{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T19:37:47Z","timestamp":1770925067368,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013947","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000}}],"reference-count":54,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302198"],"award-info":[{"award-number":["62302198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Funded by Basic Research Program of Jiangsu","award":["BK20231035"],"award-info":[{"award-number":["BK20231035"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JUSRP124014"],"award-info":[{"award-number":["JUSRP124014"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>In drug discovery and therapeutic research, the prediction of drug-disease associations (DDAs) holds significant scientific and clinical value. Drug molecules exert their effects by precisely identifying disease-related biological targets, systematically modulating the entire pharmacological process from absorption, distribution, and metabolism to final efficacy. Accurate prediction of drug-disease associations not only facilitates an in-depth understanding of molecular mechanisms of drug action but also provides critical theoretical foundations for drug repositioning and personalized medicine. While traditional prediction methods based on in vitro experiments and clinical statistics yield reliable results, they suffer from inherent drawbacks such as long development cycles, substantial resource consumption, and low throughput. In contrast, emerging machine learning techniques offer a promising solution to these bottlenecks, enabling the intelligent and efficient discovery of potential drug\u2013disease association networks and significantly improving drug development efficiency. However, it is noteworthy that existing machine learning methods still face significant challenges in practical applications: the complexity of feature construction raises the threshold for data processing; data sparsity constrains the depth of information mining; and the pervasive issue of sample imbalance poses a severe challenge to the model\u2019s predictive accuracy and generalization performance. In this study, we developed an efficient and accurate framework for drug-disease association prediction named FKSUDDAPre. The model employs a multi-modal feature fusion strategy: on one hand, it leverages an ensemble of Mol2vec and K- BERT to deeply capture the semantic features of drug molecular fingerprints; on the other hand, it integrates Medical Subject Headings (MeSH) with DeepWalk to effectively reduce the dimensionality of disease features while preserving their relational structure. To address the class imbalance problem, FKSUDDAPre designed an optimization algorithm called AMDKSU, which combined clustering with an improved distance metric strategy, significantly enhancing the discriminative power of the sample set. For data processing, F-test was employed for feature importance ranking, effectively reducing data dimensionality and improving model generalization. For the predictive architecture, FKSUDDAPre proposed a novel ensemble framework composed of XGBoost, Decision Tree, Random Forest, and HyperFast. By employing a dynamic weight allocation strategy, this ensemble effectively harnesses the complementary strengths of these models to achieve significantly enhanced predictive performance. Rigorous validation demonstrated the system\u2019s outstanding performance across multiple evaluation metrics, with an average AUC of 0.9725, improving the AUC by approximately 3.88% compared to the best-performing baseline model. In the prediction of Alzheimer\u2019s disease and Parkinson\u2019s disease, 80% and 60% of the top 10 candidate drugs recommended by FKSUDDAPre, respectively, had been confirmed by literature, demonstrating the model\u2019s good practical application potential. Furthermore, we conducted a LIME-based feature importance analysis on the model\u2019s predictions, visualizing the correlations between features and the target variable to demonstrate the model\u2019s interpretability. A cross-platform, user-friendly visualization tool had also been developed using the PyQt5 framework.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013947","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T18:47:40Z","timestamp":1770317260000},"page":"e1013947","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["FKSUDDAPre: A drug\u2013disease association prediction framework based on F-TEST feature selection and AMDKSU resampling with interpretability analysis"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4021-3836","authenticated-orcid":true,"given":"Yun","family":"Zuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9691-5948","authenticated-orcid":true,"given":"Chenyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Ning","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangrong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangxiang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"issue":"5886","key":"pcbi.1013947.ref001","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1126\/science.1158140","article-title":"Drug target identification using side-effect similarity","volume":"321","author":"M Campillos","year":"2008","journal-title":"Science"},{"issue":"4","key":"pcbi.1013947.ref002","doi-asserted-by":"crossref","first-page":"221","DOI":"10.2174\/0113894501322734241008163304","article-title":"Trends of artificial intelligence (AI) use in drug targets, discovery and development: current status and future perspectives","volume":"26","author":"M Mohapatra","year":"2025","journal-title":"Curr Drug Targets"},{"issue":"4","key":"pcbi.1013947.ref003","doi-asserted-by":"crossref","first-page":"295","DOI":"10.2174\/0115748936264692230921071504","article-title":"Bioinformatics perspective of drug repurposing","volume":"19","author":"B Patel","year":"2024","journal-title":"CBIO"},{"issue":"1","key":"pcbi.1013947.ref004","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1038\/s42003-024-07107-3","article-title":"A spatial hierarchical network learning framework for drug repositioning allowing interpretation from macro to micro scale","volume":"7","author":"Z Ren","year":"2024","journal-title":"Commun Biol"},{"issue":"6","key":"pcbi.1013947.ref005","article-title":"MTMol-GPT: de novo multi-target molecular generation with transformer-based generative adversarial imitation learning","volume":"20","author":"C Ai","year":"2024","journal-title":"PLoS Comput Biol"},{"issue":"24","key":"pcbi.1013947.ref006","doi-asserted-by":"crossref","first-page":"5191","DOI":"10.1093\/bioinformatics\/btz418","article-title":"deepDR: a network-based deep learning approach to in silico drug repositioning","volume":"35","author":"X Zeng","year":"2019","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1013947.ref007","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1109\/TCBB.2013.146","article-title":"Improved and promising identification of human microRNAs by incorporating a high-quality negative set","volume":"11","author":"L Wei","year":"2014","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"pcbi.1013947.ref008","doi-asserted-by":"crossref","first-page":"112671","DOI":"10.1016\/j.knosys.2024.112671","article-title":"MFGCN: multi-faceted spatial and temporal specific graph convolutional network for traffic-flow forecasting","volume":"306","author":"J Tian","year":"2024","journal-title":"Knowl Based Syst"},{"key":"pcbi.1013947.ref009","doi-asserted-by":"crossref","first-page":"122498","DOI":"10.1016\/j.eswa.2023.122498","article-title":"Geometric deep learning for drug discovery","volume":"240","author":"M Liu","year":"2024","journal-title":"Expert Syst Appl"},{"issue":"2","key":"pcbi.1013947.ref010","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1089\/cmb.2010.0213","article-title":"Combining drug and gene similarity measures for drug-target elucidation","volume":"18","author":"L Perlman","year":"2011","journal-title":"J Comput Biol"},{"issue":"1","key":"pcbi.1013947.ref011","doi-asserted-by":"crossref","first-page":"3997","DOI":"10.1038\/s41467-025-59431-9","article-title":"Predicting rare drug-drug interaction events with dual-granular structure-adaptive and pair variational representation","volume":"16","author":"Z Ren","year":"2025","journal-title":"Nat Commun"},{"issue":"11","key":"pcbi.1013947.ref012","article-title":"Drug repositioning by kernel-based integration of molecular structure, molecular activity, and phenotype data","volume":"8","author":"Y Wang","year":"2013","journal-title":"PLoS One"},{"issue":"1","key":"pcbi.1013947.ref013","doi-asserted-by":"crossref","first-page":"91","DOI":"10.2174\/1574893618666230417104543","article-title":"SVM-Root: identification of root-associated proteins in plants by employing the support vector machine with sequence-derived features","volume":"19","author":"P Kumar Meher","year":"2024","journal-title":"CBIO"},{"issue":"11","key":"pcbi.1013947.ref014","doi-asserted-by":"crossref","first-page":"212106","DOI":"10.1007\/s11432-024-4171-9","article-title":"SBSM-Pro: support bio-sequence machine for proteins","volume":"67","author":"Y Wang","year":"2024","journal-title":"Sci China Inf Sci"},{"issue":"10","key":"pcbi.1013947.ref015","article-title":"A network-based classification model for deriving novel drug-disease associations and assessing their molecular actions","volume":"9","author":"M Oh","year":"2014","journal-title":"PLoS One"},{"issue":"12","key":"pcbi.1013947.ref016","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007541","article-title":"Overlap matrix completion for predicting drug-associated indications","volume":"15","author":"M Yang","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1013947.ref017","doi-asserted-by":"crossref","first-page":"107811","DOI":"10.1016\/j.asoc.2021.107811","article-title":"Drug\u2013disease associations prediction via multiple kernel-based dual graph regularized least squares","volume":"112","author":"H Yang","year":"2021","journal-title":"Appl Soft Comput"},{"key":"pcbi.1013947.ref018","doi-asserted-by":"crossref","first-page":"218","DOI":"10.3389\/fbioe.2020.00218","article-title":"Predicting drug-disease associations via multi-task learning based on collective matrix factorization","volume":"8","author":"F Huang","year":"2020","journal-title":"Front Bioeng Biotechnol"},{"issue":"1","key":"pcbi.1013947.ref019","doi-asserted-by":"crossref","first-page":"4972","DOI":"10.1038\/s41598-020-61616-9","article-title":"SAEROF: an ensemble approach for large-scale drug-disease association prediction by incorporating rotation forest and sparse autoencoder deep neural network","volume":"10","author":"H-J Jiang","year":"2020","journal-title":"Sci Rep"},{"issue":"9","key":"pcbi.1013947.ref020","doi-asserted-by":"crossref","first-page":"851","DOI":"10.2174\/0115748936276510231123121404","article-title":"Application of deep learning neural networks in computer-aided drug discovery: a review","volume":"19","author":"JS Mathivanan","year":"2024","journal-title":"CBIO"},{"issue":"1","key":"pcbi.1013947.ref021","doi-asserted-by":"crossref","first-page":"4382","DOI":"10.1038\/s41467-025-59634-0","article-title":"A self-conformation-aware pre-training framework for molecular property prediction with substructure interpretability","volume":"16","author":"J Qiao","year":"2025","journal-title":"Nat Commun"},{"issue":"7","key":"pcbi.1013947.ref022","article-title":"AI in drug development: advances in response, combination therapy, repositioning, and molecular design","volume":"68","author":"R Qi","year":"2025","journal-title":"Sci China Inf Sci"},{"issue":"8","key":"pcbi.1013947.ref023","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-024-4100-7","article-title":"Multiple types of disease-associated RNAs identification for disease prognosis and therapy using heterogeneous graph learning","volume":"67","author":"W Zhang","year":"2024","journal-title":"Sci China Inf Sci"},{"key":"pcbi.1013947.ref024","article-title":"BioSeq-BLM: a platform for analyzing DNA, RNA, and protein sequences based on biological language models","volume":"49","author":"H Li","year":"2021","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1013947.ref025","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1186\/s12915-024-02049-y","article-title":"Bridging chemical structure and conceptual knowledge enables accurate prediction of compound-protein interaction","volume":"22","author":"W Tao","year":"2024","journal-title":"BMC Biol"},{"issue":"5","key":"pcbi.1013947.ref026","doi-asserted-by":"crossref","first-page":"1793","DOI":"10.1109\/JBHI.2020.3039502","article-title":"Graph convolutional autoencoder and fully-connected autoencoder with attention mechanism based method for predicting drug-disease associations","volume":"25","author":"P Xuan","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"issue":"6","key":"pcbi.1013947.ref027","doi-asserted-by":"crossref","first-page":"7419","DOI":"10.3934\/mbe.2021367","article-title":"A model for predicting drug-disease associations based on dense convolutional attention network","volume":"18","author":"H Wang","year":"2021","journal-title":"Math Biosci Eng"},{"issue":"1","key":"pcbi.1013947.ref028","article-title":"HINGRL: predicting drug-disease associations with graph representation learning on heterogeneous information networks","volume":"23","author":"B-W Zhao","year":"2022","journal-title":"Brief Bioinform"},{"issue":"6","key":"pcbi.1013947.ref029","article-title":"Similarity measures-based graph co-contrastive learning for drug-disease association prediction","volume":"39","author":"Z Gao","year":"2023","journal-title":"Bioinformatics"},{"key":"pcbi.1013947.ref030","doi-asserted-by":"crossref","first-page":"111329","DOI":"10.1016\/j.knosys.2023.111329","article-title":"AMDGT: Attention aware multi-modal fusion using a dual graph transformer for drug\u2013disease associations prediction","volume":"284","author":"J Liu","year":"2024","journal-title":"Knowl Based Syst"},{"issue":"1","key":"pcbi.1013947.ref031","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1186\/s12859-024-05705-w","article-title":"Fusing graph transformer with multi-aggregate GCN for enhanced drug-disease associations prediction","volume":"25","author":"S He","year":"2024","journal-title":"BMC Bioinform"},{"issue":"3","key":"pcbi.1013947.ref032","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1038\/s41551-024-01312-5","article-title":"Interpretable identification of cancer genes across biological networks via transformer-powered graph representation learning","volume":"9","author":"X Su","year":"2025","journal-title":"Nat Biomed Eng"},{"issue":"1","key":"pcbi.1013947.ref033","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1109\/JBHI.2025.3585290","article-title":"LLM-DDI: leveraging large language models for drug-drug interaction prediction on biomedical knowledge graph","volume":"30","author":"D Li","year":"2026","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"pcbi.1013947.ref034","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1186\/s13321-025-01085-2","article-title":"SMPR: a structure-enhanced multimodal drug\u2012disease prediction model for drug repositioning and cold start","volume":"17","author":"X Dong","year":"2025","journal-title":"J Cheminform"},{"issue":"7","key":"pcbi.1013947.ref035","doi-asserted-by":"crossref","first-page":"2174","DOI":"10.1021\/acs.jcim.3c01496","article-title":"Deep generative models in de novo drug molecule generation","volume":"64","author":"C Pang","year":"2024","journal-title":"J Chem Inf Model"},{"key":"pcbi.1013947.ref036","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkw838","article-title":"The comparative toxicogenomics database: update 2017","volume":"45","author":"AP Davis","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1013947.ref037","article-title":"DrugBank 4.0: shedding new light on drug metabolism","volume":"42","author":"V Law","year":"2014","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"pcbi.1013947.ref038","first-page":"265","article-title":"Medical Subject Headings (MeSH)","volume":"88","author":"CE Lipscomb","year":"2000","journal-title":"Bull Med Libr Assoc"},{"issue":"1","key":"pcbi.1013947.ref039","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1186\/s12859-018-2220-4","article-title":"Predicting drug-disease associations by using similarity constrained matrix factorization","volume":"19","author":"W Zhang","year":"2018","journal-title":"BMC Bioinform"},{"issue":"12","key":"pcbi.1013947.ref040","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1007\/s40262-022-01180-9","article-title":"DeepIDC: a prediction framework of injectable drug combination based on heterogeneous information and deep learning","volume":"61","author":"Y Yang","year":"2022","journal-title":"Clin Pharmacokinet"},{"issue":"1","key":"pcbi.1013947.ref041","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1021\/acs.jcim.7b00616","article-title":"Mol2vec: unsupervised machine learning approach with chemical intuition","volume":"58","author":"S Jaeger","year":"2018","journal-title":"J Chem Inf Model"},{"issue":"3","key":"pcbi.1013947.ref042","article-title":"Knowledge-based BERT: a method to extract molecular features like computational chemists","volume":"23","author":"Z Wu","year":"2022","journal-title":"Brief Bioinform"},{"issue":"2","key":"pcbi.1013947.ref043","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.1093\/bib\/bbaa037","article-title":"MeSHHeading2vec: a new method for representing MeSH headings as vectors based on graph embedding algorithm","volume":"22","author":"Z-H Guo","year":"2021","journal-title":"Brief Bioinform"},{"key":"pcbi.1013947.ref044","doi-asserted-by":"crossref","first-page":"1281880","DOI":"10.3389\/fmed.2023.1281880","article-title":"Accurately identifying hemagglutinin using sequence information and machine learning methods","volume":"10","author":"X Zou","year":"2023","journal-title":"Front Med (Lausanne)"},{"key":"pcbi.1013947.ref045","first-page":"1240","article-title":"HyperFast: instant classification for tabular data","author":"B David","year":"2024","journal-title":"Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, Washington (DC): AAAI Press"},{"issue":"4","key":"pcbi.1013947.ref046","article-title":"RepliChrom: interpretable machine learning predicts cancer-associated enhancer-promoter interactions using DNA replication timing","volume":"4","author":"F Dao","year":"2025","journal-title":"iMeta"},{"issue":"6","key":"pcbi.1013947.ref047","article-title":"Methyl-GP: accurate generic DNA methylation prediction based on a language model and representation learning","volume":"53","author":"H Xie","year":"2025","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1013947.ref048","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1186\/s12915-024-01968-0","article-title":"Identification of microbe-disease signed associations via multi-scale variational graph autoencoder based on signed message propagation","volume":"22","author":"H Zhu","year":"2024","journal-title":"BMC Biol"},{"issue":"1","key":"pcbi.1013947.ref049","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1186\/s12915-024-02085-8","article-title":"Accurate RNA velocity estimation based on multibatch network reveals complex lineage in batch scRNA-seq data","volume":"22","author":"Z Huang","year":"2024","journal-title":"BMC Biol"},{"issue":"7","key":"pcbi.1013947.ref050","article-title":"Highly accurate estimation of cell type abundance in bulk tissues based on single-cell reference and domain adaptive matching","volume":"11","author":"X Guo","year":"2024","journal-title":"Adv Sci (Weinh)"},{"key":"pcbi.1013947.ref051","doi-asserted-by":"crossref","first-page":"1529335","DOI":"10.3389\/fmed.2025.1529335","article-title":"PMPred-AE: a computational model for the detection and interpretation of pathological myopia based on artificial intelligence","volume":"12","author":"H-Q Zhang","year":"2025","journal-title":"Front Med (Lausanne)"},{"key":"pcbi.1013947.ref052","doi-asserted-by":"crossref","first-page":"2416","DOI":"10.1109\/JBHI.2024.3363080","article-title":"Hierarchical and dynamic graph attention network for drug-disease association prediction","volume":"28","author":"S Huang","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"issue":"8","key":"pcbi.1013947.ref053","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1089\/cmb.2023.0078","article-title":"A graph representation approach based on light gradient boosting machine for predicting drug-disease associations","volume":"30","author":"Y Wang","year":"2023","journal-title":"J Comput Biol"},{"key":"pcbi.1013947.ref054","first-page":"1135","article-title":"\u201cWhy should i trust you?\u201d: Explaining the predictions of any classifier","author":"MT Ribeiro","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013947","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T18:57:04Z","timestamp":1770922624000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013947"}},"subtitle":[],"editor":[{"given":"Nan","family":"Sheng","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":54,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013947","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]}}}