OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands

Biased signaling at G-protein-coupled receptors (GPCRs) enables pathway-selective modulation but remains challenging to characterize experimentally. We present OpioidBias, a machine learning tool for predicting G-protein versus β-arrestin bias in opioid ligands. A curated data set of opioid ligands...

Ամբողջական նկարագրություն

Պահպանված է:
Մատենագիտական մանրամասներ
Հիմնական հեղինակ: Rajkumar R (22674565) (author)
Այլ հեղինակներ: Anju Sharma (2900093) (author), Anuradha Badade (22674568) (author), Tanmaykumar Varma (17013628) (author), Prabha Garg (1625956) (author)
Հրապարակվել է: 2025
Խորագրեր:
Ցուցիչներ: Ավելացրեք ցուցիչ
Չկան պիտակներ, Եղեք առաջինը, ով նշում է այս գրառումը!
_version_ 1849927644850683904
author Rajkumar R (22674565)
author2 Anju Sharma (2900093)
Anuradha Badade (22674568)
Tanmaykumar Varma (17013628)
Prabha Garg (1625956)
author2_role author
author
author
author
author_facet Rajkumar R (22674565)
Anju Sharma (2900093)
Anuradha Badade (22674568)
Tanmaykumar Varma (17013628)
Prabha Garg (1625956)
author_role author
dc.creator.none.fl_str_mv Rajkumar R (22674565)
Anju Sharma (2900093)
Anuradha Badade (22674568)
Tanmaykumar Varma (17013628)
Prabha Garg (1625956)
dc.date.none.fl_str_mv 2025-11-24T12:38:06Z
dc.identifier.none.fl_str_mv 10.1021/acsmedchemlett.5c00539.s004
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/OpioidBias_A_Machine_Learning_Tool_for_Predicting_the_Biased_Agonism_of_Opioid_Ligands/30694567
dc.rights.none.fl_str_mv CC BY-NC 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biochemistry
Molecular Biology
Cancer
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
recursive feature elimination
machine learning tool
identify molecular determinants
http :// github
curated data set
protein versus β
six classifiers
selective modulation
remains challenging
opioid ligands
freely available
encompassing physicochemical
enables pathway
coupled receptors
characterize experimentally
biased agonism
best performance
based features
3800 descriptors
dc.title.none.fl_str_mv OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description Biased signaling at G-protein-coupled receptors (GPCRs) enables pathway-selective modulation but remains challenging to characterize experimentally. We present OpioidBias, a machine learning tool for predicting G-protein versus β-arrestin bias in opioid ligands. A curated data set of opioid ligands was represented with >3800 descriptors from RDKit and Mordred, encompassing physicochemical, topological, and fingerprint-based features. Feature selection using Boruta and recursive feature elimination (RFE) guided the training of six classifiers. A random forest model incorporating combined RDKit and Mordred descriptors, fingerprints, and RFE showed the best performance and was further interpreted using feature analysis to identify molecular determinants of bias. OpioidBias is freely available (http://github.com/PGlab-NIPER/OpioidBias) to support biased ligand discovery across opioid pharmacology.
eu_rights_str_mv openAccess
id Manara_a6aafa22b508b742fea33a34679570f7
identifier_str_mv 10.1021/acsmedchemlett.5c00539.s004
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30694567
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 OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid LigandsRajkumar R (22674565)Anju Sharma (2900093)Anuradha Badade (22674568)Tanmaykumar Varma (17013628)Prabha Garg (1625956)BiochemistryMolecular BiologyCancerBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedrecursive feature eliminationmachine learning toolidentify molecular determinantshttp :// githubcurated data setprotein versus βsix classifiersselective modulationremains challengingopioid ligandsfreely availableencompassing physicochemicalenables pathwaycoupled receptorscharacterize experimentallybiased agonismbest performancebased features3800 descriptorsBiased signaling at G-protein-coupled receptors (GPCRs) enables pathway-selective modulation but remains challenging to characterize experimentally. We present OpioidBias, a machine learning tool for predicting G-protein versus β-arrestin bias in opioid ligands. A curated data set of opioid ligands was represented with >3800 descriptors from RDKit and Mordred, encompassing physicochemical, topological, and fingerprint-based features. Feature selection using Boruta and recursive feature elimination (RFE) guided the training of six classifiers. A random forest model incorporating combined RDKit and Mordred descriptors, fingerprints, and RFE showed the best performance and was further interpreted using feature analysis to identify molecular determinants of bias. OpioidBias is freely available (http://github.com/PGlab-NIPER/OpioidBias) to support biased ligand discovery across opioid pharmacology.2025-11-24T12:38:06ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1021/acsmedchemlett.5c00539.s004https://figshare.com/articles/dataset/OpioidBias_A_Machine_Learning_Tool_for_Predicting_the_Biased_Agonism_of_Opioid_Ligands/30694567CC BY-NC 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306945672025-11-24T12:38:06Z
spellingShingle OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
Rajkumar R (22674565)
Biochemistry
Molecular Biology
Cancer
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
recursive feature elimination
machine learning tool
identify molecular determinants
http :// github
curated data set
protein versus β
six classifiers
selective modulation
remains challenging
opioid ligands
freely available
encompassing physicochemical
enables pathway
coupled receptors
characterize experimentally
biased agonism
best performance
based features
3800 descriptors
status_str publishedVersion
title OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
title_full OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
title_fullStr OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
title_full_unstemmed OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
title_short OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
title_sort OpioidBias: A Machine Learning Tool for Predicting the Biased Agonism of Opioid Ligands
topic Biochemistry
Molecular Biology
Cancer
Biological Sciences not elsewhere classified
Chemical Sciences not elsewhere classified
Information Systems not elsewhere classified
recursive feature elimination
machine learning tool
identify molecular determinants
http :// github
curated data set
protein versus β
six classifiers
selective modulation
remains challenging
opioid ligands
freely available
encompassing physicochemical
enables pathway
coupled receptors
characterize experimentally
biased agonism
best performance
based features
3800 descriptors