MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma

Immunoprecipitation coupled to tandem mass spectrometry (IP-MS/MS) methods are often used to identify protein–protein interactions (PPIs). While these approaches are prone to false positive identifications through contamination and antibody nonspecific binding, their results can be filtered using ne...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Emily Hashimoto-Roth (9564009) (author)
مؤلفون آخرون: Diane Forget (2007433) (author), Vanessa P. Gaspar (16511018) (author), Steffany A. L. Bennett (9564015) (author), Marie-Soleil Gauthier (6863540) (author), Benoit Coulombe (8211) (author), Mathieu Lavallée-Adam (1343481) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852023603521912832
author Emily Hashimoto-Roth (9564009)
author2 Diane Forget (2007433)
Vanessa P. Gaspar (16511018)
Steffany A. L. Bennett (9564015)
Marie-Soleil Gauthier (6863540)
Benoit Coulombe (8211)
Mathieu Lavallée-Adam (1343481)
author2_role author
author
author
author
author
author
author_facet Emily Hashimoto-Roth (9564009)
Diane Forget (2007433)
Vanessa P. Gaspar (16511018)
Steffany A. L. Bennett (9564015)
Marie-Soleil Gauthier (6863540)
Benoit Coulombe (8211)
Mathieu Lavallée-Adam (1343481)
author_role author
dc.creator.none.fl_str_mv Emily Hashimoto-Roth (9564009)
Diane Forget (2007433)
Vanessa P. Gaspar (16511018)
Steffany A. L. Bennett (9564015)
Marie-Soleil Gauthier (6863540)
Benoit Coulombe (8211)
Mathieu Lavallée-Adam (1343481)
dc.date.none.fl_str_mv 2025-01-14T20:19:21Z
dc.identifier.none.fl_str_mv 10.1021/acs.jproteome.4c00160.s003
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/MAGPIE_A_Machine_Learning_Approach_to_Decipher_Protein_Protein_Interactions_in_Human_Plasma/28152901
dc.rights.none.fl_str_mv CC BY-NC 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biophysics
Biochemistry
Medicine
Molecular Biology
Physiology
Immunology
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
tandem mass spectrometry
novel machine learning
effectively detect false
antibody nonspecific binding
false positive identifications
existing modeling algorithms
machine learning approach
leverages negative controls
magpie significantly outperformed
negative controls used
human plasma samples
positive interactions
often used
human plasma
computational modeling
based approach
approach provides
unprecedented ability
proteins cannot
predicted ppis
ppis detected
ppis ).
introduce magpie
identifying ppis
identified known
first constructed
execution without
biological processes
better understanding
77 %.
dc.title.none.fl_str_mv MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description Immunoprecipitation coupled to tandem mass spectrometry (IP-MS/MS) methods are often used to identify protein–protein interactions (PPIs). While these approaches are prone to false positive identifications through contamination and antibody nonspecific binding, their results can be filtered using negative controls and computational modeling. However, such filtering does not effectively detect false-positive interactions when IP-MS/MS is performed on human plasma samples. Therein, proteins cannot be overexpressed or inhibited, and existing modeling algorithms are not adapted for execution without such controls. Hence, we introduce MAGPIE, a novel machine learning-based approach for identifying PPIs in human plasma using IP-MS/MS, which leverages negative controls that include antibodies targeting proteins not expected to be present in human plasma. A set of negative controls used for false positive interaction modeling is first constructed. MAGPIE then assesses the reliability of PPIs detected in IP-MS/MS experiments using antibodies that target known plasma proteins. When applied to five IP-MS/MS experiments as a proof of concept, our algorithm identified 68 PPIs with an FDR of 20.77%. MAGPIE significantly outperformed a state-of-the-art PPI discovery tool and identified known and predicted PPIs. Our approach provides an unprecedented ability to detect human plasma PPIs, which enables a better understanding of biological processes in plasma.
eu_rights_str_mv openAccess
id Manara_e2d4105b3e93c1e7bb658ff5d036df8d
identifier_str_mv 10.1021/acs.jproteome.4c00160.s003
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28152901
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY-NC 4.0
spelling MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human PlasmaEmily Hashimoto-Roth (9564009)Diane Forget (2007433)Vanessa P. Gaspar (16511018)Steffany A. L. Bennett (9564015)Marie-Soleil Gauthier (6863540)Benoit Coulombe (8211)Mathieu Lavallée-Adam (1343481)BiophysicsBiochemistryMedicineMolecular BiologyPhysiologyImmunologyBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedtandem mass spectrometrynovel machine learningeffectively detect falseantibody nonspecific bindingfalse positive identificationsexisting modeling algorithmsmachine learning approachleverages negative controlsmagpie significantly outperformednegative controls usedhuman plasma samplespositive interactionsoften usedhuman plasmacomputational modelingbased approachapproach providesunprecedented abilityproteins cannotpredicted ppisppis detectedppis ).introduce magpieidentifying ppisidentified knownfirst constructedexecution withoutbiological processesbetter understanding77 %.Immunoprecipitation coupled to tandem mass spectrometry (IP-MS/MS) methods are often used to identify protein–protein interactions (PPIs). While these approaches are prone to false positive identifications through contamination and antibody nonspecific binding, their results can be filtered using negative controls and computational modeling. However, such filtering does not effectively detect false-positive interactions when IP-MS/MS is performed on human plasma samples. Therein, proteins cannot be overexpressed or inhibited, and existing modeling algorithms are not adapted for execution without such controls. Hence, we introduce MAGPIE, a novel machine learning-based approach for identifying PPIs in human plasma using IP-MS/MS, which leverages negative controls that include antibodies targeting proteins not expected to be present in human plasma. A set of negative controls used for false positive interaction modeling is first constructed. MAGPIE then assesses the reliability of PPIs detected in IP-MS/MS experiments using antibodies that target known plasma proteins. When applied to five IP-MS/MS experiments as a proof of concept, our algorithm identified 68 PPIs with an FDR of 20.77%. MAGPIE significantly outperformed a state-of-the-art PPI discovery tool and identified known and predicted PPIs. Our approach provides an unprecedented ability to detect human plasma PPIs, which enables a better understanding of biological processes in plasma.2025-01-14T20:19:21ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1021/acs.jproteome.4c00160.s003https://figshare.com/articles/dataset/MAGPIE_A_Machine_Learning_Approach_to_Decipher_Protein_Protein_Interactions_in_Human_Plasma/28152901CC BY-NC 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/281529012025-01-14T20:19:21Z
spellingShingle MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
Emily Hashimoto-Roth (9564009)
Biophysics
Biochemistry
Medicine
Molecular Biology
Physiology
Immunology
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
tandem mass spectrometry
novel machine learning
effectively detect false
antibody nonspecific binding
false positive identifications
existing modeling algorithms
machine learning approach
leverages negative controls
magpie significantly outperformed
negative controls used
human plasma samples
positive interactions
often used
human plasma
computational modeling
based approach
approach provides
unprecedented ability
proteins cannot
predicted ppis
ppis detected
ppis ).
introduce magpie
identifying ppis
identified known
first constructed
execution without
biological processes
better understanding
77 %.
status_str publishedVersion
title MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
title_full MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
title_fullStr MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
title_full_unstemmed MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
title_short MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
title_sort MAGPIE: A Machine Learning Approach to Decipher Protein–Protein Interactions in Human Plasma
topic Biophysics
Biochemistry
Medicine
Molecular Biology
Physiology
Immunology
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
tandem mass spectrometry
novel machine learning
effectively detect false
antibody nonspecific binding
false positive identifications
existing modeling algorithms
machine learning approach
leverages negative controls
magpie significantly outperformed
negative controls used
human plasma samples
positive interactions
often used
human plasma
computational modeling
based approach
approach provides
unprecedented ability
proteins cannot
predicted ppis
ppis detected
ppis ).
introduce magpie
identifying ppis
identified known
first constructed
execution without
biological processes
better understanding
77 %.