Filters








18 Hits in 2.4 sec

NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions [article]

Fangping Wan, Lixiang Hong, An Xiao, Tao Jiang, Jianyang Zeng
2018 bioRxiv   pre-print
of many network-related prediction tasks, we develop a new nonlinear end-to-end learning model, called NeoDTI, that integrates diverse information from heterogeneous network data and automatically learns  ...  In addition, NeoDTI is robust against a wide range of choices of hyperparameters and is ready to integrate more drug and target related information (e.g., compound protein binding affinity data).  ...  We acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research.  ... 
doi:10.1101/261396 fatcat:ziaiqumn2nhylgyvdq3ivs5vhe

NeoDTI: neural integration of neighbor information from a heterogeneous network for discovering new drug–target interactions

Fangping Wan, Lixiang Hong, An Xiao, Tao Jiang, Jianyang Zeng, Jonathan Wren
2018 Bioinformatics  
many network-related prediction tasks, we develop a new nonlinear endto-end learning model, called NeoDTI, that integrates diverse information from heterogeneous network data and automatically learns  ...  In addition, NeoDTI is robust against a wide range of choices of hyperparameters and is ready to integrate more drug and target related information (e.g., compound-protein binding affinity data).  ...  We acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research.  ... 
doi:10.1093/bioinformatics/bty543 fatcat:4pmchscvrzhjjj5iid3mbz7bkq

HGDTI: predicting drug–target interaction by using information aggregation based on heterogeneous graph neural network

Liyi Yu, Wangren Qiu, Weizhong Lin, Xiang Cheng, Xuan Xiao, Jiexia Dai
2022 BMC Bioinformatics  
Conclusions The HGDTI based on heterogeneous graph neural network model, can utilize heterogeneous information to capture the embedding of drugs and targets, and provide assistance for drug development  ...  These results indicate that HGDTI can utilize heterogeneous information to capture the embedding of drugs and targets, and provide assistance for drug development.  ...  This inspired us to build our own model for discovering new DTIs. In this paper, we present HGDTI model, a heterogeneous graph neural network for predicting DTI.  ... 
doi:10.1186/s12859-022-04655-5 pmid:35413800 pmcid:PMC9004085 fatcat:2dyl3dw2irf6ng4zmqkmoojjgu

GADTI: Graph Autoencoder Approach for DTI Prediction From Heterogeneous Network

Zhixian Liu, Qingfeng Chen, Wei Lan, Haiming Pan, Xinkun Hao, Shirui Pan
2021 Frontiers in Genetics  
In this article, a graph autoencoder approach for DTI prediction (GADTI) was proposed to discover potential interactions between drugs and targets using a heterogeneous network, which integrates diverse  ...  Identifying drugtarget interaction (DTI) is the basis for drug development. However, the method of using biochemical experiments to discover drug-target interactions has low coverage and high costs.  ...  GADTI first constructs a heterogeneous network that integrates eight data sources related to drugs and targets. Then, it runs a graph autoencoder model on the network to discover new DTIs.  ... 
doi:10.3389/fgene.2021.650821 pmid:33912218 pmcid:PMC8072283 fatcat:lohwdhopivdonnransj5ktbgqe

MGATRx: Discovering Drug Repositioning Candidates Using Multi-view Graph Attention [article]

Jaswanth Kumar Yella, Anil G Jegga
2020 bioRxiv   pre-print
By integrating drug-centric and disease-centric annotations as multi-views, we propose a multi-view graph attention network for indication discovery (MGATRx).  ...  In-silico drug repositioning or predicting new indications for approved or late-stage clinical trial drugs is a resourceful and time-eficient strategy in drug discovery.  ...  [3] created hetionet a heterogeneous network integrating data from 29 public resources to identify drug repositioning candidates and predict the probability of treatment for drug-disease pairs [4]  ... 
doi:10.1101/2020.06.29.171876 fatcat:iqatueqpwvacjdmzn2l7ygjjo4

An improved graph representation learning method for drug-target interaction prediction over heterogeneous biological information graph [article]

Bo-Wei Zhao, Xiaorui Su, Zhu-Hong You, Peng-Wei Hu, Lun Hu
2022 bioRxiv   pre-print
Computational-based strategies for predicting drug-target interactions (DTIs) are regarded as a high-efficiency way.  ...  The prediction task of the relationships between drugs and targets plays a significant role in the process of new drug discovery.  ...  Wan et. al [12] developed a nonlinear end-to-end learning model, namely NeoDTI, by integrating multiple information from heterogeneous network data to learn the network representations of drugs and targets  ... 
doi:10.1101/2022.06.30.498357 fatcat:m4wqkfkdfbbedebjitarxdrw7i

Machine Learning for Drug-Target Interaction Prediction

Ruolan Chen, Xiangrong Liu, Shuting Jin, Jiawei Lin, Juan Liu
2018 Molecules  
Identifying drug-target interactions will greatly narrow down the scope of search of candidate medications, and thus can serve as the vital first step in drug discovery.  ...  Considering that in vitro experiments are extremely costly and time-consuming, high efficiency computational prediction methods could serve as promising strategies for drug-target interaction (DTI) prediction  ...  Acknowledgments: We would like to thank all authors of the cited references. Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/molecules23092208 pmid:30200333 pmcid:PMC6225477 fatcat:gcijck47irhqvlttntb43r63fu

Deep learning integration of molecular and interactome data for protein-compound interaction prediction [article]

Narumi Watanabe, Yuuto Ohnuki, Yasubumi Sakakibara
2021 bioRxiv   pre-print
However, few attempts have been made to combine both types of data in molecular information and interaction networks.  ...  Results: We developed a deep learning-based method that integrates protein features, compound features, and heterogeneous interactome data to predict protein-compound interactions.  ...  Nat Commun 595 Hong L, Xiao A, Jiang T, Zeng J (2019) NeoDTI: neural integration of 597 neighbor information from a heterogeneous network for discovering new drug-target 598 interactions.  ... 
doi:10.1101/2021.01.31.429000 fatcat:wzx6ukgt6naupabjosx32hemca

Deep learning for drug repurposing: methods, databases, and applications [article]

Xiaoqin Pan, Xuan Lin, Dongsheng Cao, Xiangxiang Zeng, Philip S. Yu, Lifang He, Ruth Nussinov, Feixiong Cheng
2022 arXiv   pre-print
Repurposing existing drugs for new therapies is an attractive solution that accelerates drug development at reduced experimental costs, specifically for Coronavirus Disease 2019 (COVID-19), an infectious  ...  However, comprehensively obtaining and productively integrating available knowledge and big biomedical data to effectively advance deep learning models is still challenging for drug repurposing in other  ...  [100] NeoDTI integrated neighborhood information of nodes in the heterogeneous network and automatically learned topology-preserving representations of drugs and targets.  ... 
arXiv:2202.05145v1 fatcat:5oqujy2daffdpa33b4cbrg6hqy

Multiple Similarity Drug-Target Interaction Prediction with Random Walks and Matrix Factorization [article]

Bin Liu, Dimitrios Papadopoulos, Fragkiskos D. Malliaros, Grigorios Tsoumakas, Apostolos N. Papadopoulos
2022 arXiv   pre-print
The discovery of drug-target interactions (DTIs) is a very promising area of research with great potential.  ...  In particular, we take a multi-layered network perspective, where different layers correspond to different similarity metrics between drugs and targets.  ...  In Luo dataset, the neighbor drugs are more likely to share the same interactions, leading to the effectiveness of neighborhood-based interaction estimation for new drugs.  ... 
arXiv:2201.09508v1 fatcat:nvbbtymxbba6bigjicz47au6um

Drug-Disease Association Prediction Based on Neighborhood Information Aggregation in Neural Networks

Yingdong Wang, Gaoshan Deng, Nianyin Zeng, Xiao Song, Yuanying Zhuang
2019 IEEE Access  
Computational drug repositioning plays a vital role in the prediction of drug function. Many new functions discovered have been confirmed.  ...  It is based on neighborhood information aggregation in neural networks which combines the similarity of diseases and drugs, the associations between the drugs and diseases.  ...  NeoDTI [23] predicts new drugs and drug targets by integrating various information in heterogeneous networks and conducting end-to-end learning through a nonlinear model.  ... 
doi:10.1109/access.2019.2907522 fatcat:3i5mo3gjkrbzvflcedsqkov7le

Network approaches for modeling the effect of drugs and diseases

T J Rintala, Arindam Ghosh, V Fortino
2022 Briefings in Bioinformatics  
These methods can support fundamental stages of the drug development process, including the identification of putative drug targets, the in silico screening of drug compounds and drug combinations for  ...  The network approach is quickly becoming a fundamental building block of computational methods aiming at elucidating the mechanism of action (MoA) and therapeutic effect of drugs.  ...  Graph neural network-based methods NeoDTI Deep learning, graph Drug-target DTIs, drug-drug • Predicts drug-target interactions by Computational cost of convolutional network interactions, using several  ... 
doi:10.1093/bib/bbac229 pmid:35704883 pmcid:PMC9294412 fatcat:wbmt5bm7mbeazjc56s6fvvap3q

Optimizing Area Under the Curve Measures via Matrix Factorization for Predicting Drug-Target Interaction with Multiple Similarities [article]

Bin Liu, Grigorios Tsoumakas
2022 arXiv   pre-print
Both three proposed approaches incorporate a novel local interaction consistency aware similarity interaction method to generate fused drug and target similarities that preserve vital information from  ...  In drug discovery, identifying drug-target interactions (DTIs) via experimental approaches is a tedious and expensive procedure.  ...  ACKNOWLEDGMENTS Bin Liu was supported from the China Scholarship Council (CSC) under the Grant CSC No.201708500095.  ... 
arXiv:2105.01545v2 fatcat:ja2fcyiyajc2bgj46bridbhuw4

Target Identification among Known Drugs by Deep Learning from Heterogeneous Networks

Xiangxiang Zeng, Siyi Zhu, Weiqiang Lu, Zehui Liu, Jin Huang, Yadi Zhou, Jiangsong Fang, Yin Huang, Huimin Guo, Lang Li, Bruce Trapp, Ruth Nussinov (+3 others)
2020 Chemical Science  
Without foreknowledge of the complete drug target information, development of promising and affordable approaches for effective treatment of human diseases is challenging.  ...  Here, we develop deepDTnet, a deep learning methodology...  ...  Subsequently, the same group further proposed, NeoDTI, 19 a neural network-based approach, for DTI prediction with an improved performance.  ... 
doi:10.1039/c9sc04336e pmid:34123272 pmcid:PMC8150105 fatcat:kn7s6effine65bxx6oxq4rucxy

Graph Representation Learning in Biomedicine [article]

Michelle M. Li, Kexin Huang, Marinka Zitnik
2022 arXiv   pre-print
Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge.  ...  We synthesize a spectrum of algorithmic approaches that, at their core, leverage graph topology to embed networks into compact vector spaces.  ...  M.M.L. is supported by T HG from the National Human Genome Research Institute and a National Science Foundation Graduate Research Fellowship.  ... 
arXiv:2104.04883v3 fatcat:lrhxlztborbylazvdfmaxk5zem
« Previous Showing results 1 — 15 out of 18 results