AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonist
Abstract G protein-coupled receptors (GPCRs) play vital roles in various physiological processes, making them attractive drug discovery targets. Meanwhile, deep learning techniques have revolutionized drug discovery by facilitating efficient tools for expediting the identification and optimization o...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-024-00945-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571397316018176 |
|---|---|
| author | Rahul Brahma Sunghyun Moon Jae-Min Shin Kwang-Hwi Cho |
| author_facet | Rahul Brahma Sunghyun Moon Jae-Min Shin Kwang-Hwi Cho |
| author_sort | Rahul Brahma |
| collection | DOAJ |
| description | Abstract G protein-coupled receptors (GPCRs) play vital roles in various physiological processes, making them attractive drug discovery targets. Meanwhile, deep learning techniques have revolutionized drug discovery by facilitating efficient tools for expediting the identification and optimization of ligands. However, existing models for the GPCRs often focus on single-target or a small subset of GPCRs or employ binary classification, constraining their applicability for high throughput virtual screening. To address these issues, we introduce AiGPro, a novel multitask model designed to predict small molecule agonists (EC50) and antagonists (IC50) across the 231 human GPCRs, making it a first-in-class solution for large-scale GPCR profiling. Leveraging multi-scale context aggregation and bidirectional multi-head cross-attention mechanisms, our approach demonstrates that ensemble models may not be necessary for predicting complex GPCR states and small molecule interactions. Through extensive validation using stratified tenfold cross-validation, AiGPro achieves robust performance with Pearson's correlation coefficient of 0.91, indicating broad generalizability. This breakthrough sets a new standard in the GPCR studies, outperforming previous studies. Moreover, our first-in-class multi-tasking model can predict agonist and antagonist activities across a wide range of GPCRs, offering a comprehensive perspective on ligand bioactivity within this diverse superfamily. To facilitate easy accessibility, we have deployed a web-based platform for model access at https://aicadd.ssu.ac.kr/AiGPro . Scientific Contribution We introduce a deep learning-based multi-task model to generalize the agonist and antagonist bioactivity prediction for GPCRs accurately. The model is implemented on a user-friendly web server to facilitate rapid screening of small-molecule libraries, expediting GPCR-targeted drug discovery. Covering a diverse set of 231 GPCR targets, the platform delivers a robust, scalable solution for advancing GPCR-focused therapeutic development. The proposed framework incorporates an innovative dual-label prediction strategy, enabling the simultaneous classification of molecules as agonists, antagonists, or both. Each prediction is further accompanied by a confidence score, offering a quantitative measure of activity likelihood. This advancement moves beyond conventional models focusing solely on binding affinity, providing a more comprehensive understanding of ligand-receptor interactions. At the core of our model lies the Bi-Directional Multi-Head Cross-Attention (BMCA) module, a novel architecture that captures forward and backward contextual embeddings of protein and ligand features. By leveraging BMCA, the model effectively integrates structural and sequence-level information, ensuring a precise representation of molecular interactions. Results show that this approach is highly accurate in binding affinity predictions and consistent across diverse GPCR families. By unifying agonist and antagonist bioactivity prediction into a single model architecture, we bridge a critical gap in GPCR modeling. This enhances prediction accuracy and accelerates virtual screening workflows, offering a valuable and innovative solution for advancing GPCR-targeted drug discovery. Graphical Abstract |
| format | Article |
| id | doaj-art-abfc66274d6e4784bce08a05a925cf02 |
| institution | Kabale University |
| issn | 1758-2946 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj-art-abfc66274d6e4784bce08a05a925cf022025-02-02T12:40:17ZengBMCJournal of Cheminformatics1758-29462025-01-0117111910.1186/s13321-024-00945-7AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonistRahul Brahma0Sunghyun Moon1Jae-Min Shin2Kwang-Hwi Cho3School of Systems Biomedical Science, Soongsil UniversitySchool of Systems Biomedical Science, Soongsil UniversityAzothBio, Rm. DA724 Hyundai Knowledge Industry CenterSchool of Systems Biomedical Science, Soongsil UniversityAbstract G protein-coupled receptors (GPCRs) play vital roles in various physiological processes, making them attractive drug discovery targets. Meanwhile, deep learning techniques have revolutionized drug discovery by facilitating efficient tools for expediting the identification and optimization of ligands. However, existing models for the GPCRs often focus on single-target or a small subset of GPCRs or employ binary classification, constraining their applicability for high throughput virtual screening. To address these issues, we introduce AiGPro, a novel multitask model designed to predict small molecule agonists (EC50) and antagonists (IC50) across the 231 human GPCRs, making it a first-in-class solution for large-scale GPCR profiling. Leveraging multi-scale context aggregation and bidirectional multi-head cross-attention mechanisms, our approach demonstrates that ensemble models may not be necessary for predicting complex GPCR states and small molecule interactions. Through extensive validation using stratified tenfold cross-validation, AiGPro achieves robust performance with Pearson's correlation coefficient of 0.91, indicating broad generalizability. This breakthrough sets a new standard in the GPCR studies, outperforming previous studies. Moreover, our first-in-class multi-tasking model can predict agonist and antagonist activities across a wide range of GPCRs, offering a comprehensive perspective on ligand bioactivity within this diverse superfamily. To facilitate easy accessibility, we have deployed a web-based platform for model access at https://aicadd.ssu.ac.kr/AiGPro . Scientific Contribution We introduce a deep learning-based multi-task model to generalize the agonist and antagonist bioactivity prediction for GPCRs accurately. The model is implemented on a user-friendly web server to facilitate rapid screening of small-molecule libraries, expediting GPCR-targeted drug discovery. Covering a diverse set of 231 GPCR targets, the platform delivers a robust, scalable solution for advancing GPCR-focused therapeutic development. The proposed framework incorporates an innovative dual-label prediction strategy, enabling the simultaneous classification of molecules as agonists, antagonists, or both. Each prediction is further accompanied by a confidence score, offering a quantitative measure of activity likelihood. This advancement moves beyond conventional models focusing solely on binding affinity, providing a more comprehensive understanding of ligand-receptor interactions. At the core of our model lies the Bi-Directional Multi-Head Cross-Attention (BMCA) module, a novel architecture that captures forward and backward contextual embeddings of protein and ligand features. By leveraging BMCA, the model effectively integrates structural and sequence-level information, ensuring a precise representation of molecular interactions. Results show that this approach is highly accurate in binding affinity predictions and consistent across diverse GPCR families. By unifying agonist and antagonist bioactivity prediction into a single model architecture, we bridge a critical gap in GPCR modeling. This enhances prediction accuracy and accelerates virtual screening workflows, offering a valuable and innovative solution for advancing GPCR-targeted drug discovery. Graphical Abstracthttps://doi.org/10.1186/s13321-024-00945-7Artificial intelligenceGPCRAgonist and antagonistMachine learningDrug development |
| spellingShingle | Rahul Brahma Sunghyun Moon Jae-Min Shin Kwang-Hwi Cho AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonist Journal of Cheminformatics Artificial intelligence GPCR Agonist and antagonist Machine learning Drug development |
| title | AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonist |
| title_full | AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonist |
| title_fullStr | AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonist |
| title_full_unstemmed | AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonist |
| title_short | AiGPro: a multi-tasks model for profiling of GPCRs for agonist and antagonist |
| title_sort | aigpro a multi tasks model for profiling of gpcrs for agonist and antagonist |
| topic | Artificial intelligence GPCR Agonist and antagonist Machine learning Drug development |
| url | https://doi.org/10.1186/s13321-024-00945-7 |
| work_keys_str_mv | AT rahulbrahma aigproamultitasksmodelforprofilingofgpcrsforagonistandantagonist AT sunghyunmoon aigproamultitasksmodelforprofilingofgpcrsforagonistandantagonist AT jaeminshin aigproamultitasksmodelforprofilingofgpcrsforagonistandantagonist AT kwanghwicho aigproamultitasksmodelforprofilingofgpcrsforagonistandantagonist |