Prediction of Contact Residues in Anti-HIV Neutralizing Antibody by Deep Learning
The monoclonal antibody 1C10 targets the V3 loop of HIV-1 and neutralizes a broad range of clade B viruses. However, the mode of interaction between 1C10 and the V3 loop remains unclear because crystallization of 1C10 and the V3 peptide was unsuccessful due to the flexible regions present in both 1C...
Gespeichert in:
| Veröffentlicht in: | Japanese Journal of Infectious Diseases 2020/05/29, Vol.73(3), pp.235-241 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 241 |
|---|---|
| container_issue | 3 |
| container_start_page | 235 |
| container_title | Japanese Journal of Infectious Diseases |
| container_volume | 73 |
| creator | Kaku, Yu Kuwata, Takeo Gorny, Miroslaw K. Matsushita, Shuzo |
| description | The monoclonal antibody 1C10 targets the V3 loop of HIV-1 and neutralizes a broad range of clade B viruses. However, the mode of interaction between 1C10 and the V3 loop remains unclear because crystallization of 1C10 and the V3 peptide was unsuccessful due to the flexible regions present in both 1C10 and the V3 peptide. In this study, we predicted the 1C10 amino acid residues that make contact with the V3 loop using a deep learning (DL)-based method. Inputs from ROSIE for docking simulation and FastContact, Naccess, and PDBtools, to approximate interactions were processed by Chainer for DL, and outputs were obtained as probabilities of contact residues. Using this DL algorithm, D95, D97, P100a, and D100b of CDRH3; D53, and D56 of CDRH2; and D61 of FR3 were highly ranked as contact residues of 1C10. Substitution of these residues with alanine significantly decreased the affinity of 1C10 to the V3 peptide. Moreover, the higher the rank of the residue, the more the binding activity diminished. This study demonstrates that the prediction of contact residues using a DL-based approach is a precise and useful tool for the analysis of antibody-antigen interactions. |
| doi_str_mv | 10.7883/yoken.JJID.2019.496 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2408556269</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2408556269</sourcerecordid><originalsourceid>FETCH-LOGICAL-c618t-6952e1b8378c33832f174158a1d0e374f7fe131053c22278c41e2cced02b78ff3</originalsourceid><addsrcrecordid>eNpVkE1PGzEQhq0KVCDtL6hUWeK8wfZ4d71HlAAJiviooFfL652lThNv8DqH8OtxSIjExWN5nnnHegj5xdmwVAouNt1_9MPb2-l4KBivhrIqvpFTrpTMhILiKN1ByqwAJk_IWd_PGRN5ztl3cgKCsYoV7JQ8PgRsnI2u87Rr6ajz0dhI_2DvmjX21Hl66aPLJtO_9A7XMZiFe3P-5eO17poNrTd0jLiiMzTBp84PctyaRY8_93VAnq-vnkaTbHZ_Mx1dzjJbcBWzosoF8lpBqSyAAtHyUvJcGd4whFK2ZYscOMvBCiESJDkKa7Fhoi5V28KAnO9yV6F7TV-Net6tg08rtZBM5XkhiipRsKNs6Po-YKtXwS1N2GjO9Faj_tCotxr1VqNOGtPU7332ul5ic5j59JaA6Q6Y99G84AEwITq7wH1oCRq2x5fwA2P_maDRwzv_QIhB</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2408556269</pqid></control><display><type>article</type><title>Prediction of Contact Residues in Anti-HIV Neutralizing Antibody by Deep Learning</title><source>MEDLINE</source><source>J-STAGE (Japan Science & Technology Information Aggregator, Electronic) Freely Available Titles - Japanese</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Kaku, Yu ; Kuwata, Takeo ; Gorny, Miroslaw K. ; Matsushita, Shuzo</creator><creatorcontrib>Kaku, Yu ; Kuwata, Takeo ; Gorny, Miroslaw K. ; Matsushita, Shuzo</creatorcontrib><description>The monoclonal antibody 1C10 targets the V3 loop of HIV-1 and neutralizes a broad range of clade B viruses. However, the mode of interaction between 1C10 and the V3 loop remains unclear because crystallization of 1C10 and the V3 peptide was unsuccessful due to the flexible regions present in both 1C10 and the V3 peptide. In this study, we predicted the 1C10 amino acid residues that make contact with the V3 loop using a deep learning (DL)-based method. Inputs from ROSIE for docking simulation and FastContact, Naccess, and PDBtools, to approximate interactions were processed by Chainer for DL, and outputs were obtained as probabilities of contact residues. Using this DL algorithm, D95, D97, P100a, and D100b of CDRH3; D53, and D56 of CDRH2; and D61 of FR3 were highly ranked as contact residues of 1C10. Substitution of these residues with alanine significantly decreased the affinity of 1C10 to the V3 peptide. Moreover, the higher the rank of the residue, the more the binding activity diminished. This study demonstrates that the prediction of contact residues using a DL-based approach is a precise and useful tool for the analysis of antibody-antigen interactions.</description><identifier>ISSN: 1344-6304</identifier><identifier>EISSN: 1884-2836</identifier><identifier>DOI: 10.7883/yoken.JJID.2019.496</identifier><identifier>PMID: 32009060</identifier><language>eng</language><publisher>Japan: National Institute of Infectious Diseases, Japanese Journal of Infectious Diseases Editorial Committee</publisher><subject>Alanine ; Algorithms ; Amino Acid Sequence ; Amino Acid Substitution ; Amino acids ; Antibodies ; Antibodies, Monoclonal - chemistry ; Antibodies, Monoclonal - immunology ; Antibodies, Neutralizing - chemistry ; Antibodies, Neutralizing - immunology ; Antigen-antibody interactions ; Antigens ; Binding Sites, Antibody ; Computer simulation ; contact residue ; Crystallization ; Deep Learning ; HIV ; HIV Antibodies - chemistry ; HIV Antibodies - immunology ; HIV Envelope Protein gp120 - chemistry ; HIV Envelope Protein gp120 - immunology ; Human immunodeficiency virus ; Humans ; Machine learning ; Molecular Docking Simulation ; Monoclonal antibodies ; neutralizing antibody ; Peptide Fragments - chemistry ; Peptide Fragments - immunology ; Peptides ; Residues</subject><ispartof>Japanese Journal of Infectious Diseases, 2020/05/29, Vol.73(3), pp.235-241</ispartof><rights>2020 Authors</rights><rights>Copyright Japan Science and Technology Agency 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c618t-6952e1b8378c33832f174158a1d0e374f7fe131053c22278c41e2cced02b78ff3</citedby><cites>FETCH-LOGICAL-c618t-6952e1b8378c33832f174158a1d0e374f7fe131053c22278c41e2cced02b78ff3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,1877,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/32009060$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Kaku, Yu</creatorcontrib><creatorcontrib>Kuwata, Takeo</creatorcontrib><creatorcontrib>Gorny, Miroslaw K.</creatorcontrib><creatorcontrib>Matsushita, Shuzo</creatorcontrib><title>Prediction of Contact Residues in Anti-HIV Neutralizing Antibody by Deep Learning</title><title>Japanese Journal of Infectious Diseases</title><addtitle>Jpn J Infect Dis</addtitle><description>The monoclonal antibody 1C10 targets the V3 loop of HIV-1 and neutralizes a broad range of clade B viruses. However, the mode of interaction between 1C10 and the V3 loop remains unclear because crystallization of 1C10 and the V3 peptide was unsuccessful due to the flexible regions present in both 1C10 and the V3 peptide. In this study, we predicted the 1C10 amino acid residues that make contact with the V3 loop using a deep learning (DL)-based method. Inputs from ROSIE for docking simulation and FastContact, Naccess, and PDBtools, to approximate interactions were processed by Chainer for DL, and outputs were obtained as probabilities of contact residues. Using this DL algorithm, D95, D97, P100a, and D100b of CDRH3; D53, and D56 of CDRH2; and D61 of FR3 were highly ranked as contact residues of 1C10. Substitution of these residues with alanine significantly decreased the affinity of 1C10 to the V3 peptide. Moreover, the higher the rank of the residue, the more the binding activity diminished. This study demonstrates that the prediction of contact residues using a DL-based approach is a precise and useful tool for the analysis of antibody-antigen interactions.</description><subject>Alanine</subject><subject>Algorithms</subject><subject>Amino Acid Sequence</subject><subject>Amino Acid Substitution</subject><subject>Amino acids</subject><subject>Antibodies</subject><subject>Antibodies, Monoclonal - chemistry</subject><subject>Antibodies, Monoclonal - immunology</subject><subject>Antibodies, Neutralizing - chemistry</subject><subject>Antibodies, Neutralizing - immunology</subject><subject>Antigen-antibody interactions</subject><subject>Antigens</subject><subject>Binding Sites, Antibody</subject><subject>Computer simulation</subject><subject>contact residue</subject><subject>Crystallization</subject><subject>Deep Learning</subject><subject>HIV</subject><subject>HIV Antibodies - chemistry</subject><subject>HIV Antibodies - immunology</subject><subject>HIV Envelope Protein gp120 - chemistry</subject><subject>HIV Envelope Protein gp120 - immunology</subject><subject>Human immunodeficiency virus</subject><subject>Humans</subject><subject>Machine learning</subject><subject>Molecular Docking Simulation</subject><subject>Monoclonal antibodies</subject><subject>neutralizing antibody</subject><subject>Peptide Fragments - chemistry</subject><subject>Peptide Fragments - immunology</subject><subject>Peptides</subject><subject>Residues</subject><issn>1344-6304</issn><issn>1884-2836</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNpVkE1PGzEQhq0KVCDtL6hUWeK8wfZ4d71HlAAJiviooFfL652lThNv8DqH8OtxSIjExWN5nnnHegj5xdmwVAouNt1_9MPb2-l4KBivhrIqvpFTrpTMhILiKN1ByqwAJk_IWd_PGRN5ztl3cgKCsYoV7JQ8PgRsnI2u87Rr6ajz0dhI_2DvmjX21Hl66aPLJtO_9A7XMZiFe3P-5eO17poNrTd0jLiiMzTBp84PctyaRY8_93VAnq-vnkaTbHZ_Mx1dzjJbcBWzosoF8lpBqSyAAtHyUvJcGd4whFK2ZYscOMvBCiESJDkKa7Fhoi5V28KAnO9yV6F7TV-Net6tg08rtZBM5XkhiipRsKNs6Po-YKtXwS1N2GjO9Faj_tCotxr1VqNOGtPU7332ul5ic5j59JaA6Q6Y99G84AEwITq7wH1oCRq2x5fwA2P_maDRwzv_QIhB</recordid><startdate>20200529</startdate><enddate>20200529</enddate><creator>Kaku, Yu</creator><creator>Kuwata, Takeo</creator><creator>Gorny, Miroslaw K.</creator><creator>Matsushita, Shuzo</creator><general>National Institute of Infectious Diseases, Japanese Journal of Infectious Diseases Editorial Committee</general><general>Japan Science and Technology Agency</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>7QL</scope><scope>7T5</scope><scope>7T7</scope><scope>7TK</scope><scope>7U9</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>H94</scope><scope>M7N</scope><scope>P64</scope></search><sort><creationdate>20200529</creationdate><title>Prediction of Contact Residues in Anti-HIV Neutralizing Antibody by Deep Learning</title><author>Kaku, Yu ; Kuwata, Takeo ; Gorny, Miroslaw K. ; Matsushita, Shuzo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c618t-6952e1b8378c33832f174158a1d0e374f7fe131053c22278c41e2cced02b78ff3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Alanine</topic><topic>Algorithms</topic><topic>Amino Acid Sequence</topic><topic>Amino Acid Substitution</topic><topic>Amino acids</topic><topic>Antibodies</topic><topic>Antibodies, Monoclonal - chemistry</topic><topic>Antibodies, Monoclonal - immunology</topic><topic>Antibodies, Neutralizing - chemistry</topic><topic>Antibodies, Neutralizing - immunology</topic><topic>Antigen-antibody interactions</topic><topic>Antigens</topic><topic>Binding Sites, Antibody</topic><topic>Computer simulation</topic><topic>contact residue</topic><topic>Crystallization</topic><topic>Deep Learning</topic><topic>HIV</topic><topic>HIV Antibodies - chemistry</topic><topic>HIV Antibodies - immunology</topic><topic>HIV Envelope Protein gp120 - chemistry</topic><topic>HIV Envelope Protein gp120 - immunology</topic><topic>Human immunodeficiency virus</topic><topic>Humans</topic><topic>Machine learning</topic><topic>Molecular Docking Simulation</topic><topic>Monoclonal antibodies</topic><topic>neutralizing antibody</topic><topic>Peptide Fragments - chemistry</topic><topic>Peptide Fragments - immunology</topic><topic>Peptides</topic><topic>Residues</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kaku, Yu</creatorcontrib><creatorcontrib>Kuwata, Takeo</creatorcontrib><creatorcontrib>Gorny, Miroslaw K.</creatorcontrib><creatorcontrib>Matsushita, Shuzo</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Immunology Abstracts</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Neurosciences Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>Algology Mycology and Protozoology Abstracts (Microbiology C)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Japanese Journal of Infectious Diseases</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kaku, Yu</au><au>Kuwata, Takeo</au><au>Gorny, Miroslaw K.</au><au>Matsushita, Shuzo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prediction of Contact Residues in Anti-HIV Neutralizing Antibody by Deep Learning</atitle><jtitle>Japanese Journal of Infectious Diseases</jtitle><addtitle>Jpn J Infect Dis</addtitle><date>2020-05-29</date><risdate>2020</risdate><volume>73</volume><issue>3</issue><spage>235</spage><epage>241</epage><pages>235-241</pages><issn>1344-6304</issn><eissn>1884-2836</eissn><abstract>The monoclonal antibody 1C10 targets the V3 loop of HIV-1 and neutralizes a broad range of clade B viruses. However, the mode of interaction between 1C10 and the V3 loop remains unclear because crystallization of 1C10 and the V3 peptide was unsuccessful due to the flexible regions present in both 1C10 and the V3 peptide. In this study, we predicted the 1C10 amino acid residues that make contact with the V3 loop using a deep learning (DL)-based method. Inputs from ROSIE for docking simulation and FastContact, Naccess, and PDBtools, to approximate interactions were processed by Chainer for DL, and outputs were obtained as probabilities of contact residues. Using this DL algorithm, D95, D97, P100a, and D100b of CDRH3; D53, and D56 of CDRH2; and D61 of FR3 were highly ranked as contact residues of 1C10. Substitution of these residues with alanine significantly decreased the affinity of 1C10 to the V3 peptide. Moreover, the higher the rank of the residue, the more the binding activity diminished. This study demonstrates that the prediction of contact residues using a DL-based approach is a precise and useful tool for the analysis of antibody-antigen interactions.</abstract><cop>Japan</cop><pub>National Institute of Infectious Diseases, Japanese Journal of Infectious Diseases Editorial Committee</pub><pmid>32009060</pmid><doi>10.7883/yoken.JJID.2019.496</doi><tpages>7</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1344-6304 |
| ispartof | Japanese Journal of Infectious Diseases, 2020/05/29, Vol.73(3), pp.235-241 |
| issn | 1344-6304 1884-2836 |
| language | eng |
| recordid | cdi_proquest_journals_2408556269 |
| source | MEDLINE; J-STAGE (Japan Science & Technology Information Aggregator, Electronic) Freely Available Titles - Japanese; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Alanine Algorithms Amino Acid Sequence Amino Acid Substitution Amino acids Antibodies Antibodies, Monoclonal - chemistry Antibodies, Monoclonal - immunology Antibodies, Neutralizing - chemistry Antibodies, Neutralizing - immunology Antigen-antibody interactions Antigens Binding Sites, Antibody Computer simulation contact residue Crystallization Deep Learning HIV HIV Antibodies - chemistry HIV Antibodies - immunology HIV Envelope Protein gp120 - chemistry HIV Envelope Protein gp120 - immunology Human immunodeficiency virus Humans Machine learning Molecular Docking Simulation Monoclonal antibodies neutralizing antibody Peptide Fragments - chemistry Peptide Fragments - immunology Peptides Residues |
| title | Prediction of Contact Residues in Anti-HIV Neutralizing Antibody by Deep Learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T14%3A39%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prediction%20of%20Contact%20Residues%20in%20Anti-HIV%20Neutralizing%20Antibody%20by%20Deep%20Learning&rft.jtitle=Japanese%20Journal%20of%20Infectious%20Diseases&rft.au=Kaku,%20Yu&rft.date=2020-05-29&rft.volume=73&rft.issue=3&rft.spage=235&rft.epage=241&rft.pages=235-241&rft.issn=1344-6304&rft.eissn=1884-2836&rft_id=info:doi/10.7883/yoken.JJID.2019.496&rft_dat=%3Cproquest_cross%3E2408556269%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2408556269&rft_id=info:pmid/32009060&rfr_iscdi=true |