imbalance is a critical challenge regarding this experiment which can significantly degrade the classification accuracy that has not been effectively addressed yet. In this paper, we proposed a novel high-throughput computational model, called iDTi-CSsmoteB, for identification of DTIs based on drug chemical structures and protein sequences. More specifically, the protein sequence is extracted through position-specific scoring matrix (PSSM)-Bigram, amphiphilic pseudo amino acid composition (AM-PseAAC) and dipeptide PseAAC descriptors which represents evolutionary and sequence information. The drug chemical structure is represented as a molecular substructure fingerprint (MSF) which describes the existence of the functional fragments or groups. Finally, we used the over-sampling SMOTE technique to overcome the imbalance issue of the datasets and applied XGBoost algorithm as a classifier to predict DTIs. To evaluate the performance of iDTi-CSsmoteB, several experiments have been conducted on four benchmark datasets, namely, enzyme, ion channel, GPCR, and nuclear receptor based on fivefold cross validation. The experimental analysis exhibits that our model outperforms similar methods in terms of area under the ROC (auROC) curve. In addition, our achieved results indicate the effectiveness of the feature extraction techniques, balancing methods, and classifier for predicting the DTIs which can provide substance for new drug development. iDTi-CSsmoteB webserver is available online at http://idticssmoteb-uestc.me/ .</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2019.2910277</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; AM-PseAAC ; Chemicals ; Classifiers ; Datasets ; DP-PseAAC ; drug-target interactions ; Drugs ; Feature extraction ; Ion channels ; Molecular structure ; molecular substructure fingerprint ; over-sampling SMOTE ; Predictive models ; Protein sequence ; Proteins ; PSSM-Bigram ; Sampling methods ; Substructures ; Target recognition ; XGBoost classifier</subject><ispartof>IEEE access, 2019, Vol.7, p.48699-48714</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-53ecff2cf1094687e902a5b37dd2751d4650c6e3d7002c90619325f6628f5b563</citedby><cites>FETCH-LOGICAL-c408t-53ecff2cf1094687e902a5b37dd2751d4650c6e3d7002c90619325f6628f5b563</cites><orcidid>0000-0002-6828-3559 ; 0000-0001-9578-4351 ; 0000-0002-2867-9823</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8686077$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>315,786,790,4043,27666,27956,27957,27958,55284</link.rule.ids></links><search><creatorcontrib>Mahmud, S. M. Hasan</creatorcontrib><creatorcontrib>Chen, Wenyu</creatorcontrib><creatorcontrib>Jahan, Hosney</creatorcontrib><creatorcontrib>Liu, Yongsheng</creatorcontrib><creatorcontrib>Sujan, Nasir Islam</creatorcontrib><creatorcontrib>Ahmed, Saeed</creatorcontrib><title>iDTi-CSsmoteB: Identification of Drug-Target Interaction Based on Drug Chemical Structure and Protein Sequence Using XGBoost With Over-Sampling Technique SMOTE</title><title>IEEE access</title><addtitle>Access</addtitle><description>Identifying interaction between drug and protein is a crucial challenge in drug discovery, which can lead the researchers to develop novel drug compounds or new target proteins for the existing drugs. The determination of drug-target interactions (DTIs) is an extremely time-consuming, costly, and tedious task with wet-lab experiments. To date, multiple computational techniques have been presented to simplify the drug discovery process, but a huge number of interactions are still undiscovered. Furthermore, a class imbalance is a critical challenge regarding this experiment which can significantly degrade the classification accuracy that has not been effectively addressed yet. In this paper, we proposed a novel high-throughput computational model, called iDTi-CSsmoteB, for identification of DTIs based on drug chemical structures and protein sequences. More specifically, the protein sequence is extracted through position-specific scoring matrix (PSSM)-Bigram, amphiphilic pseudo amino acid composition (AM-PseAAC) and dipeptide PseAAC descriptors which represents evolutionary and sequence information. The drug chemical structure is represented as a molecular substructure fingerprint (MSF) which describes the existence of the functional fragments or groups. Finally, we used the over-sampling SMOTE technique to overcome the imbalance issue of the datasets and applied XGBoost algorithm as a classifier to predict DTIs. To evaluate the performance of iDTi-CSsmoteB, several experiments have been conducted on four benchmark datasets, namely, enzyme, ion channel, GPCR, and nuclear receptor based on fivefold cross validation. The experimental analysis exhibits that our model outperforms similar methods in terms of area under the ROC (auROC) curve. In addition, our achieved results indicate the effectiveness of the feature extraction techniques, balancing methods, and classifier for predicting the DTIs which can provide substance for new drug development. iDTi-CSsmoteB webserver is available online at http://idticssmoteb-uestc.me/ .</description><subject>Algorithms</subject><subject>AM-PseAAC</subject><subject>Chemicals</subject><subject>Classifiers</subject><subject>Datasets</subject><subject>DP-PseAAC</subject><subject>drug-target interactions</subject><subject>Drugs</subject><subject>Feature extraction</subject><subject>Ion channels</subject><subject>Molecular structure</subject><subject>molecular substructure fingerprint</subject><subject>over-sampling SMOTE</subject><subject>Predictive models</subject><subject>Protein sequence</subject><subject>Proteins</subject><subject>PSSM-Bigram</subject><subject>Sampling methods</subject><subject>Substructures</subject><subject>Target recognition</subject><subject>XGBoost classifier</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>DOA</sourceid><recordid>eNpNUV1r2zAUNWOFlq6_oC-CPTuTZEm299a4WRfoyMAu7ZuQ5atEIbEySR7s1-yvTqlLmV50ufeccz9Olt0SvCAE11_ummbVtguKSb2gNcG0LD9kV5SIOi94IT7-F19mNyHscXpVSvHyKvtr7zubN204ugjLr2g9wBitsVpF60bkDLr30zbvlN9CROsxglf6tbRUAQaUgjMANTs4JtIBtdFPOk4ekBoH9NMnWTuiFn5NMGpAT8GOW_TysHQuRPRs4w5tfoPPW3U8Hc6lDvRutAmN2h-bbvUpuzDqEODm7b_Onr6tuuZ7_rh5WDd3j7lmuIo5L0AbQ7VJB2GiKqHGVPG-KIeBlpwMTHCsBRRDiTHVNRakLig3QtDK8J6L4jpbz7qDU3t58vao_B_plJWvCee3Uvlo9QFkb5IWq3qdGjBMoaKGMt0TNkCagLGk9XnWOnmXFglR7t3kxzS-pIxzQdL1eUIVM0p7F4IH896VYHk2Vs7GyrOx8s3YxLqdWRYA3hmVqARO1X8HCZ8f</recordid><startdate>2019</startdate><enddate>2019</enddate><creator>Mahmud, S. M. Hasan</creator><creator>Chen, Wenyu</creator><creator>Jahan, Hosney</creator><creator>Liu, Yongsheng</creator><creator>Sujan, Nasir Islam</creator><creator>Ahmed, Saeed</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-6828-3559</orcidid><orcidid>https://orcid.org/0000-0001-9578-4351</orcidid><orcidid>https://orcid.org/0000-0002-2867-9823</orcidid></search><sort><creationdate>2019</creationdate><title>iDTi-CSsmoteB: Identification of Drug-Target Interaction Based on Drug Chemical Structure and Protein Sequence Using XGBoost With Over-Sampling Technique SMOTE</title><author>Mahmud, S. M. Hasan ; Chen, Wenyu ; Jahan, Hosney ; Liu, Yongsheng ; Sujan, Nasir Islam ; Ahmed, Saeed</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-53ecff2cf1094687e902a5b37dd2751d4650c6e3d7002c90619325f6628f5b563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>AM-PseAAC</topic><topic>Chemicals</topic><topic>Classifiers</topic><topic>Datasets</topic><topic>DP-PseAAC</topic><topic>drug-target interactions</topic><topic>Drugs</topic><topic>Feature extraction</topic><topic>Ion channels</topic><topic>Molecular structure</topic><topic>molecular substructure fingerprint</topic><topic>over-sampling SMOTE</topic><topic>Predictive models</topic><topic>Protein sequence</topic><topic>Proteins</topic><topic>PSSM-Bigram</topic><topic>Sampling methods</topic><topic>Substructures</topic><topic>Target recognition</topic><topic>XGBoost classifier</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mahmud, S. M. Hasan</creatorcontrib><creatorcontrib>Chen, Wenyu</creatorcontrib><creatorcontrib>Jahan, Hosney</creatorcontrib><creatorcontrib>Liu, Yongsheng</creatorcontrib><creatorcontrib>Sujan, Nasir Islam</creatorcontrib><creatorcontrib>Ahmed, Saeed</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Xplore</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mahmud, S. M. Hasan</au><au>Chen, Wenyu</au><au>Jahan, Hosney</au><au>Liu, Yongsheng</au><au>Sujan, Nasir Islam</au><au>Ahmed, Saeed</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>iDTi-CSsmoteB: Identification of Drug-Target Interaction Based on Drug Chemical Structure and Protein Sequence Using XGBoost With Over-Sampling Technique SMOTE</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2019</date><risdate>2019</risdate><volume>7</volume><spage>48699</spage><epage>48714</epage><pages>48699-48714</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Identifying interaction between drug and protein is a crucial challenge in drug discovery, which can lead the researchers to develop novel drug compounds or new target proteins for the existing drugs. The determination of drug-target interactions (DTIs) is an extremely time-consuming, costly, and tedious task with wet-lab experiments. To date, multiple computational techniques have been presented to simplify the drug discovery process, but a huge number of interactions are still undiscovered. Furthermore, a class imbalance is a critical challenge regarding this experiment which can significantly degrade the classification accuracy that has not been effectively addressed yet. In this paper, we proposed a novel high-throughput computational model, called iDTi-CSsmoteB, for identification of DTIs based on drug chemical structures and protein sequences. More specifically, the protein sequence is extracted through position-specific scoring matrix (PSSM)-Bigram, amphiphilic pseudo amino acid composition (AM-PseAAC) and dipeptide PseAAC descriptors which represents evolutionary and sequence information. The drug chemical structure is represented as a molecular substructure fingerprint (MSF) which describes the existence of the functional fragments or groups. Finally, we used the over-sampling SMOTE technique to overcome the imbalance issue of the datasets and applied XGBoost algorithm as a classifier to predict DTIs. To evaluate the performance of iDTi-CSsmoteB, several experiments have been conducted on four benchmark datasets, namely, enzyme, ion channel, GPCR, and nuclear receptor based on fivefold cross validation. The experimental analysis exhibits that our model outperforms similar methods in terms of area under the ROC (auROC) curve. In addition, our achieved results indicate the effectiveness of the feature extraction techniques, balancing methods, and classifier for predicting the DTIs which can provide substance for new drug development. iDTi-CSsmoteB webserver is available online at http://idticssmoteb-uestc.me/ .</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2019.2910277</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0002-6828-3559</orcidid><orcidid>https://orcid.org/0000-0001-9578-4351</orcidid><orcidid>https://orcid.org/0000-0002-2867-9823</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2169-3536 |
ispartof | IEEE access, 2019, Vol.7, p.48699-48714 |
issn | 2169-3536 2169-3536 |
language | eng |
recordid | cdi_proquest_journals_2455610815 |
source | IEEE Open Access Journals |
subjects | Algorithms AM-PseAAC Chemicals Classifiers Datasets DP-PseAAC drug-target interactions Drugs Feature extraction Ion channels Molecular structure molecular substructure fingerprint over-sampling SMOTE Predictive models Protein sequence Proteins PSSM-Bigram Sampling methods Substructures Target recognition XGBoost classifier |
title | iDTi-CSsmoteB: Identification of Drug-Target Interaction Based on Drug Chemical Structure and Protein Sequence Using XGBoost With Over-Sampling Technique SMOTE |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-23T00%3A28%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=iDTi-CSsmoteB:%20Identification%20of%20Drug-Target%20Interaction%20Based%20on%20Drug%20Chemical%20Structure%20and%20Protein%20Sequence%20Using%20XGBoost%20With%20Over-Sampling%20Technique%20SMOTE&rft.jtitle=IEEE%20access&rft.au=Mahmud,%20S.%20M.%20Hasan&rft.date=2019&rft.volume=7&rft.spage=48699&rft.epage=48714&rft.pages=48699-48714&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2019.2910277&rft_dat=%3Cproquest_ieee_%3E2455610815%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c408t-53ecff2cf1094687e902a5b37dd2751d4650c6e3d7002c90619325f6628f5b563%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2455610815&rft_id=info:pmid/&rft_ieee_id=8686077&rfr_iscdi=true |