Deep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discovery

Abstract Background NDUFS1 is the largest subunit of OXPHOS complex I (MC-I) and mutations in this gene are associated with MC-I deficiency. This study aims to develop a graph neural network and attention mechanism-based radiopharmaceutical-protein (RP-protein) interaction prediction model for ident...

Full description

Saved in:
Bibliographic Details
Main Authors: Muath Almaslamani, Jingyu Yang, Chi Soo Kang, Choong Mo Kang, Jung Mi Park, Sang-Keun Woo
Format: Article
Language:English
Published: SpringerOpen 2025-08-01
Series:EJNMMI Research
Subjects:
Online Access:https://doi.org/10.1186/s13550-025-01300-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849341558391832576
author Muath Almaslamani
Jingyu Yang
Chi Soo Kang
Choong Mo Kang
Jung Mi Park
Sang-Keun Woo
author_facet Muath Almaslamani
Jingyu Yang
Chi Soo Kang
Choong Mo Kang
Jung Mi Park
Sang-Keun Woo
author_sort Muath Almaslamani
collection DOAJ
description Abstract Background NDUFS1 is the largest subunit of OXPHOS complex I (MC-I) and mutations in this gene are associated with MC-I deficiency. This study aims to develop a graph neural network and attention mechanism-based radiopharmaceutical-protein (RP-protein) interaction prediction model for identifying an imaging candidate of mitochondrial function through targeting its core subunit NDUFS1. Results The estimated cell viability values for trastuzumab, 177Lu-DOTA-trastuzumab, and 225Ac-DOTA-trastuzumab were 290.1, 89.01, and 8.262 nM, respectively. The deep learning (DL) model was pretrained with normal compound-protein pairs. Afterwards, the model was fine-tuned with the dataset of RP-protein pairs and evaluated with five-fold cross validation. The prediction model trained with normal compound-protein pairs effectively predicted the binding affinity. The fine-tuned model incorporating radioactive properties outperformed the same model trained only on normal compounds. The model estimated the important substructure of a compound related to its binding to the target protein. NDUFS1 protein-targeting compounds were identified and BDBM210829 compound had the best binding affinities, binding rank, and LogP as it binds to the NDUFS1. Conclusions This study proposed a DL-based radiolabelled compound-protein interaction prediction model to identify a radiopharmaceutical (RP) that binds to the mitochondrial core subunit NDUFS1. The proposed model shows good performance for predicting RP-protein interaction. BDBM210829 was identified as a top candidate for radiolabeling and targeting the mitochondrial core subunit NDUFS1. This model can be used as an effective virtual screening tool for RP discovery.
format Article
id doaj-art-ef3d324fbd7a4d68966e45bb5b4428bf
institution Kabale University
issn 2191-219X
language English
publishDate 2025-08-01
publisher SpringerOpen
record_format Article
series EJNMMI Research
spelling doaj-art-ef3d324fbd7a4d68966e45bb5b4428bf2025-08-20T03:43:36ZengSpringerOpenEJNMMI Research2191-219X2025-08-0115111110.1186/s13550-025-01300-zDeep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discoveryMuath Almaslamani0Jingyu Yang1Chi Soo Kang2Choong Mo Kang3Jung Mi Park4Sang-Keun Woo5Division of Applied RI, Korea Institute of Radiological and Medical SciencesDivision of Applied RI, Korea Institute of Radiological and Medical SciencesDivision of Applied RI, Korea Institute of Radiological and Medical SciencesDivision of Applied RI, Korea Institute of Radiological and Medical SciencesDepartment of Nuclear Medicine, Soonchunhyang University Bucheon HospitalDivision of Applied RI, Korea Institute of Radiological and Medical SciencesAbstract Background NDUFS1 is the largest subunit of OXPHOS complex I (MC-I) and mutations in this gene are associated with MC-I deficiency. This study aims to develop a graph neural network and attention mechanism-based radiopharmaceutical-protein (RP-protein) interaction prediction model for identifying an imaging candidate of mitochondrial function through targeting its core subunit NDUFS1. Results The estimated cell viability values for trastuzumab, 177Lu-DOTA-trastuzumab, and 225Ac-DOTA-trastuzumab were 290.1, 89.01, and 8.262 nM, respectively. The deep learning (DL) model was pretrained with normal compound-protein pairs. Afterwards, the model was fine-tuned with the dataset of RP-protein pairs and evaluated with five-fold cross validation. The prediction model trained with normal compound-protein pairs effectively predicted the binding affinity. The fine-tuned model incorporating radioactive properties outperformed the same model trained only on normal compounds. The model estimated the important substructure of a compound related to its binding to the target protein. NDUFS1 protein-targeting compounds were identified and BDBM210829 compound had the best binding affinities, binding rank, and LogP as it binds to the NDUFS1. Conclusions This study proposed a DL-based radiolabelled compound-protein interaction prediction model to identify a radiopharmaceutical (RP) that binds to the mitochondrial core subunit NDUFS1. The proposed model shows good performance for predicting RP-protein interaction. BDBM210829 was identified as a top candidate for radiolabeling and targeting the mitochondrial core subunit NDUFS1. This model can be used as an effective virtual screening tool for RP discovery.https://doi.org/10.1186/s13550-025-01300-zBinding affinityRadiopharmaceutical discoveryCompound protein interactionGraph neural networkMitochondriaNDUFS1
spellingShingle Muath Almaslamani
Jingyu Yang
Chi Soo Kang
Choong Mo Kang
Jung Mi Park
Sang-Keun Woo
Deep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discovery
EJNMMI Research
Binding affinity
Radiopharmaceutical discovery
Compound protein interaction
Graph neural network
Mitochondria
NDUFS1
title Deep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discovery
title_full Deep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discovery
title_fullStr Deep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discovery
title_full_unstemmed Deep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discovery
title_short Deep learning-based radiolabelled compound-protein interaction prediction for NDUFS1-targeting radiopharmaceutical discovery
title_sort deep learning based radiolabelled compound protein interaction prediction for ndufs1 targeting radiopharmaceutical discovery
topic Binding affinity
Radiopharmaceutical discovery
Compound protein interaction
Graph neural network
Mitochondria
NDUFS1
url https://doi.org/10.1186/s13550-025-01300-z
work_keys_str_mv AT muathalmaslamani deeplearningbasedradiolabelledcompoundproteininteractionpredictionforndufs1targetingradiopharmaceuticaldiscovery
AT jingyuyang deeplearningbasedradiolabelledcompoundproteininteractionpredictionforndufs1targetingradiopharmaceuticaldiscovery
AT chisookang deeplearningbasedradiolabelledcompoundproteininteractionpredictionforndufs1targetingradiopharmaceuticaldiscovery
AT choongmokang deeplearningbasedradiolabelledcompoundproteininteractionpredictionforndufs1targetingradiopharmaceuticaldiscovery
AT jungmipark deeplearningbasedradiolabelledcompoundproteininteractionpredictionforndufs1targetingradiopharmaceuticaldiscovery
AT sangkeunwoo deeplearningbasedradiolabelledcompoundproteininteractionpredictionforndufs1targetingradiopharmaceuticaldiscovery