13,074 Hits in 5.2 sec

Graph of Words Embedding for Molecular Structure-Activity Relationship Analysis [chapter]

Jaume Gibert, Ernest Valveny, Horst Bunke
2010 Lecture Notes in Computer Science  
Structure-Activity relationship analysis aims at discovering chemical activity of molecular compounds based on their structure.  ...  In this article we make use of a particular graph representation of molecules and propose a new graph embedding procedure to solve the problem of structure-activity relationship analysis.  ...  Conclusions In this paper, we have introduced a new embedding procedure of graph molecular compounds for the problem of structure-activity relationship analysis.  ... 
doi:10.1007/978-3-642-16687-7_9 fatcat:mwsh5zy6snc6xa6rjpcjqmdu7q

Inductive transfer learning for molecular activity prediction: Next-Gen QSAR Models with MolPMoFiT

Xinhao Li, Denis Fourches
2020 Journal of Cheminformatics  
Deep neural networks can directly learn from chemical structures without extensive, user-driven selection of descriptors in order to predict molecular properties/activities with high reliability.  ...  Thus, it would be highly relevant to better utilize the tremendous compendium of unlabeled compounds from publicly-available datasets for improving the model performances for the user's particular series  ...  Quantitative structure property/activity relationship (QSPR/QSAR) modeling [1] [2] [3] [4] [5] [6] relies on machine learning techniques to establish quantified links between molecular structures and  ... 
doi:10.1186/s13321-020-00430-x pmid:33430978 fatcat:gbvn7mtgjvaqbgovyhayib6zp4

Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network [article]

Seongok Ryu, Jaechang Lim, Seung Hwan Hong, Woo Youn Kim
2018 arXiv   pre-print
Molecular structure-property relationships are key to molecular engineering for materials and drug discovery.  ...  Here we show that the performance of graph convolutional networks (GCNs) for the prediction of molecular properties can be improved by incorporating attention and gate mechanisms.  ...  Theoretical backgrounds Graph representation of molecules Graph convolution for updating atom states Various node embedding methods exist for updating node states in a graph structure.  ... 
arXiv:1805.10988v3 fatcat:pg52xhs3sbftxa7dnfbowipjay

Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules [article]

Benjamin Sanchez-Lengeling, Jennifer N. Wei, Brian K. Lee, Richard C. Gerkin, Alán Aspuru-Guzik, Alexander B. Wiltschko
2019 arXiv   pre-print
Additional analysis shows that the learned embeddings from graph neural networks capture a meaningful odor space representation of the underlying relationship between structure and odor, as demonstrated  ...  Based on these early results with graph neural networks for molecular properties, we hope machine learning can eventually do for olfaction what it has already done for vision and hearing.  ...  to Quantitative Structure-Activity Relationships, a term from medicinal chemistry).  ... 
arXiv:1910.10685v2 fatcat:2smeyl4bargkvfjx5jelubgwbi

Diffusion Maps for Textual Network Embedding [article]

Xinyuan Zhang, Yitong Li, Dinghan Shen, Lawrence Carin
2019 arXiv   pre-print
We present diffusion maps for textual network embedding (DMTE), integrating global structural information of the graph to capture the semantic relatedness between texts, with a diffusion-convolution operation  ...  Rather than using typical natural language processing (NLP) approaches, recent research exploits the relationship of texts on the same edge to graphically embed text.  ...  Acknowledgments The authors would like to thank the anonymous reviewers for their insightful comments. This research was supported in part by DARPA, DOE, NIH, ONR and NSF.  ... 
arXiv:1805.09906v2 fatcat:vtoz4ccnanginmgoqspr72ir7q

EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction

Yuan Jin, Jiarui Lu, Runhan Shi, Yang Yang
2021 Biomolecules  
the embedding vectors for the graphs.  ...  For drugs, we build two levels of graphs to represent compound structural information, namely the atom graph and substructure graph, and adopt graph convolutional network with an attention module to learn  ...  Acknowledgments: The authors thank the editor and anonymous reviewers for their valuable suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/biom11121783 pmid:34944427 pmcid:PMC8698792 fatcat:22xg5q4fl5eq3lebgqvsgk5n54

A visual approach for analysis and inference of molecular activity spaces

Samina Kausar, Andre O. Falcao
2019 Journal of Cheminformatics  
Molecular space visualization can help to explore the diversity of large heterogeneous chemical data, which ultimately may increase the understanding of structure-activity relationships (SAR) in drug discovery  ...  The proposed approach uses molecular similarity as the sole input for computing a probabilistic surface of molecular activity (PSMA).  ...  (LaSIGE) for providing the infrastructure.  ... 
doi:10.1186/s13321-019-0386-z pmid:33430986 fatcat:mht4zbb2m5hgjafexubqqhe2om

Graph Memory Networks for Molecular Activity Prediction [article]

Trang Pham, Truyen Tran, Svetha Venkatesh
2018 arXiv   pre-print
Molecular activity prediction is critical in drug design. Machine learning techniques such as kernel methods and random forests have been successful for this task.  ...  Applied to the molecules, the dynamic interactions enable an iterative refinement of the representation of molecular graphs with multiple bond types.  ...  Much research has focused on the analysis of quantitative structure-activity relationships (QSAR), which results in a myriad of molecular descriptors [1] .  ... 
arXiv:1801.02622v2 fatcat:mbu5afig6zbgzlbgibd43pttj4

Artificial Intelligence in Biological Activity Prediction [chapter]

João Correia, Tiago Resende, Delora Baptista, Miguel Rocha
2019 Advances in Intelligent Systems and Computing  
Here, we present a review of some of the main machine learning studies in biological activity prediction of compounds, in particular for sweetness prediction.  ...  Numerous machine learning algorithms for activity prediction recently emerged, becoming an indispensable approach to mine chemical information from large compound datasets.  ...  This study was supported by the European Commission through project SHIKIFACTORY100 -Modular cell factories for the production of 100 compounds from the shikimate pathway (Reference 814408), and by the  ... 
doi:10.1007/978-3-030-23873-5_20 fatcat:hrdvbvpiyzahjjnrwvedpaxfde

Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction [article]

Sriram Pingali, Shweta Yadav, Pratik Dutta, Sriparna Saha
2021 arXiv   pre-print
and molecular structure information and exploit the underlying features of various modalities to enable end-to-end learning.  ...  structure.  ...  For all the nodes v j in subgraph g i , the Graph-BERT computes raw feature vector embedding e x j , role embedding e r j , position embedding e p j and distance embedding e d j .  ... 
arXiv:2107.00596v1 fatcat:6u6j4nolbrfb5md6odxi7t7rje

Artificial Intelligence-Based Drug Design and Discovery [chapter]

Yu-Chen Lo, Gui Ren, Hiroshi Honda, Kara L. Davis
2019 Cheminformatics and its Applications [Working Title]  
Relationship) analysis, drug repurposing and chemical space visualization.  ...  The emphasis will be on machine learning and deep learning, which demonstrated extensive utility in many branches of computer-aided drug discovery including de novo drug design, QSAR (Quantitative Structure-Activity  ...  The molecular graph is useful for distinguishing different structural isomers but does not contain 3D conformation of the molecules.  ... 
doi:10.5772/intechopen.89012 fatcat:327njwv46rc2hi32nwx3nbkqkq

Knowledge Representation in Graphs using Convolutional Neural Networks [article]

Armando Vieira
2016 arXiv   pre-print
Knowledge Graphs (KG) constitute a flexible representation of complex relationships between entities particularly useful for biomedical data.  ...  Here we apply a compositional model to embed nodes and relationships into a vectorised semantic space to perform graph completion.  ...  The compositional model for graph embeddings Much work for knowledge graph completion was based on symbolic methods.  ... 
arXiv:1612.02255v1 fatcat:t7gbu64vizau7g4l6btdaps5iu

A Network Medicine Approach to Drug Repurposing for Chronic Pancreatitis [article]

Mission:Cure, Megan Golden
2020 bioRxiv   pre-print
Using a literature-derived knowledge graph, we train multiple machine learning models using embeddings based on i) the network topology of regulation bipartite networks, ii) protein primary structures  ...  Despite decades of clinical investigations, there is currently no effective treatment for patients diagnosed with Chronic Pancreatitis (CP).  ...  Similar NLP methods have been applied to amino acid sequences of proteins [4] , and molecular substructures of compounds [5] to generate embeddings representing primary structure and molecular substructure  ... 
doi:10.1101/2020.10.30.360263 fatcat:p5rjjyowujh3bjt2k6x6a54agi

Graph Self-supervised Learning with Accurate Discrepancy Learning [article]

Dongki Kim, Jinheon Baek, Sung Ju Hwang
2022 arXiv   pre-print
Self-supervised learning of graph neural networks (GNNs) aims to learn an accurate representation of the graphs in an unsupervised manner, to obtain transferable representations of them for diverse downstream  ...  Moreover, we further aim to accurately capture the amount of discrepancy for each perturbed graph using the graph edit distance.  ...  For example, two molecules in Figure 1 show that, although they have a highly correlated structure, one molecular graph could be actively bound to a set of inhibitors of human β-secretase 1 (Wu et al  ... 
arXiv:2202.02989v2 fatcat:7x2xshtofvbjlobnqzngkxkosm

Literature mining for context-specific molecular relations using multimodal representations (COMMODAR)

Jaehyun Lee, Doheon Lee, Kwang Hyung Lee
2020 BMC Bioinformatics  
The main idea of COMMODAR is the feature augmentation by the cooperation of multimodal representations for relation extraction.  ...  In this paper, we propose COMMODAR, a machine learning-based literature mining framework for context-specific molecular relations using multimodal representations.  ...  About this supplement This article has been published as part of BMC Bioinformatics, Volume 21 Supplement 5, 2020: Proceedings of the 13th International Workshop on Data and Text Mining in Biomedical Informatics  ... 
doi:10.1186/s12859-020-3396-y pmid:33106154 fatcat:s3oha7endfcqhnxifzdckxxi5a
« Previous Showing results 1 — 15 out of 13,074 results