Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity
Abstract Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been m...
Gespeichert in:
Veröffentlicht in: | Briefings in bioinformatics 2024-03, Vol.25 (3) |
---|---|
Hauptverfasser: | , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 3 |
container_start_page | |
container_title | Briefings in bioinformatics |
container_volume | 25 |
creator | Thrift, William John Perera, Jason Cohen, Sivan Lounsbury, Nicolas W Gurung, Hem R Rose, Christopher M Chen, Jieming Jhunjhunwala, Suchit Liu, Kai |
description | Abstract
Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been made in pMHCII presentation modeling due to the collection of large-scale pMHC mass spectrometry datasets (ligandomes) and advances in machine learning. Here, we develop graph-pMHC, a graph neural network approach to predict pMHCII presentation. We derive adjacency matrices for pMHCII using Alphafold2-multimer and address the peptide–MHC binding groove alignment problem with a simple graph enumeration strategy. We demonstrate that graph-pMHC dramatically outperforms methods with suboptimal inductive biases, such as the multilayer-perceptron-based NetMHCIIpan-4.0 (+20.17% absolute average precision). Finally, we create an antibody drug immunogenicity dataset from clinical trial data and develop a method for measuring anti-antibody immunogenicity risk using pMHCII presentation models. Our model increases receiver operating characteristic curve (ROC)-area under the ROC curve (AUC) by 2.57% compared to just filtering peptides by hits in OASis alone for predicting antibody drug immunogenicity. |
doi_str_mv | 10.1093/bib/bbae123 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10981672</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/bib/bbae123</oup_id><sourcerecordid>3039814214</sourcerecordid><originalsourceid>FETCH-LOGICAL-c399t-4734c0bcf6804778da880bd4b24a24cc1a951001ee06bdfb991f6a575d9ba233</originalsourceid><addsrcrecordid>eNp9kc9rFDEUx4MotlZP3iUgiCBj83My04uURduFipfeQ5LJ7GadSWKSUfa_b5Zdi3rw8HgP8uH73jdfAF5j9BGjnl5qpy-1VhYT-gScYyZEwxBnTw9zKxrOWnoGXuS8Q4gg0eHn4Ix2nHMm2nOwu0kqbpv49XZ1BTeHGXq7JDXVVn6F9B2qGFNQZgtLgJWCZlI5w_UaRhuLGyyMyWbriyoueKj8UKs4HYY9dPO8-LCx3hlX9i_Bs1FN2b469Qtw_-Xz_eq2uft2s15d3zWG9n1pmKDMIG3GtkPVSzeorkN6YJowRZgxWPUcI4StRa0eRt33eGwVF3zotSKUXoBPR9m46NkOpp5W7ciY3KzSXgbl5N8v3m3lJvyU9TM73ApSFd6fFFL4sdhc5OyysdOkvA1LlhQRwgXGLaro23_QXViSr_YqRaseI5hV6sORMinknOz4eA1Gh7VU1gzlKcNKv_nTwCP7O7QKvDsCYYn_VXoAkOOmcw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3039814214</pqid></control><display><type>article</type><title>Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity</title><source>MEDLINE</source><source>Oxford Journals Open Access Collection</source><source>PubMed Central</source><creator>Thrift, William John ; Perera, Jason ; Cohen, Sivan ; Lounsbury, Nicolas W ; Gurung, Hem R ; Rose, Christopher M ; Chen, Jieming ; Jhunjhunwala, Suchit ; Liu, Kai</creator><creatorcontrib>Thrift, William John ; Perera, Jason ; Cohen, Sivan ; Lounsbury, Nicolas W ; Gurung, Hem R ; Rose, Christopher M ; Chen, Jieming ; Jhunjhunwala, Suchit ; Liu, Kai</creatorcontrib><description>Abstract
Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been made in pMHCII presentation modeling due to the collection of large-scale pMHC mass spectrometry datasets (ligandomes) and advances in machine learning. Here, we develop graph-pMHC, a graph neural network approach to predict pMHCII presentation. We derive adjacency matrices for pMHCII using Alphafold2-multimer and address the peptide–MHC binding groove alignment problem with a simple graph enumeration strategy. We demonstrate that graph-pMHC dramatically outperforms methods with suboptimal inductive biases, such as the multilayer-perceptron-based NetMHCIIpan-4.0 (+20.17% absolute average precision). Finally, we create an antibody drug immunogenicity dataset from clinical trial data and develop a method for measuring anti-antibody immunogenicity risk using pMHCII presentation models. Our model increases receiver operating characteristic curve (ROC)-area under the ROC curve (AUC) by 2.57% compared to just filtering peptides by hits in OASis alone for predicting antibody drug immunogenicity.</description><identifier>ISSN: 1467-5463</identifier><identifier>EISSN: 1477-4054</identifier><identifier>DOI: 10.1093/bib/bbae123</identifier><identifier>PMID: 38555476</identifier><language>eng</language><publisher>England: Oxford University Press</publisher><subject>Adaptive immunity ; Antibodies ; Antigen Presentation ; Antigens ; Datasets ; Defence mechanisms ; Drugs ; Enumeration ; Graph neural networks ; Grooves ; Histocompatibility Antigens Class II - chemistry ; Humans ; Immune response ; Immune system ; Immunity ; Immunogenicity ; Immunosuppressive agents ; Machine learning ; Major histocompatibility complex ; Mass spectrometry ; Mass spectroscopy ; Measurement methods ; Multilayers ; Neural networks ; Neural Networks, Computer ; Pathogens ; Peptides ; Peptides - chemistry ; Problem Solving Protocol</subject><ispartof>Briefings in bioinformatics, 2024-03, Vol.25 (3)</ispartof><rights>The Author(s) 2024. Published by Oxford University Press. 2024</rights><rights>The Author(s) 2024. Published by Oxford University Press.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c399t-4734c0bcf6804778da880bd4b24a24cc1a951001ee06bdfb991f6a575d9ba233</cites><orcidid>0009-0004-5022-2119</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/PMC10981672/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10981672/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,881,1598,27903,27904,53769,53771</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38555476$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Thrift, William John</creatorcontrib><creatorcontrib>Perera, Jason</creatorcontrib><creatorcontrib>Cohen, Sivan</creatorcontrib><creatorcontrib>Lounsbury, Nicolas W</creatorcontrib><creatorcontrib>Gurung, Hem R</creatorcontrib><creatorcontrib>Rose, Christopher M</creatorcontrib><creatorcontrib>Chen, Jieming</creatorcontrib><creatorcontrib>Jhunjhunwala, Suchit</creatorcontrib><creatorcontrib>Liu, Kai</creatorcontrib><title>Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity</title><title>Briefings in bioinformatics</title><addtitle>Brief Bioinform</addtitle><description>Abstract
Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been made in pMHCII presentation modeling due to the collection of large-scale pMHC mass spectrometry datasets (ligandomes) and advances in machine learning. Here, we develop graph-pMHC, a graph neural network approach to predict pMHCII presentation. We derive adjacency matrices for pMHCII using Alphafold2-multimer and address the peptide–MHC binding groove alignment problem with a simple graph enumeration strategy. We demonstrate that graph-pMHC dramatically outperforms methods with suboptimal inductive biases, such as the multilayer-perceptron-based NetMHCIIpan-4.0 (+20.17% absolute average precision). Finally, we create an antibody drug immunogenicity dataset from clinical trial data and develop a method for measuring anti-antibody immunogenicity risk using pMHCII presentation models. Our model increases receiver operating characteristic curve (ROC)-area under the ROC curve (AUC) by 2.57% compared to just filtering peptides by hits in OASis alone for predicting antibody drug immunogenicity.</description><subject>Adaptive immunity</subject><subject>Antibodies</subject><subject>Antigen Presentation</subject><subject>Antigens</subject><subject>Datasets</subject><subject>Defence mechanisms</subject><subject>Drugs</subject><subject>Enumeration</subject><subject>Graph neural networks</subject><subject>Grooves</subject><subject>Histocompatibility Antigens Class II - chemistry</subject><subject>Humans</subject><subject>Immune response</subject><subject>Immune system</subject><subject>Immunity</subject><subject>Immunogenicity</subject><subject>Immunosuppressive agents</subject><subject>Machine learning</subject><subject>Major histocompatibility complex</subject><subject>Mass spectrometry</subject><subject>Mass spectroscopy</subject><subject>Measurement methods</subject><subject>Multilayers</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Pathogens</subject><subject>Peptides</subject><subject>Peptides - chemistry</subject><subject>Problem Solving Protocol</subject><issn>1467-5463</issn><issn>1477-4054</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>TOX</sourceid><sourceid>EIF</sourceid><recordid>eNp9kc9rFDEUx4MotlZP3iUgiCBj83My04uURduFipfeQ5LJ7GadSWKSUfa_b5Zdi3rw8HgP8uH73jdfAF5j9BGjnl5qpy-1VhYT-gScYyZEwxBnTw9zKxrOWnoGXuS8Q4gg0eHn4Ix2nHMm2nOwu0kqbpv49XZ1BTeHGXq7JDXVVn6F9B2qGFNQZgtLgJWCZlI5w_UaRhuLGyyMyWbriyoueKj8UKs4HYY9dPO8-LCx3hlX9i_Bs1FN2b469Qtw_-Xz_eq2uft2s15d3zWG9n1pmKDMIG3GtkPVSzeorkN6YJowRZgxWPUcI4StRa0eRt33eGwVF3zotSKUXoBPR9m46NkOpp5W7ciY3KzSXgbl5N8v3m3lJvyU9TM73ApSFd6fFFL4sdhc5OyysdOkvA1LlhQRwgXGLaro23_QXViSr_YqRaseI5hV6sORMinknOz4eA1Gh7VU1gzlKcNKv_nTwCP7O7QKvDsCYYn_VXoAkOOmcw</recordid><startdate>20240327</startdate><enddate>20240327</enddate><creator>Thrift, William John</creator><creator>Perera, Jason</creator><creator>Cohen, Sivan</creator><creator>Lounsbury, Nicolas W</creator><creator>Gurung, Hem R</creator><creator>Rose, Christopher M</creator><creator>Chen, Jieming</creator><creator>Jhunjhunwala, Suchit</creator><creator>Liu, Kai</creator><general>Oxford University Press</general><general>Oxford Publishing Limited (England)</general><scope>TOX</scope><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>7QO</scope><scope>7SC</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>K9.</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>RC3</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0009-0004-5022-2119</orcidid></search><sort><creationdate>20240327</creationdate><title>Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity</title><author>Thrift, William John ; Perera, Jason ; Cohen, Sivan ; Lounsbury, Nicolas W ; Gurung, Hem R ; Rose, Christopher M ; Chen, Jieming ; Jhunjhunwala, Suchit ; Liu, Kai</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c399t-4734c0bcf6804778da880bd4b24a24cc1a951001ee06bdfb991f6a575d9ba233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adaptive immunity</topic><topic>Antibodies</topic><topic>Antigen Presentation</topic><topic>Antigens</topic><topic>Datasets</topic><topic>Defence mechanisms</topic><topic>Drugs</topic><topic>Enumeration</topic><topic>Graph neural networks</topic><topic>Grooves</topic><topic>Histocompatibility Antigens Class II - chemistry</topic><topic>Humans</topic><topic>Immune response</topic><topic>Immune system</topic><topic>Immunity</topic><topic>Immunogenicity</topic><topic>Immunosuppressive agents</topic><topic>Machine learning</topic><topic>Major histocompatibility complex</topic><topic>Mass spectrometry</topic><topic>Mass spectroscopy</topic><topic>Measurement methods</topic><topic>Multilayers</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Pathogens</topic><topic>Peptides</topic><topic>Peptides - chemistry</topic><topic>Problem Solving Protocol</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Thrift, William John</creatorcontrib><creatorcontrib>Perera, Jason</creatorcontrib><creatorcontrib>Cohen, Sivan</creatorcontrib><creatorcontrib>Lounsbury, Nicolas W</creatorcontrib><creatorcontrib>Gurung, Hem R</creatorcontrib><creatorcontrib>Rose, Christopher M</creatorcontrib><creatorcontrib>Chen, Jieming</creatorcontrib><creatorcontrib>Jhunjhunwala, Suchit</creatorcontrib><creatorcontrib>Liu, Kai</creatorcontrib><collection>Oxford Journals Open Access Collection</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</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>Biotechnology and BioEngineering Abstracts</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Briefings in bioinformatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Thrift, William John</au><au>Perera, Jason</au><au>Cohen, Sivan</au><au>Lounsbury, Nicolas W</au><au>Gurung, Hem R</au><au>Rose, Christopher M</au><au>Chen, Jieming</au><au>Jhunjhunwala, Suchit</au><au>Liu, Kai</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity</atitle><jtitle>Briefings in bioinformatics</jtitle><addtitle>Brief Bioinform</addtitle><date>2024-03-27</date><risdate>2024</risdate><volume>25</volume><issue>3</issue><issn>1467-5463</issn><eissn>1477-4054</eissn><abstract>Abstract
Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been made in pMHCII presentation modeling due to the collection of large-scale pMHC mass spectrometry datasets (ligandomes) and advances in machine learning. Here, we develop graph-pMHC, a graph neural network approach to predict pMHCII presentation. We derive adjacency matrices for pMHCII using Alphafold2-multimer and address the peptide–MHC binding groove alignment problem with a simple graph enumeration strategy. We demonstrate that graph-pMHC dramatically outperforms methods with suboptimal inductive biases, such as the multilayer-perceptron-based NetMHCIIpan-4.0 (+20.17% absolute average precision). Finally, we create an antibody drug immunogenicity dataset from clinical trial data and develop a method for measuring anti-antibody immunogenicity risk using pMHCII presentation models. Our model increases receiver operating characteristic curve (ROC)-area under the ROC curve (AUC) by 2.57% compared to just filtering peptides by hits in OASis alone for predicting antibody drug immunogenicity.</abstract><cop>England</cop><pub>Oxford University Press</pub><pmid>38555476</pmid><doi>10.1093/bib/bbae123</doi><orcidid>https://orcid.org/0009-0004-5022-2119</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1467-5463 |
ispartof | Briefings in bioinformatics, 2024-03, Vol.25 (3) |
issn | 1467-5463 1477-4054 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10981672 |
source | MEDLINE; Oxford Journals Open Access Collection; PubMed Central |
subjects | Adaptive immunity Antibodies Antigen Presentation Antigens Datasets Defence mechanisms Drugs Enumeration Graph neural networks Grooves Histocompatibility Antigens Class II - chemistry Humans Immune response Immune system Immunity Immunogenicity Immunosuppressive agents Machine learning Major histocompatibility complex Mass spectrometry Mass spectroscopy Measurement methods Multilayers Neural networks Neural Networks, Computer Pathogens Peptides Peptides - chemistry Problem Solving Protocol |
title | Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T13%3A59%3A09IST&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=Graph-pMHC:%20graph%20neural%20network%20approach%20to%20MHC%20class%20II%20peptide%20presentation%20and%20antibody%20immunogenicity&rft.jtitle=Briefings%20in%20bioinformatics&rft.au=Thrift,%20William%20John&rft.date=2024-03-27&rft.volume=25&rft.issue=3&rft.issn=1467-5463&rft.eissn=1477-4054&rft_id=info:doi/10.1093/bib/bbae123&rft_dat=%3Cproquest_pubme%3E3039814214%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=3039814214&rft_id=info:pmid/38555476&rft_oup_id=10.1093/bib/bbae123&rfr_iscdi=true |