Filters








23,972 Hits in 8.1 sec

Feature generation and representations for protein–protein interaction classification

Man Lan, Chew Lim Tan, Jian Su
2009 Journal of Biomedical Informatics  
In this paper, we generated and investigated multiple types of feature representations in order to further improve the performance of PPI text classification task.  ...  The integration of these multiple features has been evaluated on the BioCreAtIvE II corpus.  ...  Acknowledgment The work was supported by a Shanghai Pujiang Talent Program 09PJ1404500.  ... 
doi:10.1016/j.jbi.2009.07.004 pmid:19616641 fatcat:aqesxmshoved5jlfp57aoexdiy

Relation Extraction from Biomedical and Clinical Text: Unified Multitask Learning Framework [article]

Shweta Yadav, Srivatsa Ramesh, Sriparna Saha, Asif Ekbal
2020 arXiv   pre-print
The fundamental notion of MTL is to simultaneously learn multiple problems together by utilizing the concepts of the shared representation.  ...  In this paper, we study the relation extraction task from three major biomedical and clinical tasks, namely drug-drug interaction, protein-protein interaction, and medical concept relation extraction.  ...  Multi-task learning exploits the correlation present among similar tasks to improve classification by learning the common features of multiple tasks simultaneously.  ... 
arXiv:2009.09509v1 fatcat:fd3zpfjrybhrdpqkwgvpzrmisi

Deep learning for regulatory genomics

Yongjin Park, Manolis Kellis
2015 Nature Biotechnology  
The method predicts binding affinity of a protein to a DNA or RNA sequence in two steps, consisting of applying a convolution module for representation learning and a prediction module for feature combinations  ...  The approach can increase predictive power for specific tasks, integrate diverse datasets across data types, and provide greater generalization given the focus on representation learning and not simply  ...  COMPETING FINANCIAL INTERESTS The authors declare no competing financial interests.  ... 
doi:10.1038/nbt.3313 pmid:26252139 fatcat:vwgdbrifo5cblojivcpi2za4uq

Biomedical Relation Classification by single and multiple source domain adaptation

Sinchani Chakraborty, Sudeshna Sarkar, Pawan Goyal, Mahanandeeshwar Gattu
2019 Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)  
However, relation classification is very domain-specific and it takes a lot of effort to label data for a new domain. In this paper, we explore domain adaptation techniques for this task.  ...  Our experiments with the model have shown to improve state-of-the-art F1 score on 3 benchmark biomedical corpora for single domain and on 2 out of 3 for multi-domain scenarios.  ...  Acknowledgments This work has been supported by the project Effective Drug Repurposing through literature and patent mining, data integration and development of systems pharmacology platform sponsored  ... 
doi:10.18653/v1/d19-6210 dblp:conf/acl-louhi/ChakrabortySGG19 fatcat:77iupedcdjd4hl6rytmztpq5be

A Shortest Dependency Path Based Convolutional Neural Network for Protein-Protein Relation Extraction

Lei Hua, Chanqin Quan
2016 BioMed Research International  
The state-of-the-art methods for protein-protein interaction (PPI) extraction are primarily based on kernel methods, and their performances strongly depend on the handcraft features.  ...  In particular, by tracking the sdpCNN model, we find that sdpCNN could extract key features automatically and it is verified that pretrained word embedding is crucial in PPI task.  ...  Acknowledgments This research has been partially supported by the National Natural Science Foundation of China under Grant no. 61472117 and the Scientific Research Foundation for the Returned Overseas  ... 
doi:10.1155/2016/8479587 pmid:27493967 pmcid:PMC4963603 fatcat:uvmren3wmfbgpg5atryr3vvh34

Recent Advances in Network-based Methods for Disease Gene Prediction [article]

Sezin Kircali Ata, Min Wu, Yuan Fang, Le Ou-Yang, Chee Keong Kwoh, Xiao-Li Li
2020 arXiv   pre-print
To summarize, we first elucidate the task definition for disease gene prediction.  ...  Disease-gene association through Genome-wide association study (GWAS) is an arduous task for researchers.  ...  Node Classification Figure 2(a) shows the node classification tasks, which is to predict the label of the genes of which disease associations are unknown, given known labels on some genes/nodes.  ... 
arXiv:2007.10848v1 fatcat:zhrspbsj6zfpfhwa42mzjp4lvy

Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysis [article]

Tianle Ma, Aidong Zhang
2018 arXiv   pre-print
Multi-omic data provides multiple views of the same patients. Integrative analysis of multi-omic data is crucial to elucidate the molecular underpinning of disease etiology.  ...  Our framework employs deep representation learning to learn feature embeddings and patient embeddings simultaneously, enabling us to integrate feature interaction network and patient view similarity network  ...  This represents the learned patient representations combining multiple views. C is the weights for the last fully connected layer typically used in neural network models for classification tasks.  ... 
arXiv:1809.01772v1 fatcat:2ca7u6dt2vet5kdfxri53hreui

TripletProt: Deep Representation Learning of Proteins based on Siamese Networks

Esmaeil Nourani, Ehsaneddin Asgari, Alice Mc Hardy, Mohammad Mofrad
2021 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
The most important distinction of our proposed method is relying on the protein-protein interaction (PPI) network.  ...  TripletProt and in general Siamese Network offer great potentials for the protein informatics tasks and can be widely applied to similar tasks.  ...  Acknowledgements Funding Conflict of Interest: none declared.  ... 
doi:10.1109/tcbb.2021.3108718 pmid:34460382 fatcat:cln6jxuqdvhdxntjks7llhlve4

Deep Learning-Powered Prediction of Human-Virus Protein-Protein Interactions

Xiaodi Yang, Shiping Yang, Panyu Ren, Stefan Wuchty, Ziding Zhang
2022 Frontiers in Microbiology  
Identifying human-virus protein-protein interactions (PPIs) is an essential step for understanding viral infection mechanisms and antiviral response of the human host.  ...  Emerging as a very promising method to predict human-virus PPIs, deep learning shows the powerful ability to integrate large-scale datasets, learn complex sequence-structure relationships of proteins and  ...  AUTHOR CONTRIBUTIONS XY wrote the draft of the manuscript. ZZ supervised the work and significantly revised the manuscript. SW, SY, and PR revised the final version of manuscript.  ... 
doi:10.3389/fmicb.2022.842976 pmid:35495666 pmcid:PMC9051481 fatcat:hsbujsdghbeo7fjvn5pta2hjdq

DeepciRGO: functional prediction of circular RNAs through hierarchical deep neural networks using heterogeneous network features

Lei Deng, Wei Lin, Jiacheng Wang, Jingpu Zhang
2020 BMC Bioinformatics  
The topology features of proteins and circRNAs are calculated using a novel representation learning approach HIN2Vec across the heterogeneous network.  ...  In addition, we demonstrate the considerable potential of integrating multiple interactions and association networks. Conclusions DeepciRGO will be a useful tool for accurately annotating circRNAs.  ...  The impact of integrating multi-source data In our method, the integration of protein interactions contributes to the functional annotations of circRNAs.  ... 
doi:10.1186/s12859-020-03748-3 pmid:33183227 fatcat:aqocgmhqejfzro4zlwykrdnkeq

Biological network analysis with deep learning

Giulia Muzio, Leslie O'Bray, Karsten Borgwardt
2020 Briefings in Bioinformatics  
Given the importance of interactions in biological processes, such as the interactions between proteins or the bonds within a chemical compound, this data is often represented in the form of a biological  ...  The rise of this data has created a need for new computational tools to analyze networks.  ...  Funding This work was supported in part from the Alfried Krupp Prize for Young University Teachers of the Alfried Krupp von Bohlen und Halbach-Stiftung (K.B.) and in part from the European Union's Horizon  ... 
doi:10.1093/bib/bbaa257 pmid:33169146 pmcid:PMC7986589 fatcat:x7salmmidjei3og6ripsizkbam

Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discovery [article]

Xiaoqi Wang, Yingjie Cheng, Yaning Yang, Fei Li, Shaoliang Peng
2022 arXiv   pre-print
Therefore, we propose multi-task joint strategies of self-supervised representation learning on biomedical networks for drug discovery, named MSSL2drug.  ...  The results suggest two important findings. (1) The combinations of multimodal tasks achieve the best performance compared to other multi-task joint strategies. (2) The joint training of local and global  ...  various combinations of multiple self-supervised tasks for drug discovery.  ... 
arXiv:2201.04437v1 fatcat:dklnrwpvlzhn7jhuxxg3dj7suy

Self-Attention-Based Models for the Extraction of Molecular Interactions from Biological Texts

Prashant Srivastava, Saptarshi Bej, Kristina Yordanova, Olaf Wolkenhauer
2021 Biomolecules  
Moreover, we also discuss some limitations in the field of BLM that identifies opportunities for the extraction of molecular interactions from biological text.  ...  For many cellular processes, the amount molecules and their interactions that need to be considered can be very large.  ...  concatenated to obtain the final feature representation.  ... 
doi:10.3390/biom11111591 pmid:34827589 pmcid:PMC8615611 fatcat:et3dsx76djapzktm64p26nqcxm

Predicting metabolic pathway membership with deep neural networks by integrating sequential and ontology information

Imam Cartealy, Li Liao
2021 BMC Genomics  
Background Inference of protein's membership in metabolic pathways has become an important task in functional annotation of protein.  ...  Specifically, we developed a neural network model with an architecture tailored to facilitate the integration of features from different sources.  ...  Acknowledgements The authors would also like to thank the anonymous reviewers for their invaluable comments.  ... 
doi:10.1186/s12864-021-07629-8 pmid:34579673 pmcid:PMC8474704 fatcat:memcvmt72vbrxg4pqf2qgpirgi

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
Next, we discuss recently developed sequence-based and graph-based representation approaches as well as state-of-the-art deep learning-based methods.  ...  Finally, we present applications of drug repurposing to fight the COVID-19 pandemic, and outline its future challenges.  ...  [73] proposed a novel featurization approach for proteins, which integrated multiple types of protein characteristics, such as sequence, structure, evolution, and physico-chemical properties, into a  ... 
arXiv:2202.05145v1 fatcat:5oqujy2daffdpa33b4cbrg6hqy
« Previous Showing results 1 — 15 out of 23,972 results