1
|
Martinez-Rodrigo A, Castillo JC, Saz-Lara A, Otero-Luis I, Cavero-Redondo I. Development of a recommendation system and data analysis in personalized medicine: an approach towards healthy vascular ageing. Health Inf Sci Syst 2024; 12:34. [PMID: 38707839 PMCID: PMC11068708 DOI: 10.1007/s13755-024-00292-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2024] [Accepted: 04/19/2024] [Indexed: 05/07/2024] Open
Abstract
Purpose Understanding early vascular ageing has become crucial for preventing adverse cardiovascular events. To this respect, recent AI-based risk clustering models offer early detection strategies focused on healthy populations, yet their complexity limits clinical use. This work introduces a novel recommendation system embedded in a web app to assess and mitigate early vascular ageing risk, leading patients towards improved cardiovascular health. Methods This system employs a methodology that calculates distances within multidimensional spaces and integrates cost functions to obtain personalized optimisation of recommendations. It also incorporates a classification system for determining the intensity levels of the clinical interventions. Results The recommendation system showed high efficiency in identifying and visualizing individuals at high risk of early vascular ageing among healthy patients. Additionally, the system corroborated its consistency and reliability in generating personalized recommendations among different levels of granularity, emphasizing its focus on moderate or low-intensity recommendations, which could improve patient adherence to the intervention. Conclusion This tool might significantly aid healthcare professionals in their daily analysis, improving the prevention and management of cardiovascular diseases.
Collapse
Affiliation(s)
| | - Jose Carlos Castillo
- Systems Automation and Engineering Department, Carlos III University of Madrid, Madrid, Spain
| | - Alicia Saz-Lara
- Health and Social Research Center, University of Castilla-La Mancha, Cuenca, Spain
| | - Iris Otero-Luis
- Health and Social Research Center, University of Castilla-La Mancha, Cuenca, Spain
| | - Iván Cavero-Redondo
- Health and Social Research Center, University of Castilla-La Mancha, Cuenca, Spain
- Facultad de Ciencias de la Salud, Universidad Autonoma de Chile, Talca, Chile
| |
Collapse
|
2
|
Niu D, Zhang L, Zhang B, Zhang Q, Li Z. DAS-DDI: A dual-view framework with drug association and drug structure for drug-drug interaction prediction. J Biomed Inform 2024; 156:104672. [PMID: 38857738 DOI: 10.1016/j.jbi.2024.104672] [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: 03/18/2024] [Revised: 05/09/2024] [Accepted: 06/06/2024] [Indexed: 06/12/2024]
Abstract
In drug development and clinical application, drug-drug interaction (DDI) prediction is crucial for patient safety and therapeutic efficacy. However, traditional methods for DDI prediction often overlook the structural features of drugs and the complex interrelationships between them, which affect the accuracy and interpretability of the model. In this paper, a novel dual-view DDI prediction framework, DAS-DDI is proposed. Firstly, a drug association network is constructed based on similarity information among drugs, which could provide rich context information for DDI prediction. Subsequently, a novel drug substructure extraction method is proposed, which could update the features of nodes and chemical bonds simultaneously, improving the comprehensiveness of the feature. Furthermore, an attention mechanism is employed to fuse multiple drug embeddings from different views dynamically, enhancing the discriminative ability of the model in handling multi-view data. Comparative experiments on three public datasets demonstrate the superiority of DAS-DDI compared with other state-of-the-art models under two scenarios.
Collapse
Affiliation(s)
- Dongjiang Niu
- College of Computer Science and Technology, Qingdao University, No. 308 Ningxia Road, Qingdao, 266071, Shandong, China
| | - Lianwei Zhang
- College of Computer Science and Technology, Qingdao University, No. 308 Ningxia Road, Qingdao, 266071, Shandong, China
| | - Beiyi Zhang
- College of Computer Science and Technology, Qingdao University, No. 308 Ningxia Road, Qingdao, 266071, Shandong, China
| | - Qiang Zhang
- College of Computer Science and Technology, Qingdao University, No. 308 Ningxia Road, Qingdao, 266071, Shandong, China
| | - Zhen Li
- College of Computer Science and Technology, Qingdao University, No. 308 Ningxia Road, Qingdao, 266071, Shandong, China.
| |
Collapse
|
3
|
Geng G, Wang L, Xu Y, Wang T, Ma W, Duan H, Zhang J, Mao A. MGDDI: A multi-scale graph neural networks for drug-drug interaction prediction. Methods 2024; 228:22-29. [PMID: 38754712 DOI: 10.1016/j.ymeth.2024.05.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2024] [Revised: 05/09/2024] [Accepted: 05/12/2024] [Indexed: 05/18/2024] Open
Abstract
Drug-drug interaction (DDI) prediction is crucial for identifying interactions within drug combinations, especially adverse effects due to physicochemical incompatibility. While current methods have made strides in predicting adverse drug interactions, limitations persist. Most methods rely on handcrafted features, restricting their applicability. They predominantly extract information from individual drugs, neglecting the importance of interaction details between drug pairs. To address these issues, we propose MGDDI, a graph neural network-based model for predicting potential adverse drug interactions. Notably, we use a multiscale graph neural network (MGNN) to learn drug molecule representations, addressing substructure size variations and preventing gradient issues. For capturing interaction details between drug pairs, we integrate a substructure interaction learning module based on attention mechanisms. Our experimental results demonstrate MGDDI's superiority in predicting adverse drug interactions, offering a solution to current methodological limitations.
Collapse
Affiliation(s)
- Guannan Geng
- Department of Endocrinology, The First Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Lizhuang Wang
- Beidahuang Industry Group General Hospital, Harbin, China
| | - Yanwei Xu
- Beidahuang Group Neuropsychiatric Hospital, Jiamusi, China; Department of Stomatology and Dental Hygiene, The Fourth Affiliated Hospital, Harbin Medical University, Harbin, China
| | - Tianshuo Wang
- School of Software, Shandong University, Jinan, China
| | - Wei Ma
- Department of Stomatology and Dental Hygiene, The Fourth Affiliated Hospital, Harbin Medical University, Harbin, China
| | - Hongliang Duan
- Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China
| | - Jiahui Zhang
- Department of Stomatology and Dental Hygiene, The Fourth Affiliated Hospital, Harbin Medical University, Harbin, China.
| | - Anqiong Mao
- The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University, Department of Anesthesiology, Luzhou, China.
| |
Collapse
|
4
|
Hauben M, Rafi M, Abdelaziz I, Hassanzadeh O. Knowledge Graphs in Pharmacovigilance: A Scoping Review. Clin Ther 2024:S0149-2918(24)00144-9. [PMID: 38981792 DOI: 10.1016/j.clinthera.2024.06.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 05/08/2024] [Accepted: 06/05/2024] [Indexed: 07/11/2024]
Abstract
PURPOSE To critically assess the role and added value of knowledge graphs in pharmacovigilance, focusing on their ability to predict adverse drug reactions. METHODS A systematic scoping review was conducted in which detailed information, including objectives, technology, data sources, methodology, and performance metrics, were extracted from a set of peer-reviewed publications reporting the use of knowledge graphs to support pharmacovigilance signal detection. FINDINGS The review, which included 47 peer-reviewed articles, found knowledge graphs were utilized for detecting/predicting single-drug adverse reactions and drug-drug interactions, with variable reported performance and sparse comparisons to legacy methods. IMPLICATIONS Research to date suggests that knowledge graphs have the potential to augment predictive signal detection in pharmacovigilance, but further research using more reliable reference sets of adverse drug reactions and comparison with legacy pharmacovigilance methods are needed to more clearly define best practices and to establish their place in holistic pharmacovigilance systems.
Collapse
Affiliation(s)
- Manfred Hauben
- Department of Family and Community Medicine, New York Medical College, Valhalla, New York; Truliant Consulting, Baltimore, Maryland
| | - Mazin Rafi
- Department of Statistics, Rutgers University, Piscataway, New Jersey.
| | | | | |
Collapse
|
5
|
Zhang D, Wang Z, Zhao D, Li J. DRGATAN: Directed relation graph attention aware network for asymmetric drug-drug interaction prediction. iScience 2024; 27:109943. [PMID: 38868194 PMCID: PMC11167430 DOI: 10.1016/j.isci.2024.109943] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Revised: 03/21/2024] [Accepted: 05/06/2024] [Indexed: 06/14/2024] Open
Abstract
In scenarios involving the treatment of complex or coexisting diseases with multiple drugs, the potential for severe adverse drug reactions in patients necessitates the identification of potential drug-drug interactions (DDIs). Most existing computational methods have not taken into account the asymmetry and relation types of drug interactions caused by the relation information between drugs, which may lead to missing information in embedded learning. Therefore, this paper proposes a directed relation graph attention aware network (DRGATAN) to predict asymmetric drug interactions. DRGATAN leverages an encoder to learn multi-relational role embeddings of drugs across different types of relations. The experimental results show that DRGATAN's performance is superior to recognized advanced methods. The visualization demonstrates the effect of utilizing asymmetric information, and the case analysis validates the reliability of the proposed method. This study provides guidance for predicting asymmetric drug interactions.
Collapse
Affiliation(s)
- Dehai Zhang
- The Key Laboratory of Software Engineering of Yunnan Province, School of Software, Yunnan University, Kunming 650091, P.R. China
| | - Zhengwu Wang
- The Key Laboratory of Software Engineering of Yunnan Province, School of Software, Yunnan University, Kunming 650091, P.R. China
| | - Di Zhao
- The Key Laboratory of Software Engineering of Yunnan Province, School of Software, Yunnan University, Kunming 650091, P.R. China
| | - Jin Li
- The Key Laboratory of Software Engineering of Yunnan Province, School of Software, Yunnan University, Kunming 650091, P.R. China
| |
Collapse
|
6
|
He SH, Yun L, Yi HC. Accurate prediction of drug combination risk levels based on relational graph convolutional network and multi-head attention. J Transl Med 2024; 22:572. [PMID: 38880914 PMCID: PMC11180398 DOI: 10.1186/s12967-024-05372-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2024] [Accepted: 06/02/2024] [Indexed: 06/18/2024] Open
Abstract
BACKGROUND Accurately identifying the risk level of drug combinations is of great significance in investigating the mechanisms of combination medication and adverse reactions. Most existing methods can only predict whether there is an interaction between two drugs, but cannot directly determine their accurate risk level. METHODS In this study, we propose a multi-class drug combination risk prediction model named AERGCN-DDI, utilizing a relational graph convolutional network with a multi-head attention mechanism. Drug-drug interaction events with varying risk levels are modeled as a heterogeneous information graph. Attribute features of drug nodes and links are learned based on compound chemical structure information. Finally, the AERGCN-DDI model is proposed to predict drug combination risk level based on heterogenous graph neural network and multi-head attention modules. RESULTS To evaluate the effectiveness of the proposed method, five-fold cross-validation and ablation study were conducted. Furthermore, we compared its predictive performance with baseline models and other state-of-the-art methods on two benchmark datasets. Empirical studies demonstrated the superior performances of AERGCN-DDI. CONCLUSIONS AERGCN-DDI emerges as a valuable tool for predicting the risk levels of drug combinations, thereby aiding in clinical medication decision-making, mitigating severe drug side effects, and enhancing patient clinical prognosis.
Collapse
Affiliation(s)
- Shi-Hui He
- School of Information Science and Technology, Yunnan Normal University, Kunming, 650500, China
- Engineering Research Center of Computer Vision and Intelligent Control Technology, Department of Education, Kunming, 650500, China
| | - Lijun Yun
- School of Information Science and Technology, Yunnan Normal University, Kunming, 650500, China.
- Engineering Research Center of Computer Vision and Intelligent Control Technology, Department of Education, Kunming, 650500, China.
| | - Hai-Cheng Yi
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710129, China.
| |
Collapse
|
7
|
Zhang S, Tian X, Chen C, Su Y, Huang W, Lv X, Chen C, Li H. AIGO-DTI: Predicting Drug-Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms. J Chem Inf Model 2024; 64:4373-4384. [PMID: 38743013 DOI: 10.1021/acs.jcim.4c00584] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/16/2024]
Abstract
Artificial intelligence-based methods for predicting drug-target interactions (DTIs) aim to explore reliable drug candidate targets rapidly and cost-effectively to accelerate the drug development process. However, current methods are often limited by the topological regularities of drug molecules, making them difficult to generalize to a broader chemical space. Additionally, the use of similarity to measure DTI network links often introduces noise, leading to false DTI relationships and affecting the prediction accuracy. To address these issues, this study proposes an Adaptive Iterative Graph Optimization (AIGO)-DTI prediction framework. This framework integrates atomic cluster information and enhances molecular features through the design of functional group prompts and graph encoders, optimizing the construction of DTI association networks. Furthermore, the optimization of graph structure is transformed into a node similarity learning problem, utilizing multihead similarity metric functions to iteratively update the network structure to improve the quality of DTI information. Experimental results demonstrate the outstanding performance of AIGO-DTI on multiple public data sets and label reversal data sets. Case studies, molecular docking, and existing research validate its effectiveness and reliability. Overall, the method proposed in this study can construct comprehensive and reliable DTI association network information, providing new graphing and optimization strategies for DTI prediction, which contribute to efficient drug development and reduce target discovery costs.
Collapse
Affiliation(s)
- Sizhe Zhang
- College of Software, Xinjiang University, Urumqi, 830046 Xinjiang, China
| | - Xuecong Tian
- College of Information Science and Engineering, Xinjiang University, Urumqi, 830046 Xinjiang, China
| | - Chen Chen
- College of Information Science and Engineering, Xinjiang University, Urumqi, 830046 Xinjiang, China
| | - Ying Su
- College of Information Science and Engineering, Xinjiang University, Urumqi, 830046 Xinjiang, China
| | - Wanhua Huang
- College of Information Science and Engineering, Xinjiang University, Urumqi, 830046 Xinjiang, China
| | - Xiaoyi Lv
- College of Software, Xinjiang University, Urumqi, 830046 Xinjiang, China
| | - Cheng Chen
- College of Software, Xinjiang University, Urumqi, 830046 Xinjiang, China
| | - Hongyi Li
- Xinjiang University, Urumqi, 830046 Xinjiang, China
| |
Collapse
|
8
|
Ronchi D, Tosca EM, Bartolucci R, Magni P. Go beyond the limits of genetic algorithm in daily covariate selection practice. J Pharmacokinet Pharmacodyn 2024; 51:109-121. [PMID: 37493851 PMCID: PMC10982092 DOI: 10.1007/s10928-023-09875-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Accepted: 07/08/2023] [Indexed: 07/27/2023]
Abstract
Covariate identification is an important step in the development of a population pharmacokinetic/pharmacodynamic model. Among the different available approaches, the stepwise covariate model (SCM) is the most used. However, SCM is based on a local search strategy, in which the model-building process iteratively tests the addition or elimination of a single covariate at a time given all the others. This introduces a heuristic to limit the searching space and then the computational complexity, but, at the same time, can lead to a suboptimal solution. The application of genetic algorithms (GAs) for covariate selection has been proposed as a possible solution to overcome these limitations. However, their actual use during model building is limited by the extremely high computational costs and convergence issues, both related to the number of models being tested. In this paper, we proposed a new GA for covariate selection to address these challenges. The GA was first developed on a simulated case study where the heuristics introduced to overcome the limitations affecting currently available GA approaches resulted able to limit the selection of redundant covariates, increase replicability of results and reduce convergence times. Then, we tested the proposed GA on a real-world problem related to remifentanil. It obtained good results both in terms of selected covariates and fitness optimization, outperforming the SCM.
Collapse
Affiliation(s)
- D Ronchi
- Dipartimento di Ingegneria Industriale e dell'Informazione, Università degli Studi di Pavia, 27100, Pavia, Italy
| | - E M Tosca
- Dipartimento di Ingegneria Industriale e dell'Informazione, Università degli Studi di Pavia, 27100, Pavia, Italy
| | - R Bartolucci
- Dipartimento di Ingegneria Industriale e dell'Informazione, Università degli Studi di Pavia, 27100, Pavia, Italy
- Clinical Pharmacology & Pharmacometrics, Janssen Research & Development, Beerse, Belgium
| | - P Magni
- Dipartimento di Ingegneria Industriale e dell'Informazione, Università degli Studi di Pavia, 27100, Pavia, Italy.
| |
Collapse
|
9
|
Luo H, Yin W, Wang J, Zhang G, Liang W, Luo J, Yan C. Drug-drug interactions prediction based on deep learning and knowledge graph: A review. iScience 2024; 27:109148. [PMID: 38405609 PMCID: PMC10884936 DOI: 10.1016/j.isci.2024.109148] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/27/2024] Open
Abstract
Drug-drug interactions (DDIs) can produce unpredictable pharmacological effects and lead to adverse events that have the potential to cause irreversible damage to the organism. Traditional methods to detect DDIs through biological or pharmacological analysis are time-consuming and expensive, therefore, there is an urgent need to develop computational methods to effectively predict drug-drug interactions. Currently, deep learning and knowledge graph techniques which can effectively extract features of entities have been widely utilized to develop DDI prediction methods. In this research, we aim to systematically review DDI prediction researches applying deep learning and graph knowledge. The available biomedical data and public databases related to drugs are firstly summarized in this review. Then, we discuss the existing drug-drug interactions prediction methods which have utilized deep learning and knowledge graph techniques and group them into three main classes: deep learning-based methods, knowledge graph-based methods, and methods that combine deep learning with knowledge graph. We comprehensively analyze the commonly used drug related data and various DDI prediction methods, and compare these prediction methods on benchmark datasets. Finally, we briefly discuss the challenges related to drug-drug interactions prediction, including asymmetric DDIs prediction and high-order DDI prediction.
Collapse
Affiliation(s)
- Huimin Luo
- School of Computer and Information Engineering, Henan University, Kaifeng, China
- Henan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, China
| | - Weijie Yin
- School of Computer and Information Engineering, Henan University, Kaifeng, China
| | - Jianlin Wang
- School of Computer and Information Engineering, Henan University, Kaifeng, China
- Academy for Advanced Interdisciplinary Studies, Zhengzhou, China
| | - Ge Zhang
- School of Computer and Information Engineering, Henan University, Kaifeng, China
- Henan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, China
| | - Wenjuan Liang
- School of Computer and Information Engineering, Henan University, Kaifeng, China
| | - Junwei Luo
- College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, China
| | - Chaokun Yan
- School of Computer and Information Engineering, Henan University, Kaifeng, China
- Academy for Advanced Interdisciplinary Studies, Zhengzhou, China
| |
Collapse
|
10
|
Jin S, Zhang Y, Yu H, Lu M. SADR: Self-Supervised Graph Learning With Adaptive Denoising for Drug Repositioning. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024; 21:265-277. [PMID: 38190661 DOI: 10.1109/tcbb.2024.3351079] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/10/2024]
Abstract
Traditional drug development is often high-risk and time-consuming. A promising alternative is to reuse or relocate approved drugs. Recently, some methods based on graph representation learning have started to be used for drug repositioning. These models learn the low dimensional embeddings of drug and disease nodes from the drug-disease interaction network to predict the potential association between drugs and diseases. However, these methods have strict requirements for the dataset, and if the dataset is sparse, the performance of these methods will be severely affected. At the same time, these methods have poor robustness to noise in the dataset. In response to the above challenges, we propose a drug repositioning model based on self-supervised graph learning with adptive denoising, called SADR. SADR uses data augmentation and contrastive learning strategies to learn feature representations of nodes, which can effectively solve the problems caused by sparse datasets. SADR includes an adaptive denoising training (ADT) component that can effectively identify noisy data during the training process and remove the impact of noise on the model. We have conducted comprehensive experiments on three datasets and have achieved better prediction accuracy compared to multiple baseline models. At the same time, we propose the top 10 new predictive approved drugs for treating two diseases. This demonstrates the ability of our model to identify potential drug candidates for disease indications.
Collapse
|
11
|
Yan X, Gu C, Feng Y, Han J. Predicting Drug-drug Interaction with Graph Mutual Interaction Attention Mechanism. Methods 2024; 223:16-25. [PMID: 38262485 DOI: 10.1016/j.ymeth.2024.01.009] [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: 10/26/2023] [Revised: 01/04/2024] [Accepted: 01/19/2024] [Indexed: 01/25/2024] Open
Abstract
Effective representation of molecules is a crucial step in AI-driven drug design and drug discovery, especially for drug-drug interaction (DDIs) prediction. Previous work usually models the drug information from the drug-related knowledge graph or the single drug molecules, but the interaction information between molecular substructures of drug pair is seldom considered, thus often ignoring the influence of bond information on atom node representation, leading to insufficient drug representation. Moreover, key molecular substructures have significant contribution to the DDIs prediction results. Therefore, in this work, we propose a novel Graph learning framework of Mutual Interaction Attention mechanism (called GMIA) to predict DDIs by effectively representing the drug molecules. Specifically, we build the node-edge message communication encoder to aggregate atom node and the incoming edge information for atom node representation and design the mutual interaction attention decoder to capture the mutual interaction context between molecular graphs of drug pairs. GMIA can bridge the gap between two encoders for the single drug molecules by attention mechanism. We also design a co-attention matrix to analyze the significance of different-size substructures obtained from the encoder-decoder layer and provide interpretability. In comparison with other recent state-of-the-art methods, our GMIA achieves the best results in terms of area under the precision-recall-curve (AUPR), area under the ROC curve (AUC), and F1 score on two different scale datasets. The case study indicates that our GMIA can detect the key substructure for potential DDIs, demonstrating the enhanced performance and interpretation ability of GMIA.
Collapse
Affiliation(s)
- Xiaoying Yan
- College of Computer Science, Xi'an Shiyou University, Xi'an 710065, China.
| | - Chi Gu
- College of Computer Science, Xi'an Shiyou University, Xi'an 710065, China
| | - Yuehua Feng
- College of Computer Science, Xi'an Shiyou University, Xi'an 710065, China
| | - Jiaxin Han
- College of Computer Science, Xi'an Shiyou University, Xi'an 710065, China
| |
Collapse
|
12
|
Luo Y, Liu XY, Yang K, Huang K, Hong M, Zhang J, Wu Y, Nie Z. Toward Unified AI Drug Discovery with Multimodal Knowledge. HEALTH DATA SCIENCE 2024; 4:0113. [PMID: 38486623 PMCID: PMC10886071 DOI: 10.34133/hds.0113] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Accepted: 01/25/2024] [Indexed: 03/17/2024]
Abstract
Background: In real-world drug discovery, human experts typically grasp molecular knowledge of drugs and proteins from multimodal sources including molecular structures, structured knowledge from knowledge bases, and unstructured knowledge from biomedical literature. Existing multimodal approaches in AI drug discovery integrate either structured or unstructured knowledge independently, which compromises the holistic understanding of biomolecules. Besides, they fail to address the missing modality problem, where multimodal information is missing for novel drugs and proteins. Methods: In this work, we present KEDD, a unified, end-to-end deep learning framework that jointly incorporates both structured and unstructured knowledge for vast AI drug discovery tasks. The framework first incorporates independent representation learning models to extract the underlying characteristics from each modality. Then, it applies a feature fusion technique to calculate the prediction results. To mitigate the missing modality problem, we leverage sparse attention and a modality masking technique to reconstruct the missing features based on top relevant molecules. Results: Benefiting from structured and unstructured knowledge, our framework achieves a deeper understanding of biomolecules. KEDD outperforms state-of-the-art models by an average of 5.2% on drug-target interaction prediction, 2.6% on drug property prediction, 1.2% on drug-drug interaction prediction, and 4.1% on protein-protein interaction prediction. Through qualitative analysis, we reveal KEDD's promising potential in assisting real-world applications. Conclusions: By incorporating biomolecular expertise from multimodal knowledge, KEDD bears promise in accelerating drug discovery.
Collapse
Affiliation(s)
- Yizhen Luo
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
- Department of Computer Science and Technology,
Tsinghua University, Beijing, China
| | - Xing Yi Liu
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
| | - Kai Yang
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
| | - Kui Huang
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
- School of Software and Microelectronics,
Peking University, Beijing, China
| | - Massimo Hong
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
- Department of Computer Science and Technology,
Tsinghua University, Beijing, China
| | - Jiahuan Zhang
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
| | - Yushuai Wu
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
| | - Zaiqing Nie
- Institute for AI Industry Research (AIR),
Tsinghua University, Beijing, China
- Beijing Academy of Artificial Intelligence (BAAI), Beijing, China
| |
Collapse
|
13
|
Jin Q, Xie J, Huang D, Zhao C, He H. MSFF-MA-DDI: Multi-Source Feature Fusion with Multiple Attention blocks for predicting Drug-Drug Interaction events. Comput Biol Chem 2024; 108:108001. [PMID: 38154317 DOI: 10.1016/j.compbiolchem.2023.108001] [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: 07/23/2023] [Revised: 11/30/2023] [Accepted: 12/03/2023] [Indexed: 12/30/2023]
Abstract
The interaction of multiple drugs could lead to severe events, which cause medical injuries and expenses. Accurate prediction of drug-drug interaction (DDI) events can help clinicians make effective decisions and establish appropriate therapy programs. However, there exist two issues worthy of further consideration. (i) The global features of drug molecules should be paid attention to, rather than just their local characteristics. (ii) The fusion of multi-source features should also be studied to capture the comprehensive features of the drug. This study designs a Multi-Source Feature Fusion framework with Multiple Attention blocks named MSFF-MA-DDI that utilizes multimodal data for DDI event prediction. MSFF-MA-DDI can (i) encode global correlations between long-distance atoms in drug molecular sequences by a self-attention layer based on a position embedding block and (ii) fuse drug sequence features and heterogeneous features (chemical substructure, target, and enzyme) through a multi-head attention block to better represent the features of drugs. Experiments on real-world datasets show that MSFF-MA-DDI can achieve performance that is close to or even better than state-of-the-art models. Especially in cold start scenarios, the model can achieve the best performance. The effectiveness of the model is also supported by the case study on nervous system drugs. The source codes and data are available at https://github.com/BioCenter-SHU/MSFF-MA-DDI.
Collapse
Affiliation(s)
- Qi Jin
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Jiang Xie
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China.
| | - Dingkai Huang
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Chang Zhao
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Hongjian He
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| |
Collapse
|
14
|
Wang NN, Zhu B, Li XL, Liu S, Shi JY, Cao DS. Comprehensive Review of Drug-Drug Interaction Prediction Based on Machine Learning: Current Status, Challenges, and Opportunities. J Chem Inf Model 2024; 64:96-109. [PMID: 38132638 DOI: 10.1021/acs.jcim.3c01304] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2023]
Abstract
Detecting drug-drug interactions (DDIs) is an essential step in drug development and drug administration. Given the shortcomings of current experimental methods, the machine learning (ML) approach has become a reliable alternative, attracting extensive attention from the academic and industrial fields. With the rapid development of computational science and the growing popularity of cross-disciplinary research, a large number of DDI prediction studies based on ML methods have been published in recent years. To give an insight into the current situation and future direction of DDI prediction research, we systemically review these studies from three aspects: (1) the classic DDI databases, mainly including databases of drugs, side effects, and DDI information; (2) commonly used drug attributes, which focus on chemical, biological, and phenotypic attributes for representing drugs; (3) popular ML approaches, such as shallow learning-based, deep learning-based, recommender system-based, and knowledge graph-based methods for DDI detection. For each section, related studies are described, summarized, and compared, respectively. In the end, we conclude the research status of DDI prediction based on ML methods and point out the existing issues, future challenges, potential opportunities, and subsequent research direction.
Collapse
Affiliation(s)
- Ning-Ning Wang
- Department of Pharmacy, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
| | - Bei Zhu
- School of Life Sciences, Northwestern Polytechnical University, Xi'an 710072, Shanxi, P.R. China
| | - Xin-Liang Li
- Department of Pharmacy, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
| | - Shao Liu
- Department of Pharmacy, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
| | - Jian-Yu Shi
- School of Life Sciences, Northwestern Polytechnical University, Xi'an 710072, Shanxi, P.R. China
| | - Dong-Sheng Cao
- Department of Pharmacy, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha 410008, Hunan, P.R. China
- Xiangya School of Pharmaceutical Sciences, Central South University, Changsha 410013, Hunan, P.R. China
| |
Collapse
|
15
|
Yu Z, Wu Z, Wang Z, Wang Y, Zhou M, Li W, Liu G, Tang Y. Network-Based Methods and Their Applications in Drug Discovery. J Chem Inf Model 2024; 64:57-75. [PMID: 38150548 DOI: 10.1021/acs.jcim.3c01613] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2023]
Abstract
Drug discovery is time-consuming, expensive, and predominantly follows the "one drug → one target → one disease" paradigm. With the rapid development of systems biology and network pharmacology, a novel drug discovery paradigm, "multidrug → multitarget → multidisease", has emerged. This new holistic paradigm of drug discovery aligns well with the essence of networks, leading to the emergence of network-based methods in the field of drug discovery. In this Perspective, we initially introduce the concept and data sources of networks and highlight classical methodologies employed in network-based methods. Subsequently, we focus on the practical applications of network-based methods across various areas of drug discovery, such as target prediction, virtual screening, prediction of drug therapeutic effects or adverse drug events, and elucidation of molecular mechanisms. In addition, we provide representative web servers for researchers to use network-based methods in specific applications. Finally, we discuss several challenges of network-based methods and the directions for future development. In a word, network-based methods could serve as powerful tools to accelerate drug discovery.
Collapse
Affiliation(s)
- Zhuohang Yu
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | - Zengrui Wu
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | - Ze Wang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | - Yimeng Wang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | - Moran Zhou
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | - Weihua Li
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | - Guixia Liu
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| | - Yun Tang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
| |
Collapse
|
16
|
Naveed M, Jabeen K, Aziz T, Mughual MS, Ul-Hassan J, Sheraz M, Rehman HM, Alharbi M, Albekairi TH, Alasmari AF. Whole proteome analysis of MDR Klebsiella pneumoniae to identify mRNA and multiple epitope based vaccine targets against emerging nosocomial and lungs associated infections. J Biomol Struct Dyn 2023:1-14. [PMID: 38141172 DOI: 10.1080/07391102.2023.2293266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2023] [Accepted: 11/29/2023] [Indexed: 12/25/2023]
Abstract
Klebsiella pneumonia is a Gram negative facultative anaerobic bacterium involved in various community-acquired pneumonia, nosocomial and lungs associated infections. Frequent usage of several antibiotics and acquired resistance mechanisms has made this bacterium multi-drug resistance (MDR), complicating the treatment of patients. To avoid the spread of this bacterium, there is an urgent need to develop a vaccine based on immuno-informatics approaches that is more efficient than conventional method of vaccine prediction or development. Initially, the complete proteomic sequence of K. pneumonia was picked over for specific and prospective vaccine targets. From the annotation of the whole proteome, eight immunogenic proteins were selected, and these shortlisted proteins were interpreted for CTL, B-cells, and HTL epitopes prediction, to construct mRNA and multi-epitope vaccines. The Antigenicity, allergenicity and toxicity analysis validate the vaccine's design, and its molecular docking was done with immuno-receptor the TLR-3. The docking interaction showed a stronger binding affinity with a minimum energy of -1153.2 kcal/mol and established 23 hydrogen bonds, 3 salt bridges, 1 disulfide bond, and 340 non-binding contacts. Further validation was done using In-silico cloning which shows the highest CAI score of 0.98 with higher GC contents of 72.25% which represents a vaccine construct with a high value of expression in E. coli. Immune Simulation shows that the antibodies (IgM, IgG1, and IgG2) production exceeded 650,000 in 2 to 3 days but the response was completely neutralized in the 5th day. In conclusion, the study provides the effective, safe and stable vaccine construct against Klebsiella pneumonia, which further needs in vitro and in vivo validations.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- Muhammad Naveed
- Department of Biotechnology, Faculty of Life Sciences, University of Central Punjab, Lahore, Pakistan
| | - Khizra Jabeen
- Department of Biotechnology, Faculty of Life Sciences, University of Central Punjab, Lahore, Pakistan
| | - Tariq Aziz
- Department of Agriculture, University of Ioannina, Arta, Greece
| | - Muhammad Saad Mughual
- Department of Biotechnology, Faculty of Life Sciences, University of Central Punjab, Lahore, Pakistan
| | - Jawad Ul-Hassan
- Department of Biotechnology, Faculty of Life Sciences, University of Central Punjab, Lahore, Pakistan
| | - Mohsin Sheraz
- Department of Biotechnology, Faculty of Life Sciences, University of Central Punjab, Lahore, Pakistan
| | | | - Metab Alharbi
- Department of Pharmacology and Toxicology, College of Pharmacy, King Saud University, Riyadh, Saudi Arabia
| | - Thamer H Albekairi
- Department of Pharmacology and Toxicology, College of Pharmacy, King Saud University, Riyadh, Saudi Arabia
| | - Abdullah F Alasmari
- Department of Pharmacology and Toxicology, College of Pharmacy, King Saud University, Riyadh, Saudi Arabia
| |
Collapse
|
17
|
Lin S, Mao X, Hong L, Lin S, Wei DQ, Xiong Y. MATT-DDI: Predicting multi-type drug-drug interactions via heterogeneous attention mechanisms. Methods 2023; 220:1-10. [PMID: 37858611 DOI: 10.1016/j.ymeth.2023.10.007] [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: 09/22/2023] [Revised: 10/13/2023] [Accepted: 10/17/2023] [Indexed: 10/21/2023] Open
Abstract
The joint use of multiple drugs can result in adverse drug-drug interactions (DDIs) and side effects that harm the body. Accurate identification of DDIs is crucial for avoiding accidental drug side effects and understanding potential mechanisms underlying DDIs. Several computational methods have been proposed for multi-type DDI prediction, but most rely on the similarity profiles of drugs as the drug feature vectors, which may result in information leakage and overoptimistic performance when predicting interactions between new drugs. To address this issue, we propose a novel method, MATT-DDI, for predicting multi-type DDIs based on the original feature vectors of drugs and multiple attention mechanisms. MATT-DDI consists of three main modules: the top k most similar drug pair selection module, heterogeneous attention mechanism module and multi‑type DDI prediction module. Firstly, based on the feature vector of the input drug pair (IDP), k drug pairs that are most similar to the input drug pair from the training dataset are selected according to cosine similarity between drug pairs. Then, the vectors of k selected drug pairs are averaged to obtain a new drug pair (NDP). Next, IDP and NDP are fed into heterogeneous attention modules, including scaled dot product attention and bilinear attention, to extract latent feature vectors. Finally, these latent feature vectors are taken as input of the classification module to predict DDI types. We evaluated MATT-DDI on three different tasks. The experimental results show that MATT-DDI provides better or comparable performance compared to several state-of-the-art methods, and its feasibility is supported by case studies. MATT-DDI is a robust model for predicting multi-type DDIs with excellent performance and no information leakage.
Collapse
Affiliation(s)
- Shenggeng Lin
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Xueying Mao
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Liang Hong
- Shanghai Artificial Intelligence Laboratory, Shanghai 200232, China; School of Physics and Astronomy, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Shuangjun Lin
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Dong-Qing Wei
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China; Zhongjing Research and Industrialization Institute of Chinese Medicine, Nanyang 473006, China; Peng Cheng National Laboratory, Shenzhen 518055, China
| | - Yi Xiong
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China; Shanghai Artificial Intelligence Laboratory, Shanghai 200232, China.
| |
Collapse
|
18
|
Zhao Y, Yin J, Zhang L, Zhang Y, Chen X. Drug-drug interaction prediction: databases, web servers and computational models. Brief Bioinform 2023; 25:bbad445. [PMID: 38113076 PMCID: PMC10782925 DOI: 10.1093/bib/bbad445] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2023] [Revised: 10/26/2023] [Accepted: 11/14/2023] [Indexed: 12/21/2023] Open
Abstract
In clinical treatment, two or more drugs (i.e. drug combination) are simultaneously or successively used for therapy with the purpose of primarily enhancing the therapeutic efficacy or reducing drug side effects. However, inappropriate drug combination may not only fail to improve efficacy, but even lead to adverse reactions. Therefore, according to the basic principle of improving the efficacy and/or reducing adverse reactions, we should study drug-drug interactions (DDIs) comprehensively and thoroughly so as to reasonably use drug combination. In this review, we first introduced the basic conception and classification of DDIs. Further, some important publicly available databases and web servers about experimentally verified or predicted DDIs were briefly described. As an effective auxiliary tool, computational models for predicting DDIs can not only save the cost of biological experiments, but also provide relevant guidance for combination therapy to some extent. Therefore, we summarized three types of prediction models (including traditional machine learning-based models, deep learning-based models and score function-based models) proposed during recent years and discussed the advantages as well as limitations of them. Besides, we pointed out the problems that need to be solved in the future research of DDIs prediction and provided corresponding suggestions.
Collapse
Affiliation(s)
- Yan Zhao
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
| | - Jun Yin
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
| | - Li Zhang
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
| | - Yong Zhang
- School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
| | - Xing Chen
- School of Science, Jiangnan University, Wuxi 214122, China
| |
Collapse
|
19
|
Shtar G, Solomon A, Mazuz E, Rokach L, Shapira B. A simplified similarity-based approach for drug-drug interaction prediction. PLoS One 2023; 18:e0293629. [PMID: 37943768 PMCID: PMC10635435 DOI: 10.1371/journal.pone.0293629] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2023] [Accepted: 10/17/2023] [Indexed: 11/12/2023] Open
Abstract
Drug-drug interactions (DDIs) are a critical component of drug safety surveillance. Laboratory studies aimed at detecting DDIs are typically difficult, expensive, and time-consuming; therefore, developing in-silico methods is critical. Machine learning-based approaches for DDI prediction have been developed; however, in many cases, their ability to achieve high accuracy relies on data only available towards the end of the molecule lifecycle. Here, we propose a simple yet effective similarity-based method for preclinical DDI prediction where only the chemical structure is available. We test the model on new, unseen drugs. To focus on the preclinical problem setting, we conducted a retrospective analysis and tested the models on drugs that were added to a later version of the DrugBank database. We extend an existing method, adjacency matrix factorization with propagation (AMFP), to support unseen molecules by applying a new lookup mechanism to the drugs' chemical structure, lookup adjacency matrix factorization with propagation (LAMFP). We show that using an ensemble of different similarity measures improves the results. We also demonstrate that Chemprop, a message-passing neural network, can be used for DDI prediction. In computational experiments, LAMFP results in high accuracy, with an area under the receiver operating characteristic curve of 0.82 for interactions involving a new drug and an existing drug and for interactions involving only existing drugs. Moreover, LAMFP outperforms state-of-the-art, complex graph neural network DDI prediction methods.
Collapse
Affiliation(s)
- Guy Shtar
- Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel
- Department of Information Systems, University of Haifa, Haifa, Israel
| | - Adir Solomon
- Department of Information Systems, University of Haifa, Haifa, Israel
| | - Eyal Mazuz
- Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel
| | - Lior Rokach
- Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel
| | - Bracha Shapira
- Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel
| |
Collapse
|
20
|
Feng J, Liang Y, Yu T. MM-GANN-DDI: Multimodal Graph-Agnostic Neural Networks for Predicting Drug-Drug Interaction Events. Comput Biol Med 2023; 166:107492. [PMID: 37820558 DOI: 10.1016/j.compbiomed.2023.107492] [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: 05/12/2023] [Revised: 08/15/2023] [Accepted: 09/15/2023] [Indexed: 10/13/2023]
Abstract
Personalized treatment of complex diseases relies on combined medication. However, the occurrence of unexpected drug-drug interactions (DDIs) in these combinations can lead to adverse effects or even fatalities. Although recent computational methods exhibit promising performance in DDI screening, their practical implementation faces two significant challenges: (i) the availability of comprehensive datasets to support clinical application, and (ii) the ability to infer DDI types for new drugs beyond the existing dataset coverage. To mitigate these challenges, we propose MM-GANN-DDI: a Multimodal Graph-Agnostic Neural Network for Predicting Drug-Drug Interaction Events. We first mine six drug modalities and incorporate a graph attention (GAT) mechanism to fuse these modalities with the topological features of the DDI graph. We further propose a novel graph neural network training mechanism called graph-agnostic meta-training (GAMT), which effectively leverages topological information from the DDI graph and efficiently predicts DDI types for new drugs beyond the available dataset. Specifically, GAMT samples meta-graphs from the original DDI graph, splitting them into support and query sets to simulate seen and unseen drugs. Two-level optimizations are applied to enhance the model's generalization capability. We evaluate our model on two datasets (DB-v1 and DB-v2) across three tasks. Our MM-GANN-DDI demonstrates competitive performance on all three tasks. Notably, in Task 2, which focuses on predicting DDI types for drugs outside the dataset, our proposed model outperforms other methods, exhibiting an improvement of 4.6 percentage points in AUPR on DB-v1 and 5.9 percentage points on DB-v2. Additionally, our model surpasses state-of-the-art methods and classic approaches in terms of accuracy, F1 score, precision, and recall. Ablation experiments provide further validation of the effectiveness of the proposed model design. Importantly, our model exhibits the potential to discover unobserved DDIs, demonstrating its practical application in clinical medication.
Collapse
Affiliation(s)
- Junning Feng
- Faculty of Innovation Engineering, Macau University of Science and Technology, 999078, Macao Special Administrative Region of China; School of Data Science, The Chinese University of Hong Kong-Shenzhen, Shenzhen, 518055, China
| | - Yong Liang
- Peng Cheng Laboratory, Shenzhen, 518055, China.
| | - Tianwei Yu
- School of Data Science, The Chinese University of Hong Kong-Shenzhen, Shenzhen, 518055, China
| |
Collapse
|
21
|
Zhong Y, Zheng H, Chen X, Zhao Y, Gao T, Dong H, Luo H, Weng Z. DDI-GCN: Drug-drug interaction prediction via explainable graph convolutional networks. Artif Intell Med 2023; 144:102640. [PMID: 37783544 DOI: 10.1016/j.artmed.2023.102640] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Revised: 03/21/2023] [Accepted: 08/20/2023] [Indexed: 10/04/2023]
Abstract
Drug-drug interactions (DDI) may lead to unexpected side effects, which is a growing concern in both academia and industry. Many DDIs have been reported, but the underlying mechanisms are not well understood. Predicting and understanding DDIs can help researchers to improve drug safety and protect patient health. Here, we introduce DDI-GCN, a method that utilizes graph convolutional networks (GCN) to predict DDIs based on chemical structures. We demonstrate that this method achieves state-of-the-art prediction performance on the independent hold-out set. It can also provide visualization of structural features associated with DDIs, which can help us to study the underlying mechanisms. To make it easy and accessible to use, we developed a web server for DDI-GCN, which is freely available at http://wengzq-lab.cn/ddi/.
Collapse
Affiliation(s)
- Yi Zhong
- The Center for Big Data Research in Burns and Trauma, College of Computer and Data Science/College of Software, Fuzhou University, Fujian Province, China
| | - Houbing Zheng
- Department of Plastic Surgery, the First Affiliated Hospital of Fujian Medical University, Fuzhou, China
| | - Xiaoming Chen
- The Center for Big Data Research in Burns and Trauma, College of Computer and Data Science/College of Software, Fuzhou University, Fujian Province, China
| | - Yu Zhao
- The Center for Big Data Research in Burns and Trauma, College of Computer and Data Science/College of Software, Fuzhou University, Fujian Province, China
| | - Tingfang Gao
- College of Biological Science and Engineering, Fuzhou University, Fujian Province, China
| | - Huiqun Dong
- College of Biological Science and Engineering, Fuzhou University, Fujian Province, China
| | - Heng Luo
- The Center for Big Data Research in Burns and Trauma, College of Computer and Data Science/College of Software, Fuzhou University, Fujian Province, China; MetaNovas Biotech Inc., Foster City, CA, USA.
| | - Zuquan Weng
- College of Biological Science and Engineering, Fuzhou University, Fujian Province, China; The Center for Big Data Research in Burns and Trauma, College of Computer and Data Science/College of Software, Fuzhou University, Fujian Province, China; Department of Plastic Surgery, the First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
| |
Collapse
|
22
|
Ning G, Sun Y, Ling J, Chen J, He J. BDN-DDI: A bilinear dual-view representation learning framework for drug-drug interaction prediction. Comput Biol Med 2023; 165:107340. [PMID: 37603959 DOI: 10.1016/j.compbiomed.2023.107340] [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: 06/02/2023] [Revised: 07/23/2023] [Accepted: 08/07/2023] [Indexed: 08/23/2023]
Abstract
Drug-drug interactions (DDIs) refer to the potential effects of two or more drugs interacting with each other when used simultaneously, which may lead to adverse reactions or reduced drug efficacy. Accurate prediction of DDIs is a significant concern in recent years. Currently, the drug chemical substructure-based learning method has substantially improved DDIs prediction. However, we notice that most related works ignore the detailed interaction among atoms when extracting the substructure information of drugs. This problem results in incomplete information extraction and may limit the model's predictive ability. In this work, we proposed a novel framework named BDN-DDI (a bilinear dual-view representation learning framework for drug-drug interaction prediction) to infer potential DDIs. In the proposed framework, the encoder consists of six stacked BDN blocks, each of which extracts the feature representation of drug molecules through a bilinear representation extraction layer. The extracted feature is then used to learn embeddings of drug substructures from the single drug learning layer (intra-layer) and the drug-pair learning layer (inter-layer). Finally, the learned embeddings are fed into a decoder to predict DDI events. Based on our experiments, BDN-DDI has an AUROC value of over 99% for the warm-start task. Additionally, it outperformed the state-of-the-art methods by an average of 3.4% for the cold-start tasks. Finally, our method's effectiveness is further validated by visualizing several case studies.
Collapse
Affiliation(s)
- Guoquan Ning
- School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
| | - Yuping Sun
- School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China.
| | - Jie Ling
- School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
| | - Jijia Chen
- School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
| | - Jiaxi He
- School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
| |
Collapse
|
23
|
Li Z, Tu X, Chen Y, Lin W. HetDDI: a pre-trained heterogeneous graph neural network model for drug-drug interaction prediction. Brief Bioinform 2023; 24:bbad385. [PMID: 37903412 DOI: 10.1093/bib/bbad385] [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: 05/20/2023] [Revised: 08/12/2023] [Accepted: 09/13/2023] [Indexed: 11/01/2023] Open
Abstract
The simultaneous use of two or more drugs due to multi-disease comorbidity continues to increase, which may cause adverse reactions between drugs that seriously threaten public health. Therefore, the prediction of drug-drug interaction (DDI) has become a hot topic not only in clinics but also in bioinformatics. In this study, we propose a novel pre-trained heterogeneous graph neural network (HGNN) model named HetDDI, which aggregates the structural information in drug molecule graphs and rich semantic information in biomedical knowledge graph to predict DDIs. In HetDDI, we first initialize the parameters of the model with different pre-training methods. Then we apply the pre-trained HGNN to learn the feature representation of drugs from multi-source heterogeneous information, which can more effectively utilize drugs' internal structure and abundant external biomedical knowledge, thus leading to better DDI prediction. We evaluate our model on three DDI prediction tasks (binary-class, multi-class and multi-label) with three datasets and further assess its performance on three scenarios (S1, S2 and S3). The results show that the accuracy of HetDDI can achieve 98.82% in the binary-class task, 98.13% in the multi-class task and 96.66% in the multi-label one on S1, which outperforms the state-of-the-art methods by at least 2%. On S2 and S3, our method also achieves exciting performance. Furthermore, the case studies confirm that our model performs well in predicting unknown DDIs. Source codes are available at https://github.com/LinsLab/HetDDI.
Collapse
Affiliation(s)
- Zhe Li
- School of Computer Science, University of South China, Hengyang, 421001 Hunan, China
| | - Xinyi Tu
- School of Computer Science, University of South China, Hengyang, 421001 Hunan, China
| | - Yuping Chen
- School of Pharmacy, University of South China, Hengyang 421001, China
| | - Wenbin Lin
- School of Mathematics and Physics, University of South China, Hengyang 421001, China
| |
Collapse
|
24
|
Gan Y, Liu W, Xu G, Yan C, Zou G. DMFDDI: deep multimodal fusion for drug-drug interaction prediction. Brief Bioinform 2023; 24:bbad397. [PMID: 37930025 DOI: 10.1093/bib/bbad397] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2023] [Revised: 09/28/2023] [Accepted: 10/13/2023] [Indexed: 11/07/2023] Open
Abstract
Drug combination therapy has gradually become a promising treatment strategy for complex or co-existing diseases. As drug-drug interactions (DDIs) may cause unexpected adverse drug reactions, DDI prediction is an important task in pharmacology and clinical applications. Recently, researchers have proposed several deep learning methods to predict DDIs. However, these methods mainly exploit the chemical or biological features of drugs, which is insufficient and limits the performances of DDI prediction. Here, we propose a new deep multimodal feature fusion framework for DDI prediction, DMFDDI, which fuses drug molecular graph, DDI network and the biochemical similarity features of drugs to predict DDIs. To fully extract drug molecular structure, we introduce an attention-gated graph neural network for capturing the global features of the molecular graph and the local features of each atom. A sparse graph convolution network is introduced to learn the topological structure information of the DDI network. In the multimodal feature fusion module, an attention mechanism is used to efficiently fuse different features. To validate the performance of DMFDDI, we compare it with 10 state-of-the-art methods. The comparison results demonstrate that DMFDDI achieves better performance in DDI prediction. Our method DMFDDI is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDEBLab/DMFDDI.git.
Collapse
Affiliation(s)
- Yanglan Gan
- School of Computer Science and Technology, Donghua University, 2999 North Renmin Road, 201600, Shanghai, China
| | - Wenxiao Liu
- School of Computer Science and Technology, Donghua University, 2999 North Renmin Road, 201600, Shanghai, China
| | - Guangwei Xu
- School of Computer Science and Technology, Donghua University, 2999 North Renmin Road, 201600, Shanghai, China
| | - Cairong Yan
- School of Computer Science and Technology, Donghua University, 2999 North Renmin Road, 201600, Shanghai, China
| | - Guobing Zou
- School of Computer Engineering and Science, Shanghai University, 99 Shangda Road, 200444, Shanghai, China
| |
Collapse
|
25
|
Masumshah R, Eslahchi C. DPSP: a multimodal deep learning framework for polypharmacy side effects prediction. BIOINFORMATICS ADVANCES 2023; 3:vbad110. [PMID: 37701676 PMCID: PMC10493180 DOI: 10.1093/bioadv/vbad110] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Revised: 08/01/2023] [Accepted: 08/15/2023] [Indexed: 09/14/2023]
Abstract
Motivation Because unanticipated drug-drug interactions (DDIs) can result in severe bodily harm, identifying the adverse effects of polypharmacy is one of the most important tasks in human health. Over the past few decades, computational methods for predicting the adverse effects of polypharmacy have been developed. Results This article presents DPSP, a framework for predicting polypharmacy side effects based on the construction of novel drug features and the application of a deep neural network to predict DDIs. In the first step, a variety of drug information is evaluated, and a feature extraction method and the Jaccard similarity are used to determine similarities between two drugs. By combining these similarities, a novel feature vector is generated for each drug. In the second step, the method predicts DDIs for specific DDI events using a multimodal framework and drug feature vectors. On three benchmark datasets, the performance of DPSP is measured by comparing its results to those of several well-known methods, such as GNN-DDI, MSTE, MDF-SA-DDI, NNPS, DDIMDL, DNN, DeepDDI, KNN, LR, and RF. DPSP outperforms these classification methods based on a variety of classification metrics. The results indicate that the use of diverse drug information is effective and efficient for identifying DDI adverse effects. Availability and implementation The source code and datasets are available at https://github.com/raziyehmasumshah/DPSP.
Collapse
Affiliation(s)
- Raziyeh Masumshah
- Department of Computer and Data Sciences, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran 1983969411, Iran
| | - Changiz Eslahchi
- Department of Computer and Data Sciences, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran 1983969411, Iran
- School of Biological Sciences, Institute for Research in Fundamental Sciences (IPM), Tehran 193955746, Iran
| |
Collapse
|
26
|
Lv J, Liu G, Ju Y, Huang H, Li D, Sun Y. Identification of Robust Antibiotic Subgroups by Integrating Multi-Species Drug-Drug Interactions. J Chem Inf Model 2023; 63:4970-4978. [PMID: 37459588 DOI: 10.1021/acs.jcim.3c00937] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/15/2023]
Abstract
Previous studies have shown that antibiotics can be divided into groups, and drug-drug interactions (DDI) depend on their groups. However, these studies focused on a specific bacteria strain (i.e., Escherichia coli BW25113). Existing datasets often contain noise. Noisy labeled data may have a bad effect on the clustering results. To address this problem, we developed a multi-source information fusion method for integrating DDI information from multiple bacterial strains. Specifically, we calculated drug similarities based on the DDI network of each bacterial strain and then fused these drug similarity matrices to obtain a new fused similarity matrix. The fused similarity matrix was combined with the T-distributed stochastic neighbor embedding algorithm, and hierarchical clustering algorithm can effectively identify antibiotic subgroups. These antibiotic subgroups are strongly correlated with known antibiotic classifications, and group-group interactions are almost monochromatic. In summary, our method provides a promising framework for understanding the mechanism of action of antibiotics and exploring multi-species group-group interactions.
Collapse
Affiliation(s)
- Ji Lv
- College of Computer Science and Technology, Jilin University, Changchun 130000, China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130000, China
| | - Guixia Liu
- College of Computer Science and Technology, Jilin University, Changchun 130000, China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130000, China
| | - Yuan Ju
- Sichuan University Library, Sichuan University, 610000 Chengdu, China
| | - Houhou Huang
- College of Chemistry, Jilin University, Changchun 130000, China
| | - Dalin Li
- School of Computer Science, Zhuhai College of Science and Technology, Zhuhai 519041, China
| | - Ying Sun
- Department of Respiratory Medicine, The First Hospital of Jilin University, Changchun 130000, China
| |
Collapse
|
27
|
Lv Q, Zhou J, Yang Z, He H, Chen CYC. 3D graph neural network with few-shot learning for predicting drug-drug interactions in scaffold-based cold start scenario. Neural Netw 2023; 165:94-105. [PMID: 37276813 DOI: 10.1016/j.neunet.2023.05.039] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2023] [Revised: 05/15/2023] [Accepted: 05/19/2023] [Indexed: 06/07/2023]
Abstract
Understanding drug-drug interactions (DDI) of new drugs is critical for minimizing unexpected adverse drug reactions. The modeling of new drugs is called a cold start scenario. In this scenario, Only a few structural information or physicochemical information about new drug is available. The 3D conformation of drug molecules usually plays a crucial role in chemical properties compared to the 2D structure. 3D graph network with few-shot learning is a promising solution. However, the 3D heterogeneity of drug molecules and the discretization of atomic distributions lead to spatial confusion in few-shot learning. Here, we propose a 3D graph neural network with few-shot learning, Meta3D-DDI, to predict DDI events in cold start scenario. The 3DGNN ensures rotation and translation invariance by calculating atomic pairwise distances, and incorporates 3D structure and distance information in the information aggregation stage. The continuous filter interaction module can continuously simulate the filter to obtain the interaction between the target atom and other atoms. Meta3D-DDI further develops a FSL strategy based on bilevel optimization to transfer meta-knowledge for DDI prediction tasks from existing drugs to new drugs. In addition, the existing cold start setting may cause the scaffold structure information in the training set to leak into the test set. We design scaffold-based cold start scenario to ensure that the drug scaffolds in the training set and test set do not overlap. The extensive experiments demonstrate that our architecture achieves the SOTA performance for DDI prediction under scaffold-based cold start scenario on two real-world datasets. The visual experiment shows that Meta3D-DDI significantly improves the learning for DDI prediction of new drugs. We also demonstrate how Meta3D-DDI can reduce the amount of data required to make meaningful DDI predictions.
Collapse
Affiliation(s)
- Qiujie Lv
- School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Jun Zhou
- School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Ziduo Yang
- School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Haohuai He
- School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China
| | - Calvin Yu-Chian Chen
- School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong 518107, China; Department of Medical Research, China Medical University Hospital, Taichung, 40447, Taiwan; Department of Bioinformatics and Medical Engineering, Asia University, Taichung, 41354, Taiwan.
| |
Collapse
|
28
|
Chang CWJ, Provencio JJ, Pascual J, Heavner MS, Olson D, Livesay SL, Kaplan LJ. State-of-the-Art Evaluation of Acute Adult Disorders of Consciousness for the General Intensivist. Crit Care Med 2023; 51:948-963. [PMID: 37070819 DOI: 10.1097/ccm.0000000000005893] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/19/2023]
Abstract
OBJECTIVES To provide a concise review of knowledge and practice pertaining to the diagnosis and initial management of unanticipated adult patient disorders of consciousness (DoC) by the general intensivist. DATA SOURCES Detailed search strategy using PubMed and OVID Medline for English language articles describing adult patient acute DoC diagnostic evaluation and initial management strategies including indications for transfer. STUDY SELECTION Descriptive and interventional studies that address acute adult DoC, their evaluation and initial management, indications for transfer, as well as outcome prognostication. DATA EXTRACTION Relevant descriptions or studies were reviewed, and the following aspects of each manuscript were identified, abstracted, and analyzed: setting, study population, aims, methods, results, and relevant implications for adult critical care practice. DATA SYNTHESIS Acute adult DoC may be categorized by etiology including structural, functional, infectious, inflammatory, and pharmacologic, the understanding of which drives diagnostic investigation, monitoring, acute therapy, and subsequent specialist care decisions including team-based local care as well as intra- and inter-facility transfer. CONCLUSIONS Acute adult DoC may be initially comprehensively addressed by the general intensivist using an etiology-driven and team-based approach. Certain clinical conditions, procedural expertise needs, or resource limitations inform transfer decision-making within a complex care facility or to one with greater complexity. Emerging collaborative science helps improve our current knowledge of acute DoC to better align therapies with underpinning etiologies.
Collapse
Affiliation(s)
| | | | - Jose Pascual
- Division of Trauma, Surgical Critical Care and Emergency Surgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - Mojdeh S Heavner
- Department of Practice, Sciences, and Health Outcomes Research, University of Maryland School of Pharmacy, Baltimore, MD
| | - DaiWai Olson
- Departments of Neurology and Neurosurgery, University of Texas Southwestern, Dallas, TX
| | - Sarah L Livesay
- Department of Adult Health and Gerontological Nursing, College of Nursing, Rush University, Chicago, IL
| | - Lewis J Kaplan
- Division of Trauma, Surgical Critical Care and Emergency Surgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| |
Collapse
|
29
|
Wang F, Yang H, Wu Y, Peng L, Li X. SAELGMDA: Identifying human microbe-disease associations based on sparse autoencoder and LightGBM. Front Microbiol 2023; 14:1207209. [PMID: 37415823 PMCID: PMC10320730 DOI: 10.3389/fmicb.2023.1207209] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2023] [Accepted: 05/18/2023] [Indexed: 07/08/2023] Open
Abstract
Introduction Identification of complex associations between diseases and microbes is important to understand the pathogenesis of diseases and design therapeutic strategies. Biomedical experiment-based Microbe-Disease Association (MDA) detection methods are expensive, time-consuming, and laborious. Methods Here, we developed a computational method called SAELGMDA for potential MDA prediction. First, microbe similarity and disease similarity are computed by integrating their functional similarity and Gaussian interaction profile kernel similarity. Second, one microbe-disease pair is presented as a feature vector by combining the microbe and disease similarity matrices. Next, the obtained feature vectors are mapped to a low-dimensional space based on a Sparse AutoEncoder. Finally, unknown microbe-disease pairs are classified based on Light Gradient boosting machine. Results The proposed SAELGMDA method was compared with four state-of-the-art MDA methods (MNNMDA, GATMDA, NTSHMDA, and LRLSHMDA) under five-fold cross validations on diseases, microbes, and microbe-disease pairs on the HMDAD and Disbiome databases. The results show that SAELGMDA computed the best accuracy, Matthews correlation coefficient, AUC, and AUPR under the majority of conditions, outperforming the other four MDA prediction models. In particular, SAELGMDA obtained the best AUCs of 0.8358 and 0.9301 under cross validation on diseases, 0.9838 and 0.9293 under cross validation on microbes, and 0.9857 and 0.9358 under cross validation on microbe-disease pairs on the HMDAD and Disbiome databases. Colorectal cancer, inflammatory bowel disease, and lung cancer are diseases that severely threat human health. We used the proposed SAELGMDA method to find possible microbes for the three diseases. The results demonstrate that there are potential associations between Clostridium coccoides and colorectal cancer and one between Sphingomonadaceae and inflammatory bowel disease. In addition, Veillonella may associate with autism. The inferred MDAs need further validation. Conclusion We anticipate that the proposed SAELGMDA method contributes to the identification of new MDAs.
Collapse
Affiliation(s)
- Feixiang Wang
- School of Computer Science, Hunan University of Technology, Zhuzhou, China
| | - Huandong Yang
- Department of Gastrointestinal Surgery, Yidu Central Hospital of Weifang, Weifang, China
| | - Yan Wu
- Geneis (Beijing) Co., Ltd., Beijing, China
| | - Lihong Peng
- School of Computer Science, Hunan University of Technology, Zhuzhou, China
| | - Xiaoling Li
- The Second Department of Oncology, Beidahuang Industry Group General Hospital, Harbin, China
- The Second Department of Oncology, Heilongjiang Second Cancer Hospital, Harbin, China
| |
Collapse
|
30
|
Zhang M, Gao H, Liao X, Ning B, Gu H, Yu B. DBGRU-SE: predicting drug-drug interactions based on double BiGRU and squeeze-and-excitation attention mechanism. Brief Bioinform 2023:7176312. [PMID: 37225428 DOI: 10.1093/bib/bbad184] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Revised: 04/03/2023] [Accepted: 04/23/2023] [Indexed: 05/26/2023] Open
Abstract
The prediction of drug-drug interactions (DDIs) is essential for the development and repositioning of new drugs. Meanwhile, they play a vital role in the fields of biopharmaceuticals, disease diagnosis and pharmacological treatment. This article proposes a new method called DBGRU-SE for predicting DDIs. Firstly, FP3 fingerprints, MACCS fingerprints, Pubchem fingerprints and 1D and 2D molecular descriptors are used to extract the feature information of the drugs. Secondly, Group Lasso is used to remove redundant features. Then, SMOTE-ENN is applied to balance the data to obtain the best feature vectors. Finally, the best feature vectors are fed into the classifier combining BiGRU and squeeze-and-excitation (SE) attention mechanisms to predict DDIs. After applying five-fold cross-validation, The ACC values of DBGRU-SE model on the two datasets are 97.51 and 94.98%, and the AUC are 99.60 and 98.85%, respectively. The results showed that DBGRU-SE had good predictive performance for drug-drug interactions.
Collapse
Affiliation(s)
| | - Hongli Gao
- Qingdao University of Science and Technology, China
| | - Xin Liao
- Qingdao University of Science and Technology, China
| | - Baoxing Ning
- Qingdao University of Science and Technology, China
| | - Haiming Gu
- Qingdao University of Science and Technology, China
| | - Bin Yu
- Qingdao University of Science and Technology, China
| |
Collapse
|
31
|
Weiskittel TM, Cao A, Meng-Lin K, Lehmann Z, Feng B, Correia C, Zhang C, Wisniewski P, Zhu S, Yong Ung C, Li H. Network Biology-Inspired Machine Learning Features Predict Cancer Gene Targets and Reveal Target Coordinating Mechanisms. Pharmaceuticals (Basel) 2023; 16:752. [PMID: 37242535 PMCID: PMC10223789 DOI: 10.3390/ph16050752] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 05/08/2023] [Accepted: 05/11/2023] [Indexed: 05/28/2023] Open
Abstract
Anticipating and understanding cancers' need for specific gene activities is key for novel therapeutic development. Here we utilized DepMap, a cancer gene dependency screen, to demonstrate that machine learning combined with network biology can produce robust algorithms that both predict what genes a cancer is dependent on and what network features coordinate such gene dependencies. Using network topology and biological annotations, we constructed four groups of novel engineered machine learning features that produced high accuracies when predicting binary gene dependencies. We found that in all examined cancer types, F1 scores were greater than 0.90, and model accuracy remained robust under multiple hyperparameter tests. We then deconstructed these models to identify tumor type-specific coordinators of gene dependency and identified that in certain cancers, such as thyroid and kidney, tumors' dependencies are highly predicted by gene connectivity. In contrast, other histologies relied on pathway-based features such as lung, where gene dependencies were highly predictive by associations with cell death pathway genes. In sum, we show that biologically informed network features can be a valuable and robust addition to predictive pharmacology models while simultaneously providing mechanistic insights.
Collapse
Affiliation(s)
- Taylor M. Weiskittel
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
- Mayo Clinic Alix School of Medicine, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA
| | - Andrew Cao
- Department of Computer Science, Duke University, Durham, NC 27708, USA
| | - Kevin Meng-Lin
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Zachary Lehmann
- Department of Chemistry, Biochemistry and Physics, South Dakota State University, Brookings, SD 57006, USA
| | - Benjamin Feng
- Department of Molecular Cell and Developmental Biology, University of California, Los Angeles, CA 90095, USA
| | - Cristina Correia
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Cheng Zhang
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Philip Wisniewski
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Shizhen Zhu
- Department of Biochemistry and Molecular Biology, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA
| | - Choong Yong Ung
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Hu Li
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| |
Collapse
|
32
|
Liu S, Zhang Y, Cui Y, Qiu Y, Deng Y, Zhang Z, Zhang W. Enhancing Drug-Drug Interaction Prediction Using Deep Attention Neural Networks. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023; 20:976-985. [PMID: 35511833 DOI: 10.1109/tcbb.2022.3172421] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
Drug-drug interactions are one of the main concerns in drug discovery. Accurate prediction of drug-drug interactions plays a key role in increasing the efficiency of drug research and safety when multiple drugs are co-prescribed. With various data sources that describe the relationships and properties between drugs, the comprehensive approach that integrates multiple data sources would be considerably effective in making high-accuracy prediction. In this paper, we propose a Deep Attention Neural Network based Drug-Drug Interaction prediction framework, abbreviated as DANN-DDI, to predict unobserved drug-drug interactions. First, we construct multiple drug feature networks and learn drug representations from these networks using the graph embedding method; then, we concatenate the learned drug embeddings and design an attention neural network to learn representations of drug-drug pairs; finally, we adopt a deep neural network to accurately predict drug-drug interactions. The experimental results demonstrate that our model DANN-DDI has improved prediction performance compared with state-of-the-art methods. Moreover, the proposed model can predict novel drug-drug interactions and drug-drug interaction-associated events.
Collapse
|
33
|
Zhang J, Chen M, Liu J, Peng D, Dai Z, Zou X, Li Z. A Knowledge-Graph-Based Multimodal Deep Learning Framework for Identifying Drug-Drug Interactions. Molecules 2023; 28:molecules28031490. [PMID: 36771157 PMCID: PMC9919258 DOI: 10.3390/molecules28031490] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2023] [Revised: 01/27/2023] [Accepted: 01/31/2023] [Indexed: 02/05/2023] Open
Abstract
The identification of drug-drug interactions (DDIs) plays a crucial role in various areas of drug development. In this study, a deep learning framework (KGCN_NFM) is presented to recognize DDIs using coupling knowledge graph convolutional networks (KGCNs) with neural factorization machines (NFMs). A KGCN is used to learn the embedding representation containing high-order structural information and semantic information in the knowledge graph (KG). The embedding and the Morgan molecular fingerprint of drugs are then used as input of NFMs to predict DDIs. The performance and effectiveness of the current method have been evaluated and confirmed based on the two real-world datasets with different sizes, and the results demonstrate that KGCN_NFM outperforms the state-of-the-art algorithms. Moreover, the identified interactions between topotecan and dantron by KGCN_NFM were validated through MTT assays, apoptosis experiments, cell cycle analysis, and molecular docking. Our study shows that the combination therapy of the two drugs exerts a synergistic anticancer effect, which provides an effective treatment strategy against lung carcinoma. These results reveal that KGCN_NFM is a valuable tool for integrating heterogeneous information to identify potential DDIs.
Collapse
Affiliation(s)
- Jing Zhang
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou 510006, China
| | - Meng Chen
- School of Biomedical Engineering, Sun Yat-sen University, Guangzhou 510275, China
| | - Jie Liu
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou 510006, China
| | - Dongdong Peng
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou 510006, China
| | - Zong Dai
- School of Biomedical Engineering, Sun Yat-sen University, Guangzhou 510275, China
| | - Xiaoyong Zou
- School of Chemistry, Sun Yat-sen University, Guangzhou 510275, China
- Correspondence: (X.Z.); (Z.L.)
| | - Zhanchao Li
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou 510006, China
- Key Laboratory of Digital Quality Evaluation of Traditional Chinese Medicine, National Administration of Traditional Chinese Medicine, Guangzhou 510006, China
- Correspondence: (X.Z.); (Z.L.)
| |
Collapse
|
34
|
Ma M, Lei X. A dual graph neural network for drug-drug interactions prediction based on molecular structure and interactions. PLoS Comput Biol 2023; 19:e1010812. [PMID: 36701288 PMCID: PMC9879511 DOI: 10.1371/journal.pcbi.1010812] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Accepted: 12/12/2022] [Indexed: 01/27/2023] Open
Abstract
Expressive molecular representation plays critical roles in researching drug design, while effective methods are beneficial to learning molecular representations and solving related problems in drug discovery, especially for drug-drug interactions (DDIs) prediction. Recently, a lot of work has been put forward using graph neural networks (GNNs) to forecast DDIs and learn molecular representations. However, under the current GNNs structure, the majority of approaches learn drug molecular representation from one-dimensional string or two-dimensional molecular graph structure, while the interaction information between chemical substructure remains rarely explored, and it is neglected to identify key substructures that contribute significantly to the DDIs prediction. Therefore, we proposed a dual graph neural network named DGNN-DDI to learn drug molecular features by using molecular structure and interactions. Specifically, we first designed a directed message passing neural network with substructure attention mechanism (SA-DMPNN) to adaptively extract substructures. Second, in order to improve the final features, we separated the drug-drug interactions into pairwise interactions between each drug's unique substructures. Then, the features are adopted to predict interaction probability of a DDI tuple. We evaluated DGNN-DDI on real-world dataset. Compared to state-of-the-art methods, the model improved DDIs prediction performance. We also conducted case study on existing drugs aiming to predict drug combinations that may be effective for the novel coronavirus disease 2019 (COVID-19). Moreover, the visual interpretation results proved that the DGNN-DDI was sensitive to the structure information of drugs and able to detect the key substructures for DDIs. These advantages demonstrated that the proposed method enhanced the performance and interpretation capability of DDI prediction modeling.
Collapse
Affiliation(s)
- Mei Ma
- School of Computer Science, Shaanxi Normal University, Xi’an, China
- School of Mathematics and Statistics, Qinghai Normal University, Qinghai, China
| | - Xiujuan Lei
- School of Computer Science, Shaanxi Normal University, Xi’an, China
- * E-mail:
| |
Collapse
|
35
|
Lin J, Wu L, Zhu J, Liang X, Xia Y, Xie S, Qin T, Liu TY. R2-DDI: relation-aware feature refinement for drug-drug interaction prediction. Brief Bioinform 2023; 24:6961471. [PMID: 36573491 DOI: 10.1093/bib/bbac576] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2022] [Revised: 11/14/2022] [Accepted: 11/25/2022] [Indexed: 12/28/2022] Open
Abstract
Precisely predicting the drug-drug interaction (DDI) is an important application and host research topic in drug discovery, especially for avoiding the adverse effect when using drug combination treatment for patients. Nowadays, machine learning and deep learning methods have achieved great success in DDI prediction. However, we notice that most of the works ignore the importance of the relation type when building the DDI prediction models. In this work, we propose a novel R$^2$-DDI framework, which introduces a relation-aware feature refinement module for drug representation learning. The relation feature is integrated into drug representation and refined in the framework. With the refinement features, we also incorporate the consistency training method to regularize the multi-branch predictions for better generalization. Through extensive experiments and studies, we demonstrate our R$^2$-DDI approach can significantly improve the DDI prediction performance over multiple real-world datasets and settings, and our method shows better generalization ability with the help of the feature refinement design.
Collapse
Affiliation(s)
- Jiacheng Lin
- Department of Automation, Tsinghua University, 30 Shuangqing Rd, Haidian District, 100084 Beijing, China
| | - Lijun Wu
- Microsoft Research AI4Science, No. 5 Dan Ling Street, Haidian District, 100080 Beijing, China
| | - Jinhua Zhu
- CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China, No. 96, JinZhai Road Baohe District, 230026 Hefei, Anhui Province, China
| | - Xiaobo Liang
- Institute of Artificial Intelligence, Soochow University, No. 178, Yucai Rd, Gusu District, 215006 Soochow, Jaingsu Province, China
| | - Yingce Xia
- Microsoft Research AI4Science, No. 5 Dan Ling Street, Haidian District, 100080 Beijing, China
| | - Shufang Xie
- Microsoft Research AI4Science, No. 5 Dan Ling Street, Haidian District, 100080 Beijing, China
| | - Tao Qin
- Microsoft Research AI4Science, No. 5 Dan Ling Street, Haidian District, 100080 Beijing, China
| | - Tie-Yan Liu
- Microsoft Research AI4Science, No. 5 Dan Ling Street, Haidian District, 100080 Beijing, China
| |
Collapse
|
36
|
Feng YH, Zhang SW, Feng YY, Zhang QQ, Shi MH, Shi JY. A social theory-enhanced graph representation learning framework for multitask prediction of drug-drug interactions. Brief Bioinform 2023; 24:6987818. [PMID: 36642408 DOI: 10.1093/bib/bbac602] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2022] [Revised: 11/30/2022] [Accepted: 12/06/2022] [Indexed: 01/17/2023] Open
Abstract
Current machine learning-based methods have achieved inspiring predictions in the scenarios of mono-type and multi-type drug-drug interactions (DDIs), but they all ignore enhancive and depressive pharmacological changes triggered by DDIs. In addition, these pharmacological changes are asymmetric since the roles of two drugs in an interaction are different. More importantly, these pharmacological changes imply significant topological patterns among DDIs. To address the above issues, we first leverage Balance theory and Status theory in social networks to reveal the topological patterns among directed pharmacological DDIs, which are modeled as a signed and directed network. Then, we design a novel graph representation learning model named SGRL-DDI (social theory-enhanced graph representation learning for DDI) to realize the multitask prediction of DDIs. SGRL-DDI model can capture the task-joint information by integrating relation graph convolutional networks with Balance and Status patterns. Moreover, we utilize task-specific deep neural networks to perform two tasks, including the prediction of enhancive/depressive DDIs and the prediction of directed DDIs. Based on DDI entries collected from DrugBank, the superiority of our model is demonstrated by the comparison with other state-of-the-art methods. Furthermore, the ablation study verifies that Balance and Status patterns help characterize directed pharmacological DDIs, and that the joint of two tasks provides better DDI representations than individual tasks. Last, we demonstrate the practical effectiveness of our model by a version-dependent test, where 88.47 and 81.38% DDI out of newly added entries provided by the latest release of DrugBank are validated in two predicting tasks respectively.
Collapse
Affiliation(s)
- Yue-Hua Feng
- Key Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
| | - Shao-Wu Zhang
- Key Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
| | - Yi-Yang Feng
- Key Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
| | - Qing-Qing Zhang
- Key Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
| | - Ming-Hui Shi
- Key Laboratory of Information Fusion Technology of Ministry of Education, School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
| | - Jian-Yu Shi
- School of Life Sciences, Northwestern Polytechnical University, Xi'an 710072, China
| |
Collapse
|
37
|
MSResG: Using GAE and Residual GCN to Predict Drug-Drug Interactions Based on Multi-source Drug Features. Interdiscip Sci 2023; 15:171-188. [PMID: 36646843 DOI: 10.1007/s12539-023-00550-6] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2022] [Revised: 01/05/2023] [Accepted: 01/07/2023] [Indexed: 01/18/2023]
Abstract
Drug-drug interaction refers to taking the two drugs may produce certain reaction which may be a threat to patients' health, or enhance the efficacy helpful for medical work. Therefore, it is necessary to study and predict it. In fact, traditional experimental methods can be used for drug-drug interaction prediction, but they are time-consuming and costly, so we prefer to use more accurate and convenient calculation methods to predict the unknown drug-drug interaction. In this paper, we proposed a deep learning framework called MSResG that considers multi-sources features of drugs and combines them with Graph Auto-Encoder to predicting. Firstly, the model obtains four feature representations of drugs from the database, namely, chemical substructure, target, pathway and enzyme, and then calculates the Jaccard similarity of the drugs. To balance different drug features, we perform similarity integration by finding the mean value. Then we will be comprehensive similarity network combined with drug interaction network, and encodes and decodes it using the graph auto-encoder based on residual graph convolution network. Encoding is to learn the potential feature vectors of drugs, which contain similar information and interaction information. Decoding is to reconstruct the network to predict unknown drug-drug interaction. The experimental results show that our model has advanced performance and is superior to other existing advanced methods. Case study also shows that MSResG has practical significance.
Collapse
|
38
|
Liu H, Bing P, Zhang M, Tian G, Ma J, Li H, Bao M, He K, He J, He B, Yang J. MNNMDA: Predicting human microbe-disease association via a method to minimize matrix nuclear norm. Comput Struct Biotechnol J 2023; 21:1414-1423. [PMID: 36824227 PMCID: PMC9941872 DOI: 10.1016/j.csbj.2022.12.053] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Revised: 12/29/2022] [Accepted: 12/30/2022] [Indexed: 01/03/2023] Open
Abstract
Identifying the potential associations between microbes and diseases is the first step for revealing the pathological mechanisms of microbe-associated diseases. However, traditional culture-based microbial experiments are expensive and time-consuming. Thus, it is critical to prioritize disease-associated microbes by computational methods for further experimental validation. In this study, we proposed a novel method called MNNMDA, to predict microbe-disease associations (MDAs) by applying a Matrix Nuclear Norm method into known microbe and disease data. Specifically, we first calculated Gaussian interaction profile kernel similarity and functional similarity for diseases and microbes. Then we constructed a heterogeneous information network by combining the integrated disease similarity network, the integrated microbe similarity network and the known microbe-disease bipartite network. Finally, we formulated the microbe-disease association prediction problem as a low-rank matrix completion problem, which was solved by minimizing the nuclear norm of a matrix with a few regularization terms. We tested the performances of MNNMDA in three datasets including HMDAD, Disbiome, and Combined Data with small, medium and large sizes respectively. We also compared MNNMDA with 5 state-of-the-art methods including KATZHMDA, LRLSHMDA, NTSHMDA, GATMDA, and KGNMDA, respectively. MNNMDA achieved area under the ROC curves (AUROC) of 0.9536 and 0.9364 respectively on HDMAD and Disbiome, better than the AUCs of compared methods under the 5-fold cross-validation for all microbe-disease associations. It also obtained a relatively good performance with AUROC 0.8858 in the combined data. In addition, MNNMDA was also better than other methods in area under precision and recall curve (AUPR) under the 5-fold cross-validation for all associations, and in both AUROC and AUPR under the 5-fold cross-validation for diseases and the 5-fold cross-validation for microbes. Finally, the case studies on colon cancer and inflammatory bowel disease (IBD) also validated the effectiveness of MNNMDA. In conclusion, MNNMDA is an effective method in predicting microbe-disease associations. Availability The codes and data for this paper are freely available at Github https://github.com/Haiyan-Liu666/MNNMDA.
Collapse
Affiliation(s)
- Haiyan Liu
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China,College of Information Engineering, Changsha Medical University, Changsha 410219, PR China,Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations, Changsha Medical University, Changsha 410219, PR China
| | - Pingping Bing
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China
| | - Meijun Zhang
- Geneis Beijing Co., Ltd., Beijing 100102, PR China
| | - Geng Tian
- Geneis Beijing Co., Ltd., Beijing 100102, PR China
| | - Jun Ma
- College of Information Engineering, Changsha Medical University, Changsha 410219, PR China
| | - Haigang Li
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China,Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations, Changsha Medical University, Changsha 410219, PR China,School of pharmacy, Changsha Medical University, Changsha 410219, PR China
| | - Meihua Bao
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China,Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations, Changsha Medical University, Changsha 410219, PR China,School of pharmacy, Changsha Medical University, Changsha 410219, PR China
| | - Kunhui He
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China,Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations, Changsha Medical University, Changsha 410219, PR China,School of pharmacy, Changsha Medical University, Changsha 410219, PR China
| | - Jianjun He
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China,Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations, Changsha Medical University, Changsha 410219, PR China,School of pharmacy, Changsha Medical University, Changsha 410219, PR China,Corresponding authors at: Academician Workstation, Changsha Medical University, Changsha 410219, PR China.
| | - Binsheng He
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China,Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations, Changsha Medical University, Changsha 410219, PR China,School of pharmacy, Changsha Medical University, Changsha 410219, PR China,Corresponding authors at: Academician Workstation, Changsha Medical University, Changsha 410219, PR China.
| | - Jialiang Yang
- Academician Workstation, Changsha Medical University, Changsha 410219, PR China,Hunan Key Laboratory of the Research and Development of Novel Pharmaceutical Preparations, Changsha Medical University, Changsha 410219, PR China,Geneis Beijing Co., Ltd., Beijing 100102, PR China,School of pharmacy, Changsha Medical University, Changsha 410219, PR China,Corresponding authors at: Academician Workstation, Changsha Medical University, Changsha 410219, PR China.
| |
Collapse
|
39
|
Hong E, Jeon J, Kim HU. Recent development of machine learning models for the prediction of drug-drug interactions. KOREAN J CHEM ENG 2023; 40:276-285. [PMID: 36748027 PMCID: PMC9894510 DOI: 10.1007/s11814-023-1377-3] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2022] [Revised: 12/09/2022] [Accepted: 12/16/2022] [Indexed: 02/05/2023]
Abstract
Polypharmacy, the co-administration of multiple drugs, has become an area of concern as the elderly population grows and an unexpected infection, such as COVID-19 pandemic, keeps emerging. However, it is very costly and time-consuming to experimentally examine the pharmacological effects of polypharmacy. To address this challenge, machine learning models that predict drug-drug interactions (DDIs) have actively been developed in recent years. In particular, the growing volume of drug datasets and the advances in machine learning have facilitated the model development. In this regard, this review discusses the DDI-predicting machine learning models that have been developed since 2018. Our discussion focuses on dataset sources used to develop the models, featurization approaches of molecular structures and biological information, and types of DDI prediction outcomes from the models. Finally, we make suggestions for research opportunities in this field.
Collapse
Affiliation(s)
- Eujin Hong
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141 Korea
| | - Junhyeok Jeon
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141 Korea
| | - Hyun Uk Kim
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141 Korea ,BioProcess Engineering Research Center and BioInformatics Research Center, KAIST, Daejeon, 34141 Korea
| |
Collapse
|
40
|
Pan D, Quan L, Jin Z, Chen T, Wang X, Xie J, Wu T, Lyu Q. Multisource Attention-Mechanism-Based Encoder-Decoder Model for Predicting Drug-Drug Interaction Events. J Chem Inf Model 2022; 62:6258-6270. [PMID: 36449561 DOI: 10.1021/acs.jcim.2c01112] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/05/2022]
Abstract
Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder-decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.
Collapse
Affiliation(s)
- Deng Pan
- School of Computer Science and Technology, Soochow University, Suzhou215006, China
| | - Lijun Quan
- School of Computer Science and Technology, Soochow University, Suzhou215006, China.,Province Key Lab for Information Processing Technologies, Soochow University, Suzhou215006, China.,Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing210000, China
| | - Zhi Jin
- School of Computer Science and Technology, Soochow University, Suzhou215006, China
| | - Taoning Chen
- School of Computer Science and Technology, Soochow University, Suzhou215006, China
| | - Xuejiao Wang
- School of Computer Science and Technology, Soochow University, Suzhou215006, China
| | - Jingxin Xie
- School of Computer Science and Technology, Soochow University, Suzhou215006, China
| | - Tingfang Wu
- School of Computer Science and Technology, Soochow University, Suzhou215006, China.,Province Key Lab for Information Processing Technologies, Soochow University, Suzhou215006, China.,Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing210000, China
| | - Qiang Lyu
- School of Computer Science and Technology, Soochow University, Suzhou215006, China.,Province Key Lab for Information Processing Technologies, Soochow University, Suzhou215006, China.,Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing210000, China
| |
Collapse
|
41
|
Galgano S, Conway L, Maggio FD, Farthing K, Dalby N, Fellows A, Houdijk JGM. Precursor-derived in-water peracetic acid impacts on broiler performance, gut microbiota, and antimicrobial resistance genes. Poult Sci 2022; 102:102368. [PMID: 36566657 PMCID: PMC9801209 DOI: 10.1016/j.psj.2022.102368] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2022] [Revised: 11/04/2022] [Accepted: 11/27/2022] [Indexed: 12/07/2022] Open
Abstract
Past antimicrobial misuse has led to the spread of antimicrobial resistance amongst pathogens, reportedly a major public health threat. Attempts to reduce the spread of antimicrobial resistant (AMR) bacteria are in place worldwide, among which finding alternatives to antimicrobials have a pivotal role. Such molecules could be used as "green alternatives" to reduce the bacterial load either by targeting specific bacterial groups or more generically, functioning as biocides when delivered in vivo. In this study, the effect of in-water peracetic acid as a broad-spectrum antibiotic alternative for broilers was assessed via hydrolysis of precursors sodium percarbonate and tetraacetylethylenediamine. Six equidistant peracetic acid levels were tested from 0 to 50 ppm using four pens per treatment and 4 birds per pen (i.e., 16 birds per treatment and 96 in total). Peracetic acid was administered daily from d 7 to 14 of age whilst measuring performance parameters and end-point bacterial concentration (qPCR) in crop, jejunum, and ceca, as well as crop 16S sequencing. PAA treatment, especially at 20, 30, and 40 ppm, increased body weight at d 14, and feed intake during PAA exposure compared to control (P < 0.05). PAA decreased bacterial concentration in the crop only (P < 0.05), which was correlated to better performance (P < 0.05). Although no differences in alpha- and beta-diversity were found, it was observed a reduction of Lactobacillus (P < 0.05) and Flectobacillus (P < 0.05) in most treatments compared to control, together with an increased abundance of predicted 4-aminobutanoate degradation (V) pathway. The analysis of the AMR genes did not point towards any systematic differences in gene abundance due to treatment administration. This, together with the rest of our observations could indicate that proximal gut microbiota modulation could result in performance amelioration. Thus, peracetic acid may be a valid antimicrobial alternative that could also positively affect performance.
Collapse
Affiliation(s)
- Salvatore Galgano
- Monogastric Science Research Centre, Scotland's Rural College, Edinburgh, Scotland, United Kingdom.
| | - Leah Conway
- Gama Healthcare Ltd and Aga Nanotech Ltd, Halifax, United Kingdom
| | | | - Kathryn Farthing
- Gama Healthcare Ltd and Aga Nanotech Ltd, Halifax, United Kingdom
| | - Nikki Dalby
- Centre for Innovation Excellence in Livestock, York, United Kingdom
| | - Adrian Fellows
- Gama Healthcare Ltd and Aga Nanotech Ltd, Halifax, United Kingdom
| | - Jos G M Houdijk
- Monogastric Science Research Centre, Scotland's Rural College, Edinburgh, Scotland, United Kingdom
| |
Collapse
|
42
|
Gider V, Budak C. Instruction of molecular structure similarity and scaffolds of drugs under investigation in ebola virus treatment by atom-pair and graph network: A combination of favipiravir and molnupiravir. Comput Biol Chem 2022; 101:107778. [DOI: 10.1016/j.compbiolchem.2022.107778] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Revised: 10/06/2022] [Accepted: 10/07/2022] [Indexed: 11/26/2022]
|
43
|
Xie J, Zhao C, Ouyang J, He H, Huang D, Liu M, Wang J, Zhang W. TP-DDI: A Two-Pathway Deep Neural Network for Drug-Drug Interaction Prediction. Interdiscip Sci 2022; 14:895-905. [PMID: 35622314 DOI: 10.1007/s12539-022-00524-0] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2022] [Revised: 04/01/2022] [Accepted: 04/18/2022] [Indexed: 06/15/2023]
Abstract
Adverse drug-drug interactions (DDIs) can severely damage the body. Thus, it is essential to accurately predict DDIs. DDIs are complex processes in which many factors can cause interactions. Rather than merely considering one or two of the factors, we design a two-pathway drug-drug interaction framework named TP-DDI that uses multimodal data for DDI prediction. TP-DDI effectively explores the combined effect of a topological structure-based pathway and a biomedical object similarity-based pathway to obtain multimodal drug representations. For the topology-based pathway, we focus on drug chemistry structures through the self-attention mechanism, which can capture hidden critical relationships, especially between pairs of atoms at remote topological distances. For the similarity-based pathway, our model can emphasize useful biomedical objects according to the channel weights. Finally, the fusion of multimodal data provides a holistic view of DDIs by learning the complementary features. On a real-world dataset, experiments show that TP-DDI can achieve better performance than the state-of-the-art models. Moreover, we can find the most critical substructures with certain interpretability in the newly predicted DDIs.
Collapse
Affiliation(s)
- Jiang Xie
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Chang Zhao
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Jiaming Ouyang
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Hongjian He
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Dingkai Huang
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Mengjiao Liu
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
| | - Jiao Wang
- School of Life Sciences, Shanghai University, Shanghai, 200444, China.
| | - Wenjun Zhang
- College of Information Technology, Shanghai Jianqiao University, Shanghai, 201306, China.
| |
Collapse
|
44
|
Chen S, Li T, Yang L, Zhai F, Jiang X, Xiang R, Ling G. Artificial intelligence-driven prediction of multiple drug interactions. Brief Bioinform 2022; 23:6720429. [PMID: 36168896 DOI: 10.1093/bib/bbac427] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2022] [Revised: 09/01/2022] [Accepted: 09/02/2022] [Indexed: 12/14/2022] Open
Abstract
When a drug is administered to exert its efficacy, it will encounter multiple barriers and go through multiple interactions. Predicting the drug-related multiple interactions is critical for drug development and safety monitoring because it provides foundations for practical, safe compatibility and rational use of multiple drugs. With the progress of artificial intelligence (AI) technology, a variety of novel prediction methods for single interaction have emerged and shown great advantages compared to the traditional, expensive and time-consuming laboratory research. To promote the comprehensive and simultaneous predictions of multiple interactions, we systematically reviewed the application of AI in drug-drug, drug-food (excipients) and drug-microbiome interactions. We began by outlining the model methods, evaluation indicators, algorithms and databases commonly used to build models for three types of drug interactions. The models based on the metabolic enzyme P450, drug similarity and drug targets have empathized among the machine learning models of drug-drug interactions. In particular, we discussed the limitations of current approaches and identified potential areas for future research. It is anticipated the in-depth review will be helpful for the development of the next-generation of systematic prediction models for simultaneous multiple interactions.
Collapse
Affiliation(s)
- Siqi Chen
- College of Medical Devices, Shenyang Pharmaceutical University, 103 Wenhua Road, Shenyang 110016, China
| | - Tiancheng Li
- College of Medical Devices, Shenyang Pharmaceutical University, 103 Wenhua Road, Shenyang 110016, China
| | - Luna Yang
- College of Medical Devices, Shenyang Pharmaceutical University, 103 Wenhua Road, Shenyang 110016, China
| | - Fei Zhai
- College of Medical Devices, Shenyang Pharmaceutical University, 103 Wenhua Road, Shenyang 110016, China
| | - Xiwei Jiang
- College of Medical Devices, Shenyang Pharmaceutical University, 103 Wenhua Road, Shenyang 110016, China
| | - Rongwu Xiang
- College of Medical Devices, Shenyang Pharmaceutical University, 103 Wenhua Road, Shenyang 110016, China.,Liaoning Medical Big Data and Artificial Intelligence Engineering Technology Research Center, Shenyang 110016, China
| | - Guixia Ling
- College of Medical Devices, Shenyang Pharmaceutical University, 103 Wenhua Road, Shenyang 110016, China
| |
Collapse
|
45
|
Hoa Vo T, Thi Kim Nguyen N, Quoc Khanh Le N. Improved prediction of drug-drug interactions using ensemble deep neural networks. MEDICINE IN DRUG DISCOVERY 2022. [DOI: 10.1016/j.medidd.2022.100149] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022] Open
|
46
|
Zhao C, Wang H, Qi W, Liu S. Toward drug-miRNA resistance association prediction by positional encoding graph neural network and multi-channel neural network. Methods 2022; 207:81-89. [PMID: 36167292 DOI: 10.1016/j.ymeth.2022.09.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2022] [Revised: 09/01/2022] [Accepted: 09/18/2022] [Indexed: 10/31/2022] Open
Abstract
Drug discovery is a costly and time-consuming process, and most drugs exert therapeutic efficacy by targeting specific proteins. However, there are a large number of proteins that are not targeted by any drug. Recently, miRNA-based therapeutics are becoming increasingly important, since miRNA can regulate the expressions of specific genes and affect a variety of human diseases. Therefore, it is of great significance to study the associations between miRNAs and drugs to enable drug discovery and disease treatment. In this work, we propose a novel method named DMR-PEG, which facilitates drug-miRNA resistance association (DMRA) prediction by leveraging positional encoding graph neural network with layer attention (LAPEG) and multi-channel neural network (MNN). LAPEG considers both the potential information in the miRNA-drug resistance heterogeneous network and the specific characteristics of entities (i.e., drugs and miRNAs) to learn favorable representations of drugs and miRNAs. And MNN models various sophisticated relations and synthesizes the predictions from different perspectives effectively. In the comprehensive experiments, DMR-PEG achieves the area under the precision-recall curve (AUPR) score of 0.2793 and the area under the receiver-operating characteristic curve (AUC) score of 0.9475, which outperforms the most state-of-the-art methods. Further experimental results show that our proposed method has good robustness and stability. The ablation study demonstrates each component in DMR-PEG is essential for drug-miRNA drug resistance association prediction. And real-world case study presents that DMR-PEG is promising for DMRA inference.
Collapse
Affiliation(s)
- Chengshuai Zhao
- College of Informatics, Huazhong Agricultural University, Wuhan 430070, China
| | - Haorui Wang
- School of Computer Science, Wuhan University, Wuhan 430072, China
| | - Weiwei Qi
- Hubei Bailianhe Pumped-storage Power Station, Wuhan 430074, China
| | - Shichao Liu
- College of Informatics, Huazhong Agricultural University, Wuhan 430070, China
| |
Collapse
|
47
|
Ren S, Yu L, Gao L. Multidrug representation learning based on pretraining model and molecular graph for drug interaction and combination prediction. Bioinformatics 2022; 38:4387-4394. [PMID: 35904544 DOI: 10.1093/bioinformatics/btac538] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Revised: 07/06/2022] [Accepted: 07/27/2022] [Indexed: 12/24/2022] Open
Abstract
MOTIVATION Approaches for the diagnosis and treatment of diseases often adopt the multidrug therapy method because it can increase the efficacy or reduce the toxic side effects of drugs. Using different drugs simultaneously may trigger unexpected pharmacological effects. Therefore, efficient identification of drug interactions is essential for the treatment of complex diseases. Currently proposed calculation methods are often limited by the collection of redundant drug features, a small amount of labeled data and low model generalization capabilities. Meanwhile, there is also a lack of unique methods for multidrug representation learning, which makes it more difficult to take full advantage of the originally scarce data. RESULTS Inspired by graph models and pretraining models, we integrated a large amount of unlabeled drug molecular graph information and target information, then designed a pretraining framework, MGP-DR (Molecular Graph Pretraining for Drug Representation), specifically for drug pair representation learning. The model uses self-supervised learning strategies to mine the contextual information within and between drug molecules to predict drug-drug interactions and drug combinations. The results achieved promising performance across multiple metrics compared with other state-of-the-art methods. Our MGP-DR model can be used to provide a reliable candidate set for the combined use of multiple drugs. AVAILABILITY AND IMPLEMENTATION Code of the model, datasets and results can be downloaded from GitHub (https://github.com/LiangYu-Xidian/MGP-DR). SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Shujie Ren
- School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China
| | - Liang Yu
- School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China
| | - Lin Gao
- School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China
| |
Collapse
|
48
|
Ren ZH, You ZH, Yu CQ, Li LP, Guan YJ, Guo LX, Pan J. A biomedical knowledge graph-based method for drug-drug interactions prediction through combining local and global features with deep neural networks. Brief Bioinform 2022; 23:6692550. [PMID: 36070624 DOI: 10.1093/bib/bbac363] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 07/23/2022] [Accepted: 08/02/2022] [Indexed: 11/12/2022] Open
Abstract
Drug-drug interactions (DDIs) prediction is a challenging task in drug development and clinical application. Due to the extremely large complete set of all possible DDIs, computer-aided DDIs prediction methods are getting lots of attention in the pharmaceutical industry and academia. However, most existing computational methods only use single perspective information and few of them conduct the task based on the biomedical knowledge graph (BKG), which can provide more detailed and comprehensive drug lateral side information flow. To this end, a deep learning framework, namely DeepLGF, is proposed to fully exploit BKG fusing local-global information to improve the performance of DDIs prediction. More specifically, DeepLGF first obtains chemical local information on drug sequence semantics through a natural language processing algorithm. Then a model of BFGNN based on graph neural network is proposed to extract biological local information on drug through learning embedding vector from different biological functional spaces. The global feature information is extracted from the BKG by our knowledge graph embedding method. In DeepLGF, for fusing local-global features well, we designed four aggregating methods to explore the most suitable ones. Finally, the advanced fusing feature vectors are fed into deep neural network to train and predict. To evaluate the prediction performance of DeepLGF, we tested our method in three prediction tasks and compared it with state-of-the-art models. In addition, case studies of three cancer-related and COVID-19-related drugs further demonstrated DeepLGF's superior ability for potential DDIs prediction. The webserver of the DeepLGF predictor is freely available at http://120.77.11.78/DeepLGF/.
Collapse
Affiliation(s)
- Zhong-Hao Ren
- School of Information Engineering, Xijing University, Xi'an 710100, China.,School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China
| | - Zhu-Hong You
- School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China
| | - Chang-Qing Yu
- School of Information Engineering, Xijing University, Xi'an 710100, China
| | - Li-Ping Li
- College of Grassland and Environment Sciences, Xinjiang Agricultural University, Urumqi 830052, China
| | - Yong-Jian Guan
- School of Information Engineering, Xijing University, Xi'an 710100, China
| | - Lu-Xiang Guo
- School of Information Engineering, Xijing University, Xi'an 710100, China
| | - Jie Pan
- School of Information Engineering, Xijing University, Xi'an 710100, China
| |
Collapse
|
49
|
Hu J, Gao J, Fang X, Liu Z, Wang F, Huang W, Wu H, Zhao G. DTSyn: a dual-transformer-based neural network to predict synergistic drug combinations. Brief Bioinform 2022; 23:6652782. [PMID: 35915050 DOI: 10.1093/bib/bbac302] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2022] [Revised: 06/23/2022] [Accepted: 07/04/2022] [Indexed: 11/14/2022] Open
Abstract
Drug combination therapies are superior to monotherapy for cancer treatment in many ways. Identifying novel drug combinations by screening is challenging for the wet-lab experiments due to the time-consuming process of the enormous search space of possible drug pairs. Thus, computational methods have been developed to predict drug pairs with potential synergistic functions. Notwithstanding the success of current models, understanding the mechanism of drug synergy from a chemical-gene-tissue interaction perspective lacks study, hindering current algorithms from drug mechanism study. Here, we proposed a deep neural network model termed DTSyn (Dual Transformer encoder model for drug pair Synergy prediction) based on a multi-head attention mechanism to identify novel drug combinations. We designed a fine-granularity transformer encoder to capture chemical substructure-gene and gene-gene associations and a coarse-granularity transformer encoder to extract chemical-chemical and chemical-cell line interactions. DTSyn achieved the highest receiver operating characteristic area under the curve of 0.73, 0.78. 0.82 and 0.81 on four different cross-validation tasks, outperforming all competing methods. Further, DTSyn achieved the best True Positive Rate (TPR) over five independent data sets. The ablation study showed that both transformer encoder blocks contributed to the performance of DTSyn. In addition, DTSyn can extract interactions among chemicals and cell lines, representing the potential mechanisms of drug action. By leveraging the attention mechanism and pretrained gene embeddings, DTSyn shows improved interpretability ability. Thus, we envision our model as a valuable tool to prioritize synergistic drug pairs with chemical and cell line gene expression profile.
Collapse
Affiliation(s)
- Jing Hu
- Baidu, Inc., 701, Na Xian Road, 201210, Shanghai, China
| | - Jie Gao
- Baidu, Inc., 701, Na Xian Road, 201210, Shanghai, China
| | - Xiaomin Fang
- Baidu, Inc., Xue Fu Road, 518000, Shenzhen, China
| | - Zijing Liu
- Baidu, Inc., Xue Fu Road, 518000, Shenzhen, China
| | - Fan Wang
- Baidu, Inc., Xue Fu Road, 518000, Shenzhen, China
| | - Weili Huang
- HWL Consulting LLC, 3328 Antigua Dr, 97408, Oregon, US
| | - Hua Wu
- Baidu, Inc., No. 10 Shangdi 10th Street, 100085, Beijing, China
| | - Guodong Zhao
- Baidu, Inc., 701, Na Xian Road, 201210, Shanghai, China
| |
Collapse
|
50
|
Jang HY, Song J, Kim JH, Lee H, Kim IW, Moon B, Oh JM. Machine learning-based quantitative prediction of drug exposure in drug-drug interactions using drug label information. NPJ Digit Med 2022; 5:88. [PMID: 35817846 PMCID: PMC9273620 DOI: 10.1038/s41746-022-00639-0] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2022] [Accepted: 06/16/2022] [Indexed: 11/27/2022] Open
Abstract
Many machine learning techniques provide a simple prediction for drug-drug interactions (DDIs). However, a systematically constructed database with pharmacokinetic (PK) DDI information does not exist, nor is there a machine learning model that numerically predicts PK fold change (FC) with it. Therefore, we propose a PK DDI prediction (PK-DDIP) model for quantitative DDI prediction with high accuracy, while constructing a highly reliable PK-DDI database. Reliable information of 3,627 PK DDIs was constructed from 3,587 drugs using 38,711 Food and Drug Administration (FDA) drug labels. This PK-DDIP model predicted the FC of the area under the time-concentration curve (AUC) within ± 0.5959. The prediction proportions within 0.8–1.25-fold, 0.67–1.5-fold, and 0.5–2-fold of the AUC were 75.77, 86.68, and 94.76%, respectively. Two external validations confirmed good prediction performance for newly updated FDA labels and FC from patients’. This model enables potential DDI evaluation before clinical trials, which will save time and cost.
Collapse
Affiliation(s)
- Ha Young Jang
- College of Pharmacy and Research Institute of Pharmaceutical Sciences, Seoul National University, Seoul, Republic of Korea
| | - Jihyeon Song
- Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea
| | - Jae Hyun Kim
- School of Pharmacy, Jeonbuk National University, Jeonju, Republic of Korea
| | - Howard Lee
- Department of Clinical Pharmacology and Therapeutics, Seoul National University College of Medicine and Hospital, Seoul, Korea
| | - In-Wha Kim
- College of Pharmacy and Research Institute of Pharmaceutical Sciences, Seoul National University, Seoul, Republic of Korea
| | - Bongki Moon
- Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea.
| | - Jung Mi Oh
- College of Pharmacy and Research Institute of Pharmaceutical Sciences, Seoul National University, Seoul, Republic of Korea.
| |
Collapse
|