{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T13:23:57Z","timestamp":1787664237078,"version":"build-2736575974"},"reference-count":46,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Drug discovery is still an expensive and time-consuming process where finding the right drug associations is important for therapeutic development. In this paper, a new system is proposed for drug design called PharmaGraphFormer (PGF). It consists of five stages: (i) Data acquisition and preprocessing (DAP), (ii) Feature extraction and feature fusion (FEF), (iii) Molecular representation (MR), (iv) Multi-task prediction, and (v) Explainable artificial intelligence (XAI). This study employs a hybrid graph neural network (GNN)-transformer architecture that combines structural and sequence-based representations. Through DAP, several processes are executed, including the imputation or removal of missing values, outlier rejection, and class balancing. Next, through FEF1, features are extracted to represent the input data efficiently. Initially, compound-protein features are generated to document the interactions and relationships between chemical compounds and their corresponding target proteins. Secondly, drug characterizations are computed to encapsulate the physical, chemical, and structural attributes of each drug. After that, MR is performed using a graph-based molecule representation. Then, a novel model integrating GNNs and graph transformers, termed GNN-T, is proposed. Initially, GNNs represent the most promising deep learning models adept at processing non-Euclidean data. The Graph Transformer layer enhances atom representations by consolidating the representations of adjacent atoms through an attention mechanism. Finally, XAI is applied to explain the internal mechanisms of AI systems, rendering them comprehensible and interpretable. Across five independent runs, the proposed model achieved an accuracy of 0.963\u00b10.002, a precision of 0.971\u00b10.002, a recall of 0.958\u00b10.003, an F1-score of 0.964\u00b10.002, and a ROC-AUC of 0.993\u00b10.001. These results demonstrate an outstanding performance when compared with all other models and emphasize that the proposed model is reliable in solving the problems of prioritizing compounds in line with the latest developments in AI-powered virtual screening and drug\u2013target interaction modeling.<\/jats:p>","DOI":"10.3390\/bioengineering13090961","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T14:49:34Z","timestamp":1787582974000},"page":"961","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End Intelligent Drug Discovery via a Scalable and Explainable Graph-Transformer Framework"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2807-1555","authenticated-orcid":false,"given":"Fatma M.","family":"Talaat","sequence":"first","affiliation":[{"name":"Faculty of Artificial Intelligence, Kafrelsheikh University, Kafrelsheikh 33516, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6084-3622","authenticated-orcid":false,"given":"Ahmed","family":"Elnakib","sequence":"additional","affiliation":[{"name":"School of Engineering, Penn State Erie-The Behrend College, Erie, PA 16563, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asmaa A.","family":"Hekal","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Information Systems, Egyptian Chinese University (ECU), Cairo 11765, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8155-8089","authenticated-orcid":false,"given":"Mona","family":"Alnaggar","sequence":"additional","affiliation":[{"name":"Department of Robotics and Intelligent Machines, Faculty of Artificial Intelligence, Kafrelsheikh University, Kafrelsheikh 33516, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3440-8448","authenticated-orcid":false,"given":"Ahmed Gamal","family":"Abdellatif","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Information Systems, Egyptian Chinese University (ECU), Cairo 11765, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3393-8460","authenticated-orcid":false,"given":"Mahmoud A.","family":"Shawky","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ, UK"},{"name":"The Egyptian Technical Research and Development Center, Cairo 11618, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soha","family":"Safwat","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Information Systems, Egyptian Chinese University (ECU), Cairo 11765, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Warda M.","family":"Shaban","sequence":"additional","affiliation":[{"name":"Faculty of Artificial Intelligence and Informatics, Horus University-Egypt, New Damietta 34517, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6640-6183","authenticated-orcid":false,"given":"Mohamed","family":"Shehata","sequence":"additional","affiliation":[{"name":"Computer Science Program, James C. Bowling School of Business, Midway University, Midway, KY 40347, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e28693","DOI":"10.1002\/jmv.28693","article-title":"Drug repurposing for viral cancers: A paradigm of machine learning, deep learning, and virtual screening-based approaches","volume":"95","author":"Ahmed","year":"2023","journal-title":"J. Med. Virol."},{"key":"ref_2","unstructured":"Cassidy, J., and Taylor, B. (2020). Artificial Intelligence in Oncology Drug Discovery and Development, IntechOpen."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kondo, J., and Inoue, M. (2019). Application of cancer organoid model for drug screening and personalized therapy. Cells, 8.","DOI":"10.3390\/cells8050470"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1007\/s11030-022-10489-3","article-title":"Artificial intelligence and machine-learning approaches in structure and ligand-based discovery of drugs affecting central nervous system","volume":"27","author":"Gautam","year":"2023","journal-title":"Mol. Divers."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zaky, M.Y., and Abaza, T. (2024). Drug Discovery and Development for Rare Genetic Disorders. Rare Genetic Disorders: Advancements in Diagnosis and Treatment, Springer.","DOI":"10.1007\/978-981-99-9323-9_6"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Odah, M. (2025). Artificial intelligence meets drug discovery: A systematic review on ai-powered target identification and molecular design. Preprints.","DOI":"10.20944\/preprints202503.0912.v1"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cichonska, A., Ravikumar, B., Parri, E., Timonen, S., Pahikkala, T., Airola, A., Wennerberg, K., Rousu, J., and Aittokallio, T. (2017). Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors. PLoS Comput. Biol., 13.","DOI":"10.1371\/journal.pcbi.1005678"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hein, Z.M., Guruparan, D., Okunsai, B., Nassir, C.M.N.C.M., Ramli, M.D.C., and Kumar, S. (2025). AI and Machine Learning in Biology: From Genes to Proteins. Biology, 14.","DOI":"10.20944\/preprints202508.1952.v1"},{"key":"ref_9","first-page":"E26673371347630","article-title":"Comprehensive framework for the global regulation and approval of AI-integrated medical devices","volume":"11","author":"Rahi","year":"2025","journal-title":"Appl. Drug Res. Clin. Trials Regul. Aff."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"951","DOI":"10.2174\/1570180819666220405225817","article-title":"The new era of drug discovery: The power of computer-aided drug design (CADD)","volume":"19","author":"Nascimento","year":"2022","journal-title":"Lett. Drug Des. Discov."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3978","DOI":"10.1039\/D4MD00522H","article-title":"Recent advances from computer-aided drug design to artificial intelligence drug design","volume":"15","author":"Wang","year":"2024","journal-title":"RSC Med. Chem."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"148","DOI":"10.3390\/ddc3010009","article-title":"Revolutionizing drug discovery: A comprehensive review of AI applications","volume":"3","author":"Dhudum","year":"2024","journal-title":"Drugs Drug Candidates"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4991","DOI":"10.1007\/s00044-014-1072-3","article-title":"Quantitative structure-activity relationship (QSAR) studies as strategic approach in drug discovery","volume":"23","author":"Patel","year":"2014","journal-title":"Med. Chem. Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1002\/1521-3838(200110)20:3<227::AID-QSAR227>3.0.CO;2-Y","article-title":"Use of support vector machine in pattern classification: Application to QSAR studies","volume":"20","author":"Yasri","year":"2001","journal-title":"Quant.-Struct.-Act. Relatsh."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random forest: A classification and regression tool for compound classification and QSAR modeling","volume":"43","author":"Svetnik","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_16","first-page":"5","article-title":"Drug design by machine learning: Support vector machines for pharmaceutical data analysis","volume":"26","author":"Burbidge","year":"2001","journal-title":"Chem. C"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A deep learning approach to antibiotic discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1002\/minf.201501008","article-title":"Deep learning in drug discovery","volume":"35","author":"Gawehn","year":"2016","journal-title":"Mol. Inform."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1016\/j.csbj.2020.03.025","article-title":"Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model","volume":"18","author":"Beck","year":"2020","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/TCBB.2023.3339645","article-title":"SMGCN: Multiple similarity and multiple kernel fusion based graph convolutional neural network for drug-target interactions prediction","volume":"21","author":"Wang","year":"2023","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_21","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_22","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph nets","volume":"33","author":"Corso","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_23","first-page":"1","article-title":"Benchmarking graph neural networks","volume":"24","author":"Dwivedi","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"22326","DOI":"10.52202\/068431-1622","article-title":"Long range graph benchmark","volume":"35","author":"Dwivedi","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7181815","DOI":"10.1155\/2021\/7181815","article-title":"Mol-BERT: An effective molecular representation with BERT for molecular property prediction","volume":"2021","author":"Li","year":"2021","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Daga, A., Khan, S.A., Cabrero, D.G., Hoehndorf, R., Kiani, N.A., and Tegn\u00e9r, J. (2023). LEP-AD: Language Embedding of Proteins and Attention to Drugs predicts drug target interactions. bioRxiv, 2023.03.14.532563.","DOI":"10.1101\/2023.03.14.532563"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101081","DOI":"10.1016\/j.jpha.2024.101081","article-title":"A review of transformer models in drug discovery and beyond","volume":"15","author":"Jiang","year":"2025","journal-title":"J. Pharm. Anal."},{"key":"ref_28","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1021\/ci034243x","article-title":"ESOL: Estimating aqueous solubility directly from molecular structure","volume":"44","author":"Delaney","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1007\/s10822-014-9747-x","article-title":"FreeSolv: A database of experimental and calculated hydration free energies, with input files","volume":"28","author":"Mobley","year":"2014","journal-title":"J.-Comput.-Aided Mol. Des."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3486","DOI":"10.1021\/acs.jcim.1c01334","article-title":"DOCKSTRING: Easy molecular docking yields better benchmarks for ligand design","volume":"62","author":"Simm","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"4263","DOI":"10.1021\/acs.jcim.0c00155","article-title":"LIT-PCBA: An unbiased data set for machine learning and virtual screening","volume":"60","author":"Jacquemard","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2667","DOI":"10.1021\/acs.jcim.2c01569","article-title":"Mf-pcba: Multifidelity high-throughput screening benchmarks for drug discovery and machine learning","volume":"63","author":"Buterez","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1038\/s41597-022-01390-7","article-title":"QMugs, quantum mechanical properties of drug-like molecules","volume":"9","author":"Isert","year":"2022","journal-title":"Sci. Data"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Mirakhori, F., and Niazi, S.K. (2025). Harnessing the AI\/ML in drug and biological products discovery and development: The regulatory perspective. Pharmaceuticals, 18.","DOI":"10.3390\/ph18010047"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Tekkesinoglu, S., and Pudas, S. (2024). Explaining graph convolutional network predictions for clinicians\u2014An explainable AI approach to Alzheimer\u2019s disease classification. Front. Artif. Intell., 6.","DOI":"10.3389\/frai.2023.1334613"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yang, J., Rahardja, S., and Franti, P. (2019). Outlier detection: How to threshold outlier scores?. Proceedings of the International Conference on Artificial Intelligence, Information Processing and Cloud Computing, ACM.","DOI":"10.1145\/3371425.3371427"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e2730","DOI":"10.1002\/env.2730","article-title":"Normalization methods for spatio-temporal analysis of environmental performance: Revisiting the Min-Max method","volume":"33","author":"Mazziotta","year":"2022","journal-title":"Environmetrics"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"35040","DOI":"10.1038\/s41598-025-20505-9","article-title":"Machine learning framework for predicting susceptibility to obesity","volume":"15","author":"Shaban","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1007\/s12652-021-02967-7","article-title":"COVID-19 classification using deep feature concatenation technique","volume":"13","author":"Saad","year":"2022","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.fmre.2024.11.027","article-title":"Molecule generation for drug design: A graph learning perspective","volume":"6","author":"Yang","year":"2024","journal-title":"Fundam. Res."},{"key":"ref_42","unstructured":"Kabir, S. (2026, February 23). Drug Discovery Virtual Screening Dataset. Kaggle Dataset, 2023. Available online: https:\/\/www.kaggle.com\/datasets\/shahriarkabir\/drug-discovery-virtual-screening-dataset."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock Vina 1.2. 0: New docking methods, expanded force field, and python bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Liao, Z., You, R., Huang, X., Yao, X., Huang, T., and Zhu, S. (2019). DeepDock: Enhancing ligand-protein interaction prediction by a combination of ligand and structure information. Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE.","DOI":"10.1109\/BIBM47256.2019.8983365"},{"key":"ref_46","unstructured":"Chithrananda, S., Grand, G., and Ramsundar, B. (2020). ChemBERTa: Large-scale self-supervised pretraining for molecular property prediction. arXiv."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/9\/961\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T13:06:43Z","timestamp":1787663203000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/9\/961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,23]]},"references-count":46,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["bioengineering13090961"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13090961","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,23]]}}}