Filters








574 Hits in 3.3 sec

Understanding microbiome dynamics via interpretable graph representation learning [article]

Kateryna Melnyk, Kuba Weimann, Tim O.F. Conrad
2022 arXiv   pre-print
Motivated by the need to analyse such complex interactions, we develop a method that learns a low-dimensional representation of the time-evolving graph and maintains the dynamics occurring in the high-dimensional  ...  Through our experiments, we show that we can extract graph features such as clusters of nodes or edges that have the highest impact on the model to learn the low-dimensional representation.  ...  Most studies are focused on node representation learning, and only a few learn the representation of the whole graph (graph2vec [26] ). Dynamic graph representation.  ... 
arXiv:2203.01830v1 fatcat:oh2do5ra7zakzczybz4ygjhzee

Application of Deep Learning in Microbiome

Qiang Zhu, Ban Huo, Han Sun, Bojing Li, Xingpeng Jiang
2020 Journal of Artificial Intelligence for Medical Sciences  
However, due to the high dimensionality, sparseness, and complexity of the data, traditional machine learning methods have insufficient learning and representational ability.  ...  the accuracy and interpretability of the model.  ...  MACHINE LEARNING IN MICROBIOME It is possible to understand better the hierarchical structure and composition of the microbial community via classifying microbial samples.  ... 
doi:10.2991/jaims.d.201028.001 fatcat:hnopfambffdlrcgbi4x4ud6phi

GraphKKE: Graph Kernel Koopman Embedding for Human Microbiome Analysis [article]

Kateryna Melnyk, Stefan Klus, Grégoire Montavon, Tim Conrad
2020 arXiv   pre-print
The key to solving this problem is the representation of the time-evolving graphs as fixed-length feature vectors preserving the original dynamics.  ...  In order to understand responses of the microbial community members to a distinct range of perturbations such as antibiotics exposure or diseases and general dynamical properties, the time-evolving graph  ...  Time-dependent embedding via the kernel-based transfer operator approach (a) Learning transfer operators using graph kernels, where k(·, ·) is a graph kernel and K k is the Koopman operator.  ... 
arXiv:2008.05903v3 fatcat:4pmfcnahgjhobbw4mfgzwoem2i

Graph Embedding Deep Learning Guides Microbial Biomarkers' Identification

Qiang Zhu, Xingpeng Jiang, Qing Zhu, Min Pan, Tingting He
2019 Frontiers in Genetics  
In addition, deep learning is considered as black box and hard to interpret. These factors make deep learning not widely used in microbiome-wide association studies.  ...  Our main contributions are: firstly, we utilize different methods to construct a variety of microbial interaction networks and combine the network via graph embedding deep learning.  ...  However, Deep neural network is a "black box", the interpretability of deep learning hasn't been well-defined (Guidotti et al., 2019) .  ... 
doi:10.3389/fgene.2019.01182 pmid:31824573 pmcid:PMC6883002 fatcat:z4l75rsobfhurihowp7ugl4mne

Robust and Scalable Models of Microbiome Dynamics [article]

Travis E. Gibson, Georg K. Gerber
2018 arXiv   pre-print
Central to the design of such therapeutics is an understanding of the causal microbial interaction network and the population dynamics of the organisms.  ...  Our contributions include a new type of dynamical systems model for microbial dynamics based on what we term interaction modules, or learned clusters of latent variables with redundant interaction structure  ...  Note that this graph in (4) is just another representation of the weighted adjacency matrix in Figure 4C .  ... 
arXiv:1805.04591v2 fatcat:b6my4syhurgm3ea64fnv5viqsi

BayReL: Bayesian Relational Learning for Multi-omics Data Integration [article]

Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna R Narayanan, Xiaoning Qian
2020 arXiv   pre-print
In this paper, we develop a novel Bayesian representation learning method that infers the relational interactions across multi-omics data types.  ...  view, to learn view-specific latent variables as well as a multi-partite graph that encodes the interactions across views.  ...  We then construct the bi-partite graph using Spearman's rank correlation between the mean projections of views. We report the results based on four independent runs.  ... 
arXiv:2010.05895v3 fatcat:lgqdd3wy7favxbl6suuznj3yg4

Deep in the Bowel: Highly Interpretable Neural Encoder-Decoder Networks Predict Gut Metabolites from Gut Microbiome

Vuong Le, Thomas P. Quinn, Truyen Tran, Svetha Venkatesh
2020 BMC Genomics  
By imposing a non-negative weights constraint, the network becomes a directed graph where each downstream node is interpretable as the additive combination of the upstream nodes.  ...  Although this hidden layer is learned without any knowledge of the patient's diagnosis, we show that the learned latent features are structured in a way that predicts IBD and treatment status with high  ...  This relaxation will extend our representation of the predictive model via two hypotheses: 1.  ... 
doi:10.1186/s12864-020-6652-7 pmid:32689932 fatcat:n4alwi6f6bh6vm4eg3i7iuk4dm

Image and graph convolution networks improve microbiome-based machine learning accuracy [article]

Shtossel Oshrit, Isakov Haim, Turjeman Sondra, Koren Omry, Louzoun Yoram
2022 arXiv   pre-print
Furthermore, these methods ease the interpretation of the classifiers. iMic is then extended to dynamic microbiome samples, and an iMic explainable AI algorithm is proposed to detect bacteria relevant  ...  We suggest two novel methods to combine information from different bacteria and improve data representation for machine learning using bacterial taxonomy. iMic and gMic translate the microbiome to images  ...  The same holds for the adaptation of graph-based machine learning to microbiome graphs.  ... 
arXiv:2205.06525v1 fatcat:orvamjc7hzft7k535bsxxcmfvy

Deep in the Bowel: Highly Interpretable Neural Encoder-Decoder Networks Predict Gut Metabolites from Gut Microbiome [article]

Vuong Le, Thomas P. Quinn, Truyen Tran, Svetha Venkatesh
2019 bioRxiv   pre-print
By imposing a non-negative weights constraint, the network becomes a directed graph where each downstream node is interpretable as the additive combination of the upstream nodes.  ...  Although this hidden layer is learned without any knowledge of the patient's diagnosis, we show that the learned latent features are structured in a way that predicts IBD and treatment status with high  ...  This relaxation will extend our representation of the predictive model via two hypotheses: 1.  ... 
doi:10.1101/686394 fatcat:gqggbo7x4rerbaaqn4lvjn4vd4

Deep Learning for Integrated Analysis of Insulin Resistance with Multi-Omics Data

Eunchong Huang, Sarah Kim, TaeJin Ahn
2021 Journal of Personalized Medicine  
To better explain the impact of microbiome features on insulin classification, we used a developed deep neural network interpretation algorithm for each microbiome feature's contribution to the discriminative  ...  Technological advances in next-generation sequencing (NGS) have made it possible to uncover extensive and dynamic alterations in diverse molecular components and biological pathways across healthy and  ...  To further understand how 17 features independently contributed to the outcome of DNN model, we applied the interpretation algorithm.  ... 
doi:10.3390/jpm11020128 pmid:33671853 fatcat:fg4ci7szsne6db53p7dejwupnq

Network analysis methods for studying microbial communities: A mini review

Monica Steffi Matchado, Michael Lauber, Sandra Reitmeier, Tim Kacprowski, Jan Baumbach, Dirk Haller, Markus List
2021 Computational and Structural Biotechnology Journal  
They engage in numerous inter- and intra- kingdom interactions which can be inferred from microbiome profiling data.  ...  This correlation-centric network representation is hence suited to capture dynamic changes in the microbial environment [89] .  ...  [102] and a deep learning model allowing the integration of microbiome and metabolome [103] .  ... 
doi:10.1016/j.csbj.2021.05.001 pmid:34093985 pmcid:PMC8131268 fatcat:ba6wne7jprat3jgnngfbzkebq4

Emerging Priorities for Microbiome Research

Chad M. Cullen, Kawalpreet K. Aneja, Sinem Beyhan, Clara E. Cho, Stephen Woloszynek, Matteo Convertino, Sophie J. McCoy, Yanyan Zhang, Matthew Z. Anderson, David Alvarez-Ponce, Ekaterina Smirnova, Lisa Karstens (+7 others)
2020 Frontiers in Microbiology  
Understanding the role of microbiota, including their dynamic interactions with their hosts and other microbes, can enable the engineering of new diagnostic techniques and interventional strategies that  ...  From June 19-23 in 2017, the NIH and NSF jointly held an Innovation Lab on Quantitative Approaches to Biomedical Data Science Challenges in our Understanding of the Microbiome.  ...  ACKNOWLEDGMENTS We thank the NIH and NSF for the 2017 Innovation Lab on Quantitative Approaches to Biomedical Data Science Challenges in our Understanding of the Microbiome, which sparked great conversations  ... 
doi:10.3389/fmicb.2020.00136 pmid:32140140 pmcid:PMC7042322 fatcat:hpo2ms7yxfbsthpvt4wswqtxiq

Common principles and best practices for engineering microbiomes

Christopher E. Lawson, William R. Harcombe, Roland Hatzenpichler, Stephen R. Lindemann, Frank E. Löffler, Michelle A. O'Malley, Héctor García Martín, Brian F. Pfleger, Lutgarde Raskin, Ophelia S. Venturelli, David G. Weissbrodt, Daniel R. Noguera (+1 others)
2019 Nature Reviews Microbiology  
We argue that structuring research and technology developments around a design-build-test-learn (DBTL) cycle will advance microbiome engineering and spur new discoveries of the basic scientific principles  ...  governing microbiome function.  ...  Acknowledgements The authors acknowledge the College of Engineering at the University of Wisconsin-Madison, which provided financial support for a workshop during the Madison Microbiome Meeting on 27 April  ... 
doi:10.1038/s41579-019-0255-9 pmid:31548653 pmcid:PMC8323346 fatcat:33lo56levzhahan3y3shhiselm

Mapping the Inner Workings of the Microbiome: Genomic- and Metagenomic-Based Study of Metabolism and Metabolic Interactions in the Human Microbiome

Ohad Manor, Roie Levy, Elhanan Borenstein
2014 Cell Metabolism  
We will specifically highlight two interrelated lines of work, the first aiming to deconvolve the microbiome and to characterize the metabolic capacity of various microbiome species and the second aiming  ...  and with the host, and the impact of such interactions on the overall metabolic machinery of the microbiome have not yet been mapped.  ...  Rather, the web of interactions between these community members and the way they impact community dynamics need to be mapped in order to gain a fundamental understanding of the microbiome.  ... 
doi:10.1016/j.cmet.2014.07.021 pmid:25176148 pmcid:PMC4252837 fatcat:2fycfi6z2fen7pbfvoe47iuxje

Dynamic interaction network inference from longitudinal microbiome data

Jose Lugo-Martinez, Daniel Ruiz-Perez, Giri Narasimhan, Ziv Bar-Joseph
2019 Microbiome  
However, analysis of such data is challenging and very few methods have been developed to reconstruct dynamic models from time series microbiome data.  ...  In many of these studies, researchers collect longitudinal data with the goal of understanding not only just the composition of the microbiome but also the interactions between the different taxa.  ...  Availability of data and materials All code and longitudinal microbiome data sets can be downloaded from https://github.com/jlugomar/longitudinal_microbiome_analysis_public.  ... 
doi:10.1186/s40168-019-0660-3 pmid:30940197 pmcid:PMC6446388 fatcat:43cjc6x7dneanphq5ytqlzdiyq
« Previous Showing results 1 — 15 out of 574 results