{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T16:36:30Z","timestamp":1787330190972,"version":"build-2736575974"},"reference-count":78,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010211","name":"Jilin Provincial Department of Education Research Project","doi-asserted-by":"publisher","award":["JJKH20262389CY"],"award-info":[{"award-number":["JJKH20262389CY"]}],"id":[{"id":"10.13039\/501100010211","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41701054"],"award-info":[{"award-number":["41701054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["41701054"],"award-info":[{"award-number":["41701054"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Mol. Sci.","IJMS"],"abstract":"<jats:p>Accurately predicting the carcinogenicity of compounds is of great significance for drug discovery, clinical drug safety, and chemical risk assessment. Traditional methods for assessing carcinogenicity rely on animal testing, which suffers from limitations such as time-consuming processes, high costs, significant interspecies differences, and low predictive throughput. In recent years, computational modeling-based prediction methods (such as Quantitative Structure\u2013Activity Relationships, QSAR) have made some progress, but they still face challenges such as insufficient molecular feature information and poor model interpretability. To overcome these barriers, the multimodal deep learning framework LMF-CP (Late Multimodal Fusion of Carcinogenicity Prediction) is proposed to enhance the performance and interpretability of compound carcinogenicity prediction. First, to comprehensively characterize the structural and physicochemical properties of compounds, a multimodal representation system based on four molecular modalities is constructed, namely SMILES sequences, molecular fingerprints, molecular images, and molecular graph structures. Specifically, Text Convolutional Neural Network (TextCNN), Multi-Layer Perceptron (MLP), Visual Geometry Group Network (VGGNet), as well as Molecular Graph Attention Network (MGAT) are employed to process this information, respectively. Second, to integrate information from different molecular representations, a late-stage fusion strategy based on Lasso stacking is employed. On the test set, LMF-CP achieves an area under curve (AUC) of 0.828, an accuracy (ACC) of 0.782, an F1 score of 0.786, a sensitivity (SEN) of 0.786, and a specificity (SPE) of 0.779. In addition, this paper combines Shapley Additive Explanations (SHAP) analysis with Bemis\u2013Murcko scaffold analysis to interpret the model results from two perspectives. Finally, a visual online platform for predicting the carcinogenicity of compounds is designed, providing a convenient tool for the rapid assessment of compound carcinogenicity and structural interpretation.<\/jats:p>","DOI":"10.3390\/ijms27167499","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:51:05Z","timestamp":1787327465000},"page":"7499","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LMF-CP: An Interpretable Multimodal Late-Fusion Framework for Compound Carcinogenicity Prediction"],"prefix":"10.3390","volume":"27","author":[{"given":"Yingjie","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2939-4838","authenticated-orcid":false,"given":"Liujie","family":"He","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3765-6537","authenticated-orcid":false,"given":"Xinjie","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Changchun University, Changchun 130022, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"ref_1","first-page":"e70090","article-title":"Global cancer statistics 2024: GLOBOCAN estimates of incidence and mortality worldwide for 34 cancers in 186 countries","volume":"76","author":"Sung","year":"2026","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"100117","DOI":"10.1016\/j.gloepi.2023.100117","article-title":"Perspectives on recent reviews of aspartame cancer epidemiology","volume":"6","author":"Goodman","year":"2023","journal-title":"Glob. Epidemiol."},{"key":"ref_3","unstructured":"Chen, Z. (2023). Research on Compound Carcinogenicity Prediction Based on Capsule Network and Attention Mechanism Chinese. [Master\u2019s Thesis, Liaoning University]. (In Chinese)."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2418","DOI":"10.1016\/j.mayocp.2021.01.036","article-title":"Nonlinear associations between cumulative dietary risk factors and cardiovascular diseases, cancer, and all-cause mortality: A prospective cohort study from UK Biobank","volume":"Volume 96","author":"Ho","year":"2021","journal-title":"Proceedings of the Mayo Clinic Proceedings"},{"key":"ref_5","unstructured":"Wu, C. (2022). Research on Screening of Carcinogenic Chemicals Based on Machine Learning Algorithms Chinese. [Master\u2019s Thesis, Dalian University of Technology]. (In Chinese)."},{"key":"ref_6","first-page":"33","article-title":"Carcinogenicity Prediction Model for Compounds Based on SGCN","volume":"48","author":"Wei","year":"2022","journal-title":"Appl. Electron. Tech."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2940","DOI":"10.1021\/cr300206t","article-title":"Nongenotoxic carcinogenicity of chemicals: Mechanisms of action and early recognition through a new set of structural alerts","volume":"113","author":"Benigni","year":"2013","journal-title":"Chem. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1080\/10590501.2016.1166879","article-title":"New clues on carcinogenicity-related substructures derived from mining two large datasets of chemical compounds","volume":"34","author":"Golbamaki","year":"2016","journal-title":"J. Environ. Sci. Health Part C"},{"key":"ref_9","first-page":"2755","article-title":"Key Points for Analysis of Rodent Carcinogenicity Test Results in Non-clinical Safety Evaluation of New Drugs","volume":"27","author":"Zhang","year":"2018","journal-title":"Chin. J. New Drugs"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1039\/c8tx00051d","article-title":"Big-data and machine learning to revamp computational toxicology and its use in risk assessment","volume":"7","author":"Luechtefeld","year":"2018","journal-title":"Toxicol. Res."},{"key":"ref_11","unstructured":"Peng, X. (2021). Research on Carcinogenic Compound Identification Method Based on Network Embedding and Association Relationships Chinese. [Master\u2019s Thesis, Shanghai Maritime University]. (In Chinese)."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1021\/acs.jcim.5b00229","article-title":"Understanding the roles of the \u201ctwo QSARs\u201d","volume":"56","author":"Fujita","year":"2016","journal-title":"J. Chem. Inf. Model."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1021\/ci600299j","article-title":"Local and global quantitative structure- activity relationship modeling and prediction for the baseline toxicity","volume":"47","author":"Yuan","year":"2007","journal-title":"J. Chem. Inf. Model."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s11030-005-9001-5","article-title":"Lazy structure-activity relationships (lazar) for the prediction of rodent carcinogenicity and Salmonella mutagenicity","volume":"10","author":"Helma","year":"2006","journal-title":"Mol. Divers."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1517\/17425255.2010.486400","article-title":"Alternatives to the carcinogenicity bioassay: In silico methods, and the in vitro and in vivo mutagenicity assays","volume":"6","author":"Benigni","year":"2010","journal-title":"Expert Opin. Drug Metab. Toxicol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11030-009-9190-4","article-title":"Quantitative and qualitative models for carcinogenicity prediction for non-congeneric chemicals using CP ANN method for regulatory uses","volume":"14","author":"Fjodorova","year":"2010","journal-title":"Mol. Divers."},{"key":"ref_17","first-page":"406","article-title":"A Computational Model for Predicting TD50 of Chemical Carcinogens Based on QSAR","volume":"25","author":"Li","year":"2011","journal-title":"J. Toxicol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1080\/1062936X.2012.762425","article-title":"Improvement of carcinogenicity prediction performances based on sensitivity analysis in variable selection of SVM models","volume":"24","author":"Tanabe","year":"2013","journal-title":"SAR QSAR Environ. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1021\/tx4000182","article-title":"Carcinogenicity prediction of noncongeneric chemicals by a support vector machine","volume":"26","author":"Zhong","year":"2013","journal-title":"Chem. Res. Toxicol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2118","DOI":"10.1038\/s41598-017-02365-0","article-title":"CarcinoPred-EL: Novel models for predicting the carcinogenicity of chemicals using molecular fingerprints and ensemble learning methods","volume":"7","author":"Zhang","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.fct.2016.09.005","article-title":"Novel na\u00efve Bayes classification models for predicting the carcinogenicity of chemicals","volume":"97","author":"Zhang","year":"2016","journal-title":"Food Chem. Toxicol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"112802","DOI":"10.1016\/j.fct.2021.112802","article-title":"A machine learning-driven approach for prioritizing food contact chemicals of carcinogenic concern based on complementary in silico methods","volume":"160","author":"Wang","year":"2022","journal-title":"Food Chem. Toxicol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"i84","DOI":"10.1093\/bioinformatics\/btac266","article-title":"A graph neural network approach for molecule carcinogenicity prediction","volume":"38","author":"Fradkin","year":"2022","journal-title":"Bioinformatics"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Limbu, S., and Dakshanamurthy, S. (2022). Predicting chemical carcinogens using a hybrid neural network deep learning method. Sensors, 22.","DOI":"10.3390\/s22218185"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3117","DOI":"10.1111\/jcmm.17889","article-title":"DCAMCP: A deep learning model based on capsule network and attention mechanism for molecular carcinogenicity prediction","volume":"27","author":"Chen","year":"2023","journal-title":"J. Cell. Mol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"8385","DOI":"10.1021\/acs.jcim.5c01362","article-title":"MMF-MCP: A Deep Transfer Learning Model Based on Multimodal Information Fusion for Molecular Feature Extraction and Carcinogenicity Prediction","volume":"65","author":"Liu","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"10194","DOI":"10.1021\/acs.jcim.5c01873","article-title":"Toward explainable carcinogenicity prediction: An integrated cheminformatics approach and consensus framework for possibly carcinogenic chemicals","volume":"65","author":"Duy","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1021\/acs.jcim.8b00785","article-title":"Predictive multitask deep neural network models for ADME-Tox properties: Learning from large data sets","volume":"59","author":"Wenzel","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"108202","DOI":"10.1016\/j.compchemeng.2023.108202","article-title":"Physical pooling functions in graph neural networks for molecular property prediction","volume":"172","author":"Schweidtmann","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Snoek, C.G., Worring, M., and Smeulders, A.W. (2005, January 6\u201311). Early versus late fusion in semantic video analysis. Proceedings of the 13th Annual ACM International Conference on Multimedia, Singapore.","DOI":"10.1145\/1101149.1101236"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","article-title":"Multimodal fusion for multimedia analysis: A survey","volume":"16","author":"Atrey","year":"2010","journal-title":"Multimed. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1038\/s42256-023-00640-6","article-title":"Multitask joint strategies of self-supervised representation learning on biomedical networks for drug discovery","volume":"5","author":"Wang","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1109\/TPAMI.2015.2461544","article-title":"Moddrop: Adaptive multi-modal gesture recognition","volume":"38","author":"Neverova","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","unstructured":"Liu, K., Li, Y., Xu, N., and Natarajan, P. (2018). Learn to combine modalities in multimodal deep learning. arXiv."},{"key":"ref_35","unstructured":"Liu, S., Wang, H., Liu, W., Lasenby, J., Guo, H., and Tang, J. (2021). Pre-training molecular graph representation with 3d geometry. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhu, J., Xia, Y., Wu, L., Xie, S., Zhou, W., Qin, T., Li, H., and Liu, T.Y. (2023, January 6\u201310). Dual-view molecular pre-training. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Long Beach, CA, USA.","DOI":"10.1145\/3580305.3599317"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"125403","DOI":"10.1016\/j.eswa.2024.125403","article-title":"MIDF-DMAP: Multimodal information dynamic fusion for drug molecule activity prediction","volume":"260","author":"Yi","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_38","unstructured":"Lu, X., Xie, L., Xu, L., Mao, R., Chang, S., and Xu, X. (2023). Integrating chemical language and molecular graph in multimodal fused deep learning for drug property prediction. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"37549","DOI":"10.1021\/acsomega.5c03753","article-title":"A Comparative Evaluation of Machine Learning and Deep Graph Learning for Chemical Ecotoxicological Prediction","volume":"10","author":"Lou","year":"2025","journal-title":"ACS Omega"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Vapnik","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Xia, J., Zhao, C., Hu, B., Gao, Z., Tan, C., Liu, Y., Li, S., and Li, S.Z. (2023, January 1\u20135). Mole-BERT: Rethinking Pre-Training Graph Neural Networks for Molecules. Proceedings of the International Conference on Learning Representations, Kigali, Rwanda.","DOI":"10.26434\/chemrxiv-2023-dngg4"},{"key":"ref_43","unstructured":"Ahmad, W., Simon, E., Chithrananda, S., Grand, G., and Ramsundar, B. (2022). ChemBERTa-2: Towards Chemical Foundation Models. arXiv."},{"key":"ref_44","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_45","first-page":"18198","article-title":"Towards trustable SHAP scores","volume":"39","author":"Huang","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e29","DOI":"10.1017\/eds.2025.19","article-title":"The influence of correlated features on neural network attribution methods in geoscience","volume":"4","author":"Krell","year":"2025","journal-title":"Environ. Data Sci."},{"key":"ref_47","unstructured":"Janzing, D., Minorics, L., and Bl\u00f6baum, P. (2020, January 26\u201328). Feature relevance quantification in explainable AI: A causal problem. Proceedings of the International Conference on Artificial Intelligence and Statistics, Online."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"11558","DOI":"10.1021\/acs.jcim.5c01586","article-title":"Establishment of an Integrated Model for Predicting Compound Mutagenicity with a Feature Importance Analysis","volume":"65","author":"Yang","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1021\/jm040835a","article-title":"Derivation and validation of toxicophores for mutagenicity prediction","volume":"48","author":"Kazius","year":"2005","journal-title":"J. Med. Chem."},{"key":"ref_50","unstructured":"Grimmer, G. (2018). Environmental Carcinogens: Polycyclic Aromatic Hydrocarbons, CRC Press."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"124816","DOI":"10.1016\/j.envpol.2024.124816","article-title":"Review of polycyclic aromatic hydrocarbons pollution characteristics and carcinogenic risk assessment in global cooking environments","volume":"361","author":"Bai","year":"2024","journal-title":"Environ. Pollut."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1093\/toxsci\/kfv040","article-title":"Polycyclic aromatic hydrocarbons: From metabolism to lung cancer","volume":"145","author":"Moorthy","year":"2015","journal-title":"Toxicol. Sci."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1007\/s12539-024-00680-5","article-title":"A domain adaptive interpretable substructure-aware graph attention network for drug\u2013drug interaction prediction","volume":"17","author":"Zhang","year":"2025","journal-title":"Interdiscip. Sci. Comput. Life Sci."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1762","DOI":"10.1109\/JBHI.2024.3354121","article-title":"SSCRB: Predicting circRNA-RBP interaction sites using a sequence and structural feature-based attention model","volume":"28","author":"Liu","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/s42256-021-00438-4","article-title":"Geometry-enhanced molecular representation learning for property prediction","volume":"4","author":"Fang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"4363","DOI":"10.1038\/s41467-024-48616-3","article-title":"Drug screening on digital microfluidics for cancer precision medicine","volume":"15","author":"Zhai","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1093\/toxsci\/kfi161","article-title":"Supplement to the Carcinogenic Potency Database (CPDB): Results of animal bioassays published in the general literature through 1997 and by the National Toxicology Program in 1997\u20131998","volume":"85","author":"Gold","year":"2005","journal-title":"Toxicol. Sci."},{"key":"ref_58","unstructured":"Cameron, T., Stump, J., and Schofield, L. (1985). Chemical Carcinogenesis Research Information System (ccris) Data Bank, 1981-June 1986 (1988 Version). Data File, National Cancer Inst.. Technical Report."},{"key":"ref_59","first-page":"48","article-title":"A novel approach: Chemical relational databases, and the role of the ISSCAN database on assessing chemical carcinogenicity","volume":"44","author":"Benigni","year":"2008","journal-title":"Ann. dell\u2019Istituto Super. Sanit\u00e0"},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"bbab138","DOI":"10.1093\/bib\/bbab138","article-title":"Pharmacometabonomics: Data processing and statistical analysis","volume":"22","author":"Fu","year":"2021","journal-title":"Brief. Bioinform."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"bbac455","DOI":"10.1093\/bib\/bbac455","article-title":"LargeMetabo: An out-of-the-box tool for processing and analyzing large-scale metabolomic data","volume":"23","author":"Yang","year":"2022","journal-title":"Brief. Bioinform."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"bbac234","DOI":"10.1093\/bib\/bbac234","article-title":"Cell\u2013cell communication inference and analysis in the tumour microenvironments from single-cell transcriptomics: Data resources and computational strategies","volume":"23","author":"Peng","year":"2022","journal-title":"Brief. Bioinform."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","article-title":"PubChem 2025 update","volume":"53","author":"Kim","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1021\/ci010132r","article-title":"Reoptimization of MDL keys for use in drug discovery","volume":"42","author":"Durant","year":"2002","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_65","unstructured":"Wang, T. (2023). Research on Compound hERG Toxicity Prediction Based on Deep Learning and Molecular Fingerprints. [Master\u2019s Thesis, University of Science and Technology Liaoning]. (In Chinese)."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1021\/ci025584y","article-title":"The Chemistry Development Kit (CDK): An open-source Java library for chemo-and bioinformatics","volume":"43","author":"Steinbeck","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_67","unstructured":"Landrum, G., Tosco, P., Kelley, B., Rodriguez, R., Cosgrove, D., Vianello, R., Gedeck, P., Jones, G., and Nealschneider, D. (2026, August 17). rdkit\/rdkit: 2024_03_6 (Q1 2024) Release. Zenodo. Available online: https:\/\/zenodo.org\/records\/13469390."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"1466","DOI":"10.1002\/jcc.21707","article-title":"PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints","volume":"32","author":"Yap","year":"2011","journal-title":"J. Comput. Chem."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.ymeth.2023.11.014","article-title":"Predicting drug-induced liver injury using graph attention mechanism and molecular fingerprints","volume":"221","author":"Wang","year":"2024","journal-title":"Methods"},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Bjerrum, E., Rastemo, T., Irwin, R., Kannas, C., and Genheden, S. (2021). PySMILESUtils\u2014Enabling deep learning with the SMILES chemical language. ChemRxiv.","DOI":"10.26434\/chemrxiv-2021-kzhbs"},{"key":"ref_72","first-page":"62","article-title":"A Molecular Property Prediction Method Based on Deep Learning Multimodal Fusion","volume":"42","author":"Lin","year":"2025","journal-title":"J. Nanning Norm. Univ. (Nat. Sci. Ed.)"},{"key":"ref_73","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_74","doi-asserted-by":"crossref","first-page":"101819","DOI":"10.1016\/j.compenvurbsys.2022.101819","article-title":"W-TextCNN: A TextCNN model with weighted word embeddings for Chinese address pattern classification","volume":"95","author":"Zhang","year":"2022","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_75","doi-asserted-by":"crossref","first-page":"108751","DOI":"10.1016\/j.compeleceng.2023.108751","article-title":"TextCNN-based ensemble learning model for Japanese Text Multi-classification","volume":"109","author":"Chen","year":"2023","journal-title":"Comput. Electr. Eng."},{"key":"ref_76","unstructured":"Nainwal, A., Sharma, G., Kansal, V., Bhatla, S., and Pant, B. (2023). Comparative study of VGG-13, AlexNet, MobileNet and modified-DarkCovidNet for chest X-ray classification. Proceedings of the 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 15\u201317 March 2023, IEEE."},{"key":"ref_77","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/TCBB.2022.3205282","article-title":"Modality-DTA: Multimodality fusion strategy for drug\u2013target affinity prediction","volume":"20","author":"Yang","year":"2022","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_78","doi-asserted-by":"crossref","first-page":"120754","DOI":"10.1016\/j.eswa.2023.120754","article-title":"TripletMultiDTI: Multimodal representation learning in drug-target interaction prediction with triplet loss function","volume":"232","author":"Dehghan","year":"2023","journal-title":"Expert Syst. Appl."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/16\/7499\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:51:49Z","timestamp":1787327509000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/16\/7499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":78,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["ijms27167499"],"URL":"https:\/\/doi.org\/10.3390\/ijms27167499","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]}}}