Article
Biochemical Research Methods
Qiguo Dai, Zhaowei Wang, Ziqiang Liu, Xiaodong Duan, Jinmiao Song, Maozu Guo
Summary: In this study, a new computational method called ERMDA is proposed to predict potential disease-related miRNAs. The method addresses the challenge of sample imbalance by using a resampling strategy to build balanced training subsets. It extracts miRNA and disease feature representations and applies a feature selection approach to reduce redundancy. Experimental results demonstrate that ERMDA outperforms other methods on testing sets, and case studies confirm its prediction capability for identifying disease-related miRNAs.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Genetics & Heredity
Yidong Rao, Minzhu Xie, Hao Wang
Summary: This paper proposes a matrix completion model with bounded nuclear norm regularization, called BNNRMDA, to predict potential miRNA-disease associations. BNNRMDA makes full use of available information of miRNAs and diseases and can handle noisy data. Experimental results show that BNNRMDA achieves the best performance compared to four state-of-the-art methods.
FRONTIERS IN GENETICS
(2022)
Article
Biochemical Research Methods
Wei Liu, Hui Lin, Li Huang, Li Peng, Ting Tang, Qi Zhao, Li Yang
Summary: In this study, a new computational method called DFELMDA is proposed to predict miRNA-disease associations using deep forest ensemble learning and autoencoder. Results from experiments on the HMDD dataset show that DFELMDA outperforms other methods in terms of performance.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Agronomy
Mario Lillo-Saavedra, Alberto Espinoza-Salgado, Angel Garcia-Pedrero, Camilo Souto, Eduardo Holzapfel, Consuelo Gonzalo-Martin, Marcelo Somos-Valenzuela, Diego Rivera
Summary: Crop yield forecasting is crucial for farmers' decision-making and planning. However, current methods have limitations, such as limited data collection time. This study presents a methodology using unmanned aerial vehicles and multispectral sensors to predict tomato yield at different stages of crop development, achieving a 9.28% error rate.
Article
Biology
Bo-Ya Ji, Liang-Rui Pan, Ji-Ren Zhou, Zhu-Hong You, Shao-Liang Peng
Summary: This study presented a computational method called SMMDA for predicting potential associations between miRNAs and diseases. SMMDA achieved high accuracy and AUC, outperforming previous works. The experimental results showed that SMMDA has a reliable prediction ability in miRNA-disease associations and could be an effective tool for biomedical researchers.
Article
Genetics & Heredity
Cunmei Ji, Yutian Wang, Jiancheng Ni, Chunhou Zheng, Yansen Su
Summary: Recent evidence suggests that miRNAs play a critical role in human diseases, but the underlying mechanisms remain unclear. The proposed HGATMDA method shows promising results in predicting miRNA-disease associations, with validation datasets confirming its effectiveness.
FRONTIERS IN GENETICS
(2021)
Article
Biochemical Research Methods
Ruiyu Guo, Hailin Chen, Wengang Wang, Guangsheng Wu, Fangliang Lv
Summary: The study proposes a computational method called KR-NSSM for selecting more reliable negative samples for miRNA-disease association predictions. By integrating two semi-supervised algorithms, the method effectively screens out reliable negative samples from unlabelled data, improving prediction accuracy and obtaining confirmation in known miRNA-disease association prediction models. This method could be a useful tool in negative sample selection for biomedical research.
BMC BIOINFORMATICS
(2022)
Article
Multidisciplinary Sciences
Syed Nisar Hussain Bukhari, Julian Webber, Abolfazl Mehbodniya
Summary: Zika fever, caused by the Zika virus, is a global infectious disease with no clinically approved vaccine. The study presents a computational model for predicting T-cell epitopes of the virus, which shows promising results and outperforms standard machine learning algorithms.
SCIENTIFIC REPORTS
(2022)
Article
Biochemical Research Methods
Xinguo Lu, Yan Gao, Zhenghao Zhu, Li Ding, Xinyu Wang, Fang Liu, Jinxin Li
Summary: This study introduces a novel method called CPMDA for predicting microRNA-disease associations with only a few known associations. The approach involves constructing disease similarity networks, applying probabilistic factorization, and utilizing similarity feature matrices as constraints. CPMDA outperforms other methods in predicting potential microRNA-disease associations and effectively infers associations for novel microRNAs and diseases.
CURRENT BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
Zhou Huang, Yu Han, Leibo Liu, Qinghua Cui, Yuan Zhou
Summary: MicroRNAs (miRNAs) are intricately linked to complex human diseases, with some directly involved in disease mechanisms. The study developed a Levenshtein-Distance-Enhanced miRNA-disease Causal Association Predictor (LE-MDCAP) model to predict potential causal miRNA-disease associations, outperforming previous models in distinguishing causal versus non-causal associations. Case studies further validated the accuracy of the model in identifying causal miRNA-disease associations.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Mathematical & Computational Biology
Yu ShengPeng, Wang Hong
Summary: This study proposed a new method based on similarity constrained learning to infer disease-associated miRNAs, achieving high AUC scores in global and local cross-validation. The prediction performance of RSCMDA was further confirmed by a case study on lung Neoplasms, demonstrating its reliability and effectiveness as a framework for exploring the relationship between miRNA and disease.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2021)
Article
Engineering, Aerospace
ZhongJie Shen, Haisheng Deng, Alireza Arabameri, M. Santosh, Matej Vojtek, Jana Vojtekova
Summary: This study presents innovative ensemble models for mapping potential inundation areas due to riverine floods in the Najafabad basin in Iran. The models showed high accuracy in both the training and testing phases, with the ensemble MB-CDT model performing the best. The results are useful for flood risk management, especially in the preliminary phase.
ADVANCES IN SPACE RESEARCH
(2023)
Article
Biochemical Research Methods
Xue-Jun Chen, Xin-Yun Hua, Zhen-Ran Jiang
Summary: The study found that the noise in the data has a significant impact on predicting potential miRNA-disease associations. The proposed anti-noise algorithm ANMDA outperforms several published methods and is a novel and practical tool for inferring miRNA-disease associations.
BMC BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Zhengwei Li, Jiashu Li, Ru Nie, Zhu-Hong You, Wenzheng Bao
Summary: The abnormal expression of miRNAs is associated with the evolution and progression of various human complex diseases. Identifying disease-related miRNAs as new biomarkers can promote the development of disease pathology and clinical medicine. Designing biological experiments to validate disease-related miRNAs is usually time-consuming and expensive, highlighting the need for effective computational methods to predict potential miRNA-disease associations.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Polymer Science
Muhammad Nasir Amin, Mudassir Iqbal, Kaffayatullah Khan, Muhammad Ghulam Qadir, Faisal Shalabi, Arshad Jamal
Summary: This research focuses on estimating the flexural capacity of FRP-reinforced concrete beams using AI decision tree and gradient boosting tree approaches. The depth of the beam is found to be the most influential parameter. The GBT model is more accurate and robust than the DT model, but the current ACI model equations are more reliable for predicting flexural strength.
Review
Biochemical Research Methods
Chun-Chun Wang, Yan Zhao, Xing Chen
Summary: Efforts are needed to develop effective drugs for complex diseases. Traditional drug discovery methods are time-consuming and costly, leading to the proposal of pathway-based drug discovery. Computational models have been established to predict drug-pathway associations, facilitating the development of new drugs.
BRIEFINGS IN BIOINFORMATICS
(2021)
Review
Biochemical Research Methods
Yan Zhao, Chun-Chun Wang, Xing Chen
Summary: Research has shown that the number of microbes in the human body is almost 10 times higher than the number of cells, and they play crucial roles in immune function, digestion, and metabolism. Recent studies have revealed close relationships between noncommunicable diseases and microbes, providing new insights into disease pathogenesis. Computational models have been developed to predict disease-related microbes, potentially revolutionizing disease diagnosis, treatment, and drug development.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Chun-Chun Wang, Chi-Chi Zhu, Xing Chen
Summary: MicroRNAs (miRNAs) play important roles in human disease, and identifying SM-miRNA associations is crucial for drug development and treatment. This study proposes EKRRSMMA, a method that combines feature dimensionality reduction and ensemble learning to predict potential SM-miRNA associations. Evaluation and case studies confirm the reliability of EKRRSMMA.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Shu-Hao Wang, Chun-Chun Wang, Li Huang, Lian-Ying Miao, Xing Chen
Summary: In this study, a novel method called Dual-network Collaborative Matrix Factorization (DCMF) was proposed for predicting potential SM-miRNA associations. The method utilized the Weighted K Nearest Known Neighbors (WKNKN) method to preprocess the association matrix and introduced a dual network to incorporate more diverse similarity information. The effectiveness of DCMF was evaluated through cross validations and case studies, achieving high AUC values.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Chun-Chun Wang, Tian-Hao Li, Li Huang, Xing Chen
Summary: In recent years, miRNA has been shown to play an important role in the development of human complex diseases. This study introduces a computational model called SAEMDA, which utilizes computational methods based on biological data to discover miRNA-disease associations. SAEMDA is able to make full use of the feature information of all unlabeled miRNA-disease pairs and is suitable for datasets with small labeled samples and large unlabeled samples. Experimental results show that SAEMDA outperforms previous models in terms of predictive accuracy.
BRIEFINGS IN BIOINFORMATICS
(2022)
Editorial Material
Biochemical Research Methods
Xing Chen, Li Huang
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemical Research Methods
Li Huang, Li Zhang, Xing Chen
Summary: MicroRNAs (miRNAs) are important gene regulators in the pathogenesis of complex diseases and have potential applications in diagnosis and therapy. Accurate discovery of miRNA-disease associations (MDAs) is crucial for effective miRNA therapy. This review revisits miRNA biogenesis, detection techniques, and functions, summarizes recent experimental findings related to common miRNA-associated diseases, introduces updates of relevant databases and web servers, and discusses the contribution of diverse data sources to accurate MDA prediction.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemical Research Methods
Li Huang, Li Zhang, Xing Chen
Summary: There is currently no widely accepted strategy for evaluating computational models for microRNA-disease associations (MDAs). The evaluation methods and procedures are often determined on a case-by-case basis and depend on the choices of researchers. This review provides a comprehensive analysis of the evaluation methods used for 29 state-of-the-art models predicting MDAs and recommends a feasible evaluation workflow for future models.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemical Research Methods
Li Huang, Li Zhang, Xing Chen
Summary: In this review, 29 state-of-the-art models for microRNA-disease association (MDA) prediction based on model fusion and non-fusion are presented. The new taxonomy demonstrates changes in the algorithmic architecture of models compared to earlier classifications. Furthermore, the progress made in overcoming obstacles to effective MDA prediction since 2017 is discussed, and future research directions are proposed for enhancing model performance.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Li Zhang, Chun-Chun Wang, Xing Chen
Summary: This study presents a novel model called MRBDTA to improve the existing computational models for drug-target binding affinity prediction. MRBDTA achieves better performance in prediction accuracy and can provide interpretability analysis. The case studies demonstrate the reliable performance of MRBDTA in drug design for SARS-CoV-2.
BRIEFINGS IN BIOINFORMATICS
(2022)
Editorial Material
Biochemical Research Methods
Xing Chen, Li Huang
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Tian-Hao Li, Chun-Chun Wang, Li Zhang, Xing Chen
Summary: Synergistic drug combinations can improve therapeutic effect and reduce toxicity. Computational methods are efficient tools for predicting potential synergistic drug combinations. We developed a new model called SNRMPACDC, which achieved better results in predicting anticancer synergistic drug combinations.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Chen-Di Han, Chun-Chun Wang, Li Huang, Xing Chen
Summary: Adverse drug-drug interactions (DDIs) have become a serious problem in healthcare. Researchers have proposed a Multi-Channel Feature Fusion model for multi-typed DDI prediction (MCFF-MTDDI), which effectively fuses different features extracted from drug chemical structure, drug pairs' extra label, and drug knowledge graph (KG) to predict multi-typed DDIs. The results of experiments on multiple datasets demonstrate the effectiveness of MCFF-MTDDI.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biology
Lihong Peng, Jingwei Tan, Wei Xiong, Li Zhang, Zhao Wang, Ruya Yuan, Zejun Li, Xing Chen
Summary: The study introduces a new deep learning framework, CellComNet, which deciphers cell-cell communication mediated by extracellular molecules through the analysis of single-cell transcriptomic data. The framework demonstrates efficient identification of credible LRIs and significantly improves the inference performance of cell-cell communication. It has the potential to contribute to anticancer drug design and tumor-targeted therapy.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biochemical Research Methods
Lihong Peng, Ruya Yuan, Chendi Han, Guosheng Han, Jingwei Tan, Zhao Wang, Min Chen, Xing Chen
Summary: Cell-to-cell communication (CCC) plays significant roles in multicellular organisms, especially in cancer genesis, development, and metastasis. This manuscript presents a Boosting-based LRI identification model (CellEnBoost) for predicting and interpreting ligand-receptor interactions in CCC. Experimental results demonstrate the superior performance of this model and its validation in human head and neck squamous cell carcinoma tissues.
IEEE TRANSACTIONS ON NANOBIOSCIENCE
(2023)