1
|
González-Colom R, Mitra K, Vela E, Gezsi A, Paajanen T, Gál Z, Hullam G, Mäkinen H, Nagy T, Kuokkanen M, Piera-Jiménez J, Roca J, Antal P, Juhasz G, Cano I. Multicentric Assessment of a Multimorbidity-Adjusted Disability Score to Stratify Depression-Related Risks Using Temporal Disease Maps: Instrument Validation Study. J Med Internet Res 2024; 26:e53162. [PMID: 38913991 PMCID: PMC11231623 DOI: 10.2196/53162] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Revised: 11/23/2023] [Accepted: 05/23/2024] [Indexed: 06/26/2024] Open
Abstract
BACKGROUND Comprehensive management of multimorbidity can significantly benefit from advanced health risk assessment tools that facilitate value-based interventions, allowing for the assessment and prediction of disease progression. Our study proposes a novel methodology, the Multimorbidity-Adjusted Disability Score (MADS), which integrates disease trajectory methodologies with advanced techniques for assessing interdependencies among concurrent diseases. This approach is designed to better assess the clinical burden of clusters of interrelated diseases and enhance our ability to anticipate disease progression, thereby potentially informing targeted preventive care interventions. OBJECTIVE This study aims to evaluate the effectiveness of the MADS in stratifying patients into clinically relevant risk groups based on their multimorbidity profiles, which accurately reflect their clinical complexity and the probabilities of developing new associated disease conditions. METHODS In a retrospective multicentric cohort study, we developed the MADS by analyzing disease trajectories and applying Bayesian statistics to determine disease-disease probabilities combined with well-established disability weights. We used major depressive disorder (MDD) as a primary case study for this evaluation. We stratified patients into different risk levels corresponding to different percentiles of MADS distribution. We statistically assessed the association of MADS risk strata with mortality, health care resource use, and disease progression across 1 million individuals from Spain, the United Kingdom, and Finland. RESULTS The results revealed significantly different distributions of the assessed outcomes across the MADS risk tiers, including mortality rates; primary care visits; specialized care outpatient consultations; visits in mental health specialized centers; emergency room visits; hospitalizations; pharmacological and nonpharmacological expenditures; and dispensation of antipsychotics, anxiolytics, sedatives, and antidepressants (P<.001 in all cases). Moreover, the results of the pairwise comparisons between adjacent risk tiers illustrate a substantial and gradual pattern of increased mortality rate, heightened health care use, increased health care expenditures, and a raised pharmacological burden as individuals progress from lower MADS risk tiers to higher-risk tiers. The analysis also revealed an augmented risk of multimorbidity progression within the high-risk groups, aligned with a higher incidence of new onsets of MDD-related diseases. CONCLUSIONS The MADS seems to be a promising approach for predicting health risks associated with multimorbidity. It might complement current risk assessment state-of-the-art tools by providing valuable insights for tailored epidemiological impact analyses of clusters of interrelated diseases and by accurately assessing multimorbidity progression risks. This study paves the way for innovative digital developments to support advanced health risk assessment strategies. Further validation is required to generalize its use beyond the initial case study of MDD.
Collapse
Affiliation(s)
- Rubèn González-Colom
- Fundació de Recerca Clínic Barcelona - Institut d'Investigacions Biomèdiques August Pi i Sunyer, Barcelona, Spain
| | - Kangkana Mitra
- Fundació de Recerca Clínic Barcelona - Institut d'Investigacions Biomèdiques August Pi i Sunyer, Barcelona, Spain
| | - Emili Vela
- Catalan Health Service, Barcelona, Spain
- Digitalization for the Sustainability of the Healthcare - Institut d'Investigació Biomèdica de Bellvitge, Barcelona, Spain
| | - Andras Gezsi
- Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary
| | - Teemu Paajanen
- Department of Public Health and Welfare, Finnish Health and Welfare Institute, Helsinki, Finland
| | - Zsófia Gál
- Department of Pharmacodynamics, Faculty of Pharmacy, Semmelweis University, Budapest, Hungary
- NAP3.0-SE Neuropsychopharmacology Research Group, Hungarian Brain Research Program, Semmelweis University, Budapest, Hungary
| | - Gabor Hullam
- Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary
- NAP3.0-SE Neuropsychopharmacology Research Group, Hungarian Brain Research Program, Semmelweis University, Budapest, Hungary
| | - Hannu Mäkinen
- Department of Public Health and Welfare, Finnish Health and Welfare Institute, Helsinki, Finland
| | - Tamas Nagy
- Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary
- Department of Pharmacodynamics, Faculty of Pharmacy, Semmelweis University, Budapest, Hungary
- NAP3.0-SE Neuropsychopharmacology Research Group, Hungarian Brain Research Program, Semmelweis University, Budapest, Hungary
| | - Mikko Kuokkanen
- Department of Public Health and Welfare, Finnish Health and Welfare Institute, Helsinki, Finland
- Department of Human Genetics and South Texas Diabetes and Obesity Institute, School of Medicine at University of Texas Rio Grande Valley, Brownsville, TX, United States
- Research Program for Clinical and Molecular Metabolism, Faculty of Medicine, University of Helsinki, Helsinki, Finland
| | - Jordi Piera-Jiménez
- Catalan Health Service, Barcelona, Spain
- Digitalization for the Sustainability of the Healthcare - Institut d'Investigació Biomèdica de Bellvitge, Barcelona, Spain
- Faculty of Informatics, Telecommunications and Multimedia, Universitat Oberta de Catalunya, Barcelona, Spain
| | - Josep Roca
- Fundació de Recerca Clínic Barcelona - Institut d'Investigacions Biomèdiques August Pi i Sunyer, Barcelona, Spain
- Hospital Clínic de Barcelona, Barcelona, Spain
- Faculty of Medicine, Universitat de Barcelona, Barcelona, Spain
| | - Peter Antal
- Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary
| | - Gabriella Juhasz
- Department of Pharmacodynamics, Faculty of Pharmacy, Semmelweis University, Budapest, Hungary
- NAP3.0-SE Neuropsychopharmacology Research Group, Hungarian Brain Research Program, Semmelweis University, Budapest, Hungary
| | - Isaac Cano
- Fundació de Recerca Clínic Barcelona - Institut d'Investigacions Biomèdiques August Pi i Sunyer, Barcelona, Spain
- Faculty of Medicine, Universitat de Barcelona, Barcelona, Spain
| |
Collapse
|
2
|
Zhang J, Xie M. Graph regularized non-negative matrix factorization with [Formula: see text] norm regularization terms for drug-target interactions prediction. BMC Bioinformatics 2023; 24:375. [PMID: 37789278 PMCID: PMC10548602 DOI: 10.1186/s12859-023-05496-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2023] [Accepted: 09/22/2023] [Indexed: 10/05/2023] Open
Abstract
BACKGROUND Identifying drug-target interactions (DTIs) plays a key role in drug development. Traditional wet experiments to identify DTIs are costly and time consuming. Effective computational methods to predict DTIs are useful to speed up the process of drug discovery. A variety of non-negativity matrix factorization based methods are proposed to predict DTIs, but most of them overlooked the sparsity of feature matrices and the convergence of adopted matrix factorization algorithms, therefore their performances can be further improved. RESULTS In order to predict DTIs more accurately, we propose a novel method iPALM-DLMF. iPALM-DLMF models DTIs prediction as a problem of non-negative matrix factorization with graph dual regularization terms and [Formula: see text] norm regularization terms. The graph dual regularization terms are used to integrate the information from the drug similarity matrix and the target similarity matrix, and [Formula: see text] norm regularization terms are used to ensure the sparsity of the feature matrices obtained by non-negative matrix factorization. To solve the model, iPALM-DLMF adopts non-negative double singular value decomposition to initialize the nonnegative matrix factorization, and an inertial Proximal Alternating Linearized Minimization iterating process, which has been proved to converge to a KKT point, to obtain the final result of the matrix factorization. Extensive experimental results show that iPALM-DLMF has better performance than other state-of-the-art methods. In case studies, in 50 highest-scoring proteins targeted by the drug gabapentin predicted by iPALM-DLMF, 46 have been validated, and in 50 highest-scoring drugs targeting prostaglandin-endoperoxide synthase 2 predicted by iPALM-DLMF, 47 have been validated.
Collapse
Affiliation(s)
- Junjun Zhang
- Key Laboratory of Computing and Stochastic Mathematics(LCSM) (Ministry of Education), School of Mathematics and Statistics, Hunan Normal University, Changsha, 410081 China
| | - Minzhu Xie
- Key Laboratory of Computing and Stochastic Mathematics(LCSM) (Ministry of Education), School of Mathematics and Statistics, Hunan Normal University, Changsha, 410081 China
- College of Information Science and Engineering, Hunan Normal University, Changsha, 410081 China
| |
Collapse
|
3
|
Qian Y, Li X, Wu J, Zhang Q. MCL-DTI: using drug multimodal information and bi-directional cross-attention learning method for predicting drug-target interaction. BMC Bioinformatics 2023; 24:323. [PMID: 37633938 PMCID: PMC10463755 DOI: 10.1186/s12859-023-05447-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2023] [Accepted: 08/15/2023] [Indexed: 08/28/2023] Open
Abstract
BACKGROUND Prediction of drug-target interaction (DTI) is an essential step for drug discovery and drug reposition. Traditional methods are mostly time-consuming and labor-intensive, and deep learning-based methods address these limitations and are applied to engineering. Most of the current deep learning methods employ representation learning of unimodal information such as SMILES sequences, molecular graphs, or molecular images of drugs. In addition, most methods focus on feature extraction from drug and target alone without fusion learning from drug-target interacting parties, which may lead to insufficient feature representation. MOTIVATION In order to capture more comprehensive drug features, we utilize both molecular image and chemical features of drugs. The image of the drug mainly has the structural information and spatial features of the drug, while the chemical information includes its functions and properties, which can complement each other, making drug representation more effective and complete. Meanwhile, to enhance the interactive feature learning of drug and target, we introduce a bidirectional multi-head attention mechanism to improve the performance of DTI. RESULTS To enhance feature learning between drugs and targets, we propose a novel model based on deep learning for DTI task called MCL-DTI which uses multimodal information of drug and learn the representation of drug-target interaction for drug-target prediction. In order to further explore a more comprehensive representation of drug features, this paper first exploits two multimodal information of drugs, molecular image and chemical text, to represent the drug. We also introduce to use bi-rectional multi-head corss attention (MCA) method to learn the interrelationships between drugs and targets. Thus, we build two decoders, which include an multi-head self attention (MSA) block and an MCA block, for cross-information learning. We use a decoder for the drug and target separately to obtain the interaction feature maps. Finally, we feed these feature maps generated by decoders into a fusion block for feature extraction and output the prediction results. CONCLUSIONS MCL-DTI achieves the best results in all the three datasets: Human, C. elegans and Davis, including the balanced datasets and an unbalanced dataset. The results on the drug-drug interaction (DDI) task show that MCL-DTI has a strong generalization capability and can be easily applied to other tasks.
Collapse
Affiliation(s)
- Ying Qian
- Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Computer Science and Technology, East China Normal University, North Zhongshan Road, Shanghai, 200062 China
| | - Xinyi Li
- Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Computer Science and Technology, East China Normal University, North Zhongshan Road, Shanghai, 200062 China
| | - Jian Wu
- Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Computer Science and Technology, East China Normal University, North Zhongshan Road, Shanghai, 200062 China
| | - Qian Zhang
- Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Computer Science and Technology, East China Normal University, North Zhongshan Road, Shanghai, 200062 China
| |
Collapse
|
4
|
Zhang J, Xie M. Graph regularized non-negative matrix factorization with prior knowledge consistency constraint for drug-target interactions prediction. BMC Bioinformatics 2022; 23:564. [PMID: 36581822 PMCID: PMC9798666 DOI: 10.1186/s12859-022-05119-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2022] [Accepted: 12/20/2022] [Indexed: 12/30/2022] Open
Abstract
BACKGROUND Identifying drug-target interactions (DTIs) plays a key role in drug development. Traditional wet experiments to identify DTIs are expensive and time consuming. Effective computational methods to predict DTIs are useful to narrow the searching scope of potential drugs and speed up the process of drug discovery. There are a variety of non-negativity matrix factorization based methods to predict DTIs, but the convergence of the algorithms used in the matrix factorization are often overlooked and the results can be further improved. RESULTS In order to predict DTIs more accurately and quickly, we propose an alternating direction algorithm to solve graph regularized non-negative matrix factorization with prior knowledge consistency constraint (ADA-GRMFC). Based on known DTIs, drug chemical structures and target sequences, ADA-GRMFC at first constructs a DTI matrix, a drug similarity matrix and a target similarity matrix. Then DTI prediction is modeled as the non-negative factorization of the DTI matrix with graph dual regularization terms and a prior knowledge consistency constraint. The graph dual regularization terms are used to integrate the information from the drug similarity matrix and the target similarity matrix, and the prior knowledge consistency constraint is used to ensure the matrix decomposition result should be consistent with the prior knowledge of known DTIs. Finally, an alternating direction algorithm is used to solve the matrix factorization. Furthermore, we prove that the algorithm can converge to a stationary point. Extensive experimental results of 10-fold cross-validation show that ADA-GRMFC has better performance than other state-of-the-art methods. In the case study, ADA-GRMFC is also used to predict the targets interacting with the drug olanzapine, and all of the 10 highest-scoring targets have been accurately predicted. In predicting drug interactions with target estrogen receptors alpha, 17 of the 20 highest-scoring drugs have been validated.
Collapse
Affiliation(s)
- Junjun Zhang
- grid.411427.50000 0001 0089 3695Key Laboratory of Computing and Stochastic Mathematics (LCSM) (Ministry of Education), School of Mathematics and Statistics, Hunan Normal University, Changsha, 410081 China
| | - Minzhu Xie
- grid.411427.50000 0001 0089 3695Key Laboratory of Computing and Stochastic Mathematics (LCSM) (Ministry of Education), School of Mathematics and Statistics, Hunan Normal University, Changsha, 410081 China ,grid.411427.50000 0001 0089 3695College of Information Science and Engineering, Hunan Normal University, Changsha, 410081 China
| |
Collapse
|
5
|
Ma Y, Ma Y. Hypergraph-based logistic matrix factorization for metabolite-disease interaction prediction. Bioinformatics 2022; 38:435-443. [PMID: 34499104 DOI: 10.1093/bioinformatics/btab652] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2021] [Revised: 08/08/2021] [Accepted: 09/06/2021] [Indexed: 02/03/2023] Open
Abstract
MOTIVATION Function-related metabolites, the terminal products of the cell regulation, show a close association with complex diseases. The identification of disease-related metabolites is critical to the diagnosis, prevention and treatment of diseases. However, most existing computational approaches build networks by calculating pairwise relationships, which is inappropriate for mining higher-order relationships. RESULTS In this study, we presented a novel approach with hypergraph-based logistic matrix factorization, HGLMF, to predict the potential interactions between metabolites and disease. First, the molecular structures and gene associations of metabolites and the hierarchical structures and GO functional annotations of diseases were extracted to build various similarity measures of metabolites and diseases. Next, the kernel neighborhood similarity of metabolites (or diseases) was calculated according to the completed interactive network. Second, multiple networks of metabolites and diseases were fused, respectively, and the hypergraph structures of metabolites and diseases were built. Finally, a logistic matrix factorization based on hypergraph was proposed to predict potential metabolite-disease interactions. In computational experiments, HGLMF accurately predicted the metabolite-disease interaction, and performed better than other state-of-the-art methods. Moreover, HGLMF could be used to predict new metabolites (or diseases). As suggested from the case studies, the proposed method could discover novel disease-related metabolites, which has been confirmed in existing studies. AVAILABILITY AND IMPLEMENTATION The codes and dataset are available at: https://github.com/Mayingjun20179/HGLMF. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Yingjun Ma
- School of Applied Mathematics, Xiamen University of Technology, Xiamen 361024, China
| | - Yuanyuan Ma
- School of Computer & Information Engineering, Anyang Normal University, Anyang 455000, China
| |
Collapse
|
6
|
Ou-Yang L, Lu F, Zhang ZC, Wu M. Matrix factorization for biomedical link prediction and scRNA-seq data imputation: an empirical survey. Brief Bioinform 2021; 23:6447434. [PMID: 34864871 DOI: 10.1093/bib/bbab479] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2021] [Revised: 09/25/2021] [Accepted: 10/18/2021] [Indexed: 02/02/2023] Open
Abstract
Advances in high-throughput experimental technologies promote the accumulation of vast number of biomedical data. Biomedical link prediction and single-cell RNA-sequencing (scRNA-seq) data imputation are two essential tasks in biomedical data analyses, which can facilitate various downstream studies and gain insights into the mechanisms of complex diseases. Both tasks can be transformed into matrix completion problems. For a variety of matrix completion tasks, matrix factorization has shown promising performance. However, the sparseness and high dimensionality of biomedical networks and scRNA-seq data have raised new challenges. To resolve these issues, various matrix factorization methods have emerged recently. In this paper, we present a comprehensive review on such matrix factorization methods and their usage in biomedical link prediction and scRNA-seq data imputation. Moreover, we select representative matrix factorization methods and conduct a systematic empirical comparison on 15 real data sets to evaluate their performance under different scenarios. By summarizing the experimental results, we provide general guidelines for selecting matrix factorization methods for different biomedical matrix completion tasks and point out some future directions to further improve the performance for biomedical link prediction and scRNA-seq data imputation.
Collapse
Affiliation(s)
- Le Ou-Yang
- Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Media Security, and Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ), College of Electronics and Information Engineering, Shenzhen University, Shenzhen, 518060, China.,Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen,518172, China
| | - Fan Lu
- Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Media Security, and Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ), College of Electronics and Information Engineering, Shenzhen University, Shenzhen, 518060, China
| | - Zi-Chao Zhang
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, 200433, China
| | - Min Wu
- Institute for Infocomm Research (I2R), A*STAR, 138632, Singapore
| |
Collapse
|
7
|
Identification of drug-target interactions via multi-view graph regularized link propagation model. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2021.05.100] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
|
8
|
He B, Hou F, Ren C, Bing P, Xiao X. A Review of Current In Silico Methods for Repositioning Drugs and Chemical Compounds. Front Oncol 2021; 11:711225. [PMID: 34367996 PMCID: PMC8340770 DOI: 10.3389/fonc.2021.711225] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2021] [Accepted: 07/07/2021] [Indexed: 12/23/2022] Open
Abstract
Drug repositioning is a new way of applying the existing therapeutics to new disease indications. Due to the exorbitant cost and high failure rate in developing new drugs, the continued use of existing drugs for treatment, especially anti-tumor drugs, has become a widespread practice. With the assistance of high-throughput sequencing techniques, many efficient methods have been proposed and applied in drug repositioning and individualized tumor treatment. Current computational methods for repositioning drugs and chemical compounds can be divided into four categories: (i) feature-based methods, (ii) matrix decomposition-based methods, (iii) network-based methods, and (iv) reverse transcriptome-based methods. In this article, we comprehensively review the widely used methods in the above four categories. Finally, we summarize the advantages and disadvantages of these methods and indicate future directions for more sensitive computational drug repositioning methods and individualized tumor treatment, which are critical for further experimental validation.
Collapse
Affiliation(s)
- Binsheng He
- Academician Workstation, Changsha Medical University, Changsha, China
| | - Fangxing Hou
- Queen Mary School, Nanchang University, Jiangxi, China
| | - Changjing Ren
- School of Science, Dalian Maritime University, Dalian, China.,Genies Beijing Co., Ltd., Beijing, China
| | - Pingping Bing
- Academician Workstation, Changsha Medical University, Changsha, China
| | - Xiangzuo Xiao
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Jiangxi, China
| |
Collapse
|
9
|
Pliakos K, Vens C, Tsoumakas G. Predicting Drug-Target Interactions With Multi-Label Classification and Label Partitioning. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2021; 18:1596-1607. [PMID: 31689203 DOI: 10.1109/tcbb.2019.2951378] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Identifying drug-target interactions is crucial for drug discovery. Despite modern technologies used in drug screening, experimental identification of drug-target interactions is an extremely demanding task. Predicting drug-target interactions in silico can thereby facilitate drug discovery as well as drug repositioning. Various machine learning models have been developed over the years to predict such interactions. Multi-output learning models in particular have drawn the attention of the scientific community due to their high predictive performance and computational efficiency. These models are based on the assumption that all the labels are correlated with each other. However, this assumption is too optimistic. Here, we address drug-target interaction prediction as a multi-label classification task that is combined with label partitioning. We show that building multi-output learning models over groups (clusters) of labels often leads to superior results. The performed experiments confirm the efficiency of the proposed framework.
Collapse
|
10
|
Ding Y, Tang J, Guo F. The Computational Models of Drug-target Interaction Prediction. Protein Pept Lett 2020; 27:348-358. [PMID: 30968771 DOI: 10.2174/0929866526666190410124110] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2019] [Revised: 02/22/2019] [Accepted: 04/02/2019] [Indexed: 12/19/2022]
Abstract
The identification of Drug-Target Interactions (DTIs) is an important process in drug discovery and medical research. However, the tradition experimental methods for DTIs identification are still time consuming, extremely expensive and challenging. In the past ten years, various computational methods have been developed to identify potential DTIs. In this paper, the identification methods of DTIs are summarized. What's more, several state-of-the-art computational methods are mainly introduced, containing network-based method and machine learning-based method. In particular, for machine learning-based methods, including the supervised and semisupervised models, have essential differences in the approach of negative samples. Although these effective computational models in identification of DTIs have achieved significant improvements, network-based and machine learning-based methods have their disadvantages, respectively. These computational methods are evaluated on four benchmark data sets via values of Area Under the Precision Recall curve (AUPR).
Collapse
Affiliation(s)
- Yijie Ding
- School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, China
| | - Jijun Tang
- Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, United States.,School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin, China
| | - Fei Guo
- School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin, China
| |
Collapse
|
11
|
Chu Y, Shan X, Chen T, Jiang M, Wang Y, Wang Q, Salahub DR, Xiong Y, Wei DQ. DTI-MLCD: predicting drug-target interactions using multi-label learning with community detection method. Brief Bioinform 2020; 22:5910189. [PMID: 32964234 DOI: 10.1093/bib/bbaa205] [Citation(s) in RCA: 32] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2020] [Revised: 08/06/2020] [Accepted: 08/10/2020] [Indexed: 12/20/2022] Open
Abstract
Identifying drug-target interactions (DTIs) is an important step for drug discovery and drug repositioning. To reduce the experimental cost, a large number of computational approaches have been proposed for this task. The machine learning-based models, especially binary classification models, have been developed to predict whether a drug-target pair interacts or not. However, there is still much room for improvement in the performance of current methods. Multi-label learning can overcome some difficulties caused by single-label learning in order to improve the predictive performance. The key challenge faced by multi-label learning is the exponential-sized output space, and considering label correlations can help to overcome this challenge. In this paper, we facilitate multi-label classification by introducing community detection methods for DTI prediction, named DTI-MLCD. Moreover, we updated the gold standard data set by adding 15,000 more positive DTI samples in comparison to the data set, which has widely been used by most of previously published DTI prediction methods since 2008. The proposed DTI-MLCD is applied to both data sets, demonstrating its superiority over other machine learning methods and several existing methods. The data sets and source code of this study are freely available at https://github.com/a96123155/DTI-MLCD.
Collapse
Affiliation(s)
- Yanyi Chu
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Xiaoqi Shan
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Tianhang Chen
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Mingming Jiang
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Yanjing Wang
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Qiankun Wang
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | | | - Yi Xiong
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Dong-Qing Wei
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| |
Collapse
|
12
|
Identification of Drug–Target Interactions via Dual Laplacian Regularized Least Squares with Multiple Kernel Fusion. Knowl Based Syst 2020. [DOI: 10.1016/j.knosys.2020.106254] [Citation(s) in RCA: 71] [Impact Index Per Article: 17.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
|
13
|
Pliakos K, Vens C. Drug-target interaction prediction with tree-ensemble learning and output space reconstruction. BMC Bioinformatics 2020; 21:49. [PMID: 32033537 PMCID: PMC7006075 DOI: 10.1186/s12859-020-3379-z] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2019] [Accepted: 01/21/2020] [Indexed: 12/21/2022] Open
Abstract
Background Computational prediction of drug-target interactions (DTI) is vital for drug discovery. The experimental identification of interactions between drugs and target proteins is very onerous. Modern technologies have mitigated the problem, leveraging the development of new drugs. However, drug development remains extremely expensive and time consuming. Therefore, in silico DTI predictions based on machine learning can alleviate the burdensome task of drug development. Many machine learning approaches have been proposed over the years for DTI prediction. Nevertheless, prediction accuracy and efficiency are persisting problems that still need to be tackled. Here, we propose a new learning method which addresses DTI prediction as a multi-output prediction task by learning ensembles of multi-output bi-clustering trees (eBICT) on reconstructed networks. In our setting, the nodes of a DTI network (drugs and proteins) are represented by features (background information). The interactions between the nodes of a DTI network are modeled as an interaction matrix and compose the output space in our problem. The proposed approach integrates background information from both drug and target protein spaces into the same global network framework. Results We performed an empirical evaluation, comparing the proposed approach to state of the art DTI prediction methods and demonstrated the effectiveness of the proposed approach in different prediction settings. For evaluation purposes, we used several benchmark datasets that represent drug-protein networks. We show that output space reconstruction can boost the predictive performance of tree-ensemble learning methods, yielding more accurate DTI predictions. Conclusions We proposed a new DTI prediction method where bi-clustering trees are built on reconstructed networks. Building tree-ensemble learning models with output space reconstruction leads to superior prediction results, while preserving the advantages of tree-ensembles, such as scalability, interpretability and inductive setting.
Collapse
Affiliation(s)
- Konstantinos Pliakos
- KU Leuven, Campus KULAK, Faculty of Medicine, Kortrijk, Belgium. .,ITEC, imec research group at KU Leuven, Kortrijk, Belgium.
| | - Celine Vens
- KU Leuven, Campus KULAK, Faculty of Medicine, Kortrijk, Belgium.,ITEC, imec research group at KU Leuven, Kortrijk, Belgium
| |
Collapse
|
14
|
Bagherian M, Sabeti E, Wang K, Sartor MA, Nikolovska-Coleska Z, Najarian K. Machine learning approaches and databases for prediction of drug-target interaction: a survey paper. Brief Bioinform 2020; 22:247-269. [PMID: 31950972 PMCID: PMC7820849 DOI: 10.1093/bib/bbz157] [Citation(s) in RCA: 148] [Impact Index Per Article: 37.0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2019] [Revised: 11/01/2019] [Accepted: 11/07/2019] [Indexed: 12/12/2022] Open
Abstract
The task of predicting the interactions between drugs and targets plays a key role in the process of drug discovery. There is a need to develop novel and efficient prediction approaches in order to avoid costly and laborious yet not-always-deterministic experiments to determine drug–target interactions (DTIs) by experiments alone. These approaches should be capable of identifying the potential DTIs in a timely manner. In this article, we describe the data required for the task of DTI prediction followed by a comprehensive catalog consisting of machine learning methods and databases, which have been proposed and utilized to predict DTIs. The advantages and disadvantages of each set of methods are also briefly discussed. Lastly, the challenges one may face in prediction of DTI using machine learning approaches are highlighted and we conclude by shedding some lights on important future research directions.
Collapse
Affiliation(s)
- Maryam Bagherian
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, 48109, USA
| | - Elyas Sabeti
- Michigan Institute for Data Science, University of Michigan, Ann Arbor, MI, 48109, USA
| | - Kai Wang
- Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI, 48109, USA
| | - Maureen A Sartor
- Department of Pathology, University of Michigan, Ann Arbor, MI, 48109, USA
| | | | - Kayvan Najarian
- Department of Electrical Engineering and Computer Science, College of Engineering, University of Michigan, Ann Arbor, MI, 48109, USA
| |
Collapse
|
15
|
Taz TA, Kawsar M, Paul BK, Ahmed K, Bhuyian T. Characterizing topological properties and network pathway model among vector borne diseases. INFORMATICS IN MEDICINE UNLOCKED 2020. [DOI: 10.1016/j.imu.2020.100312] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023] Open
|
16
|
Chu Y, Kaushik AC, Wang X, Wang W, Zhang Y, Shan X, Salahub DR, Xiong Y, Wei DQ. DTI-CDF: a cascade deep forest model towards the prediction of drug-target interactions based on hybrid features. Brief Bioinform 2019; 22:451-462. [PMID: 31885041 DOI: 10.1093/bib/bbz152] [Citation(s) in RCA: 100] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2019] [Revised: 11/01/2019] [Accepted: 11/04/2019] [Indexed: 12/18/2022] Open
Abstract
Drug-target interactions (DTIs) play a crucial role in target-based drug discovery and development. Computational prediction of DTIs can effectively complement experimental wet-lab techniques for the identification of DTIs, which are typically time- and resource-consuming. However, the performances of the current DTI prediction approaches suffer from a problem of low precision and high false-positive rate. In this study, we aim to develop a novel DTI prediction method for improving the prediction performance based on a cascade deep forest (CDF) model, named DTI-CDF, with multiple similarity-based features between drugs and the similarity-based features between target proteins extracted from the heterogeneous graph, which contains known DTIs. In the experiments, we built five replicates of 10-fold cross-validation under three different experimental settings of data sets, namely, corresponding DTI values of certain drugs (SD), targets (ST), or drug-target pairs (SP) in the training sets are missed but existed in the test sets. The experimental results demonstrate that our proposed approach DTI-CDF achieves a significantly higher performance than that of the traditional ensemble learning-based methods such as random forest and XGBoost, deep neural network, and the state-of-the-art methods such as DDR. Furthermore, there are 1352 newly predicted DTIs which are proved to be correct by KEGG and DrugBank databases. The data sets and source code are freely available at https://github.com//a96123155/DTI-CDF.
Collapse
Affiliation(s)
- Yanyi Chu
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | | | - Xiangeng Wang
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Wei Wang
- Mathematical Sciences, Shanghai Jiao Tong University
| | - Yufang Zhang
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | | | | | - Yi Xiong
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| | - Dong-Qing Wei
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University
| |
Collapse
|
17
|
Ding Y, Tang J, Guo F. Identification of drug–target interactions via fuzzy bipartite local model. Neural Comput Appl 2019. [DOI: 10.1007/s00521-019-04569-z] [Citation(s) in RCA: 64] [Impact Index Per Article: 12.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
|
18
|
Zhao Q, Yu H, Ji M, Zhao Y, Chen X. Computational Model Development of Drug-Target Interaction Prediction: A Review. Curr Protein Pept Sci 2019; 20:492-494. [DOI: 10.2174/1389203720666190123164310] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2018] [Revised: 01/16/2019] [Accepted: 01/18/2019] [Indexed: 12/14/2022]
Abstract
In the medical field, drug-target interactions are very important for the diagnosis and treatment of diseases, they also can help researchers predict the link between biomolecules in the biological field, such as drug-protein and protein-target correlations. Therefore, the drug-target research is a very popular study in both the biological and medical fields. However, due to the limitations of manual experiments in the laboratory, computational prediction methods for drug-target relationships are increasingly favored by researchers. In this review, we summarize several computational prediction models of the drug-target connections during the past two years, and briefly introduce their advantages and shortcomings. Finally, several further interesting research directions of drug-target interactions are listed.
Collapse
Affiliation(s)
- Qi Zhao
- College of Computer Science, Shenyang Aerospace University, Shenyang, 110136, China
| | - Haifan Yu
- School of Mathematics, Liaoning University, Shenyang, 110036, China
| | - Mingxuan Ji
- School of Mathematics, Liaoning University, Shenyang, 110036, China
| | - Yan Zhao
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221116, China
| | - Xing Chen
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 221116, China
| |
Collapse
|
19
|
Identification of drug-side effect association via multiple information integration with centered kernel alignment. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2018.10.028] [Citation(s) in RCA: 148] [Impact Index Per Article: 29.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
|